diff options
Diffstat (limited to 'net')
84 files changed, 617 insertions, 360 deletions
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 985046ae4231..80f5c79053a4 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -839,7 +839,6 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) if (IS_ERR(file)) { pr_err("%s (%d): failed to map fd\n", __func__, task_pid_nr(current)); - sock_release(csocket); kfree(p); return PTR_ERR(file); } diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 1b659ab652fb..bbe8414b6ee7 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1214,7 +1214,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); if_num = if_incoming->if_num; orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); @@ -1224,7 +1224,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, } else { neigh_rq_count = 0; } - spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ if (orig_eq_count > neigh_rq_count) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 341ceab8338d..e0e2bfcd6b3e 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -814,7 +814,7 @@ static bool batadv_v_gw_is_eligible(struct batadv_priv *bat_priv, } orig_gw = batadv_gw_node_get(bat_priv, orig_node); - if (!orig_node) + if (!orig_gw) goto out; if (batadv_v_gw_throughput_get(orig_gw, &orig_throughput) < 0) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index a98cf1104a30..ebe6e38934e4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -499,6 +499,8 @@ int batadv_frag_send_packet(struct sk_buff *skb, */ if (skb->priority >= 256 && skb->priority <= 263) frag_header.priority = skb->priority - 256; + else + frag_header.priority = 0; ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr); ether_addr_copy(frag_header.dest, orig_node->orig); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 15cd2139381e..ebc4e2241c77 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -482,7 +482,7 @@ static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars) /** * batadv_tp_sender_timeout - timer that fires in case of packet loss - * @arg: address of the related tp_vars + * @t: address to timer_list inside tp_vars * * If fired it means that there was packet loss. * Switch to Slow Start, set the ss_threshold to half of the current cwnd and @@ -1106,7 +1106,7 @@ static void batadv_tp_reset_receiver_timer(struct batadv_tp_vars *tp_vars) /** * batadv_tp_receiver_shutdown - stop a tp meter receiver when timeout is * reached without received ack - * @arg: address of the related tp_vars + * @t: address to timer_list inside tp_vars */ static void batadv_tp_receiver_shutdown(struct timer_list *t) { diff --git a/net/core/dev.c b/net/core/dev.c index 07ed21d64f92..f47e96b62308 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1106,7 +1106,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) * when the name is long and there isn't enough space left * for the digits, or if all bits are used. */ - return p ? -ENFILE : -EEXIST; + return -ENFILE; } static int dev_alloc_name_ns(struct net *net, diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 1c4810919a0a..b9057478d69c 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> -#include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6b0ff396fa9d..a592ca025fc4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4293,7 +4293,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) - return; + goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. @@ -4302,7 +4302,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); + return; } + +err: + kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index abd07a443219..178bb9833311 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -57,10 +57,16 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (state == DCCP_TIME_WAIT) timeo = DCCP_TIMEWAIT_LEN; + /* tw_timer is pinned, so we need to make sure BH are disabled + * in following section, otherwise timer handler could run before + * we complete the initialization. + */ + local_bh_disable(); inet_twsk_schedule(tw, timeo); /* Linkage updates. */ __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); + local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than diff --git a/net/dccp/proto.c b/net/dccp/proto.c index b68168fcc06a..9d43c1f40274 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -259,6 +259,7 @@ int dccp_disconnect(struct sock *sk, int flags) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); int err = 0; const int old_state = sk->sk_state; @@ -278,6 +279,10 @@ int dccp_disconnect(struct sock *sk, int flags) sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = NULL; + dp->dccps_hc_tx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d6e7a642493b..a95a55f79137 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -16,7 +16,6 @@ #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> -#include <linux/list.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4573bccd6da..7a93359fbc72 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1428,7 +1428,7 @@ skip: static bool inetdev_valid_mtu(unsigned int mtu) { - return mtu >= 68; + return mtu >= IPV4_MIN_MTU; } static void inetdev_send_gratuitous_arp(struct net_device *dev, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d1f8f302dbf3..726f6b608274 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -89,6 +89,7 @@ #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> +#include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } +/* source address selection per RFC 3376 section 4.2.13 */ +static __be32 igmpv3_get_srcaddr(struct net_device *dev, + const struct flowi4 *fl4) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return htonl(INADDR_ANY); + + for_ifa(in_dev) { + if (inet_ifa_match(fl4->saddr, ifa)) + return fl4->saddr; + } endfor_ifa(in_dev); + + return htonl(INADDR_ANY); +} + static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; @@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; - pip->saddr = fl4.saddr; + pip->saddr = igmpv3_get_srcaddr(dev, &fl4); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); @@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, - int type, struct igmpv3_grec **ppgr) + int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; - if (!skb) - skb = igmpv3_newpack(dev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = igmpv3_newpack(dev, mtu); + if (!skb) + return NULL; + } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV4_MIN_MTU) + return skb; + isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || @@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); } } first = 1; @@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -538,7 +562,7 @@ empty_source: igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c690cd0d9b3f..b563e0c46bac 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -93,7 +93,7 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, } /* - * Enter the time wait state. + * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it * from the SK, and mess with hash chains and list linkage. */ @@ -111,7 +111,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; - spin_lock_bh(&bhead->lock); + spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); @@ -137,7 +137,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - spin_unlock_bh(lock); + spin_unlock(lock); } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bb6239169b1a..9c1735632c8c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -266,7 +266,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, len = gre_hdr_len + sizeof(*ershdr); if (unlikely(!pskb_may_pull(skb, len))) - return -ENOMEM; + return PACKET_REJECT; iph = ip_hdr(skb); ershdr = (struct erspanhdr *)(skb->data + gre_hdr_len); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index fe6fee728ce4..5ddb1cb52bd4 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; mtu -= (dev->hard_header_len + t_hlen); - if (mtu < 68) - mtu = 68; + if (mtu < IPV4_MIN_MTU) + mtu = IPV4_MIN_MTU; return mtu; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f88221aebc9d..0c3c944a7b72 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -373,7 +373,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 4cbe5e80f3bf..2e0d339028bb 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -439,7 +439,6 @@ mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 17b4ca562944..69060e3abe85 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -813,12 +813,13 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { -#ifdef CONFIG_PROC_FS struct clusterip_net *cn = net_generic(net, clusterip_net_id); +#ifdef CONFIG_PROC_FS