diff options
Diffstat (limited to 'net')
38 files changed, 341 insertions, 299 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 77d43ae2a7bb..0ffcbdd55fa9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 676f3ad629f9..588f475019d4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1166,8 +1166,8 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && + !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5da9552b186b..2b9fdbc43205 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np) read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != + !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e01274bd5e3e..33d9227a8b80 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = 0; } ret = dumpit(skb, cb); - if (ret < 0) + if (ret) break; } cb->family = idx; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 946de0e24c87..b4ee5c8b928f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4944,6 +4944,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * + * @skb: GSO skb + * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * diff --git a/net/core/sock.c b/net/core/sock.c index 6fcc4bc07d19..080a880a1761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bcb11f3a27c0..760a9e52e02b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err; q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout); - err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev; if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9b0158fa431f..d6ee343fdb86 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -722,10 +722,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) - return skb; - if (pskb_trim_rcsum(skb, netoff + len)) - return skb; + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { + kfree_skb(skb); + return NULL; + } + if (pskb_trim_rcsum(skb, netoff + len)) { + kfree_skb(skb); + return NULL; + } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..fffcc130900e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f4d61017a69..f0cd291034f0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1001,6 +1001,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1091,6 +1094,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4e0ff7031edd..94999058e110 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,8 +44,22 @@ #include <net/checksum.h> +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) +/* anycast address hash table + */ +static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(acaddr_hash_lock); + static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); +static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr) +{ + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + /* * socket join an anycast group */ @@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk) rtnl_unlock(); } +static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) +{ + unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); + + spin_lock(&acaddr_hash_lock); + hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); + spin_unlock(&acaddr_hash_lock); +} + +static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) +{ + spin_lock(&acaddr_hash_lock); + hlist_del_init_rcu(&aca->aca_addr_lst); + spin_unlock(&acaddr_hash_lock); +} + static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } +static void aca_free_rcu(struct rcu_head *h) +{ + struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); + + fib6_info_release(aca->aca_rt); + kfree(aca); +} + static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - fib6_info_release(ac->aca_rt); - kfree(ac); + call_rcu(&ac->rcu, aca_free_rcu); } } @@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; + INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); + ipv6_add_acaddr_hash(net, aca); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) else idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); + addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { + unsigned int hash = inet6_acaddr_hash(net, addr); + struct net_device *nh_dev; + struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { + hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], + aca_addr_lst) { + nh_dev = fib6_info_nh_dev(aca->aca_rt); + if (!nh_dev || !net_eq(dev_net(nh_dev), net)) + continue; + if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } + } rcu_read_unlock(); return found; } @@ -540,3 +591,24 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif + +/* Init / cleanup code + */ +int __init ipv6_anycast_init(void) +{ + int i; + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); + return 0; +} + +void ipv6_anycast_cleanup(void) +{ + int i; + + spin_lock(&acaddr_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); + spin_unlock(&acaddr_hash_lock); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b8bc008b53b..ae3786132c23 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* fib entries are never clones */ if (arg.filter.flags & RTM_F_CLONED) - return skb->len; + goto out; w = (void *)cb->args[2]; if (!w) { @@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (arg.filter.dump_all_families) - return skb->len; + goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b8ac369f98ad..d219979c3e52 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) */ ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - else + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + if (nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; + skb->_skb_refdst = orefdst; + } else { skb_dst_drop(skb); + } out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..1577f2f76060 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); -/* When the nfnl mutex is held: */ +/* When the nfnl mutex or ip_set_ref_lock is held: */ #define ip_set_dereference(p) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&ip_set_ref_lock)) #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] +#define ip_set_ref_netlink(inst,id) \ + rcu_dereference_raw((inst)->ip_set_list)[id] /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -693,21 +697,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -961,7 +964,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Wraparound */ goto cleanup; - list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -973,7 +976,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Use new list */ index = inst->ip_set_max; inst->ip_set_max = i; - kfree(tmp); + kvfree(tmp); ret = 0; } else if (ret) { goto cleanup; @@ -1153,7 +1156,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1173,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } @@ -1252,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; - struct