diff options
Diffstat (limited to 'net')
62 files changed, 552 insertions, 309 deletions
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 1a11064f9990..8f19253024b0 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)&initial_chain, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~(1 << NF_BR_BROUTING)) - return -EINVAL; - return 0; -} - static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index cb949436bc0e..278f324e6752 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~FILTER_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 5ee0531ae506..9066f7f376d5 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~NAT_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f2dbefb61ce8..9a0ae59cdc50 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1040,8 +1040,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_iterate; } - /* the table doesn't like it */ - if (t->check && (ret = t->check(newinfo, repl->valid_hooks))) + if (repl->valid_hooks != t->valid_hooks) goto free_unlock; if (repl->num_counters && repl->num_counters != t->private->nentries) { @@ -1231,11 +1230,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (ret != 0) goto free_chainstack; - if (table->check && table->check(newinfo, table->valid_hooks)) { - ret = -EINVAL; - goto free_chainstack; - } - table->private = newinfo; rwlock_init(&table->lock); mutex_lock(&ebt_mutex); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 1b7f385643b4..94374d529ea4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { + int optmem_max = READ_ONCE(sysctl_optmem_max); struct sock *sk = (struct sock *)owner; /* same check as in sock_kmalloc() */ - if (size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + if (size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 716df64fcfa5..56c8b0921c9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (netdev_max_backlog >> 1)) + if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) return dev; if (time_after(jiffies, warning_time + - netdev_unregister_timeout_secs * HZ)) { + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); diff --git a/net/core/filter.c b/net/core/filter.c index e8508aaafd27..c191db80ce93 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); + int optmem_max = READ_ONCE(sysctl_optmem_max); /* same check as in sock_kmalloc() */ - if (filter_size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { + if (filter_size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } @@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - if (bpf_prog_size(prog->len) > sysctl_optmem_max) + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); @@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ - if (bpf_prog_size(prog->len) > sysctl_optmem_max) { + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) { err = -ENOMEM; goto err_prog_put; } @@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: - val = min_t(u32, val, sysctl_rmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_rmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: - val = min_t(u32, val, sysctl_wmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index a10335b4ba2d..c8d137ef5980 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -345,7 +345,7 @@ static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats, for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); - qstats->qlen += qcpu->backlog; + qstats->qlen += qcpu->qlen; qstats->backlog += qcpu->backlog; qstats->drops += qcpu->drops; qstats->requeues += qcpu->requeues; diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 541c7a72a28a..21619c70a82b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6a8c2596ebab..78cc8fb68814 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -307,11 +307,35 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list) +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { + struct sk_buff_head tmp; + unsigned long flags; struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) { + skb_queue_head_init(&tmp); + spin_lock_irqsave(&list->lock, flags); + skb = skb_peek(list); + while (skb != NULL) { + struct sk_buff *skb_next = skb_peek_next(skb, list); + struct net_device *dev = skb->dev; + + if (net == NULL || net_eq(dev_net(dev), net)) { + struct in_device *in_dev; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + in_dev->arp_parms->qlen--; + rcu_read_unlock(); + __skb_unlink(skb, list); + __skb_queue_tail(&tmp, skb); + } + skb = skb_next; + } + spin_unlock_irqrestore(&list->lock, flags); + + while ((skb = __skb_dequeue(&tmp))) { dev_put(skb->dev); kfree_skb(skb); } @@ -385,9 +409,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - - del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + if (skb_queue_empty_lockless(&tbl->proxy_queue)) + del_timer_sync(&tbl->proxy_timer); return 0; } @@ -1597,8 +1621,15 @@ static void neigh_proxy_process(struct timer_list *t) if (tdif <= 0) { struct net_device *dev = skb->dev; + struct in_device *in_dev; + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + in_dev->arp_parms->qlen--; + rcu_read_unlock(); __skb_unlink(skb, &tbl->proxy_queue); + if (tbl->proxy_redo && netif_running(dev)) { rcu_read_lock(); tbl->proxy_redo(skb); @@ -1623,7 +1654,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, unsigned long sched_next = jiffies + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY)); - if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { + if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1639,6 +1670,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); + p->qlen++; mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } @@ -1671,6 +1703,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + p->qlen = 0; netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; write_pnet(&p->net, net); @@ -1736,6 +1769,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); + tbl->parms.qlen = 0; tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) @@ -1787,7 +1821,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ac45328607f7..4b5b15c684ed 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -6070,6 +6070,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (kind == RTNL_KIND_DEL && (nlh->nlmsg_flags & NLM_F_BULK) && !