proc_remove(cn->procdir); cn->procdir = NULL; #endif nf_unregister_net_hook(net, &cip_arp_ops); + WARN_ON_ONCE(!list_empty(&cn->configs)); } static struct pernet_operations clusterip_net_ops = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 33b70bfd1122..125c1eab3eaa 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; + int hdrincl; err = -EMSGSIZE; if (len > 0xFFFF) goto out; + /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields + */ + hdrincl = inet->hdrincl; /* * Check the flags. */ @@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Linux does not mangle headers on raw sockets, * so that IP options + IP_HDRINCL is non-sense. */ - if (inet->hdrincl) + if (hdrincl) goto done; if (ipc.opt->opt.srr) { if (!daddr) @@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk) | - (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), + (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); - if (!inet->hdrincl) { + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; @@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto do_confirm; back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags, &ipc.sockc); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bf97317e6c97..f08eebe60446 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2412,6 +2412,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); + tp->is_sack_reneg = 0; tcp_clear_retrans(tp); inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 69ee877574d0..8322f26e770e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -110,7 +110,8 @@ struct bbr { u32 lt_last_lost; /* LT intvl start: tp->lost */ u32 pacing_gain:10, /* current gain for setting pacing rate */ cwnd_gain:10, /* current gain for setting cwnd */ - full_bw_cnt:3, /* number of rounds without large bw gains */ + full_bw_reached:1, /* reached full bw in Startup? */ + full_bw_cnt:2, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ has_seen_rtt:1, /* have we seen an RTT sample yet? */ unused_b:5; @@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk) { const struct bbr *bbr = inet_csk_ca(sk); - return bbr->full_bw_cnt >= bbr_full_bw_cnt; + return bbr->full_bw_reached; } /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ @@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk, return; } ++bbr->full_bw_cnt; + bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt; } /* If pipe is probably full, drain the queue and then enter steady-state. */ @@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk) bbr->restore_cwnd = 0; bbr->round_start = 0; bbr->idle_restart = 0; + bbr->full_bw_reached = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; bbr->cycle_mstamp = 0; @@ -871,6 +874,11 @@ static u32 bbr_sndbuf_expand(struct sock *sk) */ static u32 bbr_undo_cwnd(struct sock *sk) { + struct bbr *bbr = inet_csk_ca(sk); + + bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */ + bbr->full_bw_cnt = 0; + bbr_reset_lt_bw_sampling(sk); return tcp_sk(sk)->snd_cwnd; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 734cfc8ff76e..45f750e85714 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -508,9 +508,6 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) u32 new_sample = tp->rcv_rtt_est.rtt_us; long m = sample; - if (m == 0) - m = 1; - if (new_sample != 0) { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially @@ -547,6 +544,8 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); + if (!delta_us) + delta_us = 1; tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -563,8 +562,11 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + u32 delta_us; + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); tcp_rcv_rtt_update(tp, delta_us, 0); } } @@ -579,6 +581,7 @@ void tcp_rcv_space_adjust(struct sock *sk) int time; int copied; + tcp_mstamp_refresh(tp); time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return; @@ -1941,6 +1944,8 @@ void tcp_enter_loss(struct sock *sk) if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); tp->sacked_out = 0; + /* Mark SACK reneging until we recover from this loss event. */ + tp->is_sack_reneg = 1; } tcp_clear_all_retrans_hints(tp); @@ -2326,6 +2331,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) } tp->snd_cwnd_stamp = tcp_jiffies32; tp->undo_marker = 0; + tp->rack.advanced = 1; /* Force RACK to re-exam losses */ } static inline bool tcp_may_undo(const struct tcp_sock *tp) @@ -2364,6 +2370,7 @@ static bool tcp_try_undo_recovery(struct sock *sk) return true; } tcp_set_ca_state(sk, TCP_CA_Open); + tp->is_sack_reneg = 0; return false; } @@ -2397,8 +2404,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; - if (frto_undo || tcp_is_sack(tp)) + if (frto_undo || tcp_is_sack(tp)) { tcp_set_ca_state(sk, TCP_CA_Open); + tp->is_sack_reneg = 0; + } return true; } return false; @@ -3495,6 +3504,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct tcp_sacktag_state sack_state; struct rate_sample rs = { .prior_delivered = 0 }; u32 prior_snd_una = tp->snd_una; + bool is_sack_reneg = tp->is_sack_reneg; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; @@ -3611,7 +3621,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ lost = tp->lost - lost; /* freshly marked lost */ - tcp_rate_gen(sk, delivered, lost, sack_state.rate); + tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate); tcp_cong_control(sk, ack, delivered, flag, sack_state.rate); tcp_xmit_recovery(sk, rexmit); return 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c6bc0c4d19c6..94e28350f420 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -848,7 +848,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); @@ -1591,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_filter); +static void tcp_v4_restore_cb(struct sk_buff *skb) +{ + memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, + sizeof(struct inet_skb_parm)); +} + +static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, + const struct tcphdr *th) +{ + /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() + * barrier() makes sure compiler wont play fool^Waliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), + sizeof(struct inet_skb_parm)); + barrier(); + + TCP_SKB_CB(skb)->seq = ntohl(th->seq); + TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + + skb->len - th->doff * 4); + TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; + TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); + TCP_SKB_CB(skb)->sacked = 0; + TCP_SKB_CB(skb)->has_rxtstamp = + skb->tstamp || skb_hwtstamps(skb)->hwtstamp; +} + /* * From tcp_input.c */ @@ -1631,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); - /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() - * barrier() makes sure compiler wont play fool^Waliasing games. - */ - memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), - sizeof(struct inet_skb_parm)); - barrier(); - - TCP_SKB_CB(skb)->seq = ntohl(th->seq); - TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + - skb->len - th->doff * 4); - TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; - TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); - TCP_SKB_CB(skb)->sacked = 0; - TCP_SKB_CB(skb)->has_rxtstamp = - skb->tstamp || skb_hwtstamps(skb)->hwtstamp; - lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); @@ -1679,14 +1689,19 @@ process: sock_hold(sk); refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) + if (!tcp_filter(sk, skb)) { + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false); + } if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); + tcp_v4_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; @@ -1712,6 +1727,7 @@ process: goto discard_and_relse; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; @@ -1742,6 +1758,8 @@ no_tcp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; + tcp_v4_fill_cb(skb, iph, th); + if (tcp_checksum_complete(skb)) { csum_error: __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); @@ -1768,6 +1786,8 @@ do_time_wait: goto discard_it; } + tcp_v4_fill_cb(skb, iph, th); + if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; @@ -1784,6 +1804,7 @@ do_time_wait: if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; + tcp_v4_restore_cb(skb); refcounted = false; goto process; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e36eff0403f4..b079b619b60c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -310,10 +310,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (state == TCP_TIME_WAIT) timeo = TCP_TIMEWAIT_LEN; + /* tw_timer is pinned, so we need to make sure BH are disabled + * in following section, otherwise timer handler could run before + * we