diff options
Diffstat (limited to 'net')
38 files changed, 455 insertions, 255 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2eb0e55ef54d..b5f4ef35357c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -552,6 +552,12 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->gso_segs = skb_shinfo(skb)->gso_segs; } +static struct proto bpf_dummy_proto = { + .name = "bpf_dummy", + .owner = THIS_MODULE, + .obj_size = sizeof(struct sock), +}; + int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { @@ -596,20 +602,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, break; } - sk = kzalloc(sizeof(struct sock), GFP_USER); + sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1); if (!sk) { kfree(data); kfree(ctx); return -ENOMEM; } - sock_net_set(sk, net); sock_init_data(NULL, sk); skb = build_skb(data, 0); if (!skb) { kfree(data); kfree(ctx); - kfree(sk); + sk_free(sk); return -ENOMEM; } skb->sk = sk; @@ -682,8 +687,7 @@ out: if (dev && dev != net->loopback_dev) dev_put(dev); kfree_skb(skb); - bpf_sk_storage_free(sk); - kfree(sk); + sk_free(sk); kfree(ctx); return ret; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3523c8c7068f..f3d751105343 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1677,8 +1677,6 @@ static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, int ifindex, struct br_ip *saddr) { - lockdep_assert_held_once(&brmctx->br->multicast_lock); - write_seqcount_begin(&querier->seq); querier->port_ifidx = ifindex; memcpy(&querier->addr, saddr, sizeof(*saddr)); @@ -3867,13 +3865,13 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip4_querier.seq); + seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip6_querier.seq); + seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif timer_setup(&brmctx->ip4_mc_router_timer, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b4cef3a97f12..e8136db44462 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,7 +82,7 @@ struct bridge_mcast_other_query { struct bridge_mcast_querier { struct br_ip addr; int port_ifidx; - seqcount_t seq; + seqcount_spinlock_t seq; }; /* IGMP/MLD statistics */ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 8c39283c26ae..f0cb38344126 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -50,6 +50,11 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, if (addr_len > MAX_ADDR_LEN) return -EINVAL; + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + goto found_it; + while (*ins_point) { int diff; @@ -64,6 +69,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } else if (diff > 0) { ins_point = &parent->rb_right; } else { +found_it: if (exclusive) return -EEXIST; if (global) { diff --git a/net/core/sock.c b/net/core/sock.c index 512e629f9780..c1601f75ec4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1376,6 +1376,16 @@ set_sndbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; @@ -3210,24 +3230,8 @@ void release_sock(struct sock *sk) } EXPORT_SYMBOL(release_sock); -/** - * lock_sock_fast - fast version of lock_sock - * @sk: socket - * - * This version should be used for very small section, where process wont block - * return false if fast path is taken: - * - * sk_lock.slock locked, owned = 0, BH disabled - * - * return true if slow path is taken: - * - * sk_lock.slock unlocked, owned = 1, BH enabled - */ -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { - /* The sk_lock has mutex_lock() semantics here. */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); - might_sleep(); spin_lock_bh(&sk->sk_lock.slock); @@ -3256,7 +3260,7 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) spin_unlock_bh(&sk->sk_lock.slock); return true; } -EXPORT_SYMBOL(lock_sock_fast); +EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b42c429cebbe..3364cb9c67e0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1661,7 +1661,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, - int nh_weight, u8 rt_family) + int nh_weight, u8 rt_family, u32 nh_tclassid) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; @@ -1679,6 +1679,9 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, rtnh->rtnh_flags = flags; + if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid)) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; @@ -1706,14 +1709,13 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) } for_nexthops(fi) { - if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, - AF_INET) < 0) - goto nla_put_failure; + u32 nh_tclassid = 0; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; + nh_tclassid = nh->nh_tclassid; #endif + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, + AF_INET, nh_tclassid) < 0) + goto nla_put_failure; } endfor_nexthops(fi); mp_end: diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b88e0f36cd05..8265c6765705 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -42,7 +42,7 @@ iptable_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init iptable_raw_table_init(struct net *net) +static int iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; const struct xt_table *table = &packet_raw; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8851c9463b4b..2a7825a5b842 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1053,7 +1053,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1361,7 +1361,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, } up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) + if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; @@ -2662,9 +2662,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + WRITE_ONCE(up->corkflag, 1); } else { - up->corkflag = 0; + WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2787,7 +2787,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = up->corkflag; + val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index de2cf3943b91..a579ea14a69b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -273,6 +273,7 @@ ip6t_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ + acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dbc224023977..9b9ef09382ab 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5681,14 +5681,15 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, - rt->fib6_nh->fib_nh_weight, AF_INET6) < 0) + rt->fib6_nh->fib_nh_weight, AF_INET6, + 0) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6) < 0) + AF_INET6, 0) < 0) goto nla_put_failure; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ea53847b5b7e..e505bb007e9f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1303,7 +1303,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index efbefcbac3ac..7cab1cf09bf1 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,7 +60,10 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); - rhashtable_init(&newtbl->rhead, &mesh_rht_params); + if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) { + kfree(newtbl); + return NULL; + } return newtbl; } diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 204830a55240..3fbd0b9ff913 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -2,6 +2,7 @@ /* * Copyright 2012-2013, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de> * Copyright 2012-2013, cozybit Inc. + * Copyright (C) 2021 Intel Corporation */ #include "mesh.h" @@ -588,7 +589,7 @@ void ieee80211_mps_frame_release(struct sta_info *sta, /* only transmit to PS STA with announced, non-zero awake window */ if (test_sta_flag(sta, WLAN_STA_PS_STA) && - (!elems->awake_window || !le16_to_cpu(*elems->awake_window))) + (!elems->awake_window || !get_unaligned_le16(elems->awake_window))) return; if (!test_sta_flag(sta, WLAN_STA_MPSP_OWNER)) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index e5935e3d7a07..8c6416129d5b 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -392,10 +392,6 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, int mcast_rate; bool use_basicrate = false; - if (ieee80211_is_tx_data(txrc->skb) && - info->flags & IEEE80211_TX_CTL_NO_ACK) - return false; - if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 99ed68f7dc36..c4071b015c18 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4131,7 +4131,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) if (!bssid) return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || - ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2) || + !is_valid_ether_addr(hdr->addr2)) return false; if (ieee80211_is_beacon(hdr->frame_control)) return true; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2d1193ed3eb5..8921088a5df6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2209,7 +2209,11 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } vht_mcs = iterator.this_arg[4] >> 4; + if (vht_mcs > 11) + vht_mcs = 0; vht_nss = iterator.this_arg[4] & 0xF; + if (!vht_nss || vht_nss > 8) + vht_nss = 1; break; /* @@ -3380,6 +3384,14 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* If n == 2, the "while (*frag_tail)" loop above didn't execute + * and frag_tail should be &skb_shinfo(head)->frag_list. + * However, ieee80211_amsdu_prepare_head() can reallocate it. + * Reload frag_tail to have it pointing to the correct place. + */ + if (n == 2) + frag_tail = &skb_shinfo(head)->frag_list; + /* * Pad out the previous subframe to a multiple of 4 by adding the * padding to the next one, that's being added. Note that head->len diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bca47fad5a16..4eed23e27610 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -520,6 +520,9 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -749,6 +752,9 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f48eb6315bbb..292374fb0779 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -36,7 +36,7 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, struct sock *sk; net = sock_net(in_skb->sk); - msk = mptcp_token_get_sock(req->id.idiag_cookie[0]); + msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]); if (!msk) goto out_nosk; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c4f9a5ce3815..050eea231528 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1718,9 +1718,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) list_for_each_entry(entry, &pernet->local_addr_list, list) { if (addresses_equal(&entry->addr, &addr.addr, true)) { - ret = mptcp_nl_addr_backup(net, &entry->addr, bkup); - if (ret) - return ret; + mptcp_nl_addr_backup(net, &entry->addr, bkup); if (bkup) entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dbcebf56798f..e5df0b5971c8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2735,7 +2735,7 @@ cleanup: inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(mptcp_sk(sk), subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); + bool