ip_set *set = ip_set(inst, index); + struct ip_set *set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); @@ -1441,7 +1444,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - set = ip_set(inst, index); + set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); @@ -2059,7 +2062,7 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; inst->is_deleted = false; @@ -2087,7 +2090,7 @@ ip_set_net_exit(struct net *net) } } nfnl_unlock(NFNL_SUBSYS_IPSET); - kfree(rcu_dereference_protected(inst->ip_set_list, 1)); + kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index d391485a6acd..613e18e720a4 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..4eef55da0878 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ca1168d67fac..e92e749aff53 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 171e9e122e5f..023c1445bc39 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = }, }; -static inline struct nf_dccp_net *dccp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp; -} - static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh) @@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: - dn = dccp_pernet(net); + dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; @@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; + timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, static int dccp_init_net(struct net *net) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); struct nf_proto_net *pn = &dn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e10e867e0b55..5da19d5fbc76 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static inline struct nf_generic_net *generic_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.generic; -} - static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct, } if (!timeout) - timeout = &generic_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) @@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, static int generic_init_net(struct net *net) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 3598520bd19b..de64d8a5fdfd 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,11 +25,6 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { @@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, } if (!timeout) - timeout = &icmp_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) @@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmp_init_net(struct net *net) { - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 378618feed5d..a15eefb8e317 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,11 +30,6 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, @@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &icmpv6_pernet(net)->timeout; + return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); @@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmpv6_init_net(struct net *net) { - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3d719d3eb9a3..d53e3e78f605 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { } }; -static inline struct nf_sctp_net *sctp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); @@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; /* set default SCTP timeouts. */ @@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int sctp_init_net(struct net *net) { - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1bcf9984d45e..4dcbd51a8e97 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; -static inline struct nf_tcp_net *tcp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); - const struct nf_tcp_net *tn = tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; @@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; @@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int tcp_init_net(struct net *net) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a7aa70370913..c879d8d78cfd 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_REPLIED] = 180*HZ, }; -static inline struct nf_udp_net *udp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udp; -} - static unsigned int *udp_get_timeouts(struct net *net) { - return udp_pernet(net)->timeouts; + return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, @@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; @@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int udp_init_net(struct net *net) { - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); struct nf_proto_net *pn = &un->pn; if (!pn->users) { diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index e7a50af1b3d6..a518eb162344 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -382,7 +382,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -442,12 +444,44 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &nf_icmp_pernet(net)->timeout; + break; + case IPPROTO_TCP: + timeouts = nf_tcp_pernet(net)->timeouts; + break; + case IPPROTO_UDP: + timeouts = nf_udp_pernet(net)->timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = nf_dccp_pernet(net)->dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &nf_icmpv6_pernet(net)->timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case 255: + timeouts = &nf_generic_pernet(net)->timeout; + break; + default: + WARN_ON_ONCE(1); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -458,8 +492,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l3num, - l4proto); + l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 768292eac2a4..9d0ede474224 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt) return false; } -static int nft_compat_chain_validate_dependency(const char *tablename, - const struct nft_chain *chain) +static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, + const char *tablename) { + enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; + const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || @@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename, return 0; basechain = nft_base_chain(chain); - if (strcmp(tablename, "nat") == 0 && - basechain->type->type != NFT_CHAIN_T_NAT) - return -EINVAL; + if (strcmp(tablename, "nat") == 0) { + if (ctx->family != NFPROTO_BRIDGE) + type = NFT_CHAIN_T_NAT; + if (basechain->type->type != type) + return -EINVAL; + } return 0; } @@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(target->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } @@ -590,8 +594,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 649d1700ec5b..3cc1b3dc3c3c 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,7 +24,6 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; - struct nft_set *map; }; static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) @@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_inc_gen(priv); } -static