(flags & RTNL_FLAG_BULK_DEL_SUPPORTED)) { NL_SET_ERR_MSG(extack, "Bulk delete is not supported"); + module_put(owner); goto err_unlock; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 974bbbbe7138..84bb5e188d0d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4205,9 +4205,8 @@ normal: SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { - skb_copy_bits(head_skb, offset, - skb_put(nskb, len), - len); + if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) + goto err; } continue; } @@ -4798,7 +4797,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; - if (likely(sysctl_tstamp_allow_data || tsonly)) + if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f47338d89d5d..59e75ffcc1f4 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1194,8 +1194,9 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } - if (sk_psock_verdict_apply(psock, skb, ret) < 0) - len = 0; + ret = sk_psock_verdict_apply(psock, skb, ret); + if (ret < 0) + len = ret; out: rcu_read_unlock(); return len; diff --git a/net/core/sock.c b/net/core/sock.c index 4cb957d934a2..788c1372663c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - val = min_t(u32, val, sysctl_wmem_max); + val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. @@ -1133,7 +1133,7 @@ set_sndbuf: * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ - __sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max)); + __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: @@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > - sysctl_optmem_max) + READ_ONCE(sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); @@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned int)size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + int optmem_max = READ_ONCE(sysctl_optmem_max); + + if ((unsigned int)size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. @@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; - sk->sk_rcvbuf = sysctl_rmem_default; - sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); @@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 71a13596ea2b..725891527814 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write, static int proc_do_dev_weight(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret; + static DEFINE_MUTEX(dev_weight_mutex); + int ret, weight; + mutex_lock(&dev_weight_mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret != 0) - return ret; - - dev_rx_weight = weight_p * dev_weight_rx_bias; - dev_tx_weight = weight_p * dev_weight_tx_bias; + if (!ret && write) { + weight = READ_ONCE(weight_p); + WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + } + mutex_unlock(&dev_weight_mutex); return ret; } diff --git a/net/dsa/port.c b/net/dsa/port.c index 2dd76eb1621c..a8895ee3cd60 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -145,11 +145,14 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age) static void dsa_port_set_state_now(struct dsa_port *dp, u8 state, bool do_fast_age) { + struct dsa_switch *ds = dp->ds; int err; err = dsa_port_set_state(dp, state, do_fast_age); - if (err) - pr_err("DSA: failed to set STP state %u (%d)\n", state, err); + if (err && err != -EOPNOTSUPP) { + dev_err(ds->dev, "port %d failed to set STP state %u: %pe\n", + dp->index, state, ERR_PTR(err)); + } } int dsa_port_set_mst_state(struct dsa_port *dp, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ad6a6663feeb..1291c2431d44 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2484,7 +2484,7 @@ static int dsa_slave_changeupper(struct net_device *dev, if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { - if (!extack->_msg) + if (extack && !extack->_msg) NL_SET_ERR_MSG_MOD(extack, "Offloading not supported"); err = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 92b778e423df..e8b9a9202fec 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2682,23 +2682,27 @@ static __net_init int devinet_init_net(struct net *net) #endif if (!net_eq(net, &init_net)) { - if (IS_ENABLED(CONFIG_SYSCTL) && - sysctl_devconf_inherit_init_net == 3) { + switch (net_inherit_devconf()) { + case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); - } else if (!IS_ENABLED(CONFIG_SYSCTL) || - sysctl_devconf_inherit_init_net != 2) { - /* inherit == 0 or 1: copy from init_net */ + break; + case 0: + case 1: + /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); + break; + case 2: + /* use compiled values */ + break; } - /* else inherit == 2: use compiled values */ } #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d7bd1daf022b..04e2034f2f8e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1730,7 +1730,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a8a323ecbb54..e49a61a053a6 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > sysctl_optmem_max) + if (optlen > READ_ONCE(sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > sysctl_optmem_max - 4) + if (optlen > READ_ONCE(sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); @@ -1233,7 +1233,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, if (optlen < IP_MSFILTER_SIZE(0)) goto e_inval; - if (optlen > sysctl_optmem_max) { + if (optlen > READ_ONCE(sysctl_optmem_max)) { err = -ENOBUFS; break; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 970e9a2cca4a..e5011c136fdb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1000,7 +1000,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= sysctl_max_skb_frags) { + if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1354,7 +1354,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= sysctl_max_skb_frags) { + if (i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1567,17 +1567,11 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -void tcp_cleanup_rbuf(struct sock *sk, int copied) +static void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - - WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), - "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", - tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); - if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1623,6 +1617,17 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) tcp_send_ack(sk); } +void tcp_cleanup_rbuf(struct sock *sk, int copied) +{ + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct tcp_sock *tp = tcp_sk(sk); + + WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), + "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", + tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); + __tcp_cleanup_rbuf(sk, copied); +} + static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); @@ -1756,34 +1761,26 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { - int used; - - __skb_unlink(skb, &sk->sk_receive_queue); - used = recv_actor(sk, skb); - if (used <= 0) { - if (!copied) - copied = used; - break; - } - seq += used; - copied += used; + skb = tcp_recv_skb(sk, seq, &offset); + if (!skb) + return 0; - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { - consume_skb(skb); + __skb_unlink(skb, &sk->sk_receive_queue); + WARN_ON(!skb_set_owner_sk_safe(skb, sk)); + copied = recv_actor(sk, skb); + if (copied >= 0) { + seq += copied; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) ++seq; - break; - } - consume_skb(skb); - break; } + consume_skb(skb); WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) - tcp_cleanup_rbuf(sk, copied); + __tcp_cleanup_rbuf(sk, copied); return copied; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 78b654ff421b..290019de766d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - space = max_t(u32, space, sysctl_rmem_max); + space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); space = min_t(u32, space, *window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b624e3d8c5f0..e15f64f22fa8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -7162,9 +7162,8 @@ static int __net_init addrconf_init_net(struct net *net) if (!dflt) goto err_alloc_dflt; - if (IS_ENABLED(CONFIG_SYSCTL) && - !net_eq(net, &init_net)) { - switch (sysctl_devconf_inherit_init_net) { + if (!net_eq(net, &init_net)) { + switch (net_inherit_devconf()) { case 1: /* copy from init_net */ memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3fda5634578c..79c6a827dea9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1517,7 +1517,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) * ip6_tnl_change() updates the tunnel parameters **/ -static int +static void ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; @@ -1531,29 +1531,25 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); ip6_tnl_link_config(t); - return 0; } -static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err; ip6_tnl_unlink(ip6n, t); synchronize_net(); - err = ip6_tnl_change(t, p); + ip6_tnl_change(t, p); ip6_tnl_link(ip6n, t); netdev_state_change(t->dev); - return err; } -static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +static void ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { /* for default tnl0 device allow to change only the proto */ t->parms.proto = p->proto; netdev_state_change(t->dev); - return 0; } static void @@ -1667,9 +1663,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) - err = ip6_tnl0_update(t, &p1); + ip6_tnl0_update(t, &p1); else - err = ip6_tnl_update(t, &p1); + ip6_tnl_update(t, &p1); } if (!IS_ERR(t)) { err = 0; @@ -2091,7 +2087,8 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], } else t = netdev_priv(dev); - return ip6_tnl_update(t, &p); + ip6_tnl_update(t, &p); + return 0; } static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 222f6bf220ba..e0dcc7a193df 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > sysctl_optmem_max) + if (optlen > READ_ONCE(sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > sysctl_optmem_max - 4) + if (optlen > READ_ONCE(sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 98453693e400..3a553494ff16 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1378,6 +1378,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); + if (neigh) + neigh_release(neigh); + rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev, pref, defrtr_usr_metric); if (!rt) { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 7dd3629dd19e..38db0064d661 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -86,7 +86,6 @@ static int nf_ct_frag6_sysctl_register(struct net *net) table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; table[2].extra1 = &nf_frag->fqdir->low_thresh; - table[2].extra2 = &nf_frag->fqdir->high_thresh; hdr = register_net_sysctl(net, "net/netfilter", table); if (hdr == NULL) diff --git a/net/key/af_key.c b/net/key/af_key.c index fda2dcc8a383..c85df5b958d2 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad pfk->registered |= (1<<hdr->sadb_msg_satype); } + mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&pfkey_mutex); + if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index da4257504fad..d398f3810662 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1263,7 +1263,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); - if (!can_coalesce && i >= sysctl_max_skb_frags) { + if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 22f15ebf6045..4b8d04640ff3 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -144,7 +144,6 @@ config NF_CONNTRACK_ZONES config NF_CONNTRACK_PROCFS bool "Supply CT list in procfs (OBSOLETE)" - default y depends on PROC_FS help This option enables for the list of known conntrack entries diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 9d43277b8b4f..a56fd0b5a430 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val) lock_sock(sk); if (mode) { val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2, - sysctl_wmem_max); + READ_ONCE(sysctl_wmem_max)); sk->sk_sndbuf = val * 2; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } else { val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2, - sysctl_rmem_max); + READ_ONCE(sysctl_rmem_max)); sk->sk_rcvbuf = val * 2; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index a414274338cf..0d9332e9cf71 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -34,11 +34,6 @@ MODULE_DESCRIPTION("ftp connection tracking helper"); MODULE_ALIAS("ip_conntrack_ftp"); MODULE_ALIAS_NFCT_HELPER(HELPER_NAME); -/* This is slow, but it's simple. --RR */ -static char *ftp_buffer; - -static DEFINE_SPINLOCK(nf_ftp_lock); - #define MAX_PORTS 8 static u_int16_t ports[MAX_PORTS]; static unsigned int ports_c; @@ -398,6 +393,9 @@ static int help(struct sk_buff *skb, return NF_ACCEPT; } + if (unlikely(skb_linearize(skb))) + return NF_DROP; + th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); if (th == NULL) return NF_ACCEPT; @@ -411,12 +409,8 @@ static int help(struct sk_buff *skb, } datalen = skb->len - dataoff; - spin_lock_bh(&nf_ftp_lock); - fb_ptr = skb_header_pointer(skb, dataoff, datalen, ftp_buffer); - if (!fb_ptr) { - spin_unlock_bh(&nf_ftp_lock); - return NF_ACCEPT; - } + spin_lock_bh(&ct->lock); + fb_ptr = skb->data + dataoff; ends_in_nl = (fb_ptr[datalen - 1] == '\n'); seq = ntohl(th->seq) + datalen; @@ -544,7 +538,7 @@ out_update_nl: if (ends_in_nl) update_nl_seq(ct, seq, ct_ftp_info, dir, skb); out: - spin_unlock_bh(&nf_ftp_lock); + spin_unlock_bh(&ct->lock); return ret; } @@ -571,7 +565,6 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = { static void __exit nf_conntrack_ftp_fini(void) { nf_conntrack_helpers_unregister(ftp, ports_c * 2); - kfree(ftp_buffer); } static int __init nf_conntrack_ftp_init(void) @@ -580,10 +573,6 @@ static int __init nf_conntrack_ftp_init(void) NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_ftp_master)); - ftp_buffer = kmalloc(65536, GFP_KERNEL); - if (!ftp_buffer) - return -ENOMEM; - if (ports_c == 