complete the initialization. + */ + local_bh_disable(); inet_twsk_schedule(tw, timeo); /* Linkage updates. */ __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); + local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 3330a370d306..c61240e43923 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, /* Update the connection delivery information and generate a rate sample. */ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, - struct rate_sample *rs) + bool is_sack_reneg, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); u32 snd_us, ack_us; @@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ - /* Return an invalid sample if no timing information is available. */ - if (!rs->prior_mstamp) { + /* Return an invalid sample if no timing information is available or + * in recovery from loss with SACK reneging. Rate samples taken during + * a SACK reneging event may overestimate bw by including packets that + * were SACKed before the reneg. + */ + if (!rs->prior_mstamp || is_sack_reneg) { rs->delivered = -1; rs->interval_us = -1; return; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index d3ea89020c69..3a81720ac0c4 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -55,7 +55,8 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) * to queuing or delayed ACKs. */ reo_wnd = 1000; - if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) { + if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) && + min_rtt != ~0U) { reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd); reo_wnd = min(reo_wnd, tp->srtt_us >> 3); } @@ -79,12 +80,12 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) */ remaining = tp->rack.rtt_us + reo_wnd - tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); - if (remaining < 0) { + if (remaining <= 0) { tcp_rack_mark_skb_lost(sk, skb); list_del_init(&skb->tcp_tsorted_anchor); } else { - /* Record maximum wait time (+1 to avoid 0) */ - *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining); + /* Record maximum wait time */ + *reo_timeout = max_t(u32, *reo_timeout, remaining); } } } @@ -116,13 +117,8 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, { u32 rtt_us; - if (tp->rack.mstamp && - !tcp_rack_sent_after(xmit_time, tp->rack.mstamp, - end_seq, tp->rack.end_seq)) - return; - rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time); - if (sacked & TCPCB_RETRANS) { + if (rtt_us < tcp_min_rtt(tp) && (sacked & TCPCB_RETRANS)) { /* If the sacked packet was retransmitted, it's ambiguous * whether the retransmission or the original (or the prior * retransmission) was sacked. @@ -133,13 +129,15 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, * so it's at least one RTT (i.e., retransmission is at least * an RTT later). */ - if (rtt_us < tcp_min_rtt(tp)) - return; + return; } - tp->rack.rtt_us = rtt_us; - tp->rack.mstamp = xmit_time; - tp->rack.end_seq = end_seq; tp->rack.advanced = 1; + tp->rack.rtt_us = rtt_us; + if (tcp_rack_sent_after(xmit_time, tp->rack.mstamp, + end_seq, tp->rack.end_seq)) { + tp->rack.mstamp = xmit_time; + tp->rack.end_seq = end_seq; + } } /* We have waited long enough to accommodate reordering. Mark the expired diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 16df6dd44b98..968fda198376 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -264,6 +264,7 @@ void tcp_delack_timer_handler(struct sock *sk) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } + tcp_mstamp_refresh(tcp_sk(sk)); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } @@ -632,6 +633,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } + tcp_mstamp_refresh(tp); if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) { if (tp->linger2 >= 0) { const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3d3092adf1d2..db84f523656d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -904,7 +904,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, if (t->parms.collect_md) { tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0); if (!tun_dst) - return 0; + goto drop; } ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_error); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index fc6d7d143f2c..844642682b83 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, - int type, struct mld2_grec **ppgr) + int type, struct mld2_grec **ppgr, unsigned int mtu) { - struct net_device *dev = pmc->idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr; - if (!skb) - skb = mld_newpack(pmc->idev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = mld_newpack(pmc->idev, mtu); + if (!skb) + return NULL; + } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV6_MIN_MTU) + return skb; + isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || @@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); } } first = 1; @@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(idev, dev->mtu); + skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -1814,7 +1819,7 @@ empty_source: mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index f06e25065a34..1d7ae9366335 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -458,7 +458,6 @@ mark_source_chains(const struct xt_table_info *newinfo, if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; - e = entry0 + newpos; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 2b1a15846f9a..92c0047e7e33 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -33,13 +33,19 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; - return 0; + return nf_ct_netns_get(par->net, par->family); +} + +static void masquerade_tg6_destroy(const struct xt_tgdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_target masquerade_tg6_reg __read_mostly = { .name = "MASQUERADE", .family = NFPROTO_IPV6, .checkentry = masquerade_tg6_checkentry, + .destroy = masquerade_tg6_destroy, .target = masquerade_tg6, .targetsize = sizeof(struct nf_nat_range), .table = "nat", diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d60ddcb0bfe2..d7dc23c1b2ca 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1098,6 +1098,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; + t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6bb98c93edfe..7178476b3d2f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -994,7 +994,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr), 0, 0); } @@ -1454,7 +1454,6 @@ process: struct sock *nsk; sk = req->rsk_listener; - tcp_v6_fill_cb(skb, hdr, th); if (tcp_v6_inbound_md5_hash(sk, skb)) { sk_drops_add(sk, skb); reqsk_put(req); @@ -1467,8 +1466,12 @@ process: sock_hold(sk); refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) + if (!tcp_filter(sk, skb)) { + th = (const struct tcphdr *)skb->data; + hdr = ipv6_hdr(skb); + tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false); + } if (!nsk) { reqsk_put(req); goto discard_and_relse; @@ -1492,8 +1495,6 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - tcp_v6_fill_cb(skb, hdr, th); - if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; @@ -1501,6 +1502,7 @@ process: goto discard_and_relse; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); + tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; @@ -1590,7 +1592,6 @@ do_time_wait: tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: - tcp_v6_restore_cb(skb); tcp_v6_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 0b750a22c4b9..d4e98f20fc2a 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1625,60 +1625,30 @@ static struct proto kcm_proto = { }; /* Clone a kcm socket. */ -static int kcm_clone(struct socket *osock, struct kcm_clone *info, - struct socket **newsockp) +static struct file *kcm_clone(struct socket *osock) { struct socket *newsock; struct sock *newsk; - struct file *newfile; - int err, newfd; - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = osock->type; newsock->ops = osock->ops; __module_get(newsock->ops->owner); - newfd = get_unused_fd_flags(0); - if (unlikely(newfd < 0)) { - err = newfd; - goto out_fd_fail; - } - - newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - goto out_sock_alloc_fail; - } - newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, &kcm_proto, true); if (!newsk) { - err = -ENOMEM; - goto out_sk_alloc_fail; + sock_release(newsock); + return ERR_PTR(-ENOMEM); } - sock_init_data(newsock, newsk); init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); - fd_install(newfd, newfile); - *newsockp = newsock; - info->fd = newfd; - - return 0; - -out_sk_alloc_fail: - fput(newfile); -out_sock_alloc_fail: - put_unused_fd(newfd); -out_fd_fail: - sock_release(newsock); -out: - return