void nft_ng_inc_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_inc_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, - [NFTA_NG_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_inc_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_inc_init(ctx, expr, tb); - - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_inc_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_inc *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_INCREMENTAL, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static u32 nft_ng_random_gen(struct nft_ng_random *priv) @@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_random_gen(priv); } -static void nft_ng_random_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_random_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static int nft_ng_random_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_random_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_random_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_random *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_RANDOM, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; -static const struct nft_expr_ops nft_ng_inc_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), - .eval = nft_ng_inc_map_eval, - .init = nft_ng_inc_map_init, - .dump = nft_ng_inc_map_dump, -}; - static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; -static const struct nft_expr_ops nft_ng_random_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), - .eval = nft_ng_random_map_eval, - .init = nft_ng_random_map_init, - .dump = nft_ng_random_map_dump, -}; - static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_random_map_ops; return &nft_ng_random_ops; } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ca5e5d8c5ef8..b13618c764ec 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; - if (nla_get_u8(tb[NFTA_OSF_TTL])) { + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) return -EINVAL; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index c6acfc2d9c84..eb4cbd244c3d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } +static int idletimer_check_sysfs_name(const char *name, unsigned int size) +{ + int ret; + + ret = xt_check_proc_name(name, size); + if (ret < 0) + return ret; + + if (!strcmp(name, "power") || + !strcmp(name, "subsystem") || + !strcmp(name, "uevent")) + return -EINVAL; + + return 0; +} + static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; @@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); + if (ret < 0) + goto out_free_timer; + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6bec37ab4472..a4660c48ff01 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 382196e57a26..bc628acf4f4f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -611,6 +611,7 @@ struct rxrpc_call { * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 8e7434e92097..468efc3660c0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; + ack_at += READ_ONCE(call->tx_backoff); ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); @@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work) container_of(work, struct rxrpc_call, processor); rxrpc_serial_t *send_ack; unsigned long now, next, t; + unsigned int iterations = 0; rxrpc_see_call(call); @@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + /* Limit the number of times we do this before returning to the manager */ + iterations++; + if (iterations > 5) + goto requeue; + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; @@ -447,13 +454,16 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) { - __rxrpc_queue_call(call); - goto out; - } + if (call->events && call->state < RXRPC_CALL_COMPLETE) + goto requeue; out_put: rxrpc_put_call(call, rxrpc_call_put); out: _leave(""); + return; + +requeue: + __rxrpc_queue_call(call); + goto out; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 189418888839..736aa9281100 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -35,6 +35,21 @@ struct rxrpc_abort_buffer { static const char rxrpc_keepalive_string[] = ""; /* + * Increase Tx backoff on transmission failure and clear it on success. + */ +static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) +{ + if (ret < 0) { + u16 tx_backoff = READ_ONCE(call->tx_backoff); + + if (tx_backoff < HZ) + WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + } else { + WRITE_ONCE(call->tx_backoff, 0); + } +} + +/* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep * the route through any intervening firewall open. @@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, else trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, rxrpc_tx_point_call_ack); + rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), - true, true, + false, true, rxrpc_propose_ack_retry_tx); } else { spin_lock_bh(&call->lock); @@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) else trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); - + rxrpc_tx_backoff(call, ret); rxrpc_put_connection(conn); return ret; @@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -445,9 +462,18 @@ done: rxrpc_reduce_call_timer(call, expect_rx_by, nowj, rxrpc_timer_set_for_normal); } - } - rxrpc_set_keepalive(call); + rxrpc_set_keepalive(call); + } else { + /* Cancel the call if the initial transmission fails, + * particularly if that's due to network routing issues that + * aren't going away anytime soon. The layer above can arrange + * the retransmission. + */ + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_USER_ABORT, ret); + } _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; @@ -506,6 +532,7 @@ send_fragmentable: else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); goto done; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1dae5f2b358f..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9aada2d0ef06..c6c327874abc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 57b3ad9394ad..2c38e3d07924 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -648,15 +648,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9cb854b05342..c37e1c2dec9d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_FCFS); + sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/tipc/link.c b/net/tipc/link.c index 201c3b5bc96b..836727e363c4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (msg_peer_stopping(hdr)) + /* If peer is going down we want full re-establish cycle */ + if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - else if ((mtyp == RESET_MSG) || !link_is_up(l)) + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ - if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); |