diff options
author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-09-08 01:01:14 -0300 |
---|---|---|
committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-09-08 01:01:14 -0300 |
commit | e5fd91f1ef340da553f7a79da9540c3db711c937 (patch) | |
tree | b11842027dc6641da63f4bcc524f8678263304a3 /net/netfilter | |
parent | 2a9b0348e685a63d97486f6749622b61e9e3292f (diff) |
Linux-libre 4.2-gnu
Diffstat (limited to 'net/netfilter')
52 files changed, 2334 insertions, 1693 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index a0f3e6a3c..6eae69a69 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1,6 +1,14 @@ menu "Core Netfilter Configuration" depends on NET && INET && NETFILTER +config NETFILTER_INGRESS + bool "Netfilter ingress support" + default y + select NET_INGRESS + help + This allows you to classify packets from ingress using the Netfilter + infrastructure. + config NETFILTER_NETLINK tristate @@ -198,7 +206,7 @@ config NF_CONNTRACK_FTP config NF_CONNTRACK_H323 tristate "H.323 protocol support" - depends on (IPV6 || IPV6=n) + depends on IPV6 || IPV6=n depends on NETFILTER_ADVANCED help H.323 is a VoIP signalling protocol from ITU-T. As one of the most @@ -448,6 +456,11 @@ config NF_TABLES_INET help This option enables support for a mixed IPv4/IPv6 "inet" table. +config NF_TABLES_NETDEV + tristate "Netfilter nf_tables netdev tables support" + help + This option enables support for the "netdev" table. + config NFT_EXTHDR tristate "Netfilter nf_tables IPv6 exthdr module" help @@ -710,7 +723,7 @@ config NETFILTER_XT_TARGET_HL config NETFILTER_XT_TARGET_HMARK tristate '"HMARK" target support' - depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) + depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n depends on NETFILTER_ADVANCED ---help--- This option adds the "HMARK" target. @@ -852,7 +865,7 @@ config NETFILTER_XT_TARGET_REDIRECT config NETFILTER_XT_TARGET_TEE tristate '"TEE" - packet cloning to alternate destination' depends on NETFILTER_ADVANCED - depends on (IPV6 || IPV6=n) + depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK ---help--- This option adds a "TEE" target with which a packet can be cloned and @@ -862,8 +875,8 @@ config NETFILTER_XT_TARGET_TPROXY tristate '"TPROXY" target transparent proxying support' depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED - depends on (IPV6 || IPV6=n) - depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) + depends on IPV6 || IPV6=n + depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES @@ -902,7 +915,7 @@ config NETFILTER_XT_TARGET_SECMARK config NETFILTER_XT_TARGET_TCPMSS tristate '"TCPMSS" target support' - depends on (IPV6 || IPV6=n) + depends on IPV6 || IPV6=n default m if NETFILTER_ADVANCED=n ---help--- This option adds a `TCPMSS' target, which allows you to alter the @@ -1114,7 +1127,7 @@ config NETFILTER_XT_MATCH_ESP config NETFILTER_XT_MATCH_HASHLIMIT tristate '"hashlimit" match support' - depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) + depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n depends on NETFILTER_ADVANCED help This option adds a `hashlimit' match. @@ -1356,8 +1369,8 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK - depends on (IPV6 || IPV6=n) - depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) + depends on IPV6 || IPV6=n + depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a87d8b8ec..70d026d46 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -75,6 +75,7 @@ nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o +obj-$(CONFIG_NF_TABLES_NETDEV) += nf_tables_netdev.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e6163017c..a0e54974e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -64,10 +64,27 @@ static DEFINE_MUTEX(nf_hook_mutex); int nf_register_hook(struct nf_hook_ops *reg) { + struct list_head *nf_hook_list; struct nf_hook_ops *elem; mutex_lock(&nf_hook_mutex); - list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) { + switch (reg->pf) { + case NFPROTO_NETDEV: +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) { + BUG_ON(reg->dev == NULL); + nf_hook_list = ®->dev->nf_hooks_ingress; + net_inc_ingress_queue(); + break; + } +#endif + /* Fall through. */ + default: + nf_hook_list = &nf_hooks[reg->pf][reg->hooknum]; + break; + } + + list_for_each_entry(elem, nf_hook_list, list) { if (reg->priority < elem->priority) break; } @@ -85,10 +102,23 @@ void nf_unregister_hook(struct nf_hook_ops *reg) mutex_lock(&nf_hook_mutex); list_del_rcu(®->list); mutex_unlock(&nf_hook_mutex); + switch (reg->pf) { + case NFPROTO_NETDEV: +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) { + net_dec_ingress_queue(); + break; + } + break; +#endif + default: + break; + } #ifdef HAVE_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); + nf_queue_nf_hook_drop(reg); } EXPORT_SYMBOL(nf_unregister_hook); @@ -166,11 +196,9 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state) /* We may already have this, but read-locks nest anyway */ rcu_read_lock(); - elem = list_entry_rcu(&nf_hooks[state->pf][state->hook], - struct nf_hook_ops, list); + elem = list_entry_rcu(state->hook_list, struct nf_hook_ops, list); next_hook: - verdict = nf_iterate(&nf_hooks[state->pf][state->hook], skb, state, - &elem); + verdict = nf_iterate(state->hook_list, skb, state, &elem); if (verdict == NF_ACCEPT || verdict == NF_STOP) { ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 6f024a8a1..d05e759ed 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -41,7 +41,7 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) struct mtype *map = set->data; init_timer(&map->gc); - map->gc.data = (unsigned long) set; + map->gc.data = (unsigned long)set; map->gc.function = gc; map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); @@ -144,10 +144,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (ret == IPSET_ADD_FAILED) { if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(x, set))) + ip_set_timeout_expired(ext_timeout(x, set))) { ret = 0; - else if (!(flags & IPSET_FLAG_EXIST)) + } else if (!(flags & IPSET_FLAG_EXIST)) { + set_bit(e->id, map->members); return -IPSET_ERR_EXIST; + } /* Element is re-added, cleanup extensions */ ip_set_ext_destroy(set, x); } @@ -165,6 +167,10 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, ip_set_init_comment(ext_comment(x, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(x, set), ext); + + /* Activate element */ + set_bit(e->id, map->members); + return 0; } @@ -203,10 +209,13 @@ mtype_list(const struct ip_set *set, struct nlattr *adt, *nested; void *x; u32 id, first = cb->args[IPSET_CB_ARG0]; + int ret = 0; adt = ipset_nest_start(skb, IPSET_ATTR_ADT); if (!adt) return -EMSGSIZE; + /* Extensions may be replaced */ + rcu_read_lock(); for (; cb->args[IPSET_CB_ARG0] < map->elements; cb->args[IPSET_CB_ARG0]++) { id = cb->args[IPSET_CB_ARG0]; @@ -214,7 +223,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(id, map->members) || (SET_WITH_TIMEOUT(set) && #ifdef IP_SET_BITMAP_STORED_TIMEOUT - mtype_is_filled((const struct mtype_elem *) x) && + mtype_is_filled((const struct mtype_elem *)x) && #endif ip_set_timeout_expired(ext_timeout(x, set)))) continue; @@ -222,14 +231,16 @@ mtype_list(const struct ip_set *set, if (!nested) { if (id == first) { nla_nest_cancel(skb, adt); - return -EMSGSIZE; - } else - goto nla_put_failure; + ret = -EMSGSIZE; + goto out; + } + + goto nla_put_failure; } if (mtype_do_list(skb, map, id, set->dsize)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, x, - mtype_is_filled((const struct mtype_elem *) x))) + mtype_is_filled((const struct mtype_elem *)x))) goto nla_put_failure; ipset_nest_end(skb, nested); } @@ -238,29 +249,32 @@ mtype_list(const struct ip_set *set, /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; - return 0; + goto out; nla_put_failure: nla_nest_cancel(skb, nested); if (unlikely(id == first)) { cb->args[IPSET_CB_ARG0] = 0; - return -EMSGSIZE; + ret = -EMSGSIZE; } ipset_nest_end(skb, adt); - return 0; +out: + rcu_read_unlock(); + return ret; } static void mtype_gc(unsigned long ul_set) { - struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set *set = (struct ip_set *)ul_set; struct mtype *map = set->data; void *x; u32 id; /* We run parallel with other readers (test element) - * but adding/deleting new entries is locked out */ - read_lock_bh(&set->lock); + * but adding/deleting new entries is locked out + */ + spin_lock_bh(&set->lock); for (id = 0; id < map->elements; id++) if (mtype_gc_test(id, map, set->dsize)) { x = get_ext(set, map, id); @@ -269,7 +283,7 @@ mtype_gc(unsigned long ul_set) ip_set_ext_destroy(set, x); } } - read_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 55b083ec5..64a564334 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -36,6 +36,7 @@ IP_SET_MODULE_DESC("bitmap:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_bitmap:ip"); #define MTYPE bitmap_ip +#define HOST_MASK 32 /* Type structure */ struct bitmap_ip { @@ -58,7 +59,7 @@ struct bitmap_ip_adt_elem { static inline u32 ip_to_id(const struct bitmap_ip *m, u32 ip) { - return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip)/m->hosts; + return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip) / m->hosts; } /* Common functions */ @@ -80,7 +81,7 @@ static inline int bitmap_ip_do_add(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map, u32 flags, size_t dsize) { - return !!test_and_set_bit(e->id, map->members); + return !!test_bit(e->id, map->members); } static inline int @@ -137,20 +138,17 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret = 0; - if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + if (unlikely(!tb[IPSET_ATTR_IP])) + return -IPSET_ERR_PROTOCOL; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -174,11 +172,12 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); - } else + } else { ip_to = ip; + } if (ip_to > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; @@ -189,8 +188,8 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -277,16 +276,17 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr >= 32) + if (cidr >= HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(first_ip, last_ip, cidr); - } else + } else { return -IPSET_ERR_PROTOCOL; + } if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); - if (netmask > 32) + if (netmask > HOST_MASK) return -IPSET_ERR_INVALID_NETMASK; first_ip &= ip_set_hostmask(netmask); @@ -360,7 +360,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -377,6 +378,7 @@ bitmap_ip_init(void) static void __exit bitmap_ip_fini(void) { + rcu_barrier(); ip_set_type_unregister(&bitmap_ip_type); } diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 86104744b..143053511 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -36,6 +36,7 @@ IP_SET_MODULE_DESC("bitmap:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_bitmap:ip,mac"); #define MTYPE bitmap_ipmac +#define HOST_MASK 32 #define IP_SET_BITMAP_STORED_TIMEOUT enum { @@ -89,7 +90,7 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e, return 0; elem = get_elem(map->extensions, e->id, dsize); if (elem->filled == MAC_FILLED) - return e->ether == NULL || + return !e->ether || ether_addr_equal(e->ether, elem->ether); /* Trigger kernel to fill out the ethernet address */ return -EAGAIN; @@ -130,7 +131,8 @@ bitmap_ipmac_add_timeout(unsigned long *timeout, /* If MAC is unset yet, we store plain timeout value * because the timer is not activated yet * and we can reuse it later when MAC is filled out, - * possibly by the kernel */ + * possibly by the kernel + */ if (e->ether) ip_set_timeout_set(timeout, t); else @@ -146,28 +148,35 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, struct bitmap_ipmac_elem *elem; elem = get_elem(map->extensions, e->id, dsize); - if (test_and_set_bit(e->id, map->members)) { + if (test_bit(e->id, map->members)) { if (elem->filled == MAC_FILLED) { - if (e->ether && (flags & IPSET_FLAG_EXIST)) - memcpy(elem->ether, e->ether, ETH_ALEN); + if (e->ether && + (flags & IPSET_FLAG_EXIST) && + !ether_addr_equal(e->ether, elem->ether)) { + /* memcpy isn't atomic */ + clear_bit(e->id, map->members); + smp_mb__after_atomic(); + ether_addr_copy(elem->ether, e->ether); + } return IPSET_ADD_FAILED; } else if (!e->ether) /* Already added without ethernet address */ return IPSET_ADD_FAILED; /* Fill the MAC address and trigger the timer activation */ - memcpy(elem->ether, e->ether, ETH_ALEN); + clear_bit(e->id, map->members); + smp_mb__after_atomic(); + ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; return IPSET_ADD_START_STORED_TIMEOUT; } else if (e->ether) { /* We can store MAC too */ - memcpy(elem->ether, e->ether, ETH_ALEN); + ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; return 0; - } else { - elem->filled = MAC_UNSET; - /* MAC is not stored yet, don't start timer */ - return IPSET_ADD_STORE_PLAIN_TIMEOUT; } + elem->filled = MAC_UNSET; + /* MAC is not stored yet, don't start timer */ + return IPSET_ADD_STORE_PLAIN_TIMEOUT; } static inline int @@ -238,20 +247,17 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], u32 ip = 0; int ret = 0; - if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + if (unlikely(!tb[IPSET_ATTR_IP])) + return -IPSET_ERR_PROTOCOL; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -343,11 +349,12 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr >= 32) + if (cidr >= HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(first_ip, last_ip, cidr); - } else + } else { return -IPSET_ERR_PROTOCOL; + } elements = (u64)last_ip - first_ip + 1; @@ -397,7 +404,8 @@ static struct ip_set_type bitmap_ipmac_type = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -414,6 +422,7 @@ bitmap_ipmac_init(void) static void __exit bitmap_ipmac_fini(void) { + rcu_barrier(); ip_set_type_unregister(&bitmap_ipmac_type); } diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 005dd3644..5338ccd5d 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -73,7 +73,7 @@ static inline int bitmap_port_do_add(const struct bitmap_port_adt_elem *e, struct bitmap_port *map, u32 flags, size_t dsize) { - return !!test_and_set_bit(e->id, map->members); + return !!test_bit(e->id, map->members); } static inline int @@ -136,19 +136,13 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], u16 port_to; int ret = 0; - if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) + return -IPSET_ERR_PROTOCOL; + port = ip_set_get_h16(tb[IPSET_ATTR_PORT]); if (port < map->first_port || port > map->last_port) return -IPSET_ERR_BITMAP_RANGE; @@ -168,8 +162,9 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], if (port < map->first_port) return -IPSET_ERR_BITMAP_RANGE; } - } else + } else { port_to = port; + } if (port_to > map->last_port) return -IPSET_ERR_BITMAP_RANGE; @@ -180,8 +175,8 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -294,7 +289,8 @@ static struct ip_set_type bitmap_port_type = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -311,6 +307,7 @@ bitmap_port_init(void) static void __exit bitmap_port_fini(void) { + rcu_barrier(); ip_set_type_unregister(&bitmap_port_type); } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d259da3ce..338b40477 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -32,8 +32,10 @@ static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ struct ip_set_net { struct ip_set * __rcu *ip_set_list; /* all individual sets */ ip_set_id_t ip_set_max; /* max number of sets */ - int is_deleted; /* deleted by ip_set_net_exit */ + bool is_deleted; /* deleted by ip_set_net_exit */ + bool is_destroyed; /* all sets are destroyed */ }; + static int ip_set_net_id __read_mostly; static inline struct ip_set_net *ip_set_pernet(struct net *net) @@ -42,7 +44,7 @@ static inline struct ip_set_net *ip_set_pernet(struct net *net) } #define IP_SET_INC 64 -#define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) +#define STRNCMP(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) static unsigned int max_sets; @@ -59,8 +61,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] -/* - * The set types are implemented in modules and registered set types +/* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is * serialized by ip_set_type_mutex. */ @@ -85,7 +86,7 @@ find_set_type(const char *name, u8 family, u8 revision) struct ip_set_type *type; list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name) && + if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC) && revision >= type->revision_min && @@ -130,9 +131,10 @@ __find_set_type_get(const char *name, u8 family, u8 revision, goto unlock; } /* Make sure the type is already loaded - * but we don't support the revision */ + * but we don't support the revision + */ list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name)) { + if (STRNCMP(type->name, name)) { err = -IPSET_ERR_FIND_TYPE; goto unlock; } @@ -166,7 +168,7 @@ __find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, *min = 255; *max = 0; rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) - if (STREQ(type->name, name) && + if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC)) { found = true; @@ -208,15 +210,15 @@ ip_set_type_register(struct ip_set_type *type) pr_warn("ip_set type %s, family %s with revision min %u already registered!\n", type->name, family_name(type->family), type->revision_min); - ret = -EINVAL; - goto unlock; + ip_set_type_unlock(); + return -EINVAL; } list_add_rcu(&type->list, &ip_set_type_list); pr_debug("type %s, family %s, revision %u:%u registered.\n", type->name, family_name(type->family), type->revision_min, type->revision_max); -unlock: ip_set_type_unlock(); + return ret; } EXPORT_SYMBOL_GPL(ip_set_type_register); @@ -230,12 +232,12 @@ ip_set_type_unregister(struct ip_set_type *type) pr_warn("ip_set type %s, family %s with revision min %u not registered\n", type->name, family_name(type->family), type->revision_min); - goto unlock; + ip_set_type_unlock(); + return; } list_del_rcu(&type->list); pr_debug("type %s, family %s with revision min %u unregistered.\n", type->name, family_name(type->family), type->revision_min); -unlock: ip_set_type_unlock(); synchronize_rcu(); @@ -289,7 +291,7 @@ static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = { int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) { - struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1]; + struct nlattr *tb[IPSET_ATTR_IPADDR_MAX + 1]; if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; @@ -306,7 +308,7 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr4); int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) { - struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1]; + struct nlattr *tb[IPSET_ATTR_IPADDR_MAX + 1]; if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; @@ -317,7 +319,7 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) return -IPSET_ERR_PROTOCOL; memcpy(ipaddr, nla_data(tb[IPSET_ATTR_IPADDR_IPV6]), - sizeof(struct in6_addr)); + sizeof(struct in6_addr)); return 0; } EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); @@ -365,7 +367,7 @@ size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) { enum ip_set_ext_id id; - size_t offset = 0; + size_t offset = len; u32 cadt_flags = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) @@ -375,12 +377,12 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; - offset += ALIGN(len + offset, ip_set_extensions[id].align); + offset = ALIGN(offset, ip_set_extensions[id].align); set->offset[id] = offset; set->extensions |= ip_set_extensions[id].type; offset += ip_set_extensions[id].len; } - return len + offset; + return offset; } EXPORT_SYMBOL_GPL(ip_set_elem_len); @@ -389,13 +391,22 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext) { u64 fullmark; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + return -IPSET_ERR_PROTOCOL; + if (tb[IPSET_ATTR_TIMEOUT]) { - if (!(set->extensions & IPSET_EXT_TIMEOUT)) + if (!SET_WITH_TIMEOUT(set)) return -IPSET_ERR_TIMEOUT; ext->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } if (tb[IPSET_ATTR_BYTES] || tb[IPSET_ATTR_PACKETS]) { - if (!(set->extensions & IPSET_EXT_COUNTER)) + if (!SET_WITH_COUNTER(set)) return -IPSET_ERR_COUNTER; if (tb[IPSET_ATTR_BYTES]) ext->bytes = be64_to_cpu(nla_get_be64( @@ -405,25 +416,25 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], tb[IPSET_ATTR_PACKETS])); } if (tb[IPSET_ATTR_COMMENT]) { - if (!(set->extensions & IPSET_EXT_COMMENT)) + if (!SET_WITH_COMMENT(set)) return -IPSET_ERR_COMMENT; ext->comment = ip_set_comment_uget(tb[IPSET_ATTR_COMMENT]); } if (tb[IPSET_ATTR_SKBMARK]) { - if (!(set->extensions & IPSET_EXT_SKBINFO)) + if (!SET_WITH_SKBINFO(set)) return -IPSET_ERR_SKBINFO; fullmark = be64_to_cpu(nla_get_be64(tb[IPSET_ATTR_SKBMARK])); ext->skbmark = fullmark >> 32; ext->skbmarkmask = fullmark & 0xffffffff; } if (tb[IPSET_ATTR_SKBPRIO]) { - if (!