diff options
Diffstat (limited to 'net/netfilter')
27 files changed, 553 insertions, 352 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 54395266339d..3646fc195e7d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -10,6 +10,17 @@ config NETFILTER_INGRESS This allows you to classify packets from ingress using the Netfilter infrastructure. +config NETFILTER_EGRESS + bool "Netfilter egress support" + default y + select NET_EGRESS + help + This allows you to classify packets before transmission using the + Netfilter infrastructure. + +config NETFILTER_SKIP_EGRESS + def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB) + config NETFILTER_NETLINK tristate @@ -109,7 +120,7 @@ config NF_CONNTRACK_MARK config NF_CONNTRACK_SECMARK bool 'Connection tracking security mark support' depends on NETWORK_SECMARK - default m if NETFILTER_ADVANCED=n + default y if NETFILTER_ADVANCED=n help This option enables security markings to be applied to connections. Typically they are copied to connections from diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 63d032191e62..6dec9cd395f1 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -317,6 +317,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, return &dev->nf_hooks_ingress; } #endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hooknum == NF_NETDEV_EGRESS) { + if (dev && dev_net(dev) == net) + return &dev->nf_hooks_egress; + } +#endif WARN_ON_ONCE(1); return NULL; } @@ -335,7 +341,8 @@ static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, return 0; } -static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) +static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg, + int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) @@ -344,6 +351,12 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) return false; } +static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg, + int pf) +{ + return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; +} + static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL @@ -383,9 +396,18 @@ static int __nf_register_net_hook(struct net *net, int pf, switch (pf) { case NFPROTO_NETDEV: - err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); - if (err < 0) - return err; +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif +#ifndef CONFIG_NETFILTER_EGRESS + if (reg->hooknum == NF_NETDEV_EGRESS) + return -EOPNOTSUPP; +#endif + if ((reg->hooknum != NF_NETDEV_INGRESS && + reg->hooknum != NF_NETDEV_EGRESS) || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) @@ -418,6 +440,10 @@ static int __nf_register_net_hook(struct net *net, int pf, if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_inc_egress_queue(); +#endif nf_static_key_inc(reg, pf); BUG_ON(p == new_hooks); @@ -475,6 +501,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_dec_egress_queue(); +#endif nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6186358eac7c..6e391308431d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -130,11 +130,11 @@ htable_size(u8 hbits) { size_t hsize; - /* We must fit both into u32 in jhash and size_t */ + /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) + if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c100c6b112c8..2c467c422dc6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1468,6 +1468,10 @@ int __init ip_vs_conn_init(void) int idx; /* Compute size and mask */ + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) { + pr_info("conn_tab_bits not in [8, 20]. Using default value\n"); + ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; + } ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 128690c512df..e93c937a8bf0 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1330,12 +1330,15 @@ drop: * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int -ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + int af = state->pf; struct sock *sk; EnterFunction(11); @@ -1468,56 +1471,6 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in return NF_ACCEPT; } -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -#endif - static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -1957,8 +1910,10 @@ out: * and send it on its way... */ static unsigned int -ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; @@ -1966,6 +1921,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int int ret, pkts; int conn_reuse_mode; struct sock *sk; + int af = state->pf; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -2138,55 +2094,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int } /* - * AF_INET handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -/* - * AF_INET handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * AF_INET6 handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -/* - * AF_INET6 handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -#endif - - -/* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent @@ -2199,45 +2106,36 @@ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - int r; struct netns_ipvs *ipvs = net_ipvs(state->net); - - if (ip_hdr(skb)->protocol != IPPROTO_ICMP) - return NF_ACCEPT; + int r; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp(ipvs, skb, &r, state->hook); -} - + if (state->pf == NFPROTO_IPV4) { + if (ip_hdr(skb)->protocol != IPPROTO_ICMP) + return NF_ACCEPT; #ifdef CONFIG_IP_VS_IPV6 -static unsigned int -ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - int r; - struct netns_ipvs *ipvs = net_ipvs(state->net); - struct ip_vs_iphdr iphdr; + } else { + struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); - if (iphdr.protocol != IPPROTO_ICMPV6) - return NF_ACCEPT; + ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); - /* ipvs enabled in this netns ? */ - if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) - return NF_ACCEPT; + if (iphdr.protocol != IPPROTO_ICMPV6) + return NF_ACCEPT; - return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); -} + return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); #endif + } + return ip_vs_in_icmp(ipvs, skb, &r, state->hook); +} static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, @@ -2246,21 +2144,21 @@ static const struct nf_hook_ops ip_vs_ops4[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, @@ -2275,7 +2173,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, @@ -2286,7 +2184,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, @@ -2295,21 +2193,21 @@ static const struct nf_hook_ops ip_vs_ops6[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, @@ -2317,14 +2215,14 @@ static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { - .hook = ip_vs_forward_icmp_v6, + .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c25097092a06..39c523bd775c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -24,7 +24,6 @@ #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/workqueue.h> -#include <linux/swap.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -48,6 +47,8 @@ #include <net/ip_vs.h> +MODULE_ALIAS_GENL_FAMILY(IPVS_GENL_NAME); + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ static DEFINE_MUTEX(__ip_vs_mutex); @@ -2017,6 +2018,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "run_estimation", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -4090,6 +4097,13 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; + ipvs->sysctl_run_estimation = 1; + tbl[idx++].data = &ipvs->sysctl_run_estimation; +#ifdef CONFIG_IP_VS_DEBUG + /* Global sysctls must be ro in non-init netns */ + if (!net_eq(net, &init_net)) + tbl[idx++].mode = 0444; +#endif ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 05b8112ffb37..9a1a7af6a186 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -100,6 +100,9 @@ static void estimation_timer(struct timer_list *t) u64 rate; struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer); + if (!sysctl_run_estimation(ipvs)) + goto skip; + spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); @@ -131,6 +134,8 @@ static void estimation_timer(struct timer_list *t) spin_unlock(&s->lock); } spin_unlock(&ipvs->est_lock); + +skip: mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 94e18fb9690d..770a63103c7a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -74,10 +74,14 @@ static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* serialize hash resizes and nf_ct_iterate_cleanup */ +static DEFINE_MUTEX(nf_conntrack_mutex); + #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) -#define MAX_CHAINLEN 64u +#define MIN_CHAINLEN 8u +#define MAX_CHAINLEN (32u - MIN_CHAINLEN) static struct conntrack_gc_work conntrack_gc_work; @@ -188,11 +192,13 @@ seqcount_spinlock_t nf_conntrack_generation __read_mostly; static siphash_key_t nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, const struct net *net) { struct { struct nf_conntrack_man src; union nf_inet_addr dst_addr; + unsigned int zone; u32 net_mix; u16 dport; u16 proto; @@ -205,6 +211,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, /* The direction must be ignored, so handle usable members manually. */ combined.src = tuple->src; combined.dst_addr = tuple->dst.u3; + combined.zone = zoneid; combined.net_mix = net_hash_mix(net); combined.dport = (__force __u16)tuple->dst.u.all; combined.proto = tuple->dst.protonum; @@ -219,15 +226,17 @@ static u32 scale_hash(u32 hash) static u32 __hash_conntrack(const struct net *net, const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, unsigned int size) { - return reciprocal_scale(hash_conntrack_raw(tuple, net), size); + return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size); } static u32 hash_conntrack(const struct net *net, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, + unsigned int zoneid) { - return scale_hash(hash_conntrack_raw(tuple, net)); + return scale_hash(hash_conntrack_raw(tuple, zoneid, net)); } static bool nf_ct_get_tuple_ports(const struct sk_buff *skb, @@ -650,9 +659,11 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); clean_from_lists(ct); @@ -819,8 +830,20 @@ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, net)); + unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + struct nf_conntrack_tuple_hash *thash; + + thash = __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, zone_id, net)); + + if (thash) + return thash; + + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (rid != zone_id) + return __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, rid, net)); + return thash; } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -842,6 +865,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int max_chainlen; unsigned int chainlen = 0; unsigned int sequence; int err = -EEXIST; @@ -852,18 +876,22 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); + /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -873,7 +901,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1103,8 +1131,8 @@ drop: int __nf_conntrack_confirm(struct sk_buff *skb) { + unsigned int chainlen = 0, sequence, max_chainlen; const struct nf_conntrack_zone *zone; - unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1133,8 +1161,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = scale_hash(hash); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related @@ -1168,6 +1196,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) goto dying; } + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ @@ -1175,7 +1204,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1184,7 +1213,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) { + if (chainlen++ > max_chainlen) { chaintoolong: nf_ct_add_to_dying_list(ct); NF_CT_STAT_INC(net, chaintoolong); @@ -1246,7 +1275,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, rcu_read_lock(); begin: nf_conntrack_get_ht(&ct_hash, &hsize); - hash = __hash_conntrack(net, tuple, hsize); + hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); @@ -1687,8 +1716,8 @@ resolve_normal_ct(struct nf_conn *tmpl, struct nf_conntrack_tuple_hash *h; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + u32 hash, zone_id, rid; struct nf_conn *ct; - u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, @@ -1699,8 +1728,20 @@ resolve_normal_ct(struct nf_conn *tmpl, /* look for tuple match */ zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); - hash = hash_conntrack_raw(&tuple, state->net); + + zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + hash = hash_conntrack_raw(&tuple, zone_id, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); + + if (!h) { + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (zone_id != rid) { + u32 tmp = hash_conntrack_raw(&tuple, rid, state->net); + + h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp); + } + } + if (!h) { h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); @@ -2225,28 +2266,31 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket]; + + if (hlist_nulls_empty(hslot)) + continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); nf_conntrack_lock(lockp); - if (*bucket < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) - continue; - /* All nf_conn objects are added to hash table twice, one - * for original direction tuple, once for the reply tuple. - * - * Exception: In the IPS_NAT_CLASH case, only the reply - * tuple is added (the original tuple already existed for - * a different object). - * - * We only need to call the iterator once for each - * conntrack, so we just use the 'reply' direction - * tuple while iterating. - */ - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - goto found; - } + hlist_nulls_for_each_entry(h, n, hslot, hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) + continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; } spin_unlock(lockp); local_bh_enable(); @@ -2264,26 +2308,20 @@ found: static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - unsigned int bucket = 0, sequence; + unsigned int bucket = 0; struct nf_conn *ct; might_sleep(); - for (;;) { - sequence = read_seqcount_begin(&nf_conntrack_generation); - - while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ + mutex_lock(&nf_conntrack_mutex); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); - } - - if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) - break; - bucket = 0; + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); } + mutex_unlock(&nf_conntrack_mutex); } struct iter_data { @@ -2519,8 +2557,10 @@ int nf_conntrack_hash_resize(unsigned int hashsize) if (!hash) return -ENOMEM; + mutex_lock(&nf_conntrack_mutex); old_size = nf_conntrack_htable_size; if (old_size == hashsize) { + mutex_unlock(&nf_conntrack_mutex); kvfree(hash); return 0; } @@ -2537,12 +2577,16 @@ int nf_conntrack_hash_resize(unsigned int hashsize) for (i = 0; i < nf_conntrack_htable_size; i++) { while (!hlist_nulls_empty(&nf_conntrack_hash[i])) { + unsigned int zone_id; + h = hlist_nulls_entry(nf_conntrack_hash[i].first, struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); + + zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h)); bucket = __hash_conntrack(nf_ct_net(ct), - &h->tuple, hashsize); + &h->tuple, zone_id, hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } @@ -2556,6 +2600,8 @@ int nf_conntrack_hash_resize(unsigned int hashsize) nf_conntrack_all_unlock(); local_bh_enable(); + mutex_unlock(&nf_conntrack_mutex); + synchronize_net(); kvfree(old_hash); return 0; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 8f7a9837349c..d1f2d3c8d2b1 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -155,6 +155,16 @@ unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, } EXPORT_SYMBOL_GPL(nf_confirm); +static bool in_vrf_postrouting(const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (state->hook == NF_INET_POST_ROUTING && + netif_is_l3_master(state->out)) + return true; +#endif + return false; +} + static unsigned int ipv4_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -166,6 +176,9 @@ static unsigned int ipv4_confirm(void *priv, if (!ct || ctinfo == IP_CT_RELATED_REPLY) return nf_conntrack_confirm(skb); + if (in_vrf_postrouting(state)) + return NF_ACCEPT; + return nf_confirm(skb, skb_network_offset(skb) + ip_hdrlen(skb), ct, ctinfo); @@ -374,6 +387,9 @@ static unsigned int ipv6_confirm(void *priv, if (!ct || ctinfo == IP_CT_RELATED_REPLY) return nf_conntrack_confirm(skb); + if (in_vrf_postrouting(state)) + return NF_ACCEPT; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index f8e3c0d2602f..3b516cffc779 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -104,10 +104,13 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { unsigned long extra = timeouts[UDP_CT_UNREPLIED]; + bool stream = false; /* Still active after two seconds? Extend timeout. */ - if (time_after(jiffies, ct->proto.udp.stream_ts)) + if (time_after(jiffies, ct->proto.udp.stream_ts)) { extra = timeouts[UDP_CT_REPLIED]; + stream = true; + } nf_ct_refresh_acct(ct, ctinfo, skb, extra); @@ -116,7 +119,7 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, return NF_ACCEPT; /* Also, more likely to be important, and not a probe */ - if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + if (stream && !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 7008961f5cb0..4d50d51db796 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -150,13 +150,16 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) /* We keep an extra hash for each conntrack, for fast searching. */ static unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, + const struct nf_conntrack_zone *zone, + const struct nf_conntrack_tuple *tuple) { unsigned int hash; struct { struct nf_conntrack_man src; u32 net_mix; u32 protonum; + u32 zone; } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); @@ -165,9 +168,13 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) /* Original src, to ensure we map it consistently if poss. */ combined.src = tuple->src; - combined.net_mix = net_hash_mix(n); + combined.net_mix = net_hash_mix(net); combined.protonum = tuple->dst.protonum; + /* Zone ID can be used provided its valid for both directions */ + if (zone->dir == NF_CT_DEFAULT_ZONE_DIR) + combined.zone = zone->id; + hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); @@ -272,7 +279,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range2 *range) { - unsigned int h = hash_by_src(net, tuple); + unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn *ct; hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { @@ -619,7 +626,7 @@ nf_nat_setup_info(struct nf_conn *ct, unsigned int srchash; spinlock_t *lock; - srchash = hash_by_src(net, + srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); @@ -692,6 +699,16 @@ unsigned int nf_nat_packet(struct nf_conn *ct, } EXPORT_SYMBOL_GPL(nf_nat_packet); +static bool in_vrf_postrouting(const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (state->hook == NF_INET_POST_ROUTING && + netif_is_l3_master(state->out)) + return true; +#endif + return false; +} + unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -708,7 +725,7 @@ nf_nat_inet_fn(void *priv, struct sk_buff *skb, * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ - if (!ct) + if (!ct || in_vrf_postrouting(state)) return NF_ACCEPT; nat = nfct_nat(ct); @@ -788,7 +805,7 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; - h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c index 8e8a65d46345..acd73f717a08 100644 --- a/net/netfilter/nf_nat_masquerade.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -9,8 +9,19 @@ #include <net/netfilter/nf_nat_masquerade.h> +struct masq_dev_work { + struct work_struct work; + struct net *net; + union nf_inet_addr addr; + int ifindex; + int (*iter)(struct nf_conn *i, void *data); +}; + +#define MAX_MASQ_WORKER_COUNT 16 + static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; +static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, @@ -63,13 +74,71 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); -static int device_cmp(struct nf_conn *i, void *ifindex) +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + + w = container_of(work, struct masq_dev_work, work); + + nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&masq_worker_count); + module_put(THIS_MODULE); +} + +/* Iterate conntrack table in the background and remove conntrack entries + * that use the device/address being removed. + * + * In case too many work items have been queued already or memory allocation + * fails iteration is skipped, conntrack entries will time out eventually. + */ +static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, + int ifindex, + int (*iter)(struct nf_conn *i, void *data), + gfp_t gfp_flags) +{ + struct masq_dev_work *w; + + if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) + return; + + net = maybe_get_net(net); + if (!net) + return; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kzalloc(sizeof(*w), gfp_flags); + if (w) { + /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ + atomic_inc(&masq_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = ifindex; + w->net = net; + w->iter = iter; + if (addr) + w->addr = *addr; + schedule_work(&w->work); + return; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); +} + +static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); + const struct masq_dev_work *w = arg; if (!nat) return 0; - return nat->masq_index == (int)(long)ifindex; + return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, @@ -85,8 +154,8 @@ static int masq_device_event(struct notifier_block *this, * and forget them. */ - nf_ct_iterate_cleanup_net(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_nat_masq_schedule(net, NULL, dev->ifindex, + device_cmp, GFP_KERNEL); } return NOTIFY_DONE; @@ -94,35 +163,45 @@ static int masq_device_event(struct notifier_block *this, static int inet_cmp(struct nf_conn *ct, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct net_device *dev = ifa->ifa_dev->dev; struct nf_conntrack_tuple *tuple; + struct masq_dev_work *w = ptr; - if (!device_cmp(ct, (void *)(long)dev->ifindex)) + if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - return ifa->ifa_address == tuple->dst.u3.ip; + return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; - struct net *net = dev_net(idev->dev); + const struct in_ifaddr *ifa = ptr; + const struct in_device *idev; + const struct net_device *dev; + union nf_inet_addr addr; + + if (event != NETDEV_DOWN) + return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ + idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0); + memset(&addr, 0, sizeof(addr)); + + addr.ip = ifa->ifa_address; + + dev = idev->dev; + nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, + inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } @@ -136,8 +215,6 @@ static struct notifier_block masq_inet_notifier = { }; #if IS_ENABLED(CONFIG_IPV6) -static atomic_t v6_worker_count __read_mostly; - static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, @@ -187,40 +264,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); -struct masq_dev_work { - struct work_struct work; - struct net *net; - struct in6_addr addr; - int ifindex; -}; - -static int inet6_cmp(struct nf_conn *ct, void *work) -{ - struct masq_dev_work *w = (struct masq_dev_work *)work; - struct nf_conntrack_tuple *tuple; - - if (!device_cmp(ct, (void *)(long)w->ifindex)) - return 0; - - tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - - return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); -} - -static void iterate_cleanup_work(struct work_struct *work) -{ - struct masq_dev_work *w; - - w = container_of(work, struct masq_dev_work, work); - - nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0); - - put_net(w->net); - kfree(w); - atomic_dec(&v6_worker_count); - module_put(THIS_MODULE); -} - /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. @@ -233,36 +276,19 @@ static int masq_inet6_event(struct notifier_block *this, { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; - struct masq_dev_work *w; - struct net *net; + union nf_inet_addr addr; - if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16) + if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; - net = maybe_get_net(dev_net(dev)); - if (!net) - return NOTIFY_DONE; - if (!try_module_get(THIS_MODULE)) - goto err_module; + memset(&addr, 0, sizeof(addr)); - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - atomic_inc(&v6_worker_count); - - INIT_WORK(&w->work, iterate_cleanup_work); - w->ifindex = dev->ifindex; - w->net = net; - w->addr = ifa->addr; - schedule_work(&w->work); + addr.in6 = ifa->addr; - return NOTIFY_DONE; - } - - module_put(THIS_MODULE); - err_module: - put_net(net); + nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, + GFP_ATOMIC); return NOTIFY_DONE; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 081437dd75b7..c0851fec11d4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -780,6 +780,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -790,8 +791,11 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table); + event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; @@ -1563,6 +1567,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -1573,8 +1578,11 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, + event, flags, ctx->family, ctx->table, ctx->chain); if (err < 0) { kfree_skb(skb); @@ -2866,8 +2874,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, - const struct nft_rule *prule) + const struct nft_rule *rule, u64 handle) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; @@ -2887,9 +2894,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, NFTA_RULE_PAD)) goto nla_put_failure; - if (event != NFT_MSG_DELRULE && prule) { - if (nla_put_be64(skb, NFTA_RULE_POSITION, - cpu_to_be64(prule->handle), + if (event != NFT_MSG_DELRULE && handle) { + if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(handle), NFTA_RULE_PAD)) goto nla_put_failure; } @@ -2925,7 +2931,10 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); + const struct nft_rule *prule; struct sk_buff *skb; + u64 handle = 0; + u16 flags = 0; int err; if (!ctx->report && @@ -2936,9 +2945,20 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (event == NFT_MSG_NEWRULE && + !list_is_first(&rule->list, &ctx->chain->rules) && + !list_is_last(&rule->list, &ctx->chain->rules)) { + prule = list_prev_entry(rule, list); + handle = prule->handle; + } + if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) + flags |= NLM_F_APPEND; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, - ctx->chain, rule, NULL); + event, flags, ctx->family, ctx->table, + ctx->chain, rule, handle); if (err < 0) { kfree_skb(skb); goto err; @@ -2964,6 +2984,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + u64 handle; prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { @@ -2975,12 +2996,17 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); } + if (prule) + handle = prule->handle; + else + handle = 0; + if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, prule) < 0) + table, chain, rule, handle) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3143,7 +3169,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, NULL); + family, table, chain, rule, 0); if (err < 0) goto err_fill_rule_info; @@ -3403,17 +3429,15 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + err = nft_delrule(&ctx, old_rule); + if (err < 0) + goto err_destroy_flow_rule; + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err_destroy_flow_rule; } - err = nft_delrule(&ctx, old_rule); - if (err < 0) { - nft_trans_destroy(trans); - goto err_destroy_flow_rule; - } - list_add_tail_rcu(&rule->list, &old_rule->list); } else { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); @@ -3943,8 +3967,9 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, gfp_t gfp_flags) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); - struct sk_buff *skb; u32 portid = ctx->portid; + struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -3955,7 +3980,10 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; - err = nf_tables_fill_set(skb, ctx, set, event, 0); + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + + err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; @@ -4336,7 +4364,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; - if (alloc_size < size) + if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; set = kvzalloc(alloc_size, GFP_KERNEL); if (!set) @@ -5231,12 +5259,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_set_elem *elem, - int event, u16 flags) + int event) { struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -5246,6 +5275,9 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem); if (err < 0) { @@ -6921,7 +6953,7 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, - int family, int report, gfp_t gfp) + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; @@ -6946,8 +6978,9 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, if (skb == NULL) goto err; - err = nf_tables_fill_obj_info(skb, net, portid, seq, event, 0, family, - table, obj, false); + err = nf_tables_fill_obj_info(skb, net, portid, seq, event, + flags & (NLM_F_CREATE | NLM_F_EXCL), + family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; @@ -6964,7 +6997,7 @@ static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->family, ctx->report, GFP_KERNEL); + ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* @@ -7745,6 +7778,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -7755,8 +7789,11 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, - ctx->seq, event, 0, + ctx->seq, event, flags, ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); @@ -8634,7 +8671,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_setelem_activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_NEWSETELEM, 0); + NFT_MSG_NEWSETELEM); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -8642,7 +8679,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM, 0); + NFT_MSG_DELSETELEM); nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) { atomic_dec(&te->set->nelems); @@ -9599,7 +9636,6 @@ static void __nft_release_table(struct net *net, struct nft_table *table) table->use--; nf_tables_chain_destroy(&ctx); } - list_del(&table->list); nf_tables_table_destroy(&ctx); } @@ -9612,6 +9648,8 @@ static void __nft_release_tables(struct net *net) if (nft_table_has_owner(table)) continue; + list_del(&table->list); + __nft_release_table(net, table); } } @@ -9619,31 +9657,38 @@ static void __nft_release_tables(struct net *net) static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; - struct nft_table *table, *nt; struct net *net = n->net; - bool release = false; + unsigned int deleted; + bool restart = false; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); + deleted = 0; mutex_lock(&nft_net->commit_mutex); +again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { __nft_release_hook(net, table); - release = true; + list_del_rcu(&table->list); + to_delete[deleted++] = table; + if (deleted >= ARRAY_SIZE(to_delete)) + break; } } - if (release) { + if (deleted) { + restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); - list_for_each_entry_safe(table, nt, &nft_net->tables, list) { - if (nft_table_has_owner(table) && - n->portid == table->nlpid) - __nft_release_table(net, table); - } + while (deleted) + __nft_release_table(net, to_delete[--deleted]); + + if (restart) + goto again; } mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 866cfba04d6c..adc348056076 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -79,7 +79,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) ptr = skb_network_header(skb); else { - if (!pkt->tprot_set) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; ptr = skb_network_header(skb) + nft_thoff(pkt); } diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index e4fe2f0780eb..84a7dea46efa 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -113,13 +113,13 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, int off = skb_network_offset(skb); unsigned int len, nh_end; - nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len; + nh_end = pkt->flags & NFT_PKTINFO_L4PROTO ? nft_thoff(pkt) : skb->len; len = min_t(unsigned int, nh_end - skb_network_offset(skb), NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; - if (pkt->tprot_set) { + if (pkt->flags & NFT_PKTINFO_L4PROTO) { len = min_t(unsigned int, skb->len - nft_thoff(pkt), NFT_TRACETYPE_TRANSPORT_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index f554e2ea32ee..d5c719c9e36c 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -185,7 +185,7 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) struct net_device *netdev; #endif @@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); break; #endif -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) case NFPROTO_NETDEV: - if (hook != NF_NETDEV_INGRESS) + if (hook >= NF_NETDEV_NUMHOOKS) return ERR_PTR(-EOPNOTSUPP); if (!dev) @@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de if (!netdev) return ERR_PTR(-ENODEV); - return rcu_dereference(netdev->nf_hooks_ingress); +#ifdef CONFIG_NETFILTER_INGRESS + if (hook == NF_NETDEV_INGRESS) + return rcu_dereference(netdev->nf_hooks_ingress); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hook == NF_NETDEV_EGRESS) + return rcu_dereference(netdev->nf_hooks_egress); +#endif + fallthrough; #endif default: return ERR_PTR(-EPROTONOSUPPORT); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4c3fbaaeb103..4acc4b8e9fe5 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -560,7 +560,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nla_put_failure; if (indev && entskb->dev && - entskb->mac_header != entskb->network_header) { + skb_mac_header_was_set(entskb)) { struct nfqnl_msg_packet_hw phw; int len; diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 5b02408a920b..c3563f0be269 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, - .hook_mask = (1 << NF_NETDEV_INGRESS), + .hook_mask = (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; @@ -342,12 +344,6 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; } - /* UNREGISTER events are also happening on netns exit. - * - * Although nf_tables core releases all tables/chains, only this event - * handler provides guarantee that hook->ops.dev is still accessible, - * so we cannot skip exiting net namespaces. - */ __nft_release_basechain(ctx); } @@ -366,6 +362,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; + if (!check_net(ctx.net)) + return NOTIFY_DONE; + nft_net = nft_pernet(ctx.net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 272bcdb1392d..f69cc73c5813 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -19,6 +19,7 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_log.h> /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -257,8 +258,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); - if (ret < 0) + if (ret < 0) { + if (ret == -ENOENT) { + const char *modname = NULL; + + if (strcmp(target->name, "LOG") == 0) + modname = "nf_log_syslog"; + else if (strcmp(target->name, "NFLOG") == 0) + modname = "nfnetlink_log"; + + if (modname && + nft_request_module(ctx->net, "%s", modname) == -EAGAIN) + return -EAGAIN; + } + return ret; + } /* The standard target cannot be used */ if (!target->target) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 6ba3256fa844..87f3af4645d9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -198,17 +198,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return -EBUSY; priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP])); - switch (priv->op) { - case NFT_DYNSET_OP_ADD: - case NFT_DYNSET_OP_DELETE: - break; - case NFT_DYNSET_OP_UPDATE: - if (!(set->flags & NFT_SET_TIMEOUT)) - return -EOPNOTSUPP; - break; - default: + if (priv->op > NFT_DYNSET_OP_DELETE) return -EOPNOTSUPP; - } timeout = 0; if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index a7e01e9952f1..fe91ff5f8fbe 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -244,7 +244,11 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest, case NFT_META_OIF: nft_meta_store_ifindex(dest, nft_out(pkt)); break; - case NFT_META_IIFTYPE: + case NFT_META_IFTYPE: + if (!nft_meta_store_iftype(dest, pkt->skb->dev)) + return false; + break; + case __NFT_META_IIFTYPE: if (!nft_meta_store_iftype(dest, nft_in(pkt))) return false; break; @@ -329,7 +333,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, nft_reg_store8(dest, nft_pf(pkt)); break; case NFT_META_L4PROTO: - if (!pkt->tprot_set) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) goto err; nft_reg_store8(dest, pkt->tprot); break; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a44b14f6c0dc..cbfe4e4a4ad7 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,6 +22,7 @@ #include <linux/icmpv6.