err; + return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); } static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) @@ -1708,17 +1678,25 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } case SIOCKCMCLONE: { struct kcm_clone info; - struct socket *newsock = NULL; - - err = kcm_clone(sock, &info, &newsock); - if (!err) { - if (copy_to_user((void __user *)arg, &info, - sizeof(info))) { - err = -EFAULT; - sys_close(info.fd); - } - } + struct file *file; + + info.fd = get_unused_fd_flags(0); + if (unlikely(info.fd < 0)) + return info.fd; + file = kcm_clone(sock); + if (IS_ERR(file)) { + put_unused_fd(info.fd); + return PTR_ERR(file); + } + if (copy_to_user((void __user *)arg, &info, + sizeof(info))) { + put_unused_fd(info.fd); + fput(file); + return -EFAULT; + } + fd_install(info.fd, file); + err = 0; break; } default: diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 167f83b853e6..1621b6ab17ba 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -291,16 +291,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, int i; mutex_lock(&sta->ampdu_mlme.mtx); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_LEAVE_QBSS, reason != AGG_STOP_DESTROY_STA && reason != AGG_STOP_PEER_REQUEST); - } - mutex_unlock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) ___ieee80211_stop_tx_ba_session(sta, i, reason); + mutex_unlock(&sta->ampdu_mlme.mtx); /* stopping might queue the work again - so cancel only afterwards */ cancel_work_sync(&sta->ampdu_mlme.work); diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index cf1bf2605c10..dc6347342e34 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -103,7 +103,6 @@ struct bitstr { #define INC_BIT(bs) if((++(bs)->bit)>7){(bs)->cur++;(bs)->bit=0;} #define INC_BITS(bs,b) if(((bs)->bit+=(b))>7){(bs)->cur+=(bs)->bit>>3;(bs)->bit&=7;} #define BYTE_ALIGN(bs) if((bs)->bit){(bs)->cur++;(bs)->bit=0;} -#define CHECK_BOUND(bs,n) if((bs)->cur+(n)>(bs)->end)return(H323_ERROR_BOUND) static unsigned int get_len(struct bitstr *bs); static unsigned int get_bit(struct bitstr *bs); static unsigned int get_bits(struct bitstr *bs, unsigned int b); @@ -165,6 +164,19 @@ static unsigned int get_len(struct bitstr *bs) return v; } +static int nf_h323_error_boundary(struct bitstr *bs, size_t bytes, size_t bits) +{ + bits += bs->bit; + bytes += bits / BITS_PER_BYTE; + if (bits % BITS_PER_BYTE > 0) + bytes++; + + if (*bs->cur + bytes > *bs->end) + return 1; + + return 0; +} + /****************************************************************************/ static unsigned int get_bit(struct bitstr *bs) { @@ -279,8 +291,8 @@ static int decode_bool(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); INC_BIT(bs); - - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -293,11 +305,14 @@ static int decode_oid(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; + len = *bs->cur++; bs->cur += len; + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; - CHECK_BOUND(bs, 0); return H323_ERROR_NONE; } @@ -319,6 +334,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, bs->cur += 2; break; case CONS: /* 64K < Range < 4G */ + if (nf_h323_error_boundary(bs, 0, 2)) + return H323_ERROR_BOUND; len = get_bits(bs, 2) + 1; BYTE_ALIGN(bs); if (base && (f->attr & DECODE)) { /* timeToLive */ @@ -330,7 +347,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, break; case UNCO: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); bs->cur += len; break; @@ -341,7 +359,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f, PRINT("\n"); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -357,7 +376,8 @@ static int decode_enum(struct bitstr *bs, const struct field_t *f, INC_BITS(bs, f->sz); } - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -375,12 +395,14 @@ static int decode_bitstr(struct bitstr *bs, const struct field_t *f, len = f->lb; break; case WORD: /* 2-byte length */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) << 8; len += (*bs->cur++) + f->lb; break; case SEMI: - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); break; default: @@ -391,7 +413,8 @@ static int decode_bitstr(struct bitstr *bs, const struct field_t *f, bs->cur += len >> 3; bs->bit = len & 7; - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -404,12 +427,15 @@ static int decode_numstr(struct bitstr *bs, const struct field_t *f, PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); INC_BITS(bs, (len << 2)); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -440,15 +466,19 @@ static int decode_octstr(struct bitstr *bs, const struct field_t *f, break; case BYTE: /* Range == 256 */ BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) + f->lb; break; case SEMI: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs) + f->lb; break; default: /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); break; @@ -458,7 +488,8 @@ static int decode_octstr(struct bitstr *bs, const struct field_t *f, PRINT("\n"); - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -473,10 +504,13 @@ static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, switch (f->sz) { case BYTE: /* Range == 256 */ BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; len = (*bs->cur++) + f->lb; break; default: /* 2 <= Range <= 255 */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; len = get_bits(bs, f->sz) + f->lb; BYTE_ALIGN(bs); break; @@ -484,7 +518,8 @@ static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, bs->cur += len << 1; - CHECK_BOUND(bs, 0); + if (nf_h323_error_boundary(bs, 0, 0)) + return H323_ERROR_BOUND; return H323_ERROR_NONE; } @@ -503,9 +538,13 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; /* Extensible? */ + if (nf_h323_error_boundary(bs, 0, 1)) + return H323_ERROR_BOUND; ext = (f->attr & EXT) ? get_bit(bs) : 0; /* Get fields bitmap */ + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -525,9 +564,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Decode */ if (son->attr & OPEN) { /* Open field */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -555,8 +596,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, return H323_ERROR_NONE; /* Get the extension bitmap */ + if (nf_h323_error_boundary(bs, 0, 7)) + return H323_ERROR_BOUND; bmp2_len = get_bits(bs, 7) + 1; - CHECK_BOUND(bs, (bmp2_len + 7) >> 3); + if (nf_h323_error_boundary(bs, 0, bmp2_len)) + return H323_ERROR_BOUND; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) @@ -567,9 +611,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, for (opt = 0; opt < bmp2_len; opt++, i++, son++) { /* Check Range */ if (i >= f->ub) { /* Newer Version? */ - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; bs->cur += len; continue; } @@ -583,9 +629,11 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, if (!((0x80000000 >> opt) & bmp2)) /* Not present */ continue; - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -623,22 +671,27 @@ static int decode_seqof(struct bitstr *bs, const struct field_t *f, switch (f->sz) { case BYTE: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 1); + if (nf_h323_error_boundary(bs, 1, 0)) + return H323_ERROR_BOUND; count = *bs->cur++; break; case WORD: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; count = *bs->cur++; count <<= 8; count += *bs->cur++; break; case SEMI: BYTE_ALIGN(bs); - CHECK_BOUND(bs, 2); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; count = get_len(bs); break; default: + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; count = get_bits(bs, f->sz); break; } @@ -658,8 +711,11 @@ static int decode_seqof(struct bitstr *bs, const struct field_t *f, for (i = 0; i < count; i++) { if (son->attr & OPEN) { BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); @@ -710,11 +766,17 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; /* Decode the choice index number */ + if (nf_h323_error_boundary(bs, 0, 1)) + return H323_ERROR_BOUND; if ((f->attr & EXT) && get_bit(bs)) { ext = 1; + if (nf_h323_error_boundary(bs, 0, 7)) + return H323_ERROR_BOUND; type = get_bits(bs, 7) + f->lb; } else { ext = 0; + if (nf_h323_error_boundary(bs, 0, f->sz)) + return H323_ERROR_BOUND; type = get_bits(bs, f->sz); if (type >= f->lb) return H323_ERROR_RANGE; @@ -727,8 +789,11 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, /* Check Range */ if (type >= f->ub) { /* Newer version? */ BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, 2, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; bs->cur += len; return H323_ERROR_NONE; } @@ -742,8 +807,11 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f, if (ext || (son->attr & OPEN)) { BYTE_ALIGN(bs); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; len = get_len(bs); - CHECK_BOUND(bs, len); + if (nf_h323_error_boundary(bs, len, 0)) + return H323_ERROR_BOUND; if (!base || !