(set->extensions & IPSET_EXT_SKBINFO)) + if (!SET_WITH_SKBINFO(set)) return -IPSET_ERR_SKBINFO; ext->skbprio = be32_to_cpu(nla_get_be32( tb[IPSET_ATTR_SKBPRIO])); } if (tb[IPSET_ATTR_SKBQUEUE]) { - if (!(set->extensions & IPSET_EXT_SKBINFO)) + if (!SET_WITH_SKBINFO(set)) return -IPSET_ERR_SKBINFO; ext->skbqueue = be16_to_cpu(nla_get_be16( tb[IPSET_ATTR_SKBQUEUE])); @@ -432,8 +443,32 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_set_get_extensions); -/* - * Creating/destroying/renaming/swapping affect the existence and +int +ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, + const void *e, bool active) +{ + if (SET_WITH_TIMEOUT(set)) { + unsigned long *timeout = ext_timeout(e, set); + + if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(active ? ip_set_timeout_get(timeout) + : *timeout))) + return -EMSGSIZE; + } + if (SET_WITH_COUNTER(set) && + ip_set_put_counter(skb, ext_counter(e, set))) + return -EMSGSIZE; + if (SET_WITH_COMMENT(set) && + ip_set_put_comment(skb, ext_comment(e, set))) + return -EMSGSIZE; + if (SET_WITH_SKBINFO(set) && + ip_set_put_skbinfo(skb, ext_skbinfo(e, set))) + return -EMSGSIZE; + return 0; +} +EXPORT_SYMBOL_GPL(ip_set_put_extensions); + +/* Creating/destroying/renaming/swapping affect the existence and * the properties of a set. All of these can be executed from userspace * only and serialized by the nfnl mutex indirectly from nfnetlink. * @@ -460,8 +495,7 @@ __ip_set_put(struct ip_set *set) write_unlock_bh(&ip_set_ref_lock); } -/* - * Add, del and test set entries from kernel. +/* Add, del and test set entries from kernel. * * The set behind the index must exist and must be referenced * so it can't be destroyed (or changed) under our foot. @@ -489,23 +523,23 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, dev_net(par->in ? par->in : par->out), index); int ret = 0; - BUG_ON(set == NULL); + BUG_ON(!set); pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return 0; - read_lock_bh(&set->lock); + rcu_read_lock_bh(); ret = set->variant->kadt(set, skb, par, IPSET_TEST, opt); - read_unlock_bh(&set->lock); + rcu_read_unlock_bh(); if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -528,16 +562,16 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, dev_net(par->in ? par->in : par->out), index); int ret; - BUG_ON(set == NULL); + BUG_ON(!set); pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); return ret; } @@ -551,23 +585,22 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, dev_net(par->in ? par->in : par->out), index); int ret = 0; - BUG_ON(set == NULL); + BUG_ON(!set); pr_debug("set %s, index %u\n", set->name, index); if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); return ret; } EXPORT_SYMBOL_GPL(ip_set_del); -/* - * Find set by name, reference it once. The reference makes sure the +/* Find set by name, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * */ @@ -581,7 +614,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) rcu_read_lock(); for (i = 0; i < inst->ip_set_max; i++) { s = rcu_dereference(inst->ip_set_list)[i]; - if (s != NULL && STREQ(s->name, name)) { + if (s && STRNCMP(s->name, name)) { __ip_set_get(s); index = i; *set = s; @@ -594,8 +627,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) } EXPORT_SYMBOL_GPL(ip_set_get_byname); -/* - * If the given set pointer points to a valid set, decrement +/* If the given set pointer points to a valid set, decrement * reference count by 1. The caller shall not assume the index * to be valid, after calling this function. * @@ -608,7 +640,7 @@ __ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index) rcu_read_lock(); set = rcu_dereference(inst->ip_set_list)[index]; - if (set != NULL) + if (set) __ip_set_put(set); rcu_read_unlock(); } @@ -622,8 +654,7 @@ 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. +/* 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. @@ -634,7 +665,7 @@ ip_set_name_byindex(struct net *net, ip_set_id_t index) { const struct ip_set *set = ip_set_rcu_get(net, index); - BUG_ON(set == NULL); + BUG_ON(!set); BUG_ON(set->ref == 0); /* Referenced, so it's safe */ @@ -642,13 +673,11 @@ ip_set_name_byindex(struct net *net, ip_set_id_t index) } EXPORT_SYMBOL_GPL(ip_set_name_byindex); -/* - * Routines to call by external subsystems, which do not +/* Routines to call by external subsystems, which do not * call nfnl_lock for us. */ -/* - * Find set by index, reference it once. The reference makes sure the +/* Find set by index, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * * The nfnl mutex is used in the function. @@ -674,8 +703,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) } EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex); -/* - * If the given set pointer points to a valid set, decrement +/* If the given set pointer points to a valid set, decrement * reference count by 1. The caller shall not assume the index * to be valid, after calling this function. * @@ -690,15 +718,14 @@ ip_set_nfnl_put(struct net *net, ip_set_id_t index) nfnl_lock(NFNL_SUBSYS_IPSET); if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */ set = ip_set(inst, index); - if (set != NULL) + if (set) __ip_set_put(set); } nfnl_unlock(NFNL_SUBSYS_IPSET); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); -/* - * Communication protocol with userspace over netlink. +/* Communication protocol with userspace over netlink. * * The commands are serialized by the nfnl mutex. */ @@ -725,7 +752,7 @@ start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags, nlh = nlmsg_put(skb, portid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), sizeof(*nfmsg), flags); - if (nlh == NULL) + if (!nlh) return NULL; nfmsg = nlmsg_data(nlh); @@ -758,7 +785,7 @@ find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id) *id = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { set = ip_set(inst, i); - if (set != NULL && STREQ(set->name, name)) { + if (set && STRNCMP(set->name, name)) { *id = i; break; } @@ -784,10 +811,10 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, *index = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s == NULL) { + if (!s) { if (*index == IPSET_INVALID_ID) *index = i; - } else if (STREQ(name, s->name)) { + } else if (STRNCMP(name, s->name)) { /* Name clash */ *set = s; return -EEXIST; @@ -816,18 +843,18 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, struct ip_set_net *inst = ip_set_pernet(net); struct ip_set *set, *clash = NULL; ip_set_id_t index = IPSET_INVALID_ID; - struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {}; + struct nlattr *tb[IPSET_ATTR_CREATE_MAX + 1] = {}; const char *name, *typename; u8 family, revision; u32 flags = flag_exist(nlh); int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || - attr[IPSET_ATTR_TYPENAME] == NULL || - attr[IPSET_ATTR_REVISION] == NULL || - attr[IPSET_ATTR_FAMILY] == NULL || - (attr[IPSET_ATTR_DATA] != NULL && + !attr[IPSET_ATTR_SETNAME] || + !attr[IPSET_ATTR_TYPENAME] || + !attr[IPSET_ATTR_REVISION] || + !attr[IPSET_ATTR_FAMILY] || + (attr[IPSET_ATTR_DATA] && !flag_nested(attr[IPSET_ATTR_DATA])))) return -IPSET_ERR_PROTOCOL; @@ -838,33 +865,29 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, pr_debug("setname: %s, typename: %s, family: %s, revision: %u\n", name, typename, family_name(family), revision); - /* - * First, and without any locks, allocate and initialize + /* First, and without any locks, allocate and initialize * a normal base set structure. */ - set = kzalloc(sizeof(struct ip_set), GFP_KERNEL); + set = kzalloc(sizeof(*set), GFP_KERNEL); if (!set) return -ENOMEM; - rwlock_init(&set->lock); + spin_lock_init(&set->lock); strlcpy(set->name, name, IPSET_MAXNAMELEN); set->family = family; set->revision = revision; - /* - * Next, check that we know the type, and take + /* Next, check that we know the type, and take * a reference on the type, to make sure it stays available * while constructing our new set. * * After referencing the type, we try to create the type * specific part of the set without holding any locks. */ - ret = find_set_type_get(typename, family, revision, &(set->type)); + ret = find_set_type_get(typename, family, revision, &set->type); if (ret) goto out; - /* - * Without holding any locks, create private part. - */ + /* Without holding any locks, create private part. */ if (attr[IPSET_ATTR_DATA] && nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy)) { @@ -878,8 +901,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, /* BTW, ret==0 here. */ - /* - * Here, we have a valid, constructed set and we are protected + /* Here, we have a valid, constructed set and we are protected * by the nfnl mutex. Find the first free index in ip_set_list * and check clashing. */ @@ -887,7 +909,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, if (ret == -EEXIST) { /* If this is the same set and requested, ignore error */ if ((flags & IPSET_FLAG_EXIST) && - STREQ(set->type->name, clash->type->name) && + STRNCMP(set->type->name, clash->type->name) && set->type->family == clash->type->family && set->type->revision_min == clash->type->revision_min && set->type->revision_max == clash->type->revision_max && @@ -902,7 +924,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, /* Wraparound */ goto cleanup; - list = kzalloc(sizeof(struct ip_set *) * i, GFP_KERNEL); + list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -916,12 +938,11 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, inst->ip_set_max = i; kfree(tmp); ret = 0; - } else if (ret) + } else if (ret) { goto cleanup; + } - /* - * Finally! Add our shiny new set to the list, and be done. - */ + /* Finally! Add our shiny new set to the list, and be done. */ pr_debug("create: '%s' created with index %u!\n", set->name, index); ip_set(inst, index) = set; @@ -946,12 +967,9 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { }; static void -ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index) +ip_set_destroy_set(struct ip_set *set) { - struct ip_set *set = ip_set(inst, index); - pr_debug("set: %s\n", set->name); - ip_set(inst, index) = NULL; /* Must call it without holding any lock */ set->variant->destroy(set); @@ -986,30 +1004,36 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s != NULL && s->ref) { + if (s && s->ref) { ret = -IPSET_ERR_BUSY; goto out; } } + inst->is_destroyed = true; read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s != NULL) - ip_set_destroy_set(inst, i); + if (s) { + ip_set(inst, i) = NULL; + ip_set_destroy_set(s); + } } + /* Modified by ip_set_destroy() only, which is serialized */ + inst->is_destroyed = false; } else { s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); - if (s == NULL) { + if (!s) { ret = -ENOENT; goto out; } else if (s->ref) { ret = -IPSET_ERR_BUSY; goto out; } + ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - ip_set_destroy_set(inst, i); + ip_set_destroy_set(s); } return 0; out: @@ -1024,9 +1048,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); set->variant->flush(set); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); } static int @@ -1044,12 +1068,12 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s != NULL) + if (s) ip_set_flush_set(s); } } else { s = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (s == NULL) + if (!s) return -ENOENT; ip_set_flush_set(s); @@ -1081,12 +1105,12 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || - attr[IPSET_ATTR_SETNAME2] == NULL)) + !attr[IPSET_ATTR_SETNAME] || + !attr[IPSET_ATTR_SETNAME2])) return -IPSET_ERR_PROTOCOL; set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (set == NULL) + if (!set) return -ENOENT; read_lock_bh(&ip_set_ref_lock); @@ -1098,7 +1122,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s != NULL && STREQ(s->name, name2)) { + if (s && STRNCMP(s->name, name2)) { ret = -IPSET_ERR_EXIST_SETNAME2; goto out; } @@ -1130,23 +1154,24 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, char from_name[IPSET_MAXNAMELEN]; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || - attr[IPSET_ATTR_SETNAME2] == NULL)) + !attr[IPSET_ATTR_SETNAME] || + !attr[IPSET_ATTR_SETNAME2])) return -IPSET_ERR_PROTOCOL; from = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &from_id); - if (from == NULL) + if (!from) return -ENOENT; to = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME2]), &to_id); - if (to == NULL) + if (!to) return -IPSET_ERR_EXIST_SETNAME2; /* Features must not change. - * Not an artificial restriction anymore, as we must prevent - * possible loops created by swapping in setlist type of sets. */ + * Not an artifical restriction anymore, as we must prevent + * possible loops created by swapping in setlist type of sets. + */ if (!(from->type->features == to->type->features && from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; @@ -1177,12 +1202,16 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, static int ip_set_dump_done(struct netlink_callback *cb) { - struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; if (cb->args[IPSET_CB_ARG0]) { - pr_debug("release set %s\n", - ip_set(inst, cb->args[IPSET_CB_INDEX])->name); - __ip_set_put_byindex(inst, - (ip_set_id_t) cb->args[IPSET_CB_INDEX]); + 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); + + if (set->variant->uref) + set->variant->uref(set, cb, false); + pr_debug("release set %s\n", set->name); + __ip_set_put_byindex(inst, index); } return 0; } @@ -1204,7 +1233,7 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) { struct nlmsghdr *nlh = nlmsg_hdr(cb->skb); int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); - struct nlattr *cda[IPSET_ATTR_CMD_MAX+1]; + struct nlattr *cda[IPSET_ATTR_CMD_MAX + 1]; struct nlattr *attr = (void *)nlh + min_len; u32 dump_type; ip_set_id_t index; @@ -1213,27 +1242,23 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, nlh->nlmsg_len - min_len, ip_set_setname_policy); - /* cb->args[IPSET_CB_NET]: net namespace - * [IPSET_CB_DUMP]: dump single set/all sets - * [IPSET_CB_INDEX]: set index - * [IPSET_CB_ARG0]: type specific - */ - if (cda[IPSET_ATTR_SETNAME]) { struct ip_set *set; set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]), &index); - if (set == NULL) + if (!set) return -ENOENT; dump_type = DUMP_ONE; cb->args[IPSET_CB_INDEX] = index; - } else + } else { dump_type = DUMP_ALL; + } if (cda[IPSET_ATTR_FLAGS]) { u32 f = ip_set_get_h32(cda[IPSET_ATTR_FLAGS]); + dump_type |= (f << 16); } cb->args[IPSET_CB_NET] = (unsigned long)inst; @@ -1251,6 +1276,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0; struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk)); u32 dump_type, dump_flags; + bool is_destroyed; int ret = 0; if (!cb->args[IPSET_CB_DUMP]) { @@ -1258,7 +1284,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) if (ret < 0) { nlh = nlmsg_hdr(cb->skb); /* We have to create and send the error message - * manually :-( */ + * manually :-( + */ if (nlh->nlmsg_flags & NLM_F_ACK) netlink_ack(cb->skb, nlh, ret); return ret; @@ -1276,13 +1303,21 @@ dump_last: pr_debug("dump type, flag: %u %u index: %ld\n", dump_type, dump_flags, cb->args[IPSET_CB_INDEX]); for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) { - index = (ip_set_id_t) cb->args[IPSET_CB_INDEX]; + index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; + write_lock_bh(&ip_set_ref_lock); set = ip_set(inst, index); - if (set == NULL) { + is_destroyed = inst->is_destroyed; + if (!set || is_destroyed) { + write_unlock_bh(&ip_set_ref_lock); if (dump_type == DUMP_ONE) { ret = -ENOENT; goto out; } + if (is_destroyed) { + /* All sets are just being destroyed */ + ret = 0; + goto out; + } continue; } /* When dumping all sets, we must dump "sorted" @@ -1290,14 +1325,17 @@ dump_last: */ if (dump_type != DUMP_ONE && ((dump_type == DUMP_ALL) == - !!(set->type->features & IPSET_DUMP_LAST))) + !!(set->type->features & IPSET_DUMP_LAST))) { + write_unlock_bh(&ip_set_ref_lock); continue; + } pr_debug("List set: %s\n", set->name); if (!cb->args[IPSET_CB_ARG0]) { /* Start listing: make sure set won't be destroyed */ pr_debug("reference set\n"); - __ip_set_get(set); + set->ref++; } + write_unlock_bh(&ip_set_ref_lock); nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, IPSET_CMD_LIST); @@ -1325,11 +1363,13 @@ dump_last: goto release_refcount; if (dump_flags & IPSET_FLAG_LIST_HEADER) goto next_set; + if (set->variant->uref) + set->variant->uref(set, cb, true); /* Fall through and add elements */ default: - read_lock_bh(&set->lock); + rcu_read_lock_bh(); ret = set->variant->list(set, skb, cb); - read_unlock_bh(&set->lock); + rcu_read_unlock_bh(); if (!cb->args[IPSET_CB_ARG0]) /* Set is done, proceed with next one */ goto next_set; @@ -1341,6 +1381,8 @@ dump_last: dump_type = DUMP_LAST; cb->args[IPSET_CB_DUMP] = dump_type | (dump_flags << 16); cb->args[IPSET_CB_INDEX] = 0; + if (set && set->variant->uref) + set->variant->uref(set, cb, false); goto dump_last; } goto out; @@ -1355,7 +1397,10 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - pr_debug("release set %s\n", ip_set(inst, index)->name); + set = ip_set(inst, index); + if (set->variant->uref) + set->variant->uref(set, cb, false); + pr_debug("release set %s\n", set->name); __ip_set_put_byindex(inst, index); cb->args[IPSET_CB_ARG0] = 0; } @@ -1407,9 +1452,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); retried = true; } while (ret == -EAGAIN && set->variant->resize && @@ -1425,12 +1470,12 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, size_t payload = min(SIZE_MAX, sizeof(*errmsg) + nlmsg_len(nlh)); int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); - struct nlattr *cda[IPSET_ATTR_CMD_MAX+1]; + struct nlattr *cda[IPSET_ATTR_CMD_MAX + 1]; struct nlattr *cmdattr; u32 *errline; skb2 = nlmsg_new(payload, GFP_KERNEL); - if (skb2 == NULL) + if (!skb2) return -ENOMEM; rep = __nlmsg_put(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, payload, 0); @@ -1447,7 +1492,8 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, *errline = lineno; - netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); /* Signal netlink not to send its ACK/errmsg. */ return -EINTR; } @@ -1462,25 +1508,25 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb, { struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl)); struct ip_set *set; - struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; const struct nlattr *nla; u32 flags = flag_exist(nlh); bool use_lineno; int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || + !attr[IPSET_ATTR_SETNAME] || !((attr[IPSET_ATTR_DATA] != NULL) ^ (attr[IPSET_ATTR_ADT] != NULL)) || - (attr[IPSET_ATTR_DATA] != NULL && + (attr[IPSET_ATTR_DATA] && !flag_nested(attr[IPSET_ATTR_DATA])) || - (attr[IPSET_ATTR_ADT] != NULL && + (attr[IPSET_ATTR_ADT] && (!flag_nested(attr[IPSET_ATTR_ADT]) || - attr[IPSET_ATTR_LINENO] == NULL)))) + !attr[IPSET_ATTR_LINENO])))) return -IPSET_ERR_PROTOCOL; set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (set == NULL) + if (!set) return -ENOENT; use_lineno = !!attr[IPSET_ATTR_LINENO]; @@ -1517,25 +1563,25 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb, { struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl)); struct ip_set *set; - struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; const struct nlattr *nla; u32 flags = flag_exist(nlh); bool use_lineno; int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || + !attr[IPSET_ATTR_SETNAME] || !