slow = lock_sock_fast_nested(ssk); sock_orphan(ssk); unlock_sock_fast(ssk, slow); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d3e6fd1615f1..dc984676c5eb 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -709,7 +709,7 @@ int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); -struct mptcp_sock *mptcp_token_get_sock(u32 token); +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); void mptcp_token_destroy(struct mptcp_sock *msk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1de7ce883c37..6172f380dfb7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -86,7 +86,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) struct mptcp_sock *msk; int local_id; - msk = mptcp_token_get_sock(subflow_req->token); + msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); return NULL; diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index 37127781aee9..7f22526346a7 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -108,18 +108,12 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl e->valid = 0; - msk = mptcp_token_get_sock(e->token); + msk = mptcp_token_get_sock(net, e->token); if (!msk) { spin_unlock_bh(&join_entry_locks[i]); return false; } - /* If this fails, the token got re-used in the mean time by another - * mptcp socket in a different netns, i.e. entry is outdated. - */ - if (!net_eq(sock_net((struct sock *)msk), net)) - goto err_put; - subflow_req->remote_nonce = e->remote_nonce; subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; @@ -128,11 +122,6 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->msk = msk; spin_unlock_bh(&join_entry_locks[i]); return true; - -err_put: - spin_unlock_bh(&join_entry_locks[i]); - sock_put((struct sock *)msk); - return false; } void __init mptcp_join_cookie_init(void) diff --git a/net/mptcp/token.c b/net/mptcp/token.c index a98e554b034f..e581b341c5be 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -231,6 +231,7 @@ found: /** * mptcp_token_get_sock - retrieve mptcp connection sock using its token + * @net: restrict to this namespace * @token: token of the mptcp connection to retrieve * * This function returns the mptcp connection structure with the given token. @@ -238,7 +239,7 @@ found: * * returns NULL if no connection with the given token value exists. */ -struct mptcp_sock *mptcp_token_get_sock(u32 token) +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token) { struct hlist_nulls_node *pos; struct token_bucket *bucket; @@ -251,11 +252,15 @@ struct mptcp_sock *mptcp_token_get_sock(u32 token) again: sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { msk = mptcp_sk(sk); - if (READ_ONCE(msk->token) != token) + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) continue; + if (!refcount_inc_not_zero(&sk->sk_refcnt)) goto not_found; - if (READ_ONCE(msk->token) != token) { + + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) { sock_put(sk); goto again; } diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index e1bd6f0a0676..5d984bec1cd8 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -11,6 +11,7 @@ static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test) GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req); mptcp_token_init_request((struct request_sock *)req); + sock_net_set((struct sock *)req, &init_net); return req; } @@ -22,7 +23,7 @@ static void mptcp_token_test_req_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, 0, mptcp_token_new_request((struct request_sock *)req)); KUNIT_EXPECT_NE(test, 0, (int)req->token); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token)); /* cleanup */ mptcp_token_destroy_request((struct request_sock *)req); @@ -55,6 +56,7 @@ static struct mptcp_sock *build_msk(struct kunit *test) msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); + sock_net_set((struct sock *)msk, &init_net); return msk; } @@ -74,11 +76,11 @@ static void mptcp_token_test_msk_basic(struct kunit *test) mptcp_token_new_connect((struct sock *)icsk)); KUNIT_EXPECT_NE(test, 0, (int)ctx->token); KUNIT_EXPECT_EQ(test, ctx->token, msk->token); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token)); KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt)); mptcp_token_destroy(msk); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token)); } static void mptcp_token_test_accept(struct kunit *test) @@ -90,11 +92,11 @@ static void mptcp_token_test_accept(struct kunit *test) mptcp_token_new_request((struct request_sock *)req)); msk->token = req->token; mptcp_token_accept(req, msk); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* this is now a no-op */ mptcp_token_destroy_request((struct request_sock *)req); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); @@ -116,7 +118,7 @@ static void mptcp_token_test_destroyed(struct kunit *test) /* simulate race on removal */ refcount_set(&sk->sk_refcnt, 0); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6186358eac7c..6e391308431d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -130,11 +130,11 @@ htable_size(u8 hbits) { size_t hsize; - /* We must fit both into u32 in jhash and size_t */ + /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) + if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c100c6b112c8..2c467c422dc6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1468,6 +1468,10 @@ int __init ip_vs_conn_init(void) int idx; /* Compute size and mask */ + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) { + pr_info("conn_tab_bits not in [8, 20]. Using default value\n"); + ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; + } ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 94e18fb9690d..770a63103c7a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -74,10 +74,14 @@ static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* serialize hash resizes and nf_ct_iterate_cleanup */ +static DEFINE_MUTEX(nf_conntrack_mutex); + #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) -#define MAX_CHAINLEN 64u +#define MIN_CHAINLEN 8u +#define MAX_CHAINLEN (32u - MIN_CHAINLEN) static struct conntrack_gc_work conntrack_gc_work; @@ -188,11 +192,13 @@ seqcount_spinlock_t nf_conntrack_generation __read_mostly; static siphash_key_t nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, const struct net *net) { struct { struct nf_conntrack_man src; union nf_inet_addr dst_addr; + unsigned int zone; u32 net_mix; u16 dport; u16 proto; @@ -205,6 +211,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, /* The direction must be ignored, so handle usable members manually. */ combined.src = tuple->src; combined.dst_addr = tuple->dst.u3; + combined.zone = zoneid; combined.net_mix = net_hash_mix(net); combined.dport = (__force __u16)tuple->dst.u.all; combined.proto = tuple->dst.protonum; @@ -219,15 +226,17 @@ static u32 scale_hash(u32 hash) static u32 __hash_conntrack(const struct net *net, const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, unsigned int size) { - return reciprocal_scale(hash_conntrack_raw(tuple, net), size); + return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size); } static u32 hash_conntrack(const struct net *net, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, + unsigned int zoneid) { - return scale_hash(hash_conntrack_raw(tuple, net)); + return scale_hash(hash_conntrack_raw(tuple, zoneid, net)); } static bool nf_ct_get_tuple_ports(const struct sk_buff *skb, @@ -650,9 +659,11 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); clean_from_lists(ct); @@ -819,8 +830,20 @@ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, net)); + unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + struct nf_conntrack_tuple_hash *thash; + + thash = __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, zone_id, net)); + + if (thash) + return thash; + + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (rid != zone_id) + return __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, rid, net)); + return thash; } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -842,6 +865,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int max_chainlen; unsigned int chainlen = 0; unsigned int sequence; int err = -EEXIST; @@ -852,18 +876,22 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); + /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -873,7 +901,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1103,8 +1131,8 @@ drop: int __nf_conntrack_confirm(struct sk_buff *skb) { + unsigned int chainlen = 0, sequence, max_chainlen; const struct nf_conntrack_zone *zone; - unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1133,8 +1161,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = scale_hash(hash); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related @@ -1168,6 +1196,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) goto dying; } + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ @@ -1175,7 +1204,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1184,7 +1213,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) { + if (chainlen++ > max_chainlen) { chaintoolong: nf_ct_add_to_dying_list(ct); NF_CT_STAT_INC(net, chaintoolong); @@ -1246,7 +1275,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, rcu_read_lock(); begin: nf_conntrack_get_ht(&ct_hash, &hsize); - hash = __hash_conntrack(net, tuple, hsize); + hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); @@ -1687,8 +1716,8 @@ resolve_normal_ct(struct nf_conn *tmpl, struct nf_conntrack_tuple_hash *h; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + u32 hash, zone_id, rid; struct nf_conn *ct; - u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, @@ -1699,8 +1728,20 @@ resolve_normal_ct(struct nf_conn *tmpl, /* look for tuple match */ zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); - hash = hash_conntrack_raw(&tuple, state->net); + + zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + hash = hash_conntrack_raw(&tuple, zone_id, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); + + if (!h) { + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (zone_id != rid) { + u32 tmp = hash_conntrack_raw(&tuple, rid, state->net); + + h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp); + } + } + if (!h) { h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); @@ -2225,28 +2266,31 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket]; + + if (hlist_nulls_empty(hslot)) + continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); nf_conntrack_lock(lockp); - if (*bucket < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) - continue; - /* All nf_conn objects are added to hash table twice, one - * for original direction