(son->attr & DECODE)) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 59c08997bfdf..382d49792f42 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,6 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> -#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> @@ -1566,9 +1565,11 @@ static int ctnetlink_change_helper(struct nf_conn *ct, static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { - u_int32_t timeout = ntohl(nla_get_be32(cda[CTA_TIMEOUT])); + u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; - ct->timeout = nfct_time_stamp + timeout * HZ; + if (timeout > INT_MAX) + timeout = INT_MAX; + ct->timeout = nfct_time_stamp + (u32)timeout; if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; @@ -1768,6 +1769,7 @@ ctnetlink_create_conntrack(struct net *net, int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; + u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1776,7 +1778,10 @@ ctnetlink_create_conntrack(struct net *net, if (!cda[CTA_TIMEOUT]) goto err1; - ct->timeout = nfct_time_stamp + ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; + timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; + if (timeout > INT_MAX) + timeout = INT_MAX; + ct->timeout = (u32)timeout + nfct_time_stamp; rcu_read_lock(); if (cda[CTA_HELP]) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b12fc07111d0..37ef35b861f2 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1039,6 +1039,9 @@ static int tcp_packet(struct nf_conn *ct, IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) timeout = timeouts[TCP_CONNTRACK_UNACK]; + else if (ct->proto.tcp.last_win == 0 && + timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) + timeout = timeouts[TCP_CONNTRACK_RETRANS]; else timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d8327b43e4dc..10798b357481 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5847,6 +5847,12 @@ static int __net_init nf_tables_init_net(struct net *net) return 0; } +static void __net_exit nf_tables_exit_net(struct net *net) +{ + WARN_ON_ONCE(!list_empty(&net->nft.af_info)); + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); +} + int __nft_release_basechain(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; @@ -5917,6 +5923,7 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi) static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, + .exit = nf_tables_exit_net, }; static int __init nf_tables_module_init(void) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 41628b393673..d33ce6d5ebce 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/errno.h> +#include <linux/capability.h> #include <net/netlink.h> #include <net/sock.h> @@ -407,6 +408,9 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; int ret = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) return -EINVAL; @@ -611,6 +615,9 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; bool tuple_set = false; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_cthelper_dump_table, @@ -678,6 +685,9 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth, *n; int j = 0, ret; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tb[NFCTH_NAME]) helper_name = nla_data(tb[NFCTH_NAME]); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e5afab86381c..e955bec0acc6 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1093,10 +1093,15 @@ static int __net_init nfnl_log_net_init(struct net *net) static void __net_exit nfnl_log_net_exit(struct net *net) { + struct nfnl_log_net *log = nfnl_log_pernet(net); + unsigned int i; + #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); + for (i = 0; i < INSTANCE_BUCKETS; i++) + WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index a16356cacec3..c09b36755ed7 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1512,10 +1512,15 @@ static int __net_init nfnl_queue_net_init(struct net *net) static void __net_exit nfnl_queue_net_exit(struct net *net) { + struct nfnl_queue_net *q = nfnl_queue_pernet(net); + unsigned int i; + nf_unregister_queue_handler(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif + for (i = 0; i < INSTANCE_BUCKETS; i++) + WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a0a93d987a3b..47ec1046ad11 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -214,6 +214,8 @@ static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 }, [NFTA_EXTHDR_LEN] = { .type = NLA_U32 }, [NFTA_EXTHDR_FLAGS] = { .type = NLA_U32 }, + [NFTA_EXTHDR_OP] = { .type = NLA_U32 }, + [NFTA_EXTHDR_SREG] = { .type = NLA_U32 }, }; static int nft_exthdr_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a77dd514297c..55802e97f906 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1729,8 +1729,17 @@ static int __net_init xt_net_init(struct net *net) return 0; } +static void __net_exit xt_net_exit(struct net *net) +{ + int i; + + for (i = 0; i < NFPROTO_NUMPROTO; i++) + WARN_ON_ONCE(!list_empty(&net->xt.tables[i])); +} + static struct pernet_operations xt_net_ops = { .init = xt_net_init, + .exit = xt_net_exit, }; static int __init xt_init(void) diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 041da0d9c06f..1f7fbd3c7e5a 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -27,6 +27,9 @@ static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, { struct sock_fprog_kern program; + if (len > XT_BPF_MAX_NUM_INSTR) + return -EINVAL; + program.len = len; program.filter = insns; @@ -55,6 +58,9 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) mm_segment_t oldfs = get_fs(); int retval, fd; + if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX) + return -EINVAL; + set_fs(KERNEL_DS); fd = bpf_obj_get_user(path, 0); set_fs(oldfs); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 36e14b1f061d..a34f314a8c23 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/capability.h> #include <linux/if.h> #include <linux/inetdevice.h> #include <linux/ip.h> @@ -70,6 +71,9 @@ static int xt_osf_add_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *kf = NULL, *sf; int err = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; @@ -115,6 +119,9 @@ static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *sf; int err = -ENOENT; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b9e0ee4e22f5..79cc1bf36e4a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -253,6 +253,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct sock *sk = skb->sk; int ret = -ENOMEM; + if (!net_eq(dev_net(dev), sock_net(sk))) + return 0; + dev_hold(dev); if (is_vmalloc_addr(skb->head)) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 8886f15abe90..bc2f1e0977d6 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, long i; int ret; - if (rs->rs_bound_addr == 0) { + if (rs->rs_bound_addr == 0 || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 8f7cf4c042be..dcd818fa837e 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -860,6 +860,7 @@ static void rxrpc_sock_destructor(struct sock *sk) static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); @@ -895,8 +896,8 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_queue_work(&rx->local->rxnet->service_conn_reaper); - rxrpc_queue_work(&rx->local->rxnet->client_conn_reaper); + rxrpc_queue_work(&rxnet->service_conn_reaper); + rxrpc_queue_work(&rxnet->client_conn_reaper); rxrpc_put_local(rx->local); rx->local = NULL; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index bda952ffe6a6..ad2ab1103189 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,7 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; - ack_at = jiffies + expiry; + ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); rxrpc_reduce_call_timer(call, ack_at, now, @@ -426,7 +426,7 @@ recheck_state: next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } - + set(call->expect_req_by); set(call->expect_term_by); set(call->ack_at); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 9e9a8db1bc9c..4ca11be6be3c 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -30,22 +30,18 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL; struct rxrpc_channel *chan; struct msghdr msg; - struct kvec iov; + struct kvec iov[3]; struct { struct rxrpc_wire_header whdr; union { - struct { - __be32 code; - } abort; - struct { - struct rxrpc_ackpacket ack; - u8 padding[3]; - struct rxrpc_ackinfo info; - }; + __be32 abort_code; + struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; + struct rxrpc_ackinfo ack_info; size_t len; - u32 serial, mtu, call_id; + int ioc; + u32 