((attr[IPSET_ATTR_DATA] != NULL) ^ (attr[IPSET_ATTR_ADT] != NULL)) || - (attr[IPSET_ATTR_DATA] != NULL && + (attr[IPSET_ATTR_DATA] && !flag_nested(attr[IPSET_ATTR_DATA])) || - (attr[IPSET_ATTR_ADT] != NULL && + (attr[IPSET_ATTR_ADT] && (!flag_nested(attr[IPSET_ATTR_ADT]) || - attr[IPSET_ATTR_LINENO] == NULL)))) + !attr[IPSET_ATTR_LINENO])))) return -IPSET_ERR_PROTOCOL; set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (set == NULL) + if (!set) return -ENOENT; use_lineno = !!attr[IPSET_ATTR_LINENO]; @@ -1572,26 +1618,26 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, { struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl)); struct ip_set *set; - struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL || - attr[IPSET_ATTR_DATA] == NULL || + !attr[IPSET_ATTR_SETNAME] || + !attr[IPSET_ATTR_DATA] || !flag_nested(attr[IPSET_ATTR_DATA]))) return -IPSET_ERR_PROTOCOL; set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (set == NULL) + if (!set) return -ENOENT; if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy)) return -IPSET_ERR_PROTOCOL; - read_lock_bh(&set->lock); + rcu_read_lock_bh(); ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0); - read_unlock_bh(&set->lock); + rcu_read_unlock_bh(); /* Userspace can't trigger element to be re-added */ if (ret == -EAGAIN) ret = 1; @@ -1613,15 +1659,15 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_SETNAME] == NULL)) + !attr[IPSET_ATTR_SETNAME])) return -IPSET_ERR_PROTOCOL; set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME])); - if (set == NULL) + if (!set) return -ENOENT; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) + if (!skb2) return -ENOMEM; nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, @@ -1670,8 +1716,8 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, int ret = 0; if (unlikely(protocol_failed(attr) || - attr[IPSET_ATTR_TYPENAME] == NULL || - attr[IPSET_ATTR_FAMILY] == NULL)) + !attr[IPSET_ATTR_TYPENAME] || + !attr[IPSET_ATTR_FAMILY])) return -IPSET_ERR_PROTOCOL; family = nla_get_u8(attr[IPSET_ATTR_FAMILY]); @@ -1681,7 +1727,7 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, return ret; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) + if (!skb2) return -ENOMEM; nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, @@ -1726,11 +1772,11 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, struct nlmsghdr *nlh2; int ret = 0; - if (unlikely(attr[IPSET_ATTR_PROTOCOL] == NULL)) + if (unlikely(!attr[IPSET_ATTR_PROTOCOL])) return -IPSET_ERR_PROTOCOL; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) + if (!skb2) return -ENOMEM; nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, @@ -1858,7 +1904,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) ret = -EFAULT; goto done; } - op = (unsigned int *) data; + op = (unsigned int *)data; if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ @@ -1970,10 +2016,11 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kzalloc(sizeof(struct ip_set *) * inst->ip_set_max, GFP_KERNEL); + list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; - inst->is_deleted = 0; + inst->is_deleted = false; + inst->is_destroyed = false; rcu_assign_pointer(inst->ip_set_list, list); return 0; } @@ -1986,12 +2033,14 @@ ip_set_net_exit(struct net *net) struct ip_set *set = NULL; ip_set_id_t i; - inst->is_deleted = 1; /* flag for ip_set_nfnl_put */ + inst->is_deleted = true; /* flag for ip_set_nfnl_put */ for (i = 0; i < inst->ip_set_max; i++) { set = ip_set(inst, i); - if (set != NULL) - ip_set_destroy_set(inst, i); + if (set) { + ip_set(inst, i) = NULL; + ip_set_destroy_set(set); + } } kfree(rcu_dereference_protected(inst->ip_set_list, 1)); } @@ -2003,11 +2052,11 @@ static struct pernet_operations ip_set_net_ops = { .size = sizeof(struct ip_set_net) }; - static int __init ip_set_init(void) { int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); return ret; diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 29fb01ddf..42c3e3ba1 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -30,7 +30,7 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, const struct tcphdr *th; th = skb_header_pointer(skb, protooff, sizeof(_tcph), &_tcph); - if (th == NULL) + if (!th) /* No choice either */ return false; @@ -42,7 +42,7 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, const sctp_sctphdr_t *sh; sh = skb_header_pointer(skb, protooff, sizeof(_sh), &_sh); - if (sh == NULL) + if (!sh) /* No choice either */ return false; @@ -55,7 +55,7 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, const struct udphdr *uh; uh = skb_header_pointer(skb, protooff, sizeof(_udph), &_udph); - if (uh == NULL) + if (!uh) /* No choice either */ return false; @@ -67,7 +67,7 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, const struct icmphdr *ic; ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich); - if (ic == NULL) + if (!ic) return false; *port = (__force __be16)htons((ic->type << 8) | ic->code); @@ -78,7 +78,7 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, const struct icmp6hdr *ic; ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich); - if (ic == NULL) + if (!ic) return false; *port = (__force __be16) @@ -98,7 +98,7 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto) { const struct iphdr *iph = ip_hdr(skb); - unsigned int protooff = ip_hdrlen(skb); + unsigned int protooff = skb_network_offset(skb) + ip_hdrlen(skb); int protocol = iph->protocol; /* See comments at tcp_match in ip_tables.c */ @@ -116,7 +116,8 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src, return false; default: /* Other protocols doesn't have ports, - so we can match fragments */ + * so we can match fragments. + */ *proto = protocol; return true; } @@ -135,7 +136,9 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, __be16 frag_off = 0; nexthdr = ipv6_hdr(skb)->nexthdr; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + protoff = ipv6_skip_exthdr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) return false; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 974ff386d..afe905c20 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -10,19 +10,19 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> +#include <linux/types.h> #include <linux/netfilter/ipset/ip_set_timeout.h> -#ifndef rcu_dereference_bh -#define rcu_dereference_bh(p) rcu_dereference(p) -#endif + +#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) +#define ipset_dereference_protected(p, set) \ + __ipset_dereference_protected(p, spin_is_locked(&(set)->lock)) #define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. * Internally jhash is used with the assumption that the size of the - * stored data is a multiple of sizeof(u32). If storage supports timeout, - * the timeout field must be the last one in the data structure - that field - * is ignored when computing the hash key. + * stored data is a multiple of sizeof(u32). * * Readers and resizing * @@ -35,7 +35,9 @@ /* Number of elements to store in an initial array block */ #define AHASH_INIT_SIZE 4 /* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3*AHASH_INIT_SIZE) +#define AHASH_MAX_SIZE (3 * AHASH_INIT_SIZE) +/* Max muber of elements in the array block when tuned */ +#define AHASH_MAX_TUNED 64 /* Max number of elements can be tuned */ #ifdef IP_SET_HASH_WITH_MULTI @@ -53,8 +55,9 @@ tune_ahash_max(u8 curr, u32 multi) /* Currently, at listing one hash bucket must fit into a message. * Therefore we have a hard limit here. */ - return n > curr && n <= 64 ? n : curr; + return n > curr && n <= AHASH_MAX_TUNED ? n : curr; } + #define TUNE_AHASH_MAX(h, multi) \ ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) #else @@ -64,18 +67,23 @@ tune_ahash_max(u8 curr, u32 multi) /* A hash bucket */ struct hbucket { - void *value; /* the array of the values */ + struct rcu_head rcu; /* for call_rcu_bh */ + /* Which positions are used in the array */ + DECLARE_BITMAP(used, AHASH_MAX_TUNED); u8 size; /* size of the array */ u8 pos; /* position of the first free entry */ -}; + unsigned char value[0]; /* the array of the values */ +} __attribute__ ((aligned)); /* The hash table: the table size stored here in order to make resizing easy */ struct htable { + atomic_t ref; /* References for resizing */ + atomic_t uref; /* References for dumping */ u8 htable_bits; /* size of hash table == 2^htable_bits */ - struct hbucket bucket[0]; /* hashtable buckets */ + struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; -#define hbucket(h, i) (&((h)->bucket[i])) +#define hbucket(h, i) ((h)->bucket[i]) #ifndef IPSET_NET_COUNT #define IPSET_NET_COUNT 1 @@ -83,8 +91,8 @@ struct htable { /* Book-keeping of the prefixes added to the set */ struct net_prefixes { - u32 nets[IPSET_NET_COUNT]; /* number of elements per cidr */ - u8 cidr[IPSET_NET_COUNT]; /* the different cidr values in the set */ + u32 nets[IPSET_NET_COUNT]; /* number of elements for this cidr */ + u8 cidr[IPSET_NET_COUNT]; /* the cidr value */ }; /* Compute the hash table size */ @@ -97,11 +105,11 @@ htable_size(u8 hbits) if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable))/sizeof(struct hbucket) + if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; - return hsize * sizeof(struct hbucket) + sizeof(struct htable); + return hsize * sizeof(struct hbucket *) + sizeof(struct htable); } /* Compute htable_bits from the user input parameter hashsize */ @@ -110,6 +118,7 @@ htable_bits(u32 hashsize) { /* Assume that hashsize == 2^htable_bits */ u8 bits = fls(hashsize - 1); + if (jhash_size(bits) != hashsize) /* Round up to the first 2^n value */ bits = fls(hashsize); @@ -117,30 +126,6 @@ htable_bits(u32 hashsize) return bits; } -static int -hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) -{ - if (n->pos >= n->size) { - void *tmp; - - if (n->size >= ahash_max) - /* Trigger rehashing */ - return -EAGAIN; - - tmp = kzalloc((n->size + AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - if (n->size) { - memcpy(tmp, n->value, n->size * dsize); - kfree(n->value); - } - n->value = tmp; - n->size += AHASH_INIT_SIZE; - } - return 0; -} - #ifdef IP_SET_HASH_WITH_NETS #if IPSET_NET_COUNT > 1 #define __CIDR(cidr, i) (cidr[i]) @@ -149,17 +134,21 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #endif /* cidr + 1 is stored in net_prefixes to support /0 */ -#define SCIDR(cidr, i) (__CIDR(cidr, i) + 1) +#define NCIDR_PUT(cidr) ((cidr) + 1) +#define NCIDR_GET(cidr) ((cidr) - 1) #ifdef IP_SET_HASH_WITH_NETS_PACKED /* When cidr is packed with nomatch, cidr - 1 is stored in the data entry */ -#define GCIDR(cidr, i) (__CIDR(cidr, i) + 1) -#define NCIDR(cidr) (cidr) +#define DCIDR_PUT(cidr) ((cidr) - 1) +#define DCIDR_GET(cidr, i) (__CIDR(cidr, i) + 1) #else -#define GCIDR(cidr, i) (__CIDR(cidr, i)) -#define NCIDR(cidr) (cidr - 1) +#define DCIDR_PUT(cidr) (cidr) +#define DCIDR_GET(cidr, i) __CIDR(cidr, i) #endif +#define INIT_CIDR(cidr, host_mask) \ + DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask)) + #define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) #ifdef IP_SET_HASH_WITH_NET0 @@ -180,6 +169,7 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #undef mtype_data_equal #undef mtype_do_data_match #undef mtype_data_set_flags +#undef mtype_data_reset_elem #undef mtype_data_reset_flags #undef mtype_data_netmask #undef mtype_data_list @@ -193,7 +183,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #undef mtype_ahash_memsize #undef mtype_flush #undef mtype_destroy -#undef mtype_gc_init #undef mtype_same_set #undef mtype_kadt #undef mtype_uadt @@ -203,6 +192,7 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #undef mtype_del #undef mtype_test_cidrs #undef mtype_test +#undef mtype_uref #undef mtype_expire #undef mtype_resize #undef mtype_head @@ -227,6 +217,7 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_data_list IPSET_TOKEN(MTYPE, _data_list) #define mtype_data_next IPSET_TOKEN(MTYPE, _data_next) #define mtype_elem IPSET_TOKEN(MTYPE, _elem) + #define mtype_ahash_destroy IPSET_TOKEN(MTYPE, _ahash_destroy) #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr) @@ -234,7 +225,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) -#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) @@ -244,23 +234,36 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize) #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) +#define mtype_uref IPSET_TOKEN(MTYPE, _uref) #define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) +#ifndef MTYPE +#error "MTYPE is not defined!" +#endif + +#ifndef HOST_MASK +#error "HOST_MASK is not defined!" +#endif + #ifndef HKEY_DATALEN #define HKEY_DATALEN sizeof(struct mtype_elem) #endif #define HKEY(data, initval, htable_bits) \ -(jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \ +(jhash2((u32 *)(data), HKEY_DATALEN / sizeof(u32), initval) \ & jhash_mask(htable_bits)) #ifndef htype +#ifndef HTYPE +#error "HTYPE is not defined!" +#endif /* HTYPE */ #define htype HTYPE /* The generic hash structure */ @@ -280,18 +283,16 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif -#ifdef IP_SET_HASH_WITH_RBTREE - struct rb_root rbtree; -#endif #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[0]; /* book-keeping of prefixes */ #endif }; -#endif +#endif /* htype */ #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different - * sized networks */ + * sized networks. cidr == real cidr + 1 to support /0. + */ static void mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) { @@ -299,11 +300,11 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < nets_length && h->nets[i].cidr[n]; i++) { - if (j != -1) + if (j != -1) { continue; - else if (h->nets[i].cidr[n] < cidr) + } else if (h->nets[i].cidr[n] < cidr) { j = i; - else if (h->nets[i].cidr[n] == cidr) { + } else if (h->nets[i].cidr[n] == cidr) { h->nets[cidr - 1].nets[n]++; return; } @@ -322,15 +323,15 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) u8 i, j, net_end = nets_length - 1; for (i = 0; i < nets_length; i++) { - if (h->nets[i].cidr[n] != cidr) - continue; - h->nets[cidr -1].nets[n]--; - if (h->nets[cidr -1].nets[n] > 0) - return; + if (h->nets[i].cidr[n] != cidr) + continue; + h->nets[cidr - 1].nets[n]--; + if (h->nets[cidr - 1].nets[n] > 0) + return; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) - h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; + h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + return; } } #endif @@ -341,15 +342,18 @@ mtype_ahash_memsize(const struct htype *h, const struct htable *t, u8 nets_length, size_t dsize) { u32 i; - size_t memsize = sizeof(*h) - + sizeof(*t) + struct hbucket *n; + size_t memsize = sizeof(*h) + sizeof(*t); + #ifdef IP_SET_HASH_WITH_NETS - + sizeof(struct net_prefixes) * nets_length + memsize += sizeof(struct net_prefixes) * nets_length; #endif - + jhash_size(t->htable_bits) * sizeof(struct hbucket); - - for (i = 0; i < jhash_size(t->htable_bits); i++) - memsize += t->bucket[i].size * dsize; + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + memsize += sizeof(struct hbucket) + n->size * dsize; + } return memsize; } @@ -364,7 +368,8 @@ mtype_ext_cleanup(struct ip_set *set, struct hbucket *n) int i; for (i = 0; i < n->pos; i++) - ip_set_ext_destroy(set, ahash_data(n, i, set->dsize)); + if (test_bit(i, n->used)) + ip_set_ext_destroy(set, ahash_data(n, i, set->dsize)); } /* Flush a hash type of set: destroy all elements */ @@ -376,16 +381,16 @@ mtype_flush(struct ip_set *set) struct hbucket *n; u32 i; - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_protected(h->table, set); for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) { - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - n->size = n->pos = 0; - /* FIXME: use slab cache */ - kfree(n->value); - } + n = __ipset_dereference_protected(hbucket(t, i), 1); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(struct net_prefixes) * NLEN(set->family)); @@ -401,13 +406,13 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) { - if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - kfree(n->value); - } + n = __ipset_dereference_protected(hbucket(t, i), 1); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + kfree(n); } ip_set_free(t); @@ -419,13 +424,11 @@ mtype_destroy(struct ip_set *set) { struct htype *h = set->data; - if (set->extensions & IPSET_EXT_TIMEOUT) + if (SET_WITH_TIMEOUT(set)) del_timer_sync(&h->gc); - mtype_ahash_destroy(set, rcu_dereference_bh_nfnl(h->table), true); -#ifdef IP_SET_HASH_WITH_RBTREE - rbtree_destroy(&h->rbtree); -#endif + mtype_ahash_destroy(set, + __ipset_dereference_protected(h->table, 1), true); kfree(h); set->data = NULL; @@ -437,7 +440,7 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) struct htype *h = set->data; init_timer(&h->gc); - h->gc.data = (unsigned long) set; + h->gc.data = (unsigned long)set; h->gc.function = gc; h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&h->gc); @@ -470,61 +473,71 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) struct htable *t; struct hbucket *n; struct mtype_elem *data; - u32 i; - int j; + u32 i, j, d; #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); + t = ipset_dereference_protected(h->table, set); for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - for (j = 0; j < n->pos; j++) { + n = __ipset_dereference_protected(hbucket(t, i), 1); + if (!n) + continue; + for (j = 0, d = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) { + d++; + continue; + } data = ahash_data(n, j, dsize); if (ip_set_timeout_expired(ext_timeout(data, set))) { pr_debug("expired %u/%u\n", i, j); + clear_bit(j, n->used); + smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, SCIDR(data->cidr, k), - nets_length, k); + mtype_del_cidr(h, + NCIDR_PUT(DCIDR_GET(data->cidr, + k)), + nets_length, k); #endif ip_set_ext_destroy(set, data); - if (j != n->pos - 1) - /* Not last one */ - memcpy(data, - ahash_data(n, n->pos - 1, dsize), - dsize); - n->pos--; h->elements--; + d++; } } - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * dsize, - GFP_ATOMIC); + if (d >= AHASH_INIT_SIZE) { + struct hbucket *tmp = kzalloc(sizeof(*tmp) + + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) /* Still try to delete expired elements */ continue; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, n->size * dsize); - kfree(n->value); - n->value = tmp; + tmp->size = n->size - AHASH_INIT_SIZE; + for (j = 0, d = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + memcpy(tmp->value + d * dsize, data, dsize); + set_bit(j, tmp->used); + d++; + } + tmp->pos = d; + rcu_assign_pointer(hbucket(t, i), tmp); + kfree_rcu(n, rcu); } } - rcu_read_unlock_bh(); } static void mtype_gc(unsigned long ul_set) { - struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set *set = (struct ip_set *)ul_set; struct htype *h = set->data; pr_debug("called\n"); - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); mtype_expire(set, h, NLEN(set->family), set->dsize); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&h->gc); @@ -532,93 +545,152 @@ mtype_gc(unsigned long ul_set) /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or - * fail due to memory pressures. */ + * fail due to memory pressures. + */ static int mtype_resize(struct ip_set *set, bool retried) { struct htype *h = set->data; - struct htable *t, *orig = rcu_dereference_bh_nfnl(h->table); - u8 htable_bits = orig->htable_bits; + struct htable *t, *orig; + u8 htable_bits; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; + struct mtype_elem *tmp; #endif struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j; + u32 i, j, key; int ret; - /* Try to cleanup once */ - if (SET_WITH_TIMEOUT(set) && !retried) { - i = h->elements; - write_lock_bh(&set->lock); - mtype_expire(set, set->data, NLEN(set->family), set->dsize); - write_unlock_bh(&set->lock); - if (h->elements < i) - return 0; - } +#ifdef IP_SET_HASH_WITH_NETS + tmp = kmalloc(dsize, GFP_KERNEL); + if (!tmp) + return -ENOMEM; +#endif + rcu_read_lock_bh(); + orig = rcu_dereference_bh_nfnl(h->table); + htable_bits = orig->htable_bits; + rcu_read_unlock_bh(); retry: ret = 0; htable_bits++; - pr_debug("attempt to resize set %s from %u to %u, t %p\n", - set->name, orig->htable_bits, htable_bits, orig); if (!htable_bits) { /* In case we have plenty of memory :-) */ pr_warn("Cannot increase the hashsize of set %s further\n", set->name); - return -IPSET_ERR_HASH_FULL; + ret = -IPSET_ERR_HASH_FULL; + goto out; + } + t = ip_set_alloc(htable_size(htable_bits)); + if (!t) { + ret = -ENOMEM; + goto out; } - t = ip_set_alloc(sizeof(*t) - + jhash_size(htable_bits) * sizeof(struct hbucket)); - if (!t) - return -ENOMEM; t->htable_bits = htable_bits; - read_lock_bh(&set->lock); + spin_lock_bh(&set->lock); + orig = __ipset_dereference_protected(h->table, 1); + /* There can't be another parallel resizing, but dumping is possible */ + atomic_set(&orig->ref, 1); + atomic_inc(&orig->uref); + pr_debug("attempt to resize set %s from %u to %u, t %p\n", + set->name, orig->htable_bits, htable_bits, orig); for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = hbucket(orig, i); + n = __ipset_dereference_protected(hbucket(orig, i), 1); + if (!n) + continue; for (j = 0; j < n->pos; j++) { - data = ahash_data(n, j, set->dsize); + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); #ifdef IP_SET_HASH_WITH_NETS + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ flags = 0; + memcpy(tmp, data, dsize); + data = tmp; mtype_data_reset_flags(data, &flags); #endif - m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = hbucket_elem_add(m, AHASH_MAX(h), set->dsize); - if (ret < 0) { -#ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(data, &flags); -#endif - read_unlock_bh(&set->lock); - mtype_ahash_destroy(set, t, false); - if (ret == -EAGAIN) - goto retry; - return ret; + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference_protected(hbucket(t, key), 1); + if (!m) { + m = kzalloc(sizeof(*m) + + AHASH_INIT_SIZE * dsize, + GFP_ATOMIC); + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + + (m->size + AHASH_INIT_SIZE) + * dsize, + GFP_ATOMIC); + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - d = ahash_data(m, m->pos++, set->dsize); - memcpy(d, data, set->dsize); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); #ifdef IP_SET_HASH_WITH_NETS mtype_data_reset_flags(d, &flags); #endif } } - rcu_assign_pointer(h->table, t); - read_unlock_bh(&set->lock); + + spin_unlock_bh(&set->lock); /* Give time to other readers of the set */ synchronize_rcu_bh(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - mtype_ahash_destroy(set, orig, false); + /* If there's nobody else dumping the table, destroy it */ + if (atomic_dec_and_test(&orig->uref)) { + pr_debug("Table destroy by resize %p\n", orig); + mtype_ahash_destroy(set, orig, false); + } - return 0; +out: +#ifdef IP_SET_HASH_WITH_NETS + kfree(tmp); +#endif + return ret; + +cleanup: + atomic_set(&orig->ref, 0); + atomic_dec(&orig->uref); + spin_unlock_bh(&set->lock); + mtype_ahash_destroy(set, t, false); + if (ret == -EAGAIN) + goto retry; + goto out; } /* Add an element to a hash and update the internal counters when succeeded, - * otherwise report the proper error code. */ + * otherwise report the proper error code. + */ static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) @@ -627,17 +699,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct htable *t; const struct mtype_elem *d = value; struct mtype_elem *data; - struct hbucket *n; - int i, ret = 0; - int j = AHASH_MAX(h) + 1; + struct hbucket *n, *old = ERR_PTR(-ENOENT); + int i, j = -1; bool flag_exist = flags & IPSET_FLAG_EXIST; + bool deleted = false, forceadd = false, reuse = false; u32 key, multi = 0; - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); + if (h->elements >= h->maxelem) { + if (SET_WITH_TIMEOUT(set)) + /* FIXME: when set is full, we slow down here */ + mtype_expire(set, h, NLEN(set->family), set->dsize); + if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + forceadd = true; + } + + t = ipset_dereference_protected(h->table, set); key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); + n = __ipset_dereference_protected(hbucket(t, key), 1); + if (!n) { + if (forceadd) { + if (net_ratelimit()) + pr_warn("Set %s is full, maxelem %u reached\n", + set->name, h->maxelem); + return -IPSET_ERR_HASH_FULL; + } else if (h->elements >= h->maxelem) { + goto set_full; + } + old = NULL; + n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, + GFP_ATOMIC); + if (!n) + return -ENOMEM; + n->size = AHASH_INIT_SIZE; + goto copy_elem; + } for (i = 0; i < n->pos; i++) { + if (!test_bit(i, n->used)) { + /* Reuse first deleted entry */ + if (j == -1) { + deleted = reuse = true; + j = i; + } + continue; + } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { if (flag_exist || @@ -645,85 +749,94 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, ip_set_timeout_expired(ext_timeout(data, set)))) { /* Just the extensions could be overwritten */ j = i; - goto reuse_slot; - } else { - ret = -IPSET_ERR_EXIST; - goto out; + goto overwrite_extensions; } + return -IPSET_ERR_EXIST; } /* Reuse first timed out entry */ if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(data, set)) && - j != AHASH_MAX(h) + 1) + j == -1) { j = i; + reuse = true; + } } - if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set) && n->pos) { - /* Choosing the first entry in the array to replace */ - j = 0; - goto reuse_slot; - } - if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h, NLEN(set->family), set->dsize); - - if (h->elements >= h->maxelem) { - if (net_ratelimit()) - pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - ret = -IPSET_ERR_HASH_FULL; - goto out; - } - -reuse_slot: - if (j != AHASH_MAX(h) + 1) { - /* Fill out reused slot */ + if (reuse || forceadd) { data = ahash_data(n, j, set->dsize); + if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS - for (i = 0; i < IPSET_NET_COUNT; i++) { - mtype_del_cidr(h, SCIDR(data->cidr, i), - NLEN(set->family), i); - mtype_add_cidr(h, SCIDR(d->cidr, i), - NLEN(set->family), i); - } + for (i = 0; i < IPSET_NET_COUNT; i++) + mtype_del_cidr(h, + NCIDR_PUT(DCIDR_GET(data->cidr, i)), + NLEN(set->family), i); #endif - ip_set_ext_destroy(set, data); - } else { - /* Use/create a new slot */ + ip_set_ext_destroy(set, data); + h->elements--; + } + goto copy_data; + } + if (h->elements >= h->maxelem) + goto set_full; + /* Create a new slot */ + if (n->pos >= n->size) { TUNE_AHASH_MAX(h, multi); - ret = hbucket_elem_add(n, AHASH_MAX(h), set->dsize); - if (ret != 0) { - if (ret == -EAGAIN) - mtype_data_next(&h->next, d); - goto out; + if (n->size >= AHASH_MAX(h)) { + /* Trigger rehashing */ + mtype_data_next(&h->next, d); + return -EAGAIN; } - data = ahash_data(n, n->pos++, set->dsize); + old = n; + n = kzalloc(sizeof(*n) + + (old->size + AHASH_INIT_SIZE) * set->dsize, + GFP_ATOMIC); + if (!n) + return -ENOMEM; + memcpy(n, old, sizeof(struct hbucket) + + old->size * set->dsize); + n->size = old->size + AHASH_INIT_SIZE; + } + +copy_elem: + j = n->pos++; + data = ahash_data(n, j, set->dsize); +copy_data: + h->elements++; #ifdef IP_SET_HASH_WITH_NETS - for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, SCIDR(d->cidr, i), NLEN(set->family), - i); + for (i = 0; i < IPSET_NET_COUNT; i++) + mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), + NLEN(set->family), i); #endif - h->elements++; - } memcpy(data, d, sizeof(struct mtype_elem)); +overwrite_extensions: #ifdef IP_SET_HASH_WITH_NETS mtype_data_set_flags(data, flags); #endif - if (SET_WITH_TIMEOUT(set)) - ip_set_timeout_set(ext_timeout(data, set), ext->timeout); if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(data, set), ext); if (SET_WITH_COMMENT(set)) ip_set_init_comment(ext_comment(data, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(data, set), ext); + /* Must come last for the case when timed out entry is reused */ + if (SET_WITH_TIMEOUT(set)) + ip_set_timeout_set(ext_timeout(data, set), ext->timeout); + smp_mb__before_atomic(); + set_bit(j, n->used); + if (old != ERR_PTR(-ENOENT)) { + rcu_assign_pointer(hbucket(t, key), n); + if (old) + kfree_rcu(old, rcu); + } -out: - rcu_read_unlock_bh(); - return ret; + return 0; +set_full: + if (net_ratelimit()) + pr_warn("Set %s is full, maxelem %u reached\n", + set->name, h->maxelem); + return -IPSET_ERR_HASH_FULL; } -/* Delete an element from the hash: swap it with the last element - * and free up space if possible. +/* Delete an element from the hash and free up space if possible. */ static int mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, @@ -734,55 +847,70 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, ret = -IPSET_ERR_EXIST; -#ifdef IP_SET_HASH_WITH_NETS - u8 j; -#endif + int i, j, k, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; + size_t dsize = set->dsize; - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); + t = ipset_dereference_protected(h->table, set); key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i, set->dsize); + n = __ipset_dereference_protected(hbucket(t, key), 1); + if (!n) + goto out; + for (i = 0, k = 0; i < n->pos; i++) { + if (!test_bit(i, n->used)) { + k++; + continue; + } + data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(data, set))) goto out; - if (i != n->pos - 1) - /* Not last one */ - memcpy(data, ahash_data(n, n->pos - 1, set->dsize), - set->dsize); - n->pos--; + ret = 0; + clear_bit(i, n->used); + smp_mb__after_atomic(); + if (i + 1 == n->pos) + n->pos--; h->elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, SCIDR(d->cidr, j), NLEN(set->family), - j); + mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), + NLEN(set->family), j); #endif ip_set_ext_destroy(set, data); - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * set->dsize, - GFP_ATOMIC); - if (!tmp) { - ret = 0; + + for (; i < n->pos; i++) { + if (!test_bit(i, n->used)) + k++; + } + if (n->pos == 0 && k == 0) { + rcu_assign_pointer(hbucket(t, key), NULL); + kfree_rcu(n, rcu); + } else if (k >= AHASH_INIT_SIZE) { + struct hbucket *tmp = kzalloc(sizeof(*tmp) + + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); + if (!tmp) goto out; + tmp->size = n->size - AHASH_INIT_SIZE; + for (j = 0, k = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + memcpy(tmp->value + k * dsize, data, dsize); + set_bit(j, tmp->used); + k++; } - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, n->size * set->dsize); - kfree(n->value); - n->value = tmp; + tmp->pos = k; + rcu_assign_pointer(hbucket(t, key), tmp); + kfree_rcu(n, rcu); } - ret = 0; goto out; } out: - rcu_read_unlock_bh(); return ret; } @@ -801,7 +929,8 @@ mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_NETS /* Special test function which takes into account the different network - * sizes added to the set */ + * sizes added to the set + */ static int mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, const struct ip_set_ext *ext, @@ -824,16 +953,21 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, for (; j < nets_length && h->nets[j].cidr[0] && !multi; j++) { #if IPSET_NET_COUNT == 2 mtype_data_reset_elem(d, &orig); - mtype_data_netmask(d, NCIDR(h->nets[j].cidr[0]), false); + mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0]), false); for (k = 0; k < nets_length && h->nets[k].cidr[1] && !multi; k++) { - mtype_data_netmask(d, NCIDR(h->nets[k].cidr[1]), true); + mtype_data_netmask(d, NCIDR_GET(h->nets[k].cidr[1]), + true); #else - mtype_data_netmask(d, NCIDR(h->nets[j].cidr[0])); + mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0])); #endif key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); + n = rcu_dereference_bh(hbucket(t, key)); + if (!n) + continue; for (i = 0; i < n->pos; i++) { + if (!test_bit(i, n->used)) + continue; data = ahash_data(n, i, set->dsize); if (!mtype_data_equal(data, d, &multi)) continue; @@ -871,13 +1005,13 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; - rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, - * try all possible network sizes */ + * try all possible network sizes + */ for (i = 0; i < IPSET_NET_COUNT; i++) - if (GCIDR(d->cidr, i) != SET_HOST_MASK(set->family)) + if (DCIDR_GET(d->cidr, i) != SET_HOST_MASK(set->family)) break; if (i == IPSET_NET_COUNT) { ret = mtype_test_cidrs(set, d, ext, mext, flags); @@ -886,8 +1020,14 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, #endif key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); + n = rcu_dereference_bh(hbucket(t, key)); + if (!n) { + ret = 0; + goto out; + } for (i = 0; i < n->pos; i++) { + if (!test_bit(i, n->used)) + continue; data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi) && !(SET_WITH_TIMEOUT(set) && @@ -897,7 +1037,6 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, } } out: - rcu_read_unlock_bh(); return ret; } @@ -909,15 +1048,19 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u8 htable_bits; + rcu_read_lock_bh(); t = rcu_dereference_bh_nfnl(h->table); memsize = mtype_ahash_memsize(h, t, NLEN(set->family), set->dsize); + htable_bits = t->htable_bits; + rcu_read_unlock_bh(); nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, - htonl(jhash_size(t->htable_bits))) || + htonl(jhash_size(htable_bits))) || nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; #ifdef IP_SET_HASH_WITH_NETMASK @@ -941,32 +1084,63 @@ nla_put_failure: return -EMSGSIZE; } +/* Make possible to run dumping parallel with resizing */ +static void +mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) +{ + struct htype *h = set->data; + struct htable *t; + + if (start) { + rcu_read_lock_bh(); + t = rcu_dereference_bh_nfnl(h->table); + atomic_inc(&t->uref); + cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; + rcu_read_unlock_bh(); + } else if (cb->args[IPSET_CB_PRIVATE]) { + t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + /* Resizing didn't destroy the hash table */ + pr_debug("Table destroy by dump: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + cb->args[IPSET_CB_PRIVATE] = 0; + } +} + /* Reply a LIST/SAVE request: dump the elements of the specified set */ static int mtype_list(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb) { - const struct htype *h = set->data; - const struct htable *t = rcu_dereference_bh_nfnl(h->table); + const struct htable *t; struct nlattr *atd, *nested; const struct hbucket *n; const struct mtype_elem *e; u32 first = cb->args[IPSET_CB_ARG0]; /* We assume that one hash bucket fills into one page */ void *incomplete; - int i; + int i, ret = 0; atd = ipset_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; + pr_debug("list hash set %s\n", set->name); + t = (const struct htable *)cb->args[IPSET_CB_PRIVATE]; + /* Expire may replace a hbucket with another one */ + rcu_read_lock(); for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits); cb->args[IPSET_CB_ARG0]++) { incomplete = skb_tail_pointer(skb); - n = hbucket(t, cb->args[IPSET_CB_ARG0]); + n = rcu_dereference(hbucket(t, cb->args[IPSET_CB_ARG0])); pr_debug("cb->arg bucket: %lu, t %p n %p\n", cb->args[IPSET_CB_ARG0], t, n); + if (!n) + continue; for (i = 0; i < n->pos; i++) { + if (!test_bit(i, n->used)) + continue; e = ahash_data(n, i, set->dsize); if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) @@ -977,9 +1151,10 @@ mtype_list(const struct ip_set *set, if (!nested) { if (cb->args[IPSET_CB_ARG0] == first) { nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; + ret = -EMSGSIZE; + goto out; + } + goto nla_put_failure; } if (mtype_data_list(skb, e)) goto nla_put_failure; @@ -992,7 +1167,7 @@ mtype_list(const struct ip_set *set, /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; - return 0; + goto out; nla_put_failure: nlmsg_trim(skb, incomplete); @@ -1000,20 +1175,24 @@ nla_put_failure: pr_warn("Can't list set %s: one bucket does not fit into a message. Please report it!\n", set->name); cb->args[IPSET_CB_ARG0] = 0; - return -EMSGSIZE; + ret = -EMSGSIZE; + } else { + ipset_nest_end(skb, atd); } - ipset_nest_end(skb, atd); - return 0; +out: + rcu_read_unlock(); + return ret; } static int IPSET_TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, struct ip_set_adt_opt *opt); + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt); static int IPSET_TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); + enum ipset_adt adt, u32 *lineno, u32 flags, + bool retried); static const struct ip_set_type_variant mtype_variant = { .kadt = mtype_kadt, @@ -1027,6 +1206,7 @@ static const struct ip_set_type_variant mtype_variant = { .flush = mtype_flush, .head = mtype_head, .list = mtype_list, + .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, }; @@ -1045,7 +1225,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, u8 netmask; #endif size_t hsize; - struct HTYPE *h; + struct htype *h; struct htable *t; #ifndef IP_SET_PROTO_UNDEF @@ -1064,12 +1244,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || -#ifdef IP_SET_HASH_WITH_MARKMASK - !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) || -#endif !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; +#ifdef IP_SET_HASH_WITH_MARKMASK + /* Separated condition in order to avoid directive in argument list */ + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK))) + return -IPSET_ERR_PROTOCOL; +#endif if (tb[IPSET_ATTR_HASHSIZE]) { hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); @@ -1092,7 +1274,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif #ifdef IP_SET_HASH_WITH_MARKMASK if (tb[IPSET_ATTR_MARKMASK]) { - markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK])); + markmask = ntohl(nla_get_be32(tb[IPSET_ATTR_MARKMASK])); if (markmask == 0) return -IPSET_ERR_INVALID_MARKMASK; @@ -1165,3 +1347,5 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return 0; } #endif /* IP_SET_EMIT_CREATE */ + +#undef HKEY_DATALEN diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 76959d79e..9d6bf19f7 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -56,15 +56,15 @@ hash_ip4_data_equal(const struct hash_ip4_elem *e1, return e1->ip == e2->ip; } -static inline bool +static bool hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *e) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, e->ip)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -74,7 +74,6 @@ hash_ip4_data_next(struct hash_ip4_elem *next, const struct hash_ip4_elem *e) } #define MTYPE hash_ip4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -109,20 +108,17 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], u32 ip = 0, ip_to = 0, hosts; int ret = 0; - if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + if (unlikely(!tb[IPSET_ATTR_IP])) + return -IPSET_ERR_PROTOCOL; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -145,7 +141,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -162,8 +158,8 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -196,10 +192,10 @@ hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -208,12 +204,9 @@ hash_ip6_data_next(struct hash_ip4_elem *next, const struct hash_ip6_elem *e) } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ip6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE @@ -247,22 +240,25 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; - if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE) || - tb[IPSET_ATTR_IP_TO] || - tb[IPSET_ATTR_CIDR])) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + if (unlikely(!tb[IPSET_ATTR_IP])) + return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + if (unlikely(tb[IPSET_ATTR_CIDR])) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr != HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -301,7 +297,8 @@ static struct ip_set_type hash_ip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -318,6 +315,7 @@ hash_ip_init(void) static void __exit hash_ip_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_ip_type); } diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 7abf9788c..a0695a2ab 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -63,10 +63,10 @@ hash_ipmark4_data_list(struct sk_buff *skb, if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -76,10 +76,8 @@ hash_ipmark4_data_next(struct hash_ipmark4_elem *next, next->ip = d->ip; } -#define MTYPE hash_ipmark4 -#define PF 4 -#define HOST_MASK 32 -#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem) +#define MTYPE hash_ipmark4 +#define HOST_MASK 32 #include "ip_set_hash_gen.h" static int @@ -110,25 +108,22 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], u32 ip, ip_to = 0; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; if (adt == IPSET_TEST || @@ -147,7 +142,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -160,8 +155,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -191,10 +186,10 @@ hash_ipmark6_data_list(struct sk_buff *skb, if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -204,18 +199,13 @@ hash_ipmark6_data_next(struct hash_ipmark4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ipmark6 -#define PF 6 #define HOST_MASK 128 -#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem) -#define IP_SET_EMIT_CREATE +#define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" - static int hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -243,27 +233,30 @@ hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE) || - tb[IPSET_ATTR_IP_TO] || - tb[IPSET_ATTR_CIDR])) + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK))) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + if (unlikely(tb[IPSET_ATTR_CIDR])) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (cidr != HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; - e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; if (adt == IPSET_TEST) { @@ -274,10 +267,8 @@ hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; - return ret; + return 0; } static struct ip_set_type hash_ipmark_type __read_mostly = { @@ -307,7 +298,8 @@ static struct ip_set_type hash_ipmark_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -324,6 +316,7 @@ hash_ipmark_init(void) static void __exit hash_ipmark_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_ipmark_type); } diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index dcbcceb9a..9d84b3dff 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -69,10 +69,10 @@ hash_ipport4_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -83,10 +83,8 @@ hash_ipport4_data_next(struct hash_ipport4_elem *next, next->port = d->port; } -#define MTYPE hash_ipport4 -#define PF 4 -#define HOST_MASK 32 -#define HKEY_DATALEN sizeof(struct hash_ipport4_elem) +#define MTYPE hash_ipport4 +#define HOST_MASK 32 #include "ip_set_hash_gen.h" static int @@ -118,29 +116,23 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], bool with_ports = false; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -148,8 +140,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; @@ -171,7 +164,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -195,8 +188,8 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } } return ret; @@ -231,10 +224,10 @@ hash_ipport6_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -245,15 +238,11 @@ hash_ipport6_data_next(struct hash_ipport4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_ipport6 -#define PF 6 #define HOST_MASK 128 -#define HKEY_DATALEN sizeof(struct hash_ipport6_elem) -#define IP_SET_EMIT_CREATE +#define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int @@ -285,31 +274,31 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], bool with_ports = false; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE) || - tb[IPSET_ATTR_IP_TO] || - tb[IPSET_ATTR_CIDR])) + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + if (unlikely(tb[IPSET_ATTR_CIDR])) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (cidr != HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -317,8 +306,9 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; @@ -341,8 +331,8 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -376,7 +366,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -393,6 +384,7 @@ hash_ipport_init(void) static void __exit hash_ipport_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_ipport_type); } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 7ef93fc88..215b7b942 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -63,17 +63,17 @@ hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1, static bool hash_ipportip4_data_list(struct sk_buff *skb, - const struct hash_ipportip4_elem *data) + const struct hash_ipportip4_elem *data) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip2) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -86,7 +86,6 @@ hash_ipportip4_data_next(struct hash_ipportip4_elem *next, /* Common functions */ #define MTYPE hash_ipportip4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -120,22 +119,19 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], bool with_ports = false; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -143,10 +139,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -154,8 +147,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; @@ -177,7 +171,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -201,8 +195,8 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } } return ret; @@ -240,10 +234,10 @@ hash_ipportip6_data_list(struct sk_buff *skb, nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -254,11 +248,9 @@ hash_ipportip6_data_next(struct hash_ipportip4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_ipportip6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -293,24 +285,27 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], bool with_ports = false; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE) || - tb[IPSET_ATTR_IP_TO] || - tb[IPSET_ATTR_CIDR])) + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + if (unlikely(tb[IPSET_ATTR_CIDR])) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (cidr != HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -318,10 +313,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -329,8 +321,9 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; @@ -353,8 +346,8 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -388,7 +381,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -405,6 +399,7 @@ hash_ipportip_init(void) static void __exit hash_ipportip_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_ipportip_type); } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index b6012ad92..9ca719625 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -114,10 +114,10 @@ hash_ipportnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -130,7 +130,6 @@ hash_ipportnet4_data_next(struct hash_ipportnet4_elem *next, } #define MTYPE hash_ipportnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -142,7 +141,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1, + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -174,23 +173,20 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], u8 cidr; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -205,10 +201,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.cidr = cidr - 1; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -216,14 +209,16 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -249,7 +244,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > 32) + if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -270,8 +265,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip2_from, ip2_to); if (ip2_from + UINT_MAX == ip2_to) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr + 1); + } if (retried) ip = ntohl(h->next.ip); @@ -294,8 +290,8 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; ip2 = ip2_last + 1; } } @@ -367,10 +363,10 @@ hash_ipportnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -381,11 +377,9 @@ hash_ipportnet6_data_next(struct hash_ipportnet4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_ipportnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -398,7 +392,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet6_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1, + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -429,27 +423,28 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], u8 cidr; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE) || - tb[IPSET_ATTR_IP_TO] || - tb[IPSET_ATTR_CIDR])) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + if (unlikely(tb[IPSET_ATTR_CIDR])) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (cidr != HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -466,10 +461,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], ip6_netmask(&e.ip2, e.cidr + 1); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -477,14 +469,16 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -508,8 +502,8 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -547,7 +541,8 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -564,6 +559,7 @@ hash_ipportnet_init(void) static void __exit hash_ipportnet_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_ipportnet_type); } diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index 65690b52a..f1e7d2c0f 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -52,7 +52,12 @@ hash_mac4_data_equal(const struct hash_mac4_elem *e1, static inline bool hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e) { - return nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether); + if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether)) + goto nla_put_failure; + return false; + +nla_put_failure: + return true; } static inline void @@ -62,7 +67,6 @@ hash_mac4_data_next(struct hash_mac4_elem *next, } #define MTYPE hash_mac4 -#define PF 4 #define HOST_MASK 32 #define IP_SET_EMIT_CREATE #define IP_SET_PROTO_UNDEF @@ -85,10 +89,10 @@ hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb, return 0; if (skb_mac_header(skb) < skb->head || - (skb_mac_header(skb) + ETH_HLEN) > skb->data) + (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); + ether_addr_copy(e.ether, eth_hdr(skb)->h_source); if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); @@ -103,22 +107,16 @@ hash_mac4_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; - if (unlikely(!tb[IPSET_ATTR_ETHER] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_ETHER])) + return -IPSET_ERR_PROTOCOL; + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN); + ether_addr_copy(e.ether, nla_data(tb[IPSET_ATTR_ETHER])); if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0) return -IPSET_ERR_HASH_ELEM; @@ -149,7 +147,8 @@ static struct ip_set_type hash_mac_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -166,6 +165,7 @@ hash_mac_init(void) static void __exit hash_mac_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_mac_type); } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 6b3ac10ac..3e4bffdc1 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -95,10 +95,10 @@ hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -109,7 +109,6 @@ hash_net4_data_next(struct hash_net4_elem *next, } #define MTYPE hash_net4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -121,7 +120,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -147,21 +146,18 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], u32 ip = 0, ip_to = 0, last; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -173,6 +169,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -180,7 +177,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt, set) ? -ret: + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -202,8 +199,8 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; ip = last + 1; } return ret; @@ -264,10 +261,10 @@ hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -277,11 +274,9 @@ hash_net6_data_next(struct hash_net4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_net6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -294,7 +289,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net6_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -318,36 +313,34 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + if (tb[IPSET_ATTR_CIDR]) { e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - - if (!e.cidr || e.cidr > HOST_MASK) - return -IPSET_ERR_INVALID_CIDR; + if (!e.cidr || e.cidr > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } ip6_netmask(&e.ip, e.cidr); if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -383,7 +376,8 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -400,6 +394,7 @@ hash_net_init(void) static void __exit hash_net_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_net_type); } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 380ef5148..43d8c9896 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -13,7 +13,6 @@ #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> -#include <linux/rbtree.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> @@ -37,88 +36,13 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); IP_SET_MODULE_DESC("hash:net,iface", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,iface"); -/* Interface name rbtree */ - -struct iface_node { - struct rb_node node; - char iface[IFNAMSIZ]; -}; - -#define iface_data(n) (rb_entry(n, struct iface_node, node)->iface) - -static void -rbtree_destroy(struct rb_root *root) -{ - struct iface_node *node, *next; - - rbtree_postorder_for_each_entry_safe(node, next, root, node) - kfree(node); - - *root = RB_ROOT; -} - -static int -iface_test(struct rb_root *root, const char **iface) -{ - struct rb_node *n = root->rb_node; - - while (n) { - const char *d = iface_data(n); - int res = strcmp(*iface, d); - - if (res < 0) - n = n->rb_left; - else if (res > 0) - n = n->rb_right; - else { - *iface = d; - return 1; - } - } - return 0; -} - -static int -iface_add(struct rb_root *root, const char **iface) -{ - struct rb_node **n = &(root->rb_node), *p = NULL; - struct iface_node *d; - - while (*n) { - char *ifname = iface_data(*n); - int res = strcmp(*iface, ifname); - - p = *n; - if (res < 0) - n = &((*n)->rb_left); - else if (res > 0) - n = &((*n)->rb_right); - else { - *iface = ifname; - return 0; - } - } - - d = kzalloc(sizeof(*d), GFP_ATOMIC); - if (!d) - return -ENOMEM; - strcpy(d->iface, *iface); - - rb_link_node(&d->node, p, n); - rb_insert_color(&d->node, root); - - *iface = d->iface; - return 0; -} - /* Type specific function prefix */ #define HTYPE hash_netiface #define IP_SET_HASH_WITH_NETS -#define IP_SET_HASH_WITH_RBTREE #define IP_SET_HASH_WITH_MULTI #define IP_SET_HASH_WITH_NET0 -#define STREQ(a, b) (strcmp(a, b) == 0) +#define STRLCPY(a, b) strlcpy(a, b, IFNAMSIZ) /* IPv4 variant */ @@ -137,7 +61,7 @@ struct hash_netiface4_elem { u8 cidr; u8 nomatch; u8 elem; - const char *iface; + char iface[IFNAMSIZ]; }; /* Common functions */ @@ -151,7 +75,7 @@ hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1, ip1->cidr == ip2->cidr && (++*multi) && ip1->physdev == ip2->physdev && - ip1->iface == ip2->iface; + strcmp(ip1->iface, ip2->iface) == 0; } static inline int @@ -193,10 +117,10 @@ hash_netiface4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -207,7 +131,6 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, } #define MTYPE hash_netiface4 -#define PF 4 #define HOST_MASK 32 #define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) #include "ip_set_hash_gen.h" @@ -220,7 +143,7 @@ static const char *get_physindev_name(const struct sk_buff *skb) return dev ? dev->name : NULL; } -static const char *get_phyoutdev_name(const struct sk_buff *skb) +static const char *get_physoutdev_name(const struct sk_buff *skb) { struct net_device *dev = nf_bridge_get_physoutdev(skb); @@ -236,11 +159,10 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - int ret; if (e.cidr == 0) return -EINVAL; @@ -250,35 +172,25 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= ip_set_netmask(e.cidr); -#define IFACE(dir) (par->dir ? par->dir->name : NULL) +#define IFACE(dir) (par->dir ? par->dir->name : "") #define SRCDIR (opt->flags & IPSET_DIM_TWO_SRC) if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - e.iface = SRCDIR ? get_physindev_name(skb) : - get_phyoutdev_name(skb); + const char *eiface = SRCDIR ? get_physindev_name(skb) : + get_physoutdev_name(skb); - if (!e.iface) + if (!eiface) return -EINVAL; + STRLCPY(e.iface, eiface); e.physdev = 1; -#else - e.iface = NULL; #endif - } else - e.iface = SRCDIR ? IFACE(in) : IFACE(out); + } else { + STRLCPY(e.iface, SRCDIR ? IFACE(in) : IFACE(out)); + } - if (!e.iface) + if (strlen(e.iface) == 0) return -EINVAL; - ret = iface_test(&h->rbtree, &e.iface); - if (adt == IPSET_ADD) { - if (!ret) { - ret = iface_add(&h->rbtree, &e.iface); - if (ret) - return ret; - } - } else if (!ret) - return ret; - return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -291,25 +203,21 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, last; - char iface[IFNAMSIZ]; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IFACE] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -318,21 +226,11 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } - - strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE])); - e.iface = iface; - ret = iface_test(&h->rbtree, &e.iface); - if (adt == IPSET_ADD) { - if (!ret) { - ret = iface_add(&h->rbtree, &e.iface); - if (ret) - return ret; - } - } else if (!ret) - return ret; + nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ); if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_PHYSDEV) e.physdev = 1; if (cadt_flags & IPSET_FLAG_NOMATCH) @@ -353,8 +251,9 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip, ip_to, e.cidr); + } if (retried) ip = ntohl(h->next.ip); @@ -365,8 +264,8 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; ip = last + 1; } return ret; @@ -388,7 +287,7 @@ struct hash_netiface6_elem { u8 cidr; u8 nomatch; u8 elem; - const char *iface; + char iface[IFNAMSIZ]; }; /* Common functions */ @@ -402,7 +301,7 @@ hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, ip1->cidr == ip2->cidr && (++*multi) && ip1->physdev == ip2->physdev && - ip1->iface == ip2->iface; + strcmp(ip1->iface, ip2->iface) == 0; } static inline int @@ -444,10 +343,10 @@ hash_netiface6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -457,12 +356,9 @@ hash_netiface6_data_next(struct hash_netiface4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK -#undef HKEY_DATALEN #define MTYPE hash_netiface6 -#define PF 6 #define HOST_MASK 128 #define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed) #define IP_SET_EMIT_CREATE @@ -476,11 +372,10 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - int ret; if (e.cidr == 0) return -EINVAL; @@ -492,85 +387,64 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - e.iface = SRCDIR ? get_physindev_name(skb) : - get_phyoutdev_name(skb); - if (!e.iface) - return -EINVAL; + const char *eiface = SRCDIR ? get_physindev_name(skb) : + get_physoutdev_name(skb); + if (!eiface) + return -EINVAL; + STRLCPY(e.iface, eiface); e.physdev = 1; -#else - e.iface = NULL; #endif - } else - e.iface = SRCDIR ? IFACE(in) : IFACE(out); + } else { + STRLCPY(e.iface, SRCDIR ? IFACE(in) : IFACE(out)); + } - if (!e.iface) + if (strlen(e.iface) == 0) return -EINVAL; - ret = iface_test(&h->rbtree, &e.iface); - if (adt == IPSET_ADD) { - if (!ret) { - ret = iface_add(&h->rbtree, &e.iface); - if (ret) - return ret; - } - } else if (!ret) - return ret; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - struct hash_netiface *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - char iface[IFNAMSIZ]; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IFACE] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + if (tb[IPSET_ATTR_CIDR]) { e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (e.cidr > HOST_MASK) - return -IPSET_ERR_INVALID_CIDR; + if (e.cidr > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } + ip6_netmask(&e.ip, e.cidr); - strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE])); - e.iface = iface; - ret = iface_test(&h->rbtree, &e.iface); - if (adt == IPSET_ADD) { - if (!ret) { - ret = iface_add(&h->rbtree, &e.iface); - if (ret) - return ret; - } - } else if (!ret) - return ret; + nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ); if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_PHYSDEV) e.physdev = 1; if (cadt_flags & IPSET_FLAG_NOMATCH) @@ -613,7 +487,8 @@ static struct ip_set_type hash_netiface_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -630,6 +505,7 @@ hash_netiface_init(void) static void __exit hash_netiface_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_netiface_type); } diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index ea8772afb..3c862c0a7 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -57,8 +57,8 @@ struct hash_netnet4_elem { static inline bool hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1, - const struct hash_netnet4_elem *ip2, - u32 *multi) + const struct hash_netnet4_elem *ip2, + u32 *multi) { return ip1->ipcmp == ip2->ipcmp && ip1->ccmp == ip2->ccmp; @@ -84,7 +84,7 @@ hash_netnet4_data_reset_flags(struct hash_netnet4_elem *elem, u8 *flags) static inline void hash_netnet4_data_reset_elem(struct hash_netnet4_elem *elem, - struct hash_netnet4_elem *orig) + struct hash_netnet4_elem *orig) { elem->ip[1] = orig->ip[1]; } @@ -103,7 +103,7 @@ hash_netnet4_data_netmask(struct hash_netnet4_elem *elem, u8 cidr, bool inner) static bool hash_netnet4_data_list(struct sk_buff *skb, - const struct hash_netnet4_elem *data) + const struct hash_netnet4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; @@ -122,28 +122,27 @@ nla_put_failure: static inline void hash_netnet4_data_next(struct hash_netnet4_elem *next, - const struct hash_netnet4_elem *d) + const struct hash_netnet4_elem *d) { next->ipcmp = d->ipcmp; } #define MTYPE hash_netnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, struct ip_set_adt_opt *opt) + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -157,53 +156,50 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, static int hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet4_elem e = { }; + struct hash_netnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, last; u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2; - u8 cidr, cidr2; int ret; - e.cidr[0] = e.cidr[1] = HOST_MASK; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); + if (ret) + return ret; + + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { - cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > HOST_MASK) + e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!e.cidr[0] || e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; - e.cidr[0] = cidr; } if (tb[IPSET_ATTR_CIDR2]) { - cidr2 = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!cidr2 || cidr2 > HOST_MASK) + e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + if (!e.cidr[1] || e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; - e.cidr[1] = cidr2; } if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -226,8 +222,9 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip, ip_to); if (unlikely(ip + UINT_MAX == ip_to)) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip, ip_to, e.cidr[0]); + } ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { @@ -238,28 +235,27 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip2_from, ip2_to); if (unlikely(ip2_from + UINT_MAX == ip2_to)) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); + } if (retried) ip = ntohl(h->next.ip[0]); while (!after(ip, ip_to)) { e.ip[0] = htonl(ip); - last = ip_set_range_to_cidr(ip, ip_to, &cidr); - e.cidr[0] = cidr; + last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); ip2 = (retried && ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1]) : ip2_from; while (!after(ip2, ip2_to)) { e.ip[1] = htonl(ip2); - last2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr2); - e.cidr[1] = cidr2; + last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; ip2 = last2 + 1; } ip = last + 1; @@ -283,8 +279,8 @@ struct hash_netnet6_elem { static inline bool hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1, - const struct hash_netnet6_elem *ip2, - u32 *multi) + const struct hash_netnet6_elem *ip2, + u32 *multi) { return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) && ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) && @@ -311,7 +307,7 @@ hash_netnet6_data_reset_flags(struct hash_netnet6_elem *elem, u8 *flags) static inline void hash_netnet6_data_reset_elem(struct hash_netnet6_elem *elem, - struct hash_netnet6_elem *orig) + struct hash_netnet6_elem *orig) { elem->ip[1] = orig->ip[1]; } @@ -330,7 +326,7 @@ hash_netnet6_data_netmask(struct hash_netnet6_elem *elem, u8 cidr, bool inner) static bool hash_netnet6_data_list(struct sk_buff *skb, - const struct hash_netnet6_elem *data) + const struct hash_netnet6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; @@ -349,34 +345,32 @@ nla_put_failure: static inline void hash_netnet6_data_next(struct hash_netnet4_elem *next, - const struct hash_netnet6_elem *d) + const struct hash_netnet6_elem *d) { } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, struct ip_set_adt_opt *opt) + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) - e.ccmp = (HOST_MASK << (sizeof(u8)*8)) | HOST_MASK; + e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6); ip6addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1].in6); @@ -388,50 +382,52 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, static int hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet6_elem e = { }; + struct hash_netnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; - e.cidr[0] = e.cidr[1] = HOST_MASK; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); + if (ret) + return ret; - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) || - ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - if (tb[IPSET_ATTR_CIDR2]) + if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - - if (!