0) ports[ports_c++] = FTP_PORT; @@ -603,7 +592,6 @@ static int __init nf_conntrack_ftp_init(void) ret = nf_conntrack_helpers_register(ftp, ports_c * 2); if (ret < 0) { pr_err("failed to register helpers\n"); - kfree(ftp_buffer); return ret; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bb76305bb7ff..5a9bce24f3c3 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -34,6 +34,8 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_conntrack_h323.h> +#define H323_MAX_SIZE 65535 + /* Parameters */ static unsigned int default_rrq_ttl __read_mostly = 300; module_param(default_rrq_ttl, uint, 0600); @@ -86,6 +88,9 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff, if (tcpdatalen <= 0) /* No TCP data */ goto clear_out; + if (tcpdatalen > H323_MAX_SIZE) + tcpdatalen = H323_MAX_SIZE; + if (*data == NULL) { /* first TPKT */ /* Get first TPKT pointer */ tpkt = skb_header_pointer(skb, tcpdataoff, tcpdatalen, @@ -1169,6 +1174,9 @@ static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff, if (dataoff >= skb->len) return NULL; *datalen = skb->len - dataoff; + if (*datalen > H323_MAX_SIZE) + *datalen = H323_MAX_SIZE; + return skb_header_pointer(skb, dataoff, *datalen, h323_buffer); } @@ -1770,7 +1778,7 @@ static int __init nf_conntrack_h323_init(void) NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_h323_master)); - h323_buffer = kmalloc(65536, GFP_KERNEL); + h323_buffer = kmalloc(H323_MAX_SIZE + 1, GFP_KERNEL); if (!h323_buffer) return -ENOMEM; ret = h323_helper_init(); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 08ee4e760a3d..1796c456ac98 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -39,6 +39,7 @@ unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_irc_hook); #define HELPER_NAME "irc" +#define MAX_SEARCH_SIZE 4095 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("IRC (DCC) connection tracking helper"); @@ -121,6 +122,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, int i, ret = NF_ACCEPT; char *addr_beg_p, *addr_end_p; typeof(nf_nat_irc_hook) nf_nat_irc; + unsigned int datalen; /* If packet is coming from IRC server */ if (dir == IP_CT_DIR_REPLY) @@ -140,8 +142,12 @@ static int help(struct sk_buff *skb, unsigned int protoff, if (dataoff >= skb->len) return NF_ACCEPT; + datalen = skb->len - dataoff; + if (datalen > MAX_SEARCH_SIZE) + datalen = MAX_SEARCH_SIZE; + spin_lock_bh(&irc_buffer_lock); - ib_ptr = skb_header_pointer(skb, dataoff, skb->len - dataoff, + ib_ptr = skb_header_pointer(skb, dataoff, datalen, irc_buffer); if (!ib_ptr) { spin_unlock_bh(&irc_buffer_lock); @@ -149,7 +155,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, } data = ib_ptr; - data_limit = ib_ptr + skb->len - dataoff; + data_limit = ib_ptr + datalen; /* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24 * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */ @@ -251,7 +257,7 @@ static int __init nf_conntrack_irc_init(void) irc_exp_policy.max_expected = max_dcc_channels; irc_exp_policy.timeout = dcc_timeout; - irc_buffer = kmalloc(65536, GFP_KERNEL); + irc_buffer = kmalloc(MAX_SEARCH_SIZE + 1, GFP_KERNEL); if (!irc_buffer) return -ENOMEM; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a63b51dceaf2..a634c72b1ffc 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct, tn->tcp_be_liberal) res = true; if (!res) { + bool seq_ok = before(seq, sender->td_maxend + 1); + + if (!seq_ok) { + u32 overshot = end - sender->td_maxend + 1; + bool ack_ok; + + ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1); + + if (in_recv_win && + ack_ok && + overshot <= receiver->td_maxwin && + before(sack, receiver->td_end + 1)) { + /* Work around TCPs that send more bytes than allowed by + * the receive window. + * + * If the (marked as invalid) packet is allowed to pass by + * the ruleset and the peer acks this data, then its possible + * all future packets will trigger 'ACK is over upper bound' check. + * + * Thus if only the sequence check fails then do update td_end so + * possible ACK for this data can update internal state. + */ + sender->td_end = end; + sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; + + nf_ct_l4proto_log_invalid(skb, ct, hook_state, + "%u bytes more than expected", overshot); + return res; + } + } + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ? diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index fcb33b1d5456..13dc421fc4f5 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -34,10 +34,6 @@ MODULE_AUTHOR("Michal Schmidt <mschmidt@redhat.com>"); MODULE_DESCRIPTION("SANE connection tracking helper"); MODULE_ALIAS_NFCT_HELPER(HELPER_NAME); -static char *sane_buffer; - -static DEFINE_SPINLOCK(nf_sane_lock); - #define MAX_PORTS 8 static u_int16_t ports[MAX_PORTS]; static unsigned int ports_c; @@ -67,14 +63,16 @@ static int help(struct sk_buff *skb, unsigned int dataoff, datalen; const struct tcphdr *th; struct tcphdr _tcph; - void *sb_ptr; int ret = NF_ACCEPT; int dir = CTINFO2DIR(ctinfo); struct nf_ct_sane_master *ct_sane_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple *tuple; - struct sane_request *req; struct sane_reply_net_start *reply; + union { + struct sane_request req; + struct sane_reply_net_start repl; + } buf; /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && @@ -92,59 +90,62 @@ static int help(struct sk_buff *skb, return NF_ACCEPT; datalen = skb->len - dataoff; - - spin_lock_bh(&nf_sane_lock); - sb_ptr = skb_header_pointer(skb, dataoff, datalen, sane_buffer); - if (!sb_ptr) { - spin_unlock_bh(&nf_sane_lock); - return NF_ACCEPT; - } - if (dir == IP_CT_DIR_ORIGINAL) { + const struct sane_request *req; + if (datalen != sizeof(struct sane_request)) - goto out; + return NF_ACCEPT; + + req = skb_header_pointer(skb, dataoff, datalen, &buf.req); + if (!req) + return NF_ACCEPT; - req = sb_ptr; if (req->RPC_code != htonl(SANE_NET_START)) { /* Not an interesting command */ - ct_sane_info->state = SANE_STATE_NORMAL; - goto out; + WRITE_ONCE(ct_sane_info->state, SANE_STATE_NORMAL); + return NF_ACCEPT; } /* We're interested in the next reply */ - ct_sane_info->state = SANE_STATE_START_REQUESTED; - goto out; + WRITE_ONCE(ct_sane_info->state, SANE_STATE_START_REQUESTED); + return NF_ACCEPT; } + /* IP_CT_DIR_REPLY */ + /* Is it a reply to an uninteresting command? */ - if (ct_sane_info->state != SANE_STATE_START_REQUESTED) - goto out; + if (READ_ONCE(ct_sane_info->state) != SANE_STATE_START_REQUESTED) + return NF_ACCEPT; /* It's a reply to SANE_NET_START. */ - ct_sane_info->state = SANE_STATE_NORMAL; + WRITE_ONCE(ct_sane_info->state, SANE_STATE_NORMAL); if (datalen < sizeof(struct sane_reply_net_start)) { pr_debug("NET_START