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/ip.h> #include <net/sctp/checksum.h> static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, @@ -79,6 +80,45 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; } +static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) +{ + unsigned int thoff = nft_thoff(pkt); + + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + return -1; + + switch (pkt->tprot) { + case IPPROTO_UDP: + pkt->inneroff = thoff + sizeof(struct udphdr); + break; + case IPPROTO_TCP: { + struct tcphdr *th, _tcph; + + th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph); + if (!th) + return -1; + + pkt->inneroff = thoff + __tcp_hdrlen(th); + } + break; + default: + return -1; + } + + pkt->flags |= NFT_PKTINFO_INNER; + + return 0; +} + +static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +{ + if (!(pkt->flags & NFT_PKTINFO_INNER) && + __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0) + return -1; + + return pkt->inneroff; +} + void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -108,10 +148,15 @@ void nft_payload_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: - if (!pkt->tprot_set) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -610,10 +655,15 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: - if (!pkt->tprot_set) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -622,7 +672,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset += priv->offset; if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) && - (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER || + ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER && + priv->base != NFT_PAYLOAD_INNER_HEADER) || skb->ip_summed != CHECKSUM_PARTIAL)) { fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); @@ -741,6 +792,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, case NFT_PAYLOAD_LL_HEADER: case NFT_PAYLOAD_NETWORK_HEADER: case NFT_PAYLOAD_TRANSPORT_HEADER: + case NFT_PAYLOAD_INNER_HEADER: break; default: return ERR_PTR(-EOPNOTSUPP); @@ -759,7 +811,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && - base != NFT_PAYLOAD_LL_HEADER) + base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0363f533a42b..c4d1389f7185 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -60,7 +60,7 @@ static void nft_quota_obj_eval(struct nft_object *obj, if (overquota && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, - NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); + NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC); } static int nft_quota_do_init(const struct nlattr * const tb[], diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 7b2f359bfce4..2f7cf5ecebf4 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -137,7 +137,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; - info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL); + info->timer = kzalloc(sizeof(*info->timer), GFP_KERNEL); if (!info->timer) { ret = -ENOMEM; goto out; diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 2ff75f7637b0..f39244f9c0ed 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -44,6 +44,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; + int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; @@ -58,7 +59,14 @@ static int log_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } - return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nf_log_syslog"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + } + + return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index fb5793208059..e660c3710a10 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -42,13 +42,21 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int nflog_tg_check(const struct xt_tgchk_param *par) { const struct xt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~XT_NFLOG_MASK) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; } static void nflog_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 0d5c422f8745..8aec1b529364 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -94,11 +94,11 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic_packed *stats = &info->est->bstats; + struct gnet_stats_basic_sync *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); - stats->bytes += skb->len; - stats->packets++; + u64_stats_add(&stats->bytes, skb->len); + u64_stats_inc(&stats->packets); spin_unlock_bh(&info->est->lock); return XT_CONTINUE; @@ -143,6 +143,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) if (!est) goto err1; + gnet_stats_basic_sync_init(&est->bstats); strlcpy(est->name, info->name, sizeof(est->name)); spin_lock_init(&est->lock); est->refcnt = 1; |