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] || - e.cidr[1] > HOST_MASK) - return -IPSET_ERR_INVALID_CIDR; + if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -470,7 +466,8 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -487,6 +484,7 @@ hash_netnet_init(void) static void __exit hash_netnet_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_netnet_type); } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index c0ddb58d1..731813e0f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -110,10 +110,10 @@ hash_netport4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -125,7 +125,6 @@ hash_netport4_data_next(struct hash_netport4_elem *next, } #define MTYPE hash_netport4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" @@ -137,7 +136,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1, + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -167,23 +166,20 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], u8 cidr; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -194,10 +190,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], e.cidr = cidr - 1; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -205,8 +198,9 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; @@ -215,6 +209,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -240,8 +235,9 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); + } if (retried) ip = ntohl(h->next.ip); @@ -257,8 +253,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } ip = last + 1; } @@ -326,10 +322,10 @@ hash_netport6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -340,11 +336,9 @@ hash_netport6_data_next(struct hash_netport4_elem *next, } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netport6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" @@ -357,7 +351,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { - .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1, + .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -387,25 +381,22 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], u8 cidr; int ret; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); + if (ret) + return ret; - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -417,10 +408,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], } ip6_netmask(&e.ip, e.cidr + 1); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -428,14 +416,16 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -459,8 +449,8 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -495,7 +485,8 @@ static struct ip_set_type hash_netport_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -512,6 +503,7 @@ hash_netport_init(void) static void __exit hash_netport_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_netport_type); } diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index bfaa94c7b..0c68734f5 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -54,7 +54,7 @@ struct hash_netportnet4_elem { u16 ccmp; }; u16 padding; - u8 nomatch:1; + u8 nomatch; u8 proto; }; @@ -62,8 +62,8 @@ struct hash_netportnet4_elem { static inline bool hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1, - const struct hash_netportnet4_elem *ip2, - u32 *multi) + const struct hash_netportnet4_elem *ip2, + u32 *multi) { return ip1->ipcmp == ip2->ipcmp && ip1->ccmp == ip2->ccmp && @@ -91,7 +91,7 @@ hash_netportnet4_data_reset_flags(struct hash_netportnet4_elem *elem, u8 *flags) static inline void hash_netportnet4_data_reset_elem(struct hash_netportnet4_elem *elem, - struct hash_netportnet4_elem *orig) + struct hash_netportnet4_elem *orig) { elem->ip[1] = orig->ip[1]; } @@ -111,7 +111,7 @@ hash_netportnet4_data_netmask(struct hash_netportnet4_elem *elem, static bool hash_netportnet4_data_list(struct sk_buff *skb, - const struct hash_netportnet4_elem *data) + const struct hash_netportnet4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; @@ -124,37 +124,36 @@ hash_netportnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void hash_netportnet4_data_next(struct hash_netportnet4_elem *next, - const struct hash_netportnet4_elem *d) + const struct hash_netportnet4_elem *d) { next->ipcmp = d->ipcmp; next->port = d->port; } #define MTYPE hash_netportnet4 -#define PF 4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, struct ip_set_adt_opt *opt) + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -172,58 +171,51 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, static int hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet4_elem e = { }; + struct hash_netportnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to; u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2; bool with_ports = false; - u8 cidr, cidr2; int ret; - e.cidr[0] = e.cidr[1] = HOST_MASK; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); + if (ret) + return ret; - ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) || - ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { - cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!cidr || cidr > HOST_MASK) + e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!e.cidr[0] || e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; - e.cidr[0] = cidr; } if (tb[IPSET_ATTR_CIDR2]) { - cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!cidr || cidr > HOST_MASK) + e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + if (!e.cidr[1] || e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; - e.cidr[1] = cidr; } - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -231,14 +223,16 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -262,8 +256,9 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip, ip_to); if (unlikely(ip + UINT_MAX == ip_to)) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip, ip_to, e.cidr[0]); + } port_to = port = ntohs(e.port); if (tb[IPSET_ATTR_PORT_TO]) { @@ -281,16 +276,16 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(ip2_from, ip2_to); if (unlikely(ip2_from + UINT_MAX == ip2_to)) return -IPSET_ERR_HASH_RANGE; - } else + } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); + } if (retried) ip = ntohl(h->next.ip[0]); while (!after(ip, ip_to)) { e.ip[0] = htonl(ip); - ip_last = ip_set_range_to_cidr(ip, ip_to, &cidr); - e.cidr[0] = cidr; + ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { @@ -301,13 +296,12 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], while (!after(ip2, ip2_to)) { e.ip[1] = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, - &cidr2); - e.cidr[1] = cidr2; + &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; ip2 = ip2_last + 1; } } @@ -326,7 +320,7 @@ struct hash_netportnet6_elem { u16 ccmp; }; u16 padding; - u8 nomatch:1; + u8 nomatch; u8 proto; }; @@ -334,8 +328,8 @@ struct hash_netportnet6_elem { static inline bool hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1, - const struct hash_netportnet6_elem *ip2, - u32 *multi) + const struct hash_netportnet6_elem *ip2, + u32 *multi) { return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) && ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) && @@ -364,7 +358,7 @@ hash_netportnet6_data_reset_flags(struct hash_netportnet6_elem *elem, u8 *flags) static inline void hash_netportnet6_data_reset_elem(struct hash_netportnet6_elem *elem, - struct hash_netportnet6_elem *orig) + struct hash_netportnet6_elem *orig) { elem->ip[1] = orig->ip[1]; } @@ -384,7 +378,7 @@ hash_netportnet6_data_netmask(struct hash_netportnet6_elem *elem, static bool hash_netportnet6_data_list(struct sk_buff *skb, - const struct hash_netportnet6_elem *data) + const struct hash_netportnet6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; @@ -397,41 +391,39 @@ hash_netportnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void hash_netportnet6_data_next(struct hash_netportnet4_elem *next, - const struct hash_netportnet6_elem *d) + const struct hash_netportnet6_elem *d) { next->port = d->port; } #undef MTYPE -#undef PF #undef HOST_MASK #define MTYPE hash_netportnet6 -#define PF 6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, struct ip_set_adt_opt *opt) + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; @@ -449,57 +441,55 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, static int hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet6_elem e = { }; + struct hash_netportnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; - e.cidr[0] = e.cidr[1] = HOST_MASK; + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; - if (tb[IPSET_ATTR_LINENO]) - *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); + if (ret) + return ret; - ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) || - ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) || - ip_set_get_extensions(set, tb, &ext); + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + ret = ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } - if (tb[IPSET_ATTR_CIDR2]) + if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - - if (unlikely(!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] || - e.cidr[1] > HOST_MASK)) - return -IPSET_ERR_INVALID_CIDR; + if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + return -IPSET_ERR_INVALID_CIDR; + } ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); - if (tb[IPSET_ATTR_PORT]) - e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); - else - return -IPSET_ERR_PROTOCOL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); @@ -507,14 +497,16 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; - } else + } else { return -IPSET_ERR_MISSING_PROTO; + } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } @@ -538,8 +530,8 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret && !ip_set_eexist(ret, flags)) return ret; - else - ret = 0; + + ret = 0; } return ret; } @@ -577,7 +569,8 @@ static struct ip_set_type hash_netportnet_type __read_mostly = { [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -594,6 +587,7 @@ hash_netportnet_init(void) static void __exit hash_netportnet_fini(void) { + rcu_barrier(); ip_set_type_unregister(&hash_netportnet_type); } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index f8f682806..a1fe5377a 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/ip.h> +#include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/errno.h> @@ -27,6 +28,8 @@ MODULE_ALIAS("ip_set_list:set"); /* Member elements */ struct set_elem { + struct rcu_head rcu; + struct list_head list; ip_set_id_t id; }; @@ -41,12 +44,9 @@ struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ struct net *net; /* namespace */ - struct set_elem members[0]; /* the set members */ + struct list_head members; /* the set members */ }; -#define list_set_elem(set, map, id) \ - (struct set_elem *)((void *)(map)->members + (id) * (set)->dsize) - static int list_set_ktest(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -54,17 +54,14 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb, { struct list_set *map = set->data; struct set_elem *e; - u32 i, cmdflags = opt->cmdflags; + u32 cmdflags = opt->cmdflags; int ret; /* Don't lookup sub-counters at all */ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS; if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE) opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE; - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - return 0; + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -91,13 +88,9 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb, { struct list_set *map = set->data; struct set_elem *e; - u32 i; int ret; - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - return 0; + list_for_each_entry(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -115,13 +108,9 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb, { struct list_set *map = set->data; struct set_elem *e; - u32 i; int ret; - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - return 0; + list_for_each_entry(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -138,110 +127,65 @@ list_set_kadt(struct ip_set *set, const struct sk_buff *skb, enum ipset_adt adt, struct ip_set_adt_opt *opt) { struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + int ret = -EINVAL; + rcu_read_lock(); switch (adt) { case IPSET_TEST: - return list_set_ktest(set, skb, par, opt, &ext); + ret = list_set_ktest(set, skb, par, opt, &ext); + break; case IPSET_ADD: - return list_set_kadd(set, skb, par, opt, &ext); + ret = list_set_kadd(set, skb, par, opt, &ext); + break; case IPSET_DEL: - return list_set_kdel(set, skb, par, opt, &ext); + ret = list_set_kdel(set, skb, par, opt, &ext); + break; default: break; } - return -EINVAL; -} - -static bool -id_eq(const struct ip_set *set, u32 i, ip_set_id_t id) -{ - const struct list_set *map = set->data; - const struct set_elem *e; - - if (i >= map->size) - return 0; + rcu_read_unlock(); - e = list_set_elem(set, map, i); - return !!(e->id == id && - !(SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set)))); + return ret; } -static int -list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d, - const struct ip_set_ext *ext) -{ - struct list_set *map = set->data; - struct set_elem *e = list_set_elem(set, map, i); +/* Userspace interfaces: we are protected by the nfnl mutex */ - if (e->id != IPSET_INVALID_ID) { - if (i == map->size - 1) { - /* Last element replaced: e.g. add new,before,last */ - ip_set_put_byindex(map->net, e->id); - ip_set_ext_destroy(set, e); - } else { - struct set_elem *x = list_set_elem(set, map, - map->size - 1); - - /* Last element pushed off */ - if (x->id != IPSET_INVALID_ID) { - ip_set_put_byindex(map->net, x->id); - ip_set_ext_destroy(set, x); - } - memmove(list_set_elem(set, map, i + 1), e, - set->dsize * (map->size - (i + 1))); - /* Extensions must be initialized to zero */ - memset(e, 0, set->dsize); - } - } - - e->id = d->id; - if (SET_WITH_TIMEOUT(set)) - ip_set_timeout_set(ext_timeout(e, set), ext->timeout); - if (SET_WITH_COUNTER(set)) - ip_set_init_counter(ext_counter(e, set), ext); - if (SET_WITH_COMMENT(set)) - ip_set_init_comment(ext_comment(e, set), ext); - if (SET_WITH_SKBINFO(set)) - ip_set_init_skbinfo(ext_skbinfo(e, set), ext); - return 0; -} - -static int -list_set_del(struct ip_set *set, u32 i) +static void +__list_set_del(struct ip_set *set, struct set_elem *e) { struct list_set *map = set->data; - struct set_elem *e = list_set_elem(set, map, i); ip_set_put_byindex(map->net, e->id); + /* We may call it, because we don't have a to be destroyed + * extension which is used by the kernel. + */ ip_set_ext_destroy(set, e); + kfree_rcu(e, rcu); +} - if (i < map->size - 1) - memmove(e, list_set_elem(set, map, i + 1), - set->dsize * (map->size - (i + 1))); +static inline void +list_set_del(struct ip_set *set, struct set_elem *e) +{ + list_del_rcu(&e->list); + __list_set_del(set, e); +} - /* Last element */ - e = list_set_elem(set, map, map->size - 1); - e->id = IPSET_INVALID_ID; - return 0; +static inline void +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) +{ + list_replace_rcu(&old->list, &e->list); + __list_set_del(set, old); } static void set_cleanup_entries(struct ip_set *set) { struct list_set *map = set->data; - struct set_elem *e; - u32 i = 0; + struct set_elem *e, *n; - while (i < map->size) { - e = list_set_elem(set, map, i); - if (e->id != IPSET_INVALID_ID && - ip_set_timeout_expired(ext_timeout(e, set))) - list_set_del(set, i); - /* Check element moved to position i in next loop */ - else - i++; - } + list_for_each_entry_safe(e, n, &map->members, list) + if (ip_set_timeout_expired(ext_timeout(e, set))) + list_set_del(set, e); } static int @@ -250,31 +194,46 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, { struct list_set *map = set->data; struct set_adt_elem *d = value; - struct set_elem *e; - u32 i; + struct set_elem *e, *next, *prev = NULL; int ret; - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - return 0; - else if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + list_for_each_entry(e, &map->members, list) { + if (SET_WITH_TIMEOUT(set) && + ip_set_timeout_expired(ext_timeout(e, set))) continue; - else if (e->id != d->id) + else if (e->id != d->id) { + prev = e; continue; + } - if (d->before == 0) - return 1; - else if (d->before > 0) - ret = id_eq(set, i + 1, d->refid); - else - ret = i > 0 && id_eq(set, i - 1, d->refid); + if (d->before == 0) { + ret = 1; + } else if (d->before > 0) { + next = list_next_entry(e, list); + ret = !list_is_last(&e->list, &map->members) && + next->id == d->refid; + } else { + ret = prev && prev->id == d->refid; + } return ret; } return 0; } +static void +list_set_init_extensions(struct ip_set *set, const struct ip_set_ext *ext, + struct set_elem *e) +{ + if (SET_WITH_COUNTER(set)) + ip_set_init_counter(ext_counter(e, set), ext); + if (SET_WITH_COMMENT(set)) + ip_set_init_comment(ext_comment(e, set), ext); + if (SET_WITH_SKBINFO(set)) + ip_set_init_skbinfo(ext_skbinfo(e, set), ext); + /* Update timeout last */ + if (SET_WITH_TIMEOUT(set)) + ip_set_timeout_set(ext_timeout(e, set), ext->timeout); +} static int list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, @@ -282,60 +241,78 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, { struct list_set *map = set->data; struct set_adt_elem *d = value; - struct set_elem *e; + struct set_elem *e, *n, *prev, *next; bool flag_exist = flags & IPSET_FLAG_EXIST; - u32 i, ret = 0; if (SET_WITH_TIMEOUT(set)) set_cleanup_entries(set); - /* Check already added element */ - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - goto insert; - else if (e->id != d->id) + /* Find where to add the new entry */ + n = prev = next = NULL; + list_for_each_entry(e, &map->members, list) { + if (SET_WITH_TIMEOUT(set) && + ip_set_timeout_expired(ext_timeout(e, set))) continue; - - if ((d->before > 1 && !id_eq(set, i + 1, d->refid)) || - (d->before < 0 && - (i == 0 || !id_eq(set, i - 1, d->refid)))) - /* Before/after doesn't match */ + else if (d->id == e->id) + n = e; + else if (d->before == 0 || e->id != d->refid) + continue; + else if (d->before > 0) + next = e; + else + prev = e; + } + /* Re-add already existing element */ + if (n) { + if ((d->before > 0 && !next) || + (d->before < 0 && !prev)) return -IPSET_ERR_REF_EXIST; if (!flag_exist) - /* Can't re-add */ return -IPSET_ERR_EXIST; /* Update extensions */ - ip_set_ext_destroy(set, e); + ip_set_ext_destroy(set, n); + list_set_init_extensions(set, ext, n); - if (SET_WITH_TIMEOUT(set)) - ip_set_timeout_set(ext_timeout(e, set), ext->timeout); - if (SET_WITH_COUNTER(set)) - ip_set_init_counter(ext_counter(e, set), ext); - if (SET_WITH_COMMENT(set)) - ip_set_init_comment(ext_comment(e, set), ext); - if (SET_WITH_SKBINFO(set)) - ip_set_init_skbinfo(ext_skbinfo(e, set), ext); /* Set is already added to the list */ ip_set_put_byindex(map->net, d->id); return 0; } -insert: - ret = -IPSET_ERR_LIST_FULL; - for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - ret = d->before != 0 ? -IPSET_ERR_REF_EXIST - : list_set_add(set, i, d, ext); - else if (e->id != d->refid) - continue; - else if (d->before > 0) - ret = list_set_add(set, i, d, ext); - else if (i + 1 < map->size) - ret = list_set_add(set, i + 1, d, ext); + /* Add new entry */ + if (d->before == 0) { + /* Append */ + n = list_empty(&map->members) ? NULL : + list_last_entry(&map->members, struct set_elem, list); + } else if (d->before > 0) { + /* Insert after next element */ + if (!list_is_last(&next->list, &map->members)) + n = list_next_entry(next, list); + } else { + /* Insert before prev element */ + if (prev->list.prev != &map->members) + n = list_prev_entry(prev, list); } + /* Can we replace a timed out entry? */ + if (n && + !