reply too short\n"); - goto out; + return NF_ACCEPT; } - reply = sb_ptr; + datalen = sizeof(struct sane_reply_net_start); + + reply = skb_header_pointer(skb, dataoff, datalen, &buf.repl); + if (!reply) + return NF_ACCEPT; + if (reply->status != htonl(SANE_STATUS_SUCCESS)) { /* saned refused the command */ pr_debug("unsuccessful SANE_STATUS = %u\n", ntohl(reply->status)); - goto out; + return NF_ACCEPT; } /* Invalid saned reply? Ignore it. */ if (reply->zero != 0) - goto out; + return NF_ACCEPT; exp = nf_ct_expect_alloc(ct); if (exp == NULL) { nf_ct_helper_log(skb, ct, "cannot alloc expectation"); - ret = NF_DROP; - goto out; + return NF_DROP; } tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; @@ -162,9 +163,6 @@ static int help(struct sk_buff *skb, } nf_ct_expect_put(exp); - -out: - spin_unlock_bh(&nf_sane_lock); return ret; } @@ -178,7 +176,6 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = { static void __exit nf_conntrack_sane_fini(void) { nf_conntrack_helpers_unregister(sane, ports_c * 2); - kfree(sane_buffer); } static int __init nf_conntrack_sane_init(void) @@ -187,10 +184,6 @@ static int __init nf_conntrack_sane_init(void) NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_sane_master)); - sane_buffer = kmalloc(65536, GFP_KERNEL); - if (!sane_buffer) - return -ENOMEM; - if (ports_c == 0) ports[ports_c++] = SANE_PORT; @@ -210,7 +203,6 @@ static int __init nf_conntrack_sane_init(void) ret = nf_conntrack_helpers_register(sane, ports_c * 2); if (ret < 0) { pr_err("failed to register helpers\n"); - kfree(sane_buffer); return ret; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 765ac779bfc8..81c26a96c30b 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -437,12 +437,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, } } +void nf_flow_table_gc_run(struct nf_flowtable *flow_table) +{ + nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); +} + static void nf_flow_offload_work_gc(struct work_struct *work) { struct nf_flowtable *flow_table; flow_table = container_of(work, struct nf_flowtable, gc_work.work); - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); + nf_flow_table_gc_run(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } @@ -600,11 +605,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) mutex_unlock(&flowtable_lock); cancel_delayed_work_sync(&flow_table->gc_work); - nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); nf_flow_table_offload_flush(flow_table); - if (nf_flowtable_hw_offload(flow_table)) - nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); + /* ... no more pending work after this stage ... */ + nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); + nf_flow_table_gc_run(flow_table); + nf_flow_table_offload_flush_cleanup(flow_table); rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 103b6cbf257f..b04645ced89b 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1074,6 +1074,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, flow_offload_queue_work(offload); } +void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable) +{ + if (nf_flowtable_hw_offload(flowtable)) { + flush_workqueue(nf_flow_offload_del_wq); + nf_flow_table_gc_run(flowtable); + } +} + void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { if (nf_flowtable_hw_offload(flowtable)) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3cc88998b879..2ee50e23c9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); -static u64 table_handle; enum { NFT_VALIDATE_SKIP = 0, @@ -889,7 +888,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -1235,7 +1234,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&table->flowtables); table->family = family; table->flags = flags; - table->handle = ++table_handle; + table->handle = ++nft_net->table_handle; if (table->flags & NFT_TABLE_F_OWNER) table->nlpid = NETLINK_CB(skb).portid; @@ -1705,7 +1704,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -2196,9 +2195,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; + struct nft_stats __percpu *stats = NULL; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; - struct nft_stats __percpu *stats; struct net *net = ctx->net; char name[NFT_NAME_MAXLEN]; struct nft_rule_blob *blob; @@ -2236,7 +2235,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return PTR_ERR(stats); } rcu_assign_pointer(basechain->stats, stats); - static_branch_inc(&nft_counters_enabled); } err = nft_basechain_init(basechain, family, &hook, flags); @@ -2319,6 +2317,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } + if (stats) + static_branch_inc(&nft_counters_enabled); + table->use++; return 0; @@ -2574,6 +2575,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { + if (chain->flags & NFT_CHAIN_BINDING) + return -EINVAL; + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; @@ -3149,7 +3153,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -3907,7 +3911,7 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; - if (!nft_is_active_next(ctx->net, set)) + if (!nft_is_active_next(ctx->net, i)) continue; if (!sscanf(i->name, name, &tmp)) continue; @@ -4133,7 +4137,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && @@ -4451,6 +4455,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; + + if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { + return -EINVAL; } if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) @@ -5061,6 +5070,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) @@ -5196,6 +5207,9 @@ static int nft_setelem_parse_flags(const struct nft_set *set, if (!(set->flags & NFT_SET_INTERVAL) && *flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; + if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) == + (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) + return -EINVAL; return 0; } @@ -5599,7 +5613,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, err = nft_expr_clone(expr, set->exprs[i]); if (err < 0) { - nft_expr_destroy(ctx, expr); + kfree(expr); goto err_expr; } expr_array[i] = expr; @@ -5842,6 +5856,24 @@ static void nft_setelem_remove(const struct net *net, set->ops->remove(net, set, elem); } +static bool nft_setelem_valid_key_end(const struct nft_set *set, + struct nlattr **nla, u32 flags) +{ + if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) == + (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { + if (flags & NFT_SET_ELEM_INTERVAL_END) + return false; + if (!nla[NFTA_SET_ELEM_KEY_END] && + !(flags & NFT_SET_ELEM_CATCHALL)) + return false; + } else { + if (nla[NFTA_SET_ELEM_KEY_END]) + return false; + } + + return true; +} + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { @@ -5892,6 +5924,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return -EINVAL; } + if (set->flags & NFT_SET_OBJECT) { + if (!nla[NFTA_SET_ELEM_OBJREF] && + !