tuple, once for the reply tuple. - * - * Exception: In the IPS_NAT_CLASH case, only the reply - * tuple is added (the original tuple already existed for - * a different object). - * - * We only need to call the iterator once for each - * conntrack, so we just use the 'reply' direction - * tuple while iterating. - */ - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - goto found; - } + hlist_nulls_for_each_entry(h, n, hslot, hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) + continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; } spin_unlock(lockp); local_bh_enable(); @@ -2264,26 +2308,20 @@ found: static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - unsigned int bucket = 0, sequence; + unsigned int bucket = 0; struct nf_conn *ct; might_sleep(); - for (;;) { - sequence = read_seqcount_begin(&nf_conntrack_generation); - - while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ + mutex_lock(&nf_conntrack_mutex); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); - } - - if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) - break; - bucket = 0; + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); } + mutex_unlock(&nf_conntrack_mutex); } struct iter_data { @@ -2519,8 +2557,10 @@ int nf_conntrack_hash_resize(unsigned int hashsize) if (!hash) return -ENOMEM; + mutex_lock(&nf_conntrack_mutex); old_size = nf_conntrack_htable_size; if (old_size == hashsize) { + mutex_unlock(&nf_conntrack_mutex); kvfree(hash); return 0; } @@ -2537,12 +2577,16 @@ int nf_conntrack_hash_resize(unsigned int hashsize) for (i = 0; i < nf_conntrack_htable_size; i++) { while (!hlist_nulls_empty(&nf_conntrack_hash[i])) { + unsigned int zone_id; + h = hlist_nulls_entry(nf_conntrack_hash[i].first, struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); + + zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h)); bucket = __hash_conntrack(nf_ct_net(ct), - &h->tuple, hashsize); + &h->tuple, zone_id, hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } @@ -2556,6 +2600,8 @@ int nf_conntrack_hash_resize(unsigned int hashsize) nf_conntrack_all_unlock(); local_bh_enable(); + mutex_unlock(&nf_conntrack_mutex); + synchronize_net(); kvfree(old_hash); return 0; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 7008961f5cb0..273117683922 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -150,13 +150,16 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) /* We keep an extra hash for each conntrack, for fast searching. */ static unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, + const struct nf_conntrack_zone *zone, + const struct nf_conntrack_tuple *tuple) { unsigned int hash; struct { struct nf_conntrack_man src; u32 net_mix; u32 protonum; + u32 zone; } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); @@ -165,9 +168,13 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) /* Original src, to ensure we map it consistently if poss. */ combined.src = tuple->src; - combined.net_mix = net_hash_mix(n); + combined.net_mix = net_hash_mix(net); combined.protonum = tuple->dst.protonum; + /* Zone ID can be used provided its valid for both directions */ + if (zone->dir == NF_CT_DEFAULT_ZONE_DIR) + combined.zone = zone->id; + hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); @@ -272,7 +279,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range2 *range) { - unsigned int h = hash_by_src(net, tuple); + unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn *ct; hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { @@ -619,7 +626,7 @@ nf_nat_setup_info(struct nf_conn *ct, unsigned int srchash; spinlock_t *lock; - srchash = hash_by_src(net, + srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); @@ -788,7 +795,7 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; - h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c index 8e8a65d46345..acd73f717a08 100644 --- a/net/netfilter/nf_nat_masquerade.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -9,8 +9,19 @@ #include <net/netfilter/nf_nat_masquerade.h> +struct masq_dev_work { + struct work_struct work; + struct net *net; + union nf_inet_addr addr; + int ifindex; + int (*iter)(struct nf_conn *i, void *data); +}; + +#define MAX_MASQ_WORKER_COUNT 16 + static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; +static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, @@ -63,13 +74,71 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); -static int device_cmp(struct nf_conn *i, void *ifindex) +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + + w = container_of(work, struct masq_dev_work, work); + + nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&masq_worker_count); + module_put(THIS_MODULE); +} + +/* Iterate conntrack table in the background and remove conntrack entries + * that use the device/address being removed. + * + * In case too many work items have been queued already or memory allocation + * fails iteration is skipped, conntrack entries will time out eventually. + */ +static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, + int ifindex, + int (*iter)(struct nf_conn *i, void *data), + gfp_t gfp_flags) +{ + struct masq_dev_work *w; + + if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) + return; + + net = maybe_get_net(net); + if (!net) + return; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kzalloc(sizeof(*w), gfp_flags); + if (w) { + /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ + atomic_inc(&masq_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = ifindex; + w->net = net; + w->iter = iter; + if (addr) + w->addr = *addr; + schedule_work(&w->work); + return; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); +} + +static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); + const struct masq_dev_work *w = arg; if (!nat) return 0; - return nat->masq_index == (int)(long)ifindex; + return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, @@ -85,8 +154,8 @@ static int masq_device_event(struct notifier_block *this, * and forget them. */ - nf_ct_iterate_cleanup_net(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_nat_masq_schedule(net, NULL, dev->ifindex, + device_cmp, GFP_KERNEL); } return NOTIFY_DONE; @@ -94,35 +163,45 @@ static int masq_device_event(struct notifier_block *this, static int inet_cmp(struct nf_conn *ct, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct net_device *dev = ifa->ifa_dev->dev; struct nf_conntrack_tuple *tuple; + struct masq_dev_work *w = ptr; - if (!device_cmp(ct, (void *)(long)dev->ifindex)) + if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - return ifa->ifa_address == tuple->dst.u3.ip; + return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; - struct net *net = dev_net(idev->dev); + const struct in_ifaddr *ifa = ptr; + const struct in_device *idev; + const struct net_device *dev; + union nf_inet_addr addr; + + if (event != NETDEV_DOWN) + return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ + idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0); + memset(&addr, 0, sizeof(addr)); + + addr.ip = ifa->ifa_address; + + dev = idev->dev; + nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, + inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } @@ -136,8 +215,6 @@ static struct notifier_block masq_inet_notifier = { }; #if IS_ENABLED(CONFIG_IPV6) -static atomic_t v6_worker_count __read_mostly; - static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, @@ -187,40 +264,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); -struct masq_dev_work { - struct work_struct work; - struct net *net; - struct in6_addr addr; - int ifindex; -}; - -static int inet6_cmp(struct nf_conn *ct, void *work) -{ - struct masq_dev_work *w = (struct masq_dev_work *)work; - struct nf_conntrack_tuple *tuple; - - if (!device_cmp(ct, (void *)(long)w->ifindex)) - return 0; - - tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - - return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); -} - -static void iterate_cleanup_work(struct work_struct *work) -{ - struct masq_dev_work *w; - - w = container_of(work, struct masq_dev_work, work); - - nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0); - - put_net(w->net); - kfree(w); - atomic_dec(&v6_worker_count); - module_put(THIS_MODULE); -} - /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. @@ -233,36 +276,19 @@ static int masq_inet6_event(struct notifier_block *this, { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; - struct masq_dev_work *w; - struct net *net; + union nf_inet_addr addr; - if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16) + if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; - net = maybe_get_net(dev_net(dev)); - if (!net) - return NOTIFY_DONE; - if (!try_module_get(THIS_MODULE)) - goto err_module; + memset(&addr, 0, sizeof(addr)); - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - atomic_inc(&v6_worker_count); - - INIT_WORK(&w->work, iterate_cleanup_work); - w->ifindex = dev->ifindex; - w->net = net; - w->addr = ifa->addr; - schedule_work(&w->work); + addr.in6 = ifa->addr; - return NOTIFY_DONE; - } - - module_put(THIS_MODULE); - err_module: - put_net(net); + nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, + GFP_ATOMIC); return NOTIFY_DONE; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 081437dd75b7..b9546defdc28 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4336,7 +4336,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; - if (alloc_size < size) + if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; set = kvzalloc(alloc_size, GFP_KERNEL); if (!set) @@ -9599,7 +9599,6 @@ static void __nft_release_table(struct net *net, struct nft_table *table) table->use--; nf_tables_chain_destroy(&ctx); } - list_del(&table->list); nf_tables_table_destroy(&ctx); } @@ -9612,6 +9611,8 @@ static void __nft_release_tables(struct net *net) if (nft_table_has_owner(table)) continue; + list_del(&table->list); + __nft_release_table(net, table); } } @@ -9619,31 +9620,38 @@ static void __nft_release_tables(struct net *net) static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; - struct nft_table *table, *nt; struct net *net = n->net; - bool release = false; + unsigned int deleted; + bool restart = false; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); + deleted = 0; mutex_lock(&nft_net->commit_mutex); +again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { __nft_release_hook(net, table); - release = true; + list_del_rcu(&table->list); + to_delete[deleted++] = table; + if (deleted >= ARRAY_SIZE(to_delete)) + break; } } - if (release) { + if (deleted) { + restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); - list_for_each_entry_safe(table, nt, &nft_net->tables, list) { - if (nft_table_has_owner(table) && - n->portid == table->nlpid) - __nft_release_table(net, table); - } + while (deleted) + __nft_release_table(net, to_delete[--deleted]); + + if (restart) + goto again; } mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 272bcdb1392d..f69cc73c5813 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -19,6 +19,7 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_log.h> /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -257,8 +258,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); - if (ret < 0) + if (ret < 0) { + if (ret == -ENOENT) { + const char *modname = NULL; + + if (strcmp(target->name, "LOG") == 0) + modname = "nf_log_syslog"; + else if (strcmp(target->name, "NFLOG") == 0) + modname = "nfnetlink_log"; + + if (modname && + nft_request_module(ctx->net, "%s", modname) == -EAGAIN) + return -EAGAIN; + } + return ret; + } /* The standard target cannot be used */ if (!target->target) diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 2ff75f7637b0..f39244f9c0ed 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -44,6 +44,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; + int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; @@ -58,7 +59,14 @@ static int log_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } - return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nf_log_syslog"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + } + + return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index fb5793208059..e660c3710a10 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -42,13 +42,21 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int nflog_tg_check(const struct xt_tgchk_param *par) { const struct xt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~XT_NFLOG_MASK) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; } static void nflog_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 23b21253b3c3..eb6345a027e1 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2188,18 +2188,24 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, arg->count = arg->skip; + rcu_read_lock(); idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { /* don't return filters that are being deleted */ if (!refcount_inc_not_zero(&f->refcnt)) continue; + rcu_read_unlock(); + if (arg->fn(tp, f, arg) < 0) { __fl_put(f); arg->stop = 1; + rcu_read_lock(); break; } __fl_put(f); arg->count++; + rcu_read_lock(); } + rcu_read_unlock(); arg->cookie = id; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5e90e9b160e3..12f39a2dffd4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -513,6 +513,12 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return stab; } + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); diff --git a/net/sctp/input.c b/net/sctp/input.c index 5ef86fdb1176..1f1786021d9c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -702,7 +702,7 @@ static int sctp_rcv_ootb(struct sk_buff *skb) ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(_ch)) + if (!ch || ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 92345c9bb60c..efac5989edb5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) @@ -828,20 +850,25 @@ struct proto unix_stream_proto = { static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type) { - struct sock *sk = NULL; struct unix_sock *u; + struct sock *sk; + int err; atomic_long_inc(&unix_nr_socks); - if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) - goto out; + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) { + err = -ENFILE; + goto err; + } if (type == SOCK_STREAM) sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern); else /*dgram and seqpacket */ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern); - if (!sk) - goto out; + if (!sk) { + err = -ENOMEM; + goto err; + } sock_init_data(sock, sk); @@ -861,20 +888,23 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); memset(&u->scm_stat, 0, sizeof(struct scm_stat)); unix_insert_socket(unix_sockets_unbound(sk), sk); -out: - if (sk == NULL) - atomic_long_dec(&unix_nr_socks); - else { - local_bh_disable(); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - local_bh_enable(); - } + + local_bh_disable(); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + local_bh_enable(); + return sk; + +err: + atomic_long_dec(&unix_nr_socks); + return ERR_PTR(err); } static int unix_create(struct net *net, struct socket *sock, int protocol, int kern) { + struct sock *sk; + if (protocol && protocol != PF_UNIX) return -EPROTONOSUPPORT; @@ -901,7 +931,11 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM; + sk = unix_create1(net, sock, kern, sock->type); + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return 0; } static int unix_release(struct socket *sock) @@ -1314,12 +1348,15 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, we will have to recheck all again in any case. */ - err = -ENOMEM; - /* create new sock for complete connection */ newsk = unix_create1(sock_net(sk), NULL, 0, sock->type); - if (newsk == NULL) + if (IS_ERR(newsk)) { + err = PTR_ERR(newsk); + newsk = NULL; goto out; + } + + err = -ENOMEM; /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); |