(SET_WITH_TIMEOUT(set) && + ip_set_timeout_expired(ext_timeout(n, set)))) + n = NULL; + + e = kzalloc(set->dsize, GFP_KERNEL); + if (!e) + return -ENOMEM; + e->id = d->id; + INIT_LIST_HEAD(&e->list); + list_set_init_extensions(set, ext, e); + if (n) + list_set_replace(set, e, n); + else if (next) + list_add_tail_rcu(&e->list, &next->list); + else if (prev) + list_add_rcu(&e->list, &prev->list); + else + list_add_tail_rcu(&e->list, &map->members); - return ret; + return 0; } static int @@ -344,32 +321,30 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext, { struct list_set *map = set->data; struct set_adt_elem *d = value; - struct set_elem *e; - u32 i; - - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - return d->before != 0 ? -IPSET_ERR_REF_EXIST - : -IPSET_ERR_EXIST; - else if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + struct set_elem *e, *next, *prev = NULL; + + list_for_each_entry(e, &map->members, list) { + if (SET_WITH_TIMEOUT(set) && + ip_set_timeout_expired(ext_timeout(e, set))) continue; - else if (e->id != d->id) + else if (e->id != d->id) { + prev = e; continue; + } - if (d->before == 0) - return list_set_del(set, i); - else if (d->before > 0) { - if (!id_eq(set, i + 1, d->refid)) + if (d->before > 0) { + next = list_next_entry(e, list); + if (list_is_last(&e->list, &map->members) || + next->id != d->refid) return -IPSET_ERR_REF_EXIST; - return list_set_del(set, i); - } else if (i == 0 || !id_eq(set, i - 1, d->refid)) - return -IPSET_ERR_REF_EXIST; - else - return list_set_del(set, i); + } else if (d->before < 0) { + if (!prev || prev->id != d->refid) + return -IPSET_ERR_REF_EXIST; + } + list_set_del(set, e); + return 0; } - return -IPSET_ERR_EXIST; + return d->before != 0 ? -IPSET_ERR_REF_EXIST : -IPSET_ERR_EXIST; } static int @@ -383,19 +358,13 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], struct ip_set *s; int ret = 0; - if (unlikely(!tb[IPSET_ATTR_NAME] || - !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) || - !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE))) - return -IPSET_ERR_PROTOCOL; - if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + if (unlikely(!tb[IPSET_ATTR_NAME] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) + return -IPSET_ERR_PROTOCOL; + ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; @@ -410,6 +379,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + e.before = f & IPSET_FLAG_BEFORE; } @@ -447,27 +417,26 @@ static void list_set_flush(struct ip_set *set) { struct list_set *map = set->data; - struct set_elem *e; - u32 i; - - for (i = 0; i < map->size; i++) { - e = list_set_elem(set, map, i); - if (e->id != IPSET_INVALID_ID) { - ip_set_put_byindex(map->net, e->id); - ip_set_ext_destroy(set, e); - e->id = IPSET_INVALID_ID; - } - } + struct set_elem *e, *n; + + list_for_each_entry_safe(e, n, &map->members, list) + list_set_del(set, e); } static void list_set_destroy(struct ip_set *set) { struct list_set *map = set->data; + struct set_elem *e, *n; if (SET_WITH_TIMEOUT(set)) del_timer_sync(&map->gc); - list_set_flush(set); + list_for_each_entry_safe(e, n, &map->members, list) { + list_del(&e->list); + ip_set_put_byindex(map->net, e->id); + ip_set_ext_destroy(set, e); + kfree(e); + } kfree(map); set->data = NULL; @@ -478,6 +447,11 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; + struct set_elem *e; + u32 n = 0; + + list_for_each_entry(e, &map->members, list) + n++; nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) @@ -485,7 +459,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + map->size * set->dsize))) + htonl(sizeof(*map) + n * set->dsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -502,18 +476,22 @@ list_set_list(const struct ip_set *set, { const struct list_set *map = set->data; struct nlattr *atd, *nested; - u32 i, first = cb->args[IPSET_CB_ARG0]; - const struct set_elem *e; + u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + struct set_elem *e; + int ret = 0; atd = ipset_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; - for (; cb->args[IPSET_CB_ARG0] < map->size; - cb->args[IPSET_CB_ARG0]++) { - i = cb->args[IPSET_CB_ARG0]; - e = list_set_elem(set, map, i); - if (e->id == IPSET_INVALID_ID) - goto finish; + list_for_each_entry(e, &map->members, list) { + if (i == first) + break; + i++; + } + + rcu_read_lock(); + list_for_each_entry_from(e, &map->members, list) { + i++; if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -521,9 +499,10 @@ list_set_list(const struct ip_set *set, if (!nested) { if (i == first) { nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; + ret = -EMSGSIZE; + goto out; + } + goto nla_put_failure; } if (nla_put_string(skb, IPSET_ATTR_NAME, ip_set_name_byindex(map->net, e->id))) @@ -532,20 +511,23 @@ list_set_list(const struct ip_set *set, goto nla_put_failure; ipset_nest_end(skb, nested); } -finish: + ipset_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; - return 0; + goto out; nla_put_failure: nla_nest_cancel(skb, nested); if (unlikely(i == first)) { cb->args[IPSET_CB_ARG0] = 0; - return -EMSGSIZE; + ret = -EMSGSIZE; } + cb->args[IPSET_CB_ARG0] = i - 1; ipset_nest_end(skb, atd); - return 0; +out: + rcu_read_unlock(); + return ret; } static bool @@ -577,12 +559,12 @@ static const struct ip_set_type_variant set_variant = { static void list_set_gc(unsigned long ul_set) { - struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set *set = (struct ip_set *)ul_set; struct list_set *map = set->data; - write_lock_bh(&set->lock); + spin_lock_bh(&set->lock); set_cleanup_entries(set); - write_unlock_bh(&set->lock); + spin_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); @@ -594,7 +576,7 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) struct list_set *map = set->data; init_timer(&map->gc); - map->gc.data = (unsigned long) set; + map->gc.data = (unsigned long)set; map->gc.function = gc; map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); @@ -606,24 +588,16 @@ static bool init_list_set(struct net *net, struct ip_set *set, u32 size) { struct list_set *map; - struct set_elem *e; - u32 i; - map = kzalloc(sizeof(*map) + - min_t(u32, size, IP_SET_LIST_MAX_SIZE) * set->dsize, - GFP_KERNEL); + map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) return false; map->size = size; map->net = net; + INIT_LIST_HEAD(&map->members); set->data = map; - for (i = 0; i < size; i++) { - e = list_set_elem(set, map, i); - e->id = IPSET_INVALID_ID; - } - return true; } @@ -678,7 +652,8 @@ static struct ip_set_type list_set_type __read_mostly = { [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, - [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, + .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, @@ -695,6 +670,7 @@ list_set_init(void) static void __exit list_set_fini(void) { + rcu_barrier(); ip_set_type_unregister(&list_set_type); } diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c index 04d15fdc9..1c8a42c10 100644 --- a/net/netfilter/ipset/pfxlen.c +++ b/net/netfilter/ipset/pfxlen.c @@ -1,9 +1,7 @@ #include <linux/export.h> #include <linux/netfilter/ipset/pfxlen.h> -/* - * Prefixlen maps for fast conversions, by Jan Engelhardt. - */ +/* Prefixlen maps for fast conversions, by Jan Engelhardt. */ #define E(a, b, c, d) \ {.ip6 = { \ @@ -11,8 +9,7 @@ htonl(c), htonl(d), \ } } -/* - * This table works for both IPv4 and IPv6; +/* This table works for both IPv4 and IPv6; * just use prefixlen_netmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_netmask_map[] = { @@ -149,13 +146,12 @@ const union nf_inet_addr ip_set_netmask_map[] = { EXPORT_SYMBOL_GPL(ip_set_netmask_map); #undef E -#define E(a, b, c, d) \ - {.ip6 = { (__force __be32) a, (__force __be32) b, \ - (__force __be32) c, (__force __be32) d, \ +#define E(a, b, c, d) \ + {.ip6 = { (__force __be32)a, (__force __be32)b, \ + (__force __be32)c, (__force __be32)d, \ } } -/* - * This table works for both IPv4 and IPv6; +/* This table works for both IPv4 and IPv6; * just use prefixlen_hostmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_hostmask_map[] = { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5d2b806a8..38fbc194b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -319,7 +319,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); @@ -467,7 +473,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 285eae3a1..24c554201 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -842,15 +842,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, __ip_vs_dst_cache_reset(dest); spin_unlock_bh(&dest->dst_lock); - sched = rcu_dereference_protected(svc->scheduler, 1); if (add) { ip_vs_start_estimator(svc->net, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; - if (sched->add_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->add_dest) sched->add_dest(svc, dest); } else { - if (sched->upd_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->upd_dest) sched->upd_dest(svc, dest); } } @@ -1084,7 +1085,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_scheduler *sched; sched = rcu_dereference_protected(svc->scheduler, 1); - if (sched->del_dest) + if (sched && sched->del_dest) sched->del_dest(svc, dest); } } @@ -1175,11 +1176,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, ip_vs_use_count_inc(); /* Lookup the scheduler by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - ret = -ENOENT; - goto out_err; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + ret = -ENOENT; + goto out_err; + } } if (u->pe_name && *u->pe_name) { @@ -1240,10 +1244,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) - goto out_err; - sched = NULL; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) + goto out_err; + sched = NULL; + } /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); @@ -1291,17 +1297,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { - struct ip_vs_scheduler *sched, *old_sched; + struct ip_vs_scheduler *sched = NULL, *old_sched; struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; /* * Lookup the scheduler, by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - return -ENOENT; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + return -ENOENT; + } } old_sched = sched; @@ -1329,14 +1338,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { + if (old_sched) { + ip_vs_unbind_scheduler(svc, old_sched); + RCU_INIT_POINTER(svc->scheduler, NULL); + /* Wait all svc->sched_data users */ + synchronize_rcu(); + } /* Bind the new scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) { - old_sched = sched; - goto out; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) { + ip_vs_scheduler_put(sched); + goto out; + } } - /* Unbind the old scheduler on success */ - ip_vs_unbind_scheduler(svc, old_sched); } /* @@ -1982,6 +1997,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 @@ -1990,18 +2006,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), - sched->name); + sched_name); else #endif seq_printf(seq, "%s %08X:%04X %s %s ", ip_vs_proto_name(svc->protocol), ntohl(svc->addr.ip), ntohs(svc->port), - sched->name, + sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } else { seq_printf(seq, "FWM %08X %s %s", - svc->fwmark, sched->name, + svc->fwmark, sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } @@ -2427,13 +2443,15 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; struct ip_vs_kstats kstats; + char *sched_name; sched = rcu_dereference_protected(src->scheduler, 1); + sched_name = sched ? sched->name : "none"; dst->protocol = src->protocol; dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; - strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name)); + strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name)); dst->flags = src->flags; dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; @@ -2892,6 +2910,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; struct ip_vs_kstats kstats; + char *sched_name; nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) @@ -2910,8 +2929,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, } sched = rcu_dereference_protected(svc->scheduler, 1); + sched_name = sched ? sched->name : "none"; pe = rcu_dereference_protected(svc->pe, 1); - if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) || + if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) || (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) || nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 199760c71..7e8141647 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc, if (sched->done_service) sched->done_service(svc); - /* svc->scheduler can not be set to NULL */ + /* svc->scheduler can be set to NULL only by caller */ } @@ -147,21 +147,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg) { - struct ip_vs_scheduler *sched; + struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; - sched = rcu_dereference(svc->scheduler); if (svc->fwmark) { IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n", - sched->name, svc->fwmark, svc->fwmark, msg); + sched_name, svc->fwmark, svc->fwmark, msg); #ifdef CONFIG_IP_VS_IPV6 } else if (svc->af == AF_INET6) { IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), msg); #endif } else { IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.ip, ntohs(svc->port), msg); } } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 19b9cce6c..d99ad93eb 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(net, cp->control, pkts); + ip_vs_sync_conn(net, cp, pkts); } } @@ -1457,18 +1457,12 @@ static struct socket *make_send_sock(struct net *net, int id) struct socket *sock; int result; - /* First create a socket move it to right name space later */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + /* First create a socket */ + result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - /* - * Kernel sockets that are a part of a namespace, should not - * hold a reference to a namespace in order to allow to stop it. - * After sk_change_net should be released using sk_release_kernel. - */ - sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1497,7 +1491,7 @@ static struct socket *make_send_sock(struct net *net, int id) return sock; error: - sk_release_kernel(sock->sk); + sock_release(sock); return ERR_PTR(result); } @@ -1518,17 +1512,11 @@ static struct socket *make_receive_sock(struct net *net, int id) int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - /* - * Kernel sockets that are a part of a namespace, should not - * hold a reference to a namespace in order to allow to stop it. - * After sk_change_net should be released using sk_release_kernel. - */ - sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); @@ -1554,7 +1542,7 @@ static struct socket *make_receive_sock(struct net *net, int id) return sock; error: - sk_release_kernel(sock->sk); + sock_release(sock); return ERR_PTR(result); } @@ -1692,7 +1680,7 @@ done: ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo); return 0; @@ -1729,7 +1717,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo->buf); kfree(tinfo); @@ -1854,11 +1842,11 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) return 0; outsocket: - sk_release_kernel(sock->sk); + sock_release(sock); outtinfo: if (tinfo) { - sk_release_kernel(tinfo->sock->sk); + sock_release(tinfo->sock); kfree(tinfo->buf); kfree(tinfo); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 19986ec5f..258a0b0e8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; - fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? FLOWI_FLAG_KNOWN_NH : 0; @@ -364,13 +363,16 @@ err_unreach: #ifdef CONFIG_IP_VS_IPV6 static struct dst_entry * __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, - struct in6_addr *ret_saddr, int do_xfrm) + struct in6_addr *ret_saddr, int do_xfrm, int rt_mode) { struct dst_entry *dst; struct flowi6 fl6 = { .daddr = *daddr, }; + if (rt_mode & IP_VS_RT_MODE_KNOWN_NH) + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; + dst = ip6_route_output(net, NULL, &fl6); if (dst->error) goto out_err; @@ -427,7 +429,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, } dst = __ip_vs_route_output_v6(net, &dest->addr.in6, &dest_dst->dst_saddr.in6, - do_xfrm); + do_xfrm, rt_mode); if (!dst) { __ip_vs_dst_set(dest, NULL, NULL, 0); spin_unlock_bh(&dest->dst_lock); @@ -435,7 +437,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, goto err_unreach; } rt = (struct rt6_info *) dst; - cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + cookie = rt6_get_cookie(rt); __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", @@ -446,7 +448,8 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, *ret_saddr = dest_dst->dst_saddr.in6; } else { noref = 0; - dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); + dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm, + rt_mode); if (!dst) goto err_unreach; rt = (struct rt6_info *) dst; @@ -501,6 +504,13 @@ err_put: return -1; err_unreach: + /* The ip6_link_failure function requires the dev field to be set + * in order to get the net (further for the sake of fwmark + * reflection). + */ + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } @@ -519,10 +529,27 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); } return ret; } +/* In the event of a remote destination, it's possible that we would have + * matches against an old socket (particularly a TIME-WAIT socket). This + * causes havoc down the line (ip_local_out et. al. expect regular sockets + * and invalid memory accesses will happen) so simply drop the association + * in this case. +*/ +static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb) +{ + /* If dev is set, the packet came from the LOCAL_IN callback and + * not from a local TCP socket. + */ + if (skb->dev) + skb_orphan(skb); +} + /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, struct ip_vs_conn *cp, int local) @@ -534,12 +561,23 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 1); + + /* Remove the early_demux association unless it's bound for the + * exact same port and address on this host after translation. + */ + if (!local || cp->vport != cp->dport || + !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr)) + ip_vs_drop_early_demux_sk(skb); + if (!local) { skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; + return ret; } @@ -553,7 +591,10 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (likely(!