(flags & NFT_SET_ELEM_INTERVAL_END)) + return -EINVAL; + } else { + if (nla[NFTA_SET_ELEM_OBJREF]) + return -EINVAL; + } + + if (!nft_setelem_valid_key_end(set, nla, flags)) + return -EINVAL; + if ((flags & NFT_SET_ELEM_INTERVAL_END) && (nla[NFTA_SET_ELEM_DATA] || nla[NFTA_SET_ELEM_OBJREF] || @@ -5899,6 +5943,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, nla[NFTA_SET_ELEM_EXPIRATION] || nla[NFTA_SET_ELEM_USERDATA] || nla[NFTA_SET_ELEM_EXPR] || + nla[NFTA_SET_ELEM_KEY_END] || nla[NFTA_SET_ELEM_EXPRESSIONS])) return -EINVAL; @@ -6029,10 +6074,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { - if (!(set->flags & NFT_SET_OBJECT)) { - err = -EINVAL; - goto err_parse_key_end; - } obj = nft_obj_lookup(ctx->net, ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); @@ -6325,6 +6366,9 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; + if (!nft_setelem_valid_key_end(set, nla, flags)) + return -EINVAL; + nft_set_ext_prepare(&tmpl); if (flags != 0) { @@ -6941,7 +6985,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -7873,7 +7917,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = nft_net->base_seq; + cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -8806,6 +8850,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + unsigned int base_seq; LIST_HEAD(adl); int err; @@ -8855,9 +8900,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++nft_net->base_seq == 0) + base_seq = READ_ONCE(nft_net->base_seq); + while (++base_seq == 0) ; + WRITE_ONCE(nft_net->base_seq, base_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9419,13 +9467,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, break; } } - - cond_resched(); } list_for_each_entry(set, &ctx->table->sets, list) { - cond_resched(); - if (!nft_is_active_next(ctx->net, set)) continue; if (!(set->flags & NFT_SET_MAP) || @@ -9667,6 +9711,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; + if (nft_chain_is_bound(chain)) + return -EINVAL; if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index c24b1240908f..9c44518cb70f 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -44,6 +44,10 @@ MODULE_DESCRIPTION("Netfilter messages via netlink socket"); static unsigned int nfnetlink_pernet_id __read_mostly; +#ifdef CONFIG_NF_CONNTRACK_EVENTS +static DEFINE_SPINLOCK(nfnl_grp_active_lock); +#endif + struct nfnl_net { struct sock *nfnl; }; @@ -654,6 +658,44 @@ static void nfnetlink_rcv(struct sk_buff *skb) netlink_rcv_skb(skb, nfnetlink_rcv_msg); } +static void nfnetlink_bind_event(struct net *net, unsigned int group) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + int type, group_bit; + u8 v; + + /* All NFNLGRP_CONNTRACK_* group bits fit into u8. + * The other groups are not relevant and can be ignored. + */ + if (group >= 8) + return; + + type = nfnl_group2type[group]; + + switch (type) { + case NFNL_SUBSYS_CTNETLINK: + break; + case NFNL_SUBSYS_CTNETLINK_EXP: + break; + default: + return; + } + + group_bit = (1 << group); + + spin_lock(&nfnl_grp_active_lock); + v = READ_ONCE(net->ct.ctnetlink_has_listener); + if ((v & group_bit) == 0) { + v |= group_bit; + + /* read concurrently without nfnl_grp_active_lock held. */ + WRITE_ONCE(net->ct.ctnetlink_has_listener, v); + } + + spin_unlock(&nfnl_grp_active_lock); +#endif +} + static int nfnetlink_bind(struct net *net, int group) { const struct nfnetlink_subsystem *ss; @@ -670,28 +712,45 @@ static int nfnetlink_bind(struct net *net, int group) if (!ss) request_module_nowait("nfnetlink-subsys-%d", type); -#ifdef CONFIG_NF_CONNTRACK_EVENTS - if (type == NFNL_SUBSYS_CTNETLINK) { - nfnl_lock(NFNL_SUBSYS_CTNETLINK); - WRITE_ONCE(net->ct.ctnetlink_has_listener, true); - nfnl_unlock(NFNL_SUBSYS_CTNETLINK); - } -#endif + nfnetlink_bind_event(net, group); return 0; } static void nfnetlink_unbind(struct net *net, int group) { #ifdef CONFIG_NF_CONNTRACK_EVENTS + int type, group_bit; + if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) return; - if (nfnl_group2type[group] == NFNL_SUBSYS_CTNETLINK) { - nfnl_lock(NFNL_SUBSYS_CTNETLINK); - if (!nfnetlink_has_listeners(net, group)) - WRITE_ONCE(net->ct.ctnetlink_has_listener, false); - nfnl_unlock(NFNL_SUBSYS_CTNETLINK); + type = nfnl_group2type[group]; + + switch (type) { + case NFNL_SUBSYS_CTNETLINK: + break; + case NFNL_SUBSYS_CTNETLINK_EXP: + break; + default: + return; + } + + /* ctnetlink_has_listener is u8 */ + if (group >= 8) + return; + + group_bit = (1 << group); + + spin_lock(&nfnl_grp_active_lock); + if (!nfnetlink_has_listeners(net, group)) { + u8 v = READ_ONCE(net->ct.ctnetlink_has_listener); + + v &= ~group_bit; + + /* read concurrently without nfnl_grp_active_lock held. */ + WRITE_ONCE(net->ct.ctnetlink_has_listener, v); } + spin_unlock(&nfnl_grp_active_lock); #endif } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 0053a697c931..89342ccccdcc 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { - return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_FORWARD)); + unsigned int hooks; + + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_FORWARD); + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); } static bool nft_osf_reduce(struct nft_regs_track *track, diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 2e7ac007cb30..eb0e40c29712 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -740,17 +740,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_payload_set *priv = nft_expr_priv(expr); + u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE; + int err; priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (tb[NFTA_PAYLOAD_CSUM_TYPE]) - priv->csum_type = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); - if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) - priv->csum_offset = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); + if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) { + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX, + &csum_offset); + if (err < 0) + return err; + + priv->csum_offset = csum_offset; + } if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) { u32 flags; @@ -761,7 +767,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->csum_flags = flags; } - switch (priv->csum_type) { + switch (csum_type) { case NFT_PAYLOAD_CSUM_NONE: case NFT_PAYLOAD_CSUM_INET: break; @@ -775,6 +781,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, default: return -EOPNOTSUPP; } + priv->csum_type = csum_type; return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, priv->len); @@ -833,6 +840,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, { enum nft_payload_bases base; unsigned int offset, len; + int err; if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || @@ -859,8 +867,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_DREG] == NULL) return ERR_PTR(-EINVAL); - offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset); + if (err < 0) + return ERR_PTR(err); + + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER) diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 68b2eed742df..62da25ad264b 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -312,6 +312,13 @@ static int nft_tproxy_dump(struct sk_buff *skb, return 0; } +static int nft_tproxy_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); +} + static struct nft_expr_type nft_tproxy_type; static const struct nft_expr_ops nft_tproxy_ops = { .type = &nft_tproxy_type, @@ -321,6 +328,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .destroy = nft_tproxy_destroy, .dump = nft_tproxy_dump, .reduce = NFT_REDUCE_READONLY, + .validate = nft_tproxy_validate, }; static struct nft_expr_type nft_tproxy_type __read_mostly = { diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 5edaaded706d..983ade4be3b3 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -161,6 +161,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = { static struct nft_expr_type nft_tunnel_type __read_mostly = { .name = "tunnel", + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_get_ops, .policy = nft_tunnel_policy, .maxattr = NFTA_TUNNEL_MAX, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1afca2a6c2ac..57010927e20a 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1174,13 +1174,17 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) op.policy, op.maxattr); if (err) - return err; + goto err_free_state; } } if (!ctx->state) return -ENODATA; return 0; + +err_free_state: + netlink_policy_dump_free(ctx->state); + return err; } static void *ctrl_dumppolicy_prep(struct sk_buff *skb, diff --git a/net/netlink/policy.c b/net/netlink/policy.c index 8d7c900e27f4..87e3de0fde89 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -144,7 +144,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, err = add_policy(&state, policy, maxtype); if (err) - return err; + goto err_try_undo; for (policy_idx = 0; policy_idx < state->n_alloc && state->policies[policy_idx].policy; @@ -164,7 +164,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, policy[type].nested_policy, policy[type].len); if (err) - return err; + goto err_try_undo; break; default: break; @@ -174,6 +174,16 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, *pstate = state; return 0; + +err_try_undo: + /* Try to preserve reasonable unwind semantics - if we're starting from + * scratch clean up fully, otherwise record what we got and caller will. + */ + if (!*pstate) + netlink_policy_dump_free(state); + else + *pstate = state; + return err; } static bool diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index 18196e1c8c2f..9ced13c0627a 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -78,11 +78,6 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, struct qrtr_mhi_dev *qdev; int rc; - /* start channels */ - rc = mhi_prepare_for_transfer_autoqueue(mhi_dev); - if (rc) - return rc; - qdev = devm_kzalloc(&mhi_dev->dev, sizeof(*qdev), GFP_KERNEL); if (!qdev) return -ENOMEM; @@ -96,6 +91,13 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; + /* start channels */ + rc = mhi_prepare_for_transfer_autoqueue(mhi_dev); + if (rc) { + qrtr_endpoint_unregister(&qdev->ep); + return rc; + } + dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 6fdedd9dbbc2..cfbf0e129cba 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,6 +363,7 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { clear_bit(RDS_RECV_REFILL, &conn->c_flags); + smp_mb__after_atomic(); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 11c45c8c6c16..036d92c0ad79 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if (!rose_loopback_neigh->dev) { + if (!rose_loopback_neigh->dev && + !rose_loopback_neigh->loopback) { kfree_skb(skb); continue; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 84d0a4109645..6401cdf7a624 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, _enter("%p,%lx", rx, p->user_call_ID); limiter = rxrpc_get_call_slot(p, gfp); - if (!limiter) + if (!limiter) { + release_sock(&rx->sk); return ERR_PTR(-ERESTARTSYS); + } call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); if (IS_ERR(call)) { diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 1d38e279e2ef..3c3a626459de 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, return sock_intr_errno(*timeo); trace_rxrpc_transmit(call, rxrpc_transmit_wait); - mutex_unlock(&call->user_mutex); *timeo = schedule_timeout(*timeo); - if (mutex_lock_interruptible(&call->user_mutex) < 0) - return sock_intr_errno(*timeo); } } @@ -290,37 +287,48 @@ out: static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, struct msghdr *msg, size_t len, - rxrpc_notify_end_tx_t notify_end_tx) + rxrpc_notify_end_tx_t notify_end_tx, + bool *_dropped_lock) { struct rxrpc_skb_priv *sp; struct sk_buff *skb; struct sock *sk = &rx->sk; + enum rxrpc_call_state state; long timeo; - bool more; - int ret, copied; + bool more = msg->msg_flags & MSG_MORE; + int ret, copied = 0; timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); +reload: + ret = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) - return -EPIPE; - - more = msg->msg_flags & MSG_MORE; - + goto maybe_error; + state = READ_ONCE(call->state); + ret = -ESHUTDOWN; + if (state >= RXRPC_CALL_COMPLETE) + goto maybe_error; + ret = -EPROTO; + if (state != RXRPC_CALL_CLIENT_SEND_REQUEST && + state != RXRPC_CALL_SERVER_ACK_REQUEST && + state != RXRPC_CALL_SERVER_SEND_REPLY) + goto maybe_error; + + ret = -EMSGSIZE; if (call->tx_total_len != -1) { - if (len > call->tx_total_len) - return -EMSGSIZE; - if (!more && len != call->tx_total_len) - return -EMSGSIZE; + if (len - copied > call->tx_total_len) + goto maybe_error; + if (!more && len - copied != call->tx_total_len) + goto maybe_error; } skb = call->tx_pending; call->tx_pending = NULL; rxrpc_see_skb(skb, rxrpc_skb_seen); - copied = 0; do { /* Check to see if there's a ping ACK to reply to. */ if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) @@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, _debug("alloc"); - if (!rxrpc_check_tx_space(call, NULL)) { - ret = -EAGAIN; - if (msg->msg_flags & MSG_DONTWAIT) - goto maybe_error; - ret = rxrpc_wait_for_tx_window(rx, call, - &timeo, - msg->msg_flags & MSG_WAITALL); - if (ret < 0) - goto maybe_error; - } + if (!rxrpc_check_tx_space(call, NULL)) + goto wait_for_space; /* Work out the maximum size of a packet. Assume that * the security header is going to be in the padded @@ -468,6 +468,27 @@ maybe_error: efault: ret = -EFAULT; goto out; + +wait_for_space: + ret = -EAGAIN; + if (msg->msg_flags & MSG_DONTWAIT) + goto maybe_error; + mutex_unlock(&call->user_mutex); + *_dropped_lock = true; + ret = rxrpc_wait_for_tx_window(rx, call, &timeo, + msg->msg_flags & MSG_WAITALL); + if (ret < 0) + goto maybe_error; + if (call->interruptibility == RXRPC_INTERRUPTIBLE) { + if (mutex_lock_interruptible(&call->user_mutex) < 0) { + ret = sock_intr_errno(timeo); + goto maybe_error; + } + } else { + mutex_lock(&call->user_mutex); + } + *_dropped_lock = false; + goto reload; } /* @@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) enum rxrpc_call_state state; struct rxrpc_call *call; unsigned long now, j; + bool dropped_lock = false; int ret; struct rxrpc_send_params p = { @@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = rxrpc_send_abort_packet(call); } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; - } else if (rxrpc_is_client_call(call) && - state != RXRPC_CALL_CLIENT_SEND_REQUEST) { - /* request phase complete for this client call */ - ret = -EPROTO; - } else if (rxrpc_is_service_call(call) && - state != RXRPC_CALL_SERVER_ACK_REQUEST && - state != RXRPC_CALL_SERVER_SEND_REPLY) { - /* Reply phase not begun or not complete for service call. */ - ret = -EPROTO; } else { - ret = rxrpc_send_data(rx, call, msg, len, NULL); + ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock); } out_put_unlock: - mutex_unlock(&call->user_mutex); + if (!dropped_lock) + mutex_unlock(&call->user_mutex); error_put: rxrpc_put_call(call, rxrpc_call_put); _leave(" = %d", ret); @@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, struct msghdr *msg, size_t len, rxrpc_notify_end_tx_t notify_end_tx) { + bool dropped_lock = false; int ret; _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]); @@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: case RXRPC_CALL_SERVER_SEND_REPLY: ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, - notify_end_tx); + notify_end_tx, &dropped_lock); break; case RXRPC_CALL_COMPLETE: read_lock_bh(&call->state_lock); @@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, break; } - mutex_unlock(&call->user_mutex); + if (!dropped_lock) + mutex_unlock(&call->user_mutex); _leave(" = %d", ret); return ret; } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 3f935cbbaff6..48712bc51bda 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -424,6 +424,11 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, return -EINVAL; } + if (!nhandle) { + NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid"); + return -EINVAL; + } + h1 = to_hash(nhandle); b = rtnl_dereference(head->table[h1]); if (!b) { @@ -477,6 +482,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, int err; bool new = true; + if (!handle) { + NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); + return -EINVAL; + } + if (opt == NULL) return handle ? -EINVAL : 0; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d47b9689eba6..99b697ad2b98 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = dev_tx_weight; + int quota = READ_ONCE(dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/socket.c b/net/socket.c index 9b27c5e4e5ba..7378375d3a5b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1801,7 +1801,7 @@ int __sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b098e707ad41..7d268a291486 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1902,7 +1902,7 @@ call_encode(struct rpc_task *task) break; case -EKEYEXPIRED: if (!task->tk_cred_retry) { - rpc_exit(task, task->tk_status); + rpc_call_rpcerror(task, task->tk_status); } else { task->tk_action = call_refresh; task->tk_cred_retry--; diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 7330eb9a70cf..c65c90ad626a 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -291,8 +291,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, int offline = 0, online = 0, remove = 0; struct rpc_xprt_switch *xps = rpc_sysfs_xprt_kobj_get_xprt_switch(kobj); - if (!xprt) - return 0; + if (!xprt || !xps) { + count = 0; + goto out_put; + } if (!strncmp(buf, "offline", 7)) offline = 1; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index f76119f62f1b..fe27241cd13f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2702,7 +2702,9 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) crypto_info->version != TLS_1_3_VERSION && !!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC); - tls_strp_init(&sw_ctx_rx->strp, sk); + rc = tls_strp_init(&sw_ctx_rx->strp, sk); + if (rc) + goto free_aead; } goto out; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 82d14eea1b5a..974eb97b77d2 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -168,7 +168,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog) + if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 144238a50f3d..b2f4ec9c537f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -669,7 +669,6 @@ resume: x->curlft.bytes += skb->len; x->curlft.packets++; - x->curlft.use_time = ktime_get_real_seconds(); spin_unlock(&x->lock); @@ -783,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= netdev_max_backlog) + if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 555ab35cd119..9a5e79a38c67 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -534,7 +534,6 @@ static int xfrm_output_one(struct sk_buff *skb, int err) x->curlft.bytes += skb->len; x->curlft.packets++; - x->curlft.use_time = ktime_get_real_seconds(); spin_unlock_bh(&x->lock); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f1a0bab920a5..cc6ab79609e2 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3162,7 +3162,7 @@ ok: return dst; nopol: - if (!(dst_orig->dev->flags & IFF_LOOPBACK) && + if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) && net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { err = -EPERM; goto error; @@ -3599,6 +3599,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); + xfrm_pol_put(pols[0]); return 0; } pols[1]->curlft.use_time = ktime_get_real_seconds(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 52e60e607f8a..91c32a3b6924 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1592,6 +1592,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->replay = orig->replay; x->preplay = orig->preplay; x->mapping_maxage = orig->mapping_maxage; + x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; |