serial, mtu, call_id, padding; _enter("%d", conn->debug_id); @@ -66,6 +62,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, msg.msg_controllen = 0; msg.msg_flags = 0; + iov[0].iov_base = &pkt; + iov[0].iov_len = sizeof(pkt.whdr); + iov[1].iov_base = &padding; + iov[1].iov_len = 3; + iov[2].iov_base = &ack_info; + iov[2].iov_len = sizeof(ack_info); + pkt.whdr.epoch = htonl(conn->proto.epoch); pkt.whdr.cid = htonl(conn->proto.cid); pkt.whdr.callNumber = htonl(call_id); @@ -80,8 +83,10 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, len = sizeof(pkt.whdr); switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - pkt.abort.code = htonl(chan->last_abort); - len += sizeof(pkt.abort); + pkt.abort_code = htonl(chan->last_abort); + iov[0].iov_len += sizeof(pkt.abort_code); + len += sizeof(pkt.abort_code); + ioc = 1; break; case RXRPC_PACKET_TYPE_ACK: @@ -94,13 +99,19 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - pkt.info.rxMTU = htonl(rxrpc_rx_mtu); - pkt.info.maxMTU = htonl(mtu); - pkt.info.rwind = htonl(rxrpc_rx_window_size); - pkt.info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + ack_info.rxMTU = htonl(rxrpc_rx_mtu); + ack_info.maxMTU = htonl(mtu); + ack_info.rwind = htonl(rxrpc_rx_window_size); + ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; - len += sizeof(pkt.ack) + sizeof(pkt.info); + padding = 0; + iov[0].iov_len += sizeof(pkt.ack); + len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + ioc = 3; break; + + default: + return; } /* Resync with __rxrpc_disconnect_call() and check that the last call @@ -110,9 +121,6 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, if (READ_ONCE(chan->last_call) != call_id) return; - iov.iov_base = &pkt; - iov.iov_len = len; - serial = atomic_inc_return(&conn->serial); pkt.whdr.serial = htonl(serial); @@ -127,7 +135,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, break; } - kernel_sendmsg(conn->params.local->socket, &msg, &iov, 1, len); + kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); _leave(""); return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 1aad04a32d5e..c628351eb900 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -424,7 +424,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (earliest != now + MAX_JIFFY_OFFSET) { _debug("reschedule reaper %ld", (long)earliest - (long)now); ASSERT(time_after(earliest, now)); - rxrpc_set_service_reap_timer(rxnet, earliest); + rxrpc_set_service_reap_timer(rxnet, earliest); } while (!list_empty(&graveyard)) { diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 23a5e61d8f79..6fc61400337f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -976,7 +976,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, rxrpc_reduce_call_timer(call, expect_rx_by, now, rxrpc_timer_set_for_normal); } - + switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: rxrpc_input_data(call, skb, skew); @@ -1213,7 +1213,7 @@ void rxrpc_data_ready(struct sock *udp_sk) goto reupgrade; conn->service_id = sp->hdr.serviceId; } - + if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a1c53ac066a1..09f2a3e05221 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -233,7 +233,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (resend_at < 1) resend_at = 1; - resend_at = now + rxrpc_resend_timeout; + resend_at += now; WRITE_ONCE(call->resend_at, resend_at); rxrpc_reduce_call_timer(call, resend_at, now, rxrpc_timer_set_for_send); diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 1e3f10e5da99..6445184b2759 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -22,7 +22,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbmark_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 2ea1f26c9e96..7221437ca3a6 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -22,7 +22,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbtcindex_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 8b5abcd2f32f..9438969290a6 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -96,23 +96,16 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_sample_cleanup_rcu(struct rcu_head *rcu) +static void tcf_sample_cleanup(struct tc_action *a, int bind) { - struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu); + struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; - psample_group = rcu_dereference_protected(s->psample_group, 1); + psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); psample_group_put(psample_group); } -static void tcf_sample_cleanup(struct tc_action *a, int bind) -{ - struct tcf_sample *s = to_sample(a); - - call_rcu(&s->rcu, tcf_sample_cleanup_rcu); -} - static bool tcf_sample_dev_ok_push(struct net_device *dev) { switch (dev->type) { @@ -264,7 +257,6 @@ static int __init sample_init_module(void) static void __exit sample_cleanup_module(void) { - rcu_barrier(); tcf_unregister_action(&act_sample_ops, &sample_net_ops); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ddcf04b4ab43..b91ea03e3afa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -23,7 +23,6 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/kmod.h> -#include <linux/err.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -352,6 +351,8 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { struct tcf_chain *chain; + if (!block) + return; /* Hold a refcnt for all chains, except 0, so that they don't disappear * while we are iterating. */ @@ -378,8 +379,6 @@ void tcf_block_put(struct tcf_block *block) { struct tcf_block_ext_info ei = {0, }; - if (!block) - return; tcf_block_put_ext(block, block->q, &ei); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac152b4f4247..507859cdd1cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -45,7 +45,6 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> -#include <linux/netdevice.h> #include <linux/idr.h> struct tc_u_knode { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b6c4f536876b..0f1eab99ff4e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -795,6 +795,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; + if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) + goto nla_put_failure; if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; qlen = q->q.qlen; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index b30a2c70bd48..531250fceb9e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -369,6 +369,9 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) ctl = nla_data(tb[TCA_CHOKE_PARMS]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + return -EINVAL; + if (ctl->limit > CHOKE_MAX_QUEUE) return -EINVAL; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3839cbbdc32b..cd1b200acae7 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -26,6 +26,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> +#include <linux/if_macvlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -277,6 +278,8 @@ unsigned long dev_trans_start(struct net_device *dev) if (is_vlan_dev(dev)) dev = vlan_dev_real_dev(dev); + else if (netif_is_macvlan(dev)) + dev = macvlan_dev_real_dev(dev); res = netdev_get_tx_queue(dev, 0)->trans_start; for (i = 1; i < dev->num_tx_queues; i++) { val = netdev_get_tx_queue(dev, i)->trans_start; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 17c7130454bd..bc30f9186ac6 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -356,6 +356,9 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + return -EINVAL; + if (!q) { table->tab[dp] = q = *prealloc; *prealloc = NULL; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 5ecc38f35d47..fc1286f499c1 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -68,6 +68,8 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + net_inc_ingress_queue(); + mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; @@ -78,7 +80,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) if (err) return err; - net_inc_ingress_queue(); sch->flags |= TCQ_F_CPUSTATS; return 0; @@ -172,6 +173,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + net_inc_ingress_queue(); + net_inc_egress_queue(); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; @@ -190,18 +194,11 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); if (err) - goto err_egress_block_get; - - net_inc_ingress_queue(); - net_inc_egress_queue(); + return err; sch->flags |= TCQ_F_CPUSTATS; return 0; - -err_egress_block_get: - tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); - return err; } static void clsact_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 7f8ea9e297c3..f0747eb87dc4 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -157,6 +157,7 @@ static int red_offload(struct Qdisc *sch, bool enable) .handle = sch->handle, .parent = sch->parent, }; + int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -171,7 +172,14 @@ static int red_offload(struct Qdisc *sch, bool enable) opt.command = TC_RED_DESTROY; } - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); + + if (!err && enable) + sch->flags |= TCQ_F_OFFLOADED; + else + sch->flags &= ~TCQ_F_OFFLOADED; + + return err; } static void red_destroy(struct Qdisc *sch) @@ -212,6 +220,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + return -EINVAL; if (ctl->limit > 0) { child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit); @@ -272,7 +282,7 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) return red_change(sch, opt); } -static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) +static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) { struct net_device *dev = qdisc_dev(sch); struct tc_red_qopt_offload hw_stats = { @@ -284,21 +294,12 @@ static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) .stats.qstats = &sch->qstats, }, }; - int err; - opt->flags &= ~TC_RED_OFFLOADED; - if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) - return 0; - - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, - &hw_stats); - if (err == -EOPNOTSUPP) + if (!(sch->flags & TCQ_F_OFFLOADED)) return 0; - if (!err) - opt->flags |= TC_RED_OFFLOADED; - - return err; + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats); } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -317,7 +318,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) int err; sch->qstats.backlog = q->qdisc->qstats.backlog; - err = red_dump_offload(sch, &opt); + err = red_dump_offload_stats(sch, &opt); if (err) goto nla_put_failure; @@ -345,7 +346,7 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .marked = q->stats.prob_mark + q->stats.forced_mark, }; - if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) { + if (sch->flags & TCQ_F_OFFLOADED) { struct red_stats hw_stats = {0}; struct tc_red_qopt_offload hw_stats_request = { .command = TC_RED_XSTATS, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 09c1203c1711..930e5bd26d3d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -639,6 +639,9 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, + ctl_v1->Wlog)) + return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); if (!p) diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 7b261afc47b9..7f8baa48e7c2 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -53,6 +53,7 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg) msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; + msg->abandoned = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); } @@ -304,6 +305,13 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (!chunk->asoc->peer.prsctp_capable) return 0; + if (chunk->msg->abandoned) + return 1; + + if (!chunk->has_tsn && + !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG)) + return 0; + if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = @@ -316,6 +324,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } + chunk->msg->abandoned = 1; return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { @@ -324,10 +333,12 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; + chunk->msg->abandoned = 1; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && time_after(jiffies, chunk->msg->expires_at)) { + chunk->msg->abandoned = 1; return 1; } /* PRIO policy is processed by sendmsg, not here */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 4db012aa25f7..7d67feeeffc1 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -364,10 +364,12 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; - if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || - chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) + if (!chk->msg->abandoned && + (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; + chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); @@ -377,7 +379,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; - if (!chk->tsn_gap_acked) { + if (queue != &asoc->outqueue.retransmit && + !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); @@ -403,10 +406,13 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { - if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || - chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) + if (!chk->msg->abandoned && + (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || + !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; + chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; @@ -1434,7 +1440,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ - if (!tchunk->tsn_gap_acked) { + if (transmitted_queue != &q->retransmit && + !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 014847e25648..3253f724a995 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3891,13 +3891,17 @@ static int sctp_setsockopt_reset_streams(struct sock *sk, struct sctp_association *asoc; int retval = -EINVAL; - if (optlen < sizeof(struct sctp_reset_streams)) + if (optlen < sizeof(*params)) return -EINVAL; params = memdup_user(optval, optlen); if (IS_ERR(params)) return PTR_ERR(params); + if (params->srs_number_streams * sizeof(__u16) > + optlen - sizeof(*params)) + goto out; + asoc = sctp_id2assoc(sk, params->srs_assoc_id); if (!asoc) goto out; @@ -5080,7 +5084,6 @@ static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *p *newfile = sock_alloc_file(newsock, 0, NULL); if (IS_ERR(*newfile)) { put_unused_fd(retval); - sock_release(newsock); retval = PTR_ERR(*newfile); *newfile = NULL; return retval; diff --git a/net/socket.c b/net/socket.c index 42d8e9c9ccd5..05f361faec45 100644 --- a/net/socket.c +++ b/net/socket.c @@ -406,8 +406,10 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) name.len = strlen(name.name); } path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name); - if (unlikely(!path.dentry)) + if (unlikely(!path.dentry)) { + sock_release(sock); return ERR_PTR(-ENOMEM); + } path.mnt = mntget(sock_mnt); d_instantiate(path.dentry, SOCK_INODE(sock)); @@ -415,9 +417,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &socket_file_ops); if (IS_ERR(file)) { - /* drop dentry, keep inode */ + /* drop dentry, keep inode for a bit */ ihold(d_inode(path.dentry)); path_put(&path); + /* ... and now kill it properly */ + sock_release(sock); return file; } @@ -1330,19 +1334,9 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) retval = sock_create(family, type, protocol, &sock); if (retval < 0) - goto out; - - retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); - if (retval < 0) - goto out_release; - -out: - /* It may be already another descriptor 8) Not kernel problem. */ - return retval; + return retval; -out_release: - sock_release(sock); - return retval; + return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } /* @@ -1366,87 +1360,72 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* + * reserve descriptors and make sure we won't fail + * to return them to userland. + */ + fd1 = get_unused_fd_flags(flags); + if (unlikely(fd1 < 0)) + return fd1; + + fd2 = get_unused_fd_flags(flags); + if (unlikely(fd2 < 0)) { + put_unused_fd(fd1); + return fd2; + } + + err = put_user(fd1, &usockvec[0]); + if (err) + goto out; + + err = put_user(fd2, &usockvec[1]); + if (err) + goto out; + + /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); - if (err < 0) + if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); - if (err < 0) - goto out_release_1; - - err = sock1->ops->socketpair(sock1, sock2); - if (err < 0) - goto out_release_both; - - fd1 = get_unused_fd_flags(flags); - if (unlikely(fd1 < 0)) { - err = fd1; - goto out_release_both; + if (unlikely(err < 0)) { + sock_release(sock1); + goto out; } - fd2 = get_unused_fd_flags(flags); - if (unlikely(fd2 < 0)) { - err = fd2; - goto out_put_unused_1; + err = sock1->ops->socketpair(sock1, sock2); + if (unlikely(err < 0)) { + sock_release(sock2); + sock_release(sock1); + goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); - goto out_put_unused_both; + sock_release(sock2); + goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); - goto out_fput_1; + fput(newfile1); + goto out; } - err = put_user(fd1, &usockvec[0]); - if (err) - goto out_fput_both; - - err = put_user(fd2, &usockvec[1]); - if (err) - goto out_fput_both; - audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); - /* fd1 and fd2 may be already another descriptors. - * Not kernel problem. - */ - return 0; -out_fput_both: - fput(newfile2); - fput(newfile1); - put_unused_fd(fd2); - put_unused_fd(fd1); - goto out; - -out_fput_1: - fput(newfile1); - put_unused_fd(fd2); - put_unused_fd(fd1); - sock_release(sock2); - goto out; - -out_put_unused_both: +out: put_unused_fd(fd2); -out_put_unused_1: put_unused_fd(fd1); -out_release_both: - sock_release(sock2); -out_release_1: - sock_release(sock1); -out: return err; } @@ -1562,7 +1541,6 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, if (IS_ERR(newfile)) { err = PTR_ERR(newfile); put_unused_fd(newfd); - sock_release(newsock); goto out_put; } diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index c4778cae58ef..444380f968f1 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -231,6 +231,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, goto out_free_groups; creds->cr_group_info->gid[i] = kgid; } + groups_sort(creds->cr_group_info); return 0; out_free_groups: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5dd4e6c9fef2..26531193fce4 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -481,6 +481,7 @@ static int rsc_parse(struct cache_detail *cd, goto out; rsci.cred.cr_group_info->gid[i] = kgid; } + groups_sort(rsci.cred.cr_group_info); /* mech name */ len = qword_get(&mesg, buf, mlen); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 740b67d5a733..af7f28fb8102 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -520,6 +520,7 @@ static int unix_gid_parse(struct cache_detail *cd, ug.gi->gid[i] = kgid; } + groups_sort(ug.gi); ugp = unix_gid_lookup(cd, uid); if (ugp) { struct cache_head *ch; @@ -819,6 +820,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv)); cred->cr_group_info->gid[i] = kgid; } + groups_sort(cred->cr_group_info); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 333b9d697ae5..33b74fd84051 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1001,6 +1001,7 @@ void xprt_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + unsigned int connect_cookie; int status, numreqs; dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); @@ -1024,6 +1025,7 @@ void xprt_transmit(struct rpc_task *task) } else if (!req->rq_bytes_sent) return; + connect_cookie = xprt->connect_cookie; req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); trace_xprt_transmit(xprt, req->rq_xid, status); @@ -1047,20 +1049,28 @@ void xprt_transmit(struct rpc_task *task) xprt->stat.bklog_u += xprt->backlog.qlen; xprt->stat.sending_u += xprt->sending.qlen; xprt->stat.pending_u += xprt->pending.qlen; + spin_unlock_bh(&xprt->transport_lock); - /* Don't race with disconnect */ - if (!xprt_connected(xprt)) - task->tk_status = -ENOTCONN; - else { + req->rq_connect_cookie = connect_cookie; + if (rpc_reply_expected(task) && !READ_ONCE(req->rq_reply_bytes_recvd)) { /* - * Sleep on the pending queue since - * we're expecting a reply. + * Sleep on the pending queue if we're expecting a reply. + * The spinlock ensures atomicity between the test of + * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). */ - if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) + spin_lock(&xprt->recv_lock); + if (!req->rq_reply_bytes_recvd) { rpc_sleep_on(&xprt->pending, task, xprt_timer); - req->rq_connect_cookie = xprt->connect_cookie; + /* + * Send an extra queue wakeup call if the + * connection was dropped in case the call to + * rpc_sleep_on() raced. + */ + if (!xprt_connected(xprt)) + xprt_wake_pending_tasks(xprt, -ENOTCONN); + } + spin_unlock(&xprt->recv_lock); } - spin_unlock_bh(&xprt->transport_lock); } static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index ed34dc0f144c..a3f2ab283aeb 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1408,11 +1408,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", __func__, rep, req, be32_to_cpu(rep->rr_xid)); - if (list_empty(&req->rl_registered) && - !test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) - rpcrdma_complete_rqst(rep); - else - queue_work(rpcrdma_receive_wq, &rep->rr_work); + queue_work_on(req->rl_cpu, rpcrdma_receive_wq, &rep->rr_work); return; out_badstatus: diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 646c24494ea7..6ee1ad8978f3 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -52,6 +52,7 @@ #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/sunrpc/addr.h> +#include <linux/smp.h> #include "xprt_rdma.h" @@ -656,6 +657,7 @@ xprt_rdma_allocate(struct rpc_task *task) task->tk_pid, __func__, rqst->rq_callsize, rqst->rq_rcvsize, req); + req->rl_cpu = smp_processor_id(); req->rl_connect_cookie = 0; /* our reserved value */ rpcrdma_set_xprtdata(rqst, req); rqst->rq_buffer = req->rl_sendbuf->rg_base; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 710b3f77db82..8607c029c0dd 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -83,7 +83,7 @@ rpcrdma_alloc_wq(void) struct workqueue_struct *recv_wq; recv_wq = alloc_workqueue("xprtrdma_receive", - WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_HIGHPRI, + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!recv_wq) return -ENOMEM; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 51686d9eac5f..1342f743f1c4 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -342,6 +342,7 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_list; + int rl_cpu; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply; diff --git a/net/tipc/server.c b/net/tipc/server.c index acaef80fb88c..d60c30342327 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -314,6 +314,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con) newcon->usr_data = s->tipc_conn_new(newcon->conid); if (!newcon->usr_data) { sock_release(newsock); + conn_put(newcon); return -ENOMEM; } @@ -511,7 +512,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, s = con->server; scbr = s->tipc_conn_new(*conid); if (!scbr) { - tipc_close_conn(con); + conn_put(con); return false; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 5d18c0caa92b..41127d0b925e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1140,7 +1140,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, __skb_dequeue(arrvq); __skb_queue_tail(inputq, skb); } - refcount_dec(&skb->users); + kfree_skb(skb); spin_unlock_bh(&inputq->lock); continue; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index ecca64fc6a6f..3deabcab4882 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -371,10 +371,6 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) goto rcu_out; } - tipc_rcv(sock_net(sk), skb, b); - rcu_read_unlock(); - return 0; - rcu_out: rcu_read_unlock(); out: diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 5583df708b8c..a827547aa102 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -487,7 +487,7 @@ static void hvs_release(struct vsock_sock *vsk) lock_sock(sk); - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; vsock_remove_sock(vsk); release_sock(sk); diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 278d979c211a..d7d6cb00c47b 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -25,17 +25,45 @@ endif $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) @$(kecho) " GEN $@" - @echo '#include "reg.h"' > $@ - @echo 'const u8 shipped_regdb_certs[] = {' >> $@ - @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done - @echo '};' >> $@ - @echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@ + @(set -e; \ + allf=""; \ + for f in $^ ; do \ + # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ + thisf=$$(od -An -v -tx1 < $$f | \ + sed -e 's/ /\n/g' | \ + sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ + sed -e 's/^/0x/;s/$$/,/'); \ + # file should not be empty - maybe command substitution failed? \ + test ! -z "$$thisf";\ + allf=$$allf$$thisf;\ + done; \ + ( \ + echo '#include "reg.h"'; \ + echo 'const u8 shipped_regdb_certs[] = {'; \ + echo "$$allf"; \ + echo '};'; \ + echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ + ) >> $@) $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @$(kecho) " GEN $@" - @echo '#include "reg.h"' > $@ - @echo 'const u8 extra_regdb_certs[] = {' >> $@ - @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done - @echo '};' >> $@ - @echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@ + @(set -e; \ + allf=""; \ + for f in $^ ; do \ + # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ + thisf=$$(od -An -v -tx1 < $$f | \ + sed -e 's/ /\n/g' | \ + sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ + sed -e 's/^/0x/;s/$$/,/'); \ + # file should not be empty - maybe command substitution failed? \ + test ! -z "$$thisf";\ + allf=$$allf$$thisf;\ + done; \ + ( \ + echo '#include "reg.h"'; \ + echo 'const u8 extra_regdb_certs[] = {'; \ + echo "$$allf"; \ + echo '};'; \ + echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);'; \ + ) >> $@) |