(cp->flags & IP_VS_CONN_F_NFCT))) ip_vs_notrack(skb); if (!local) { + ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else @@ -781,7 +822,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); @@ -841,6 +882,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, struct ipv6hdr *old_ipv6h = NULL; #endif + ip_vs_drop_early_demux_sk(skb); + if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) { new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) @@ -1164,7 +1207,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, NULL, ipvsh, 0, IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL); + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_KNOWN_NH); if (local < 0) goto tx_error; if (local) { @@ -1346,7 +1390,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && - ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { + ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI6\n", __func__, &cp->daddr.in6); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 13fad8668..0625a42df 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -287,6 +287,47 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) spin_unlock(&pcpu->lock); } +/* Released via destroy_conntrack() */ +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) +{ + struct nf_conn *tmpl; + + tmpl = kzalloc(sizeof(*tmpl), flags); + if (tmpl == NULL) + return NULL; + + tmpl->status = IPS_TEMPLATE; + write_pnet(&tmpl->ct_net, net); + +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (zone) { + struct nf_conntrack_zone *nf_ct_zone; + + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, flags); + if (!nf_ct_zone) + goto out_free; + nf_ct_zone->id = zone; + } +#endif + atomic_set(&tmpl->ct_general.use, 0); + + return tmpl; +#ifdef CONFIG_NF_CONNTRACK_ZONES +out_free: + kfree(tmpl); + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); + +void nf_ct_tmpl_free(struct nf_conn *tmpl) +{ + nf_ct_ext_destroy(tmpl); + nf_ct_ext_free(tmpl); + kfree(tmpl); +} +EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -298,6 +339,10 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); + if (unlikely(nf_ct_is_template(ct))) { + nf_ct_tmpl_free(ct); + return; + } rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -540,28 +585,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); -/* deletion from this larval template list happens via nf_ct_put() */ -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) -{ - struct ct_pcpu *pcpu; - - __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); - - /* add this conntrack to the (per cpu) tmpl list */ - local_bh_disable(); - tmpl->cpu = smp_processor_id(); - pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); - - spin_lock(&pcpu->lock); - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &pcpu->tmpl); - spin_unlock_bh(&pcpu->lock); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); - /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -1522,10 +1545,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); - if (!hash) { - printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); + if (!hash) hash = vzalloc(sz); - } if (hash && nulls) for (i = 0; i < nr_slots; i++) @@ -1751,7 +1772,6 @@ int nf_conntrack_init_net(struct net *net) spin_lock_init(&pcpu->lock); INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } net->ct.stat = alloc_percpu(struct ip_conntrack_stat); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 7a17070c5..b45a4223c 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } - return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask); + return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } static inline int expect_matches(const struct nf_conntrack_expect *a, diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1d69f5b97..9511af04d 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -779,8 +779,8 @@ static int callforward_do_filter(struct net *net, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (ipv6_addr_equal(rt6_nexthop(rt1), - rt6_nexthop(rt2)) && + if (ipv6_addr_equal(rt6_nexthop(rt1, &fl1.daddr), + rt6_nexthop(rt2, &fl2.daddr)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d1c23940a..6b8b0abbf 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2995,11 +2995,6 @@ ctnetlink_create_expect(struct net *net, u16 zone, } err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) - goto err_exp; - - return 0; -err_exp: nf_ct_expect_put(exp); err_ct: nf_ct_put(ct); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 60865f110..2281be419 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -90,7 +90,13 @@ static int generic_packet(struct nf_conn *ct, static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { - return nf_generic_should_process(nf_ct_protonum(ct)); + bool ret; + + ret = nf_generic_should_process(nf_ct_protonum(ct)); + if (!ret) + pr_warn_once("conntrack: generic helper won't handle protocol %d. Please consider loading the specific helper module.\n", + nf_ct_protonum(ct)); + return ret; } #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index ea7f36784..399210693 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -19,6 +19,7 @@ unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, /* nf_queue.c */ int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, struct nf_hook_state *state, unsigned int queuenum); +void nf_queue_nf_hook_drop(struct nf_hook_ops *ops); int __init netfilter_queue_init(void); /* nf_log.c */ diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 2e88032cd..8a8b2abc3 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -105,6 +105,23 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); +void nf_queue_nf_hook_drop(struct nf_hook_ops *ops) +{ + const struct nf_queue_handler *qh; + struct net *net; + + rtnl_lock(); + rcu_read_lock(); + qh = rcu_dereference(queue_handler); + if (qh) { + for_each_net(net) { + qh->nf_hook_drop(net, ops); + } + } + rcu_read_unlock(); + rtnl_unlock(); +} + /* * Any packet that leaves via this function must come back * through nf_reinject(). @@ -196,7 +213,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT) { next_hook: - verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook], + verdict = nf_iterate(entry->state.hook_list, skb, &entry->state, &elem); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 52e20c9a4..d6ee8f8b1 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -11,6 +11,7 @@ #include <asm/unaligned.h> #include <net/tcp.h> #include <net/netns/generic.h> +#include <linux/proc_fs.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter/x_tables.h> @@ -348,23 +349,20 @@ static void __net_exit synproxy_proc_exit(struct net *net) static int __net_init synproxy_net_init(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - struct nf_conntrack_tuple t; struct nf_conn *ct; int err = -ENOMEM; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); + ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); + if (!ct) goto err1; - } if (!nfct_seqadj_ext_add(ct)) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; - nf_conntrack_tmpl_insert(net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); @@ -380,7 +378,7 @@ static int __net_init synproxy_net_init(struct net *net) err3: free_percpu(snet->stats); err2: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err1: return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 34ded0931..cfe636808 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -127,13 +127,46 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +int nft_register_basechain(struct nft_base_chain *basechain, + unsigned int hook_nops) +{ + if (basechain->flags & NFT_BASECHAIN_DISABLED) + return 0; + + return nf_register_hooks(basechain->ops, hook_nops); +} +EXPORT_SYMBOL_GPL(nft_register_basechain); + +void nft_unregister_basechain(struct nft_base_chain *basechain, + unsigned int hook_nops) +{ + if (basechain->flags & NFT_BASECHAIN_DISABLED) + return; + + nf_unregister_hooks(basechain->ops, hook_nops); +} +EXPORT_SYMBOL_GPL(nft_unregister_basechain); + +static int nf_tables_register_hooks(const struct nft_table *table, + struct nft_chain *chain, + unsigned int hook_nops) +{ + if (table->flags & NFT_TABLE_F_DORMANT || + !(chain->flags & NFT_BASE_CHAIN)) + return 0; + + return nft_register_basechain(nft_base_chain(chain), hook_nops); +} + static void nf_tables_unregister_hooks(const struct nft_table *table, - const struct nft_chain *chain, + struct nft_chain *chain, unsigned int hook_nops) { - if (!(table->flags & NFT_TABLE_F_DORMANT) && - chain->flags & NFT_BASE_CHAIN) - nf_unregister_hooks(nft_base_chain(chain)->ops, hook_nops); + if (table->flags & NFT_TABLE_F_DORMANT || + !(chain->flags & NFT_BASE_CHAIN)) + return; + + nft_unregister_basechain(nft_base_chain(chain), hook_nops); } /* Internal table flags */ @@ -560,7 +593,7 @@ static int nf_tables_table_enable(const struct nft_af_info *afi, if (!(chain->flags & NFT_BASE_CHAIN)) continue; - err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops); + err = nft_register_basechain(nft_base_chain(chain), afi->nops); if (err < 0) goto err; @@ -575,20 +608,20 @@ err: if (i-- <= 0) break; - nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops); + nft_unregister_basechain(nft_base_chain(chain), afi->nops); } return err; } static void nf_tables_table_disable(const struct nft_af_info *afi, - struct nft_table *table) + struct nft_table *table) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { if (chain->flags & NFT_BASE_CHAIN) - nf_unregister_hooks(nft_base_chain(chain)->ops, - afi->nops); + nft_unregister_basechain(nft_base_chain(chain), + afi->nops); } } @@ -679,13 +712,14 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, return -EINVAL; } + err = -EAFNOSUPPORT; if (!try_module_get(afi->owner)) - return -EAFNOSUPPORT; + goto err1; err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL); if (table == NULL) - goto err1; + goto err2; nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); @@ -695,14 +729,15 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&table->list, &afi->tables); return 0; -err2: +err3: kfree(table); -err1: +err2: module_put(afi->owner); +err1: return err; } @@ -881,6 +916,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { [NFTA_HOOK_HOOKNUM] = { .type = NLA_U32 }, [NFTA_HOOK_PRIORITY] = { .type = NLA_U32 }, + [NFTA_HOOK_DEV] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, }; static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) @@ -954,6 +991,9 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) goto nla_put_failure; + if (basechain->dev_name[0] && + nla_put_string(skb, NFTA_HOOK_DEV, basechain->dev_name)) + goto nla_put_failure; nla_nest_end(skb, nest); if (nla_put_be32(skb, NFTA_CHAIN_POLICY, @@ -1165,9 +1205,13 @@ static void nf_tables_chain_destroy(struct nft_chain *chain) BUG_ON(chain->use > 0); if (chain->flags & NFT_BASE_CHAIN) { - module_put(nft_base_chain(chain)->type->owner); - free_percpu(nft_base_chain(chain)->stats); - kfree(nft_base_chain(chain)); + struct nft_base_chain *basechain = nft_base_chain(chain); + + module_put(basechain->type->owner); + free_percpu(basechain->stats); + if (basechain->ops[0].dev != NULL) + dev_put(basechain->ops[0].dev); + kfree(basechain); } else { kfree(chain); } @@ -1186,6 +1230,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, struct nlattr *ha[NFTA_HOOK_MAX + 1]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct net_device *dev = NULL; u8 policy = NF_ACCEPT; u64 handle = 0; unsigned int i; @@ -1325,17 +1370,43 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, return -ENOENT; hookfn = type->hooks[hooknum]; + if (afi->flags & NFT_AF_NEEDS_DEV) { + char ifname[IFNAMSIZ]; + + if (!ha[NFTA_HOOK_DEV]) { + module_put(type->owner); + return -EOPNOTSUPP; + } + + nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ); + dev = dev_get_by_name(net, ifname); + if (!dev) { + module_put(type->owner); + return -ENOENT; + } + } else if (ha[NFTA_HOOK_DEV]) { + module_put(type->owner); + return -EOPNOTSUPP; + } + basechain = kzalloc(sizeof(*basechain), GFP_KERNEL); if (basechain == NULL) { module_put(type->owner); + if (dev != NULL) + dev_put(dev); return -ENOMEM; } + if (dev != NULL) + strncpy(basechain->dev_name, dev->name, IFNAMSIZ); + if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR(stats)) { module_put(type->owner); kfree(basechain); + if (dev != NULL) + dev_put(dev); return PTR_ERR(stats); } basechain->stats = stats; @@ -1344,6 +1415,8 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (stats == NULL) { module_put(type->owner); kfree(basechain); + if (dev != NULL) + dev_put(dev); return -ENOMEM; } rcu_assign_pointer(basechain->stats, stats); @@ -1361,6 +1434,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, ops->priority = priority; ops->priv = chain; ops->hook = afi->hooks[ops->hooknum]; + ops->dev = dev; if (hookfn) ops->hook = hookfn; if (afi->hook_ops_init) @@ -1380,12 +1454,9 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, chain->table = table; nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); - if (!(table->flags & NFT_TABLE_F_DORMANT) && - chain->flags & NFT_BASE_CHAIN) { - err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops); - if (err < 0) - goto err1; - } + err = nf_tables_register_hooks(table, chain, afi->nops); + if (err < 0) + goto err1; nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index f153b0707..f77bad46a 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -114,7 +114,8 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv, *basechain = chain; - const struct net *net = read_pnet(&nft_base_chain(basechain)->pnet); + const struct net *chain_net = read_pnet(&nft_base_chain(basechain)->pnet); + const struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_regs regs; @@ -124,6 +125,10 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) int rulenum; unsigned int gencursor = nft_genmask_cur(net); + /* Ignore chains that are not for the current network namespace */ + if (!net_eq(net, chain_net)) + return NF_ACCEPT; + do_chain: rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c new file mode 100644 index 000000000..2cae4d4a0 --- /dev/null +++ b/net/netfilter/nf_tables_netdev.c @@ -0,0 +1,258 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <net/netfilter/nf_tables.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/netfilter/nf_tables_ipv4.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static inline void +nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct iphdr *iph, _iph; + u32 len, thoff; + + nft_set_pktinfo(pkt, ops, skb, state); + + iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), + &_iph); + if (!iph) + return; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) + return; + else if (len < thoff) + return; + + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; +} + +static inline void +__nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ip6h, _ip6h; + unsigned int thoff = 0; + unsigned short frag_off; + int protohdr; + u32 pkt_len; + + ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), + &_ip6h); + if (!ip6h) + return; + + if (ip6h->version != 6) + return; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) + return; + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); + if (protohdr < 0) + return; + + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; +#endif +} + +static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, ops, skb, state); + __nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state); +} + +static unsigned int +nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nft_pktinfo pkt; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state); + break; + case htons(ETH_P_IPV6): + nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state); + break; + default: + nft_set_pktinfo(&pkt, ops, skb, state); + break; + } + + return nft_do_chain(&pkt, ops); +} + +static struct nft_af_info nft_af_netdev __read_mostly = { + .family = NFPROTO_NETDEV, + .nhooks = NF_NETDEV_NUMHOOKS, + .owner = THIS_MODULE, + .flags = NFT_AF_NEEDS_DEV, + .nops = 1, + .hooks = { + [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + }, +}; + +static int nf_tables_netdev_init_net(struct net *net) +{ + net->nft.netdev = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.netdev == NULL) + return -ENOMEM; + + memcpy(net->nft.netdev, &nft_af_netdev, sizeof(nft_af_netdev)); + + if (nft_register_afinfo(net, net->nft.netdev) < 0) + goto err; + + return 0; +err: + kfree(net->nft.netdev); + return -ENOMEM; +} + +static void nf_tables_netdev_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.netdev); + kfree(net->nft.netdev); +} + +static struct pernet_operations nf_tables_netdev_net_ops = { + .init = nf_tables_netdev_init_net, + .exit = nf_tables_netdev_exit_net, +}; + +static const struct nf_chain_type nft_filter_chain_netdev = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_NETDEV, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_NETDEV_INGRESS), +}; + +static void nft_netdev_event(unsigned long event, struct nft_af_info *afi, + struct net_device *dev, struct nft_table *table, + struct nft_base_chain *basechain) +{ + switch (event) { + case NETDEV_REGISTER: + if (strcmp(basechain->dev_name, dev->name) != 0) + return; + + BUG_ON(!(basechain->flags & NFT_BASECHAIN_DISABLED)); + + dev_hold(dev); + basechain->ops[0].dev = dev; + basechain->flags &= ~NFT_BASECHAIN_DISABLED; + if (!(table->flags & NFT_TABLE_F_DORMANT)) + nft_register_basechain(basechain, afi->nops); + break; + case NETDEV_UNREGISTER: + if (strcmp(basechain->dev_name, dev->name) != 0) + return; + + BUG_ON(basechain->flags & NFT_BASECHAIN_DISABLED); + + if (!(table->flags & NFT_TABLE_F_DORMANT)) + nft_unregister_basechain(basechain, afi->nops); + + dev_put(basechain->ops[0].dev); + basechain->ops[0].dev = NULL; + basechain->flags |= NFT_BASECHAIN_DISABLED; + break; + case NETDEV_CHANGENAME: + if (dev->ifindex != basechain->ops[0].dev->ifindex) + return; + + strncpy(basechain->dev_name, dev->name, IFNAMSIZ); + break; + } +} + +static int nf_tables_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_af_info *afi; + struct nft_table *table; + struct nft_chain *chain; + + nfnl_lock(NFNL_SUBSYS_NFTABLES); + list_for_each_entry(afi, &dev_net(dev)->nft.af_info, list) { + if (afi->family != NFPROTO_NETDEV) + continue; + + list_for_each_entry(table, &afi->tables, list) { + list_for_each_entry(chain, &table->chains, list) { + if (!(chain->flags & NFT_BASE_CHAIN)) + continue; + + nft_netdev_event(event, afi, dev, table, + nft_base_chain(chain)); + } + } + } + nfnl_unlock(NFNL_SUBSYS_NFTABLES); + + return NOTIFY_DONE; +} + +static struct notifier_block nf_tables_netdev_notifier = { + .notifier_call = nf_tables_netdev_event, +}; + +static int __init nf_tables_netdev_init(void) +{ + int ret; + + nft_register_chain_type(&nft_filter_chain_netdev); + ret = register_pernet_subsys(&nf_tables_netdev_net_ops); + if (ret < 0) + nft_unregister_chain_type(&nft_filter_chain_netdev); + + register_netdevice_notifier(&nf_tables_netdev_notifier); + + return ret; +} + +static void __exit nf_tables_netdev_exit(void) +{ + unregister_netdevice_notifier(&nf_tables_netdev_notifier); + unregister_pernet_subsys(&nf_tables_netdev_net_ops); + nft_unregister_chain_type(&nft_filter_chain_netdev); +} + +module_init(nf_tables_netdev_init); +module_exit(nf_tables_netdev_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_FAMILY(5); /* NFPROTO_NETDEV */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 8b117c90e..0c0e8ecf0 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -269,6 +269,12 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) } } +enum { + NFNL_BATCH_FAILURE = (1 << 0), + NFNL_BATCH_DONE = (1 << 1), + NFNL_BATCH_REPLAY = (1 << 2), +}; + static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u_int16_t subsys_id) { @@ -276,13 +282,15 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; - bool success = true, done = false; static LIST_HEAD(err_list); + u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL); replay: + status = 0; + skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); @@ -336,10 +344,10 @@ replay: if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { - done = true; + status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; @@ -382,11 +390,8 @@ replay: * original skb. */ if (err == -EAGAIN) { - nfnl_err_reset(&err_list); - ss->abort(oskb); - nfnl_unlock(subsys_id); - kfree_skb(skb); - goto replay; + status |= NFNL_BATCH_REPLAY; + goto next; } } ack: @@ -402,7 +407,7 @@ ack: */ nfnl_err_reset(&err_list); netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, @@ -410,19 +415,26 @@ ack: * triggers. */ if (err) - success = false; + status |= NFNL_BATCH_FAILURE; } - +next: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: - if (success && done) + if (status & NFNL_BATCH_REPLAY) { + ss->abort(oskb); + nfnl_err_reset(&err_list); + nfnl_unlock(subsys_id); + kfree_skb(skb); + goto replay; + } else if (status == NFNL_BATCH_DONE) { ss->commit(oskb); - else + } else { ss->abort(oskb); + } nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 4ef1fae84..4670821b5 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -598,8 +598,6 @@ nla_put_failure: return -1; } -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_ULOG, .u = { diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 11c7682fa..685cc6a17 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -278,6 +278,23 @@ nla_put_failure: return -1; } +static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata) +{ + u32 seclen = 0; +#if IS_ENABLED(CONFIG_NETWORK_SECMARK) + if (!skb || !sk_fullsock(skb->sk)) + return 0; + + read_lock_bh(&skb->sk->sk_callback_lock); + + if (skb->secmark) + security_secid_to_secctx(skb->secmark, secdata, &seclen); + + read_unlock_bh(&skb->sk->sk_callback_lock); +#endif + return seclen; +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -297,6 +314,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_conn *ct = NULL; enum ip_conntrack_info uninitialized_var(ctinfo); bool csum_verify; + char *secdata = NULL; + u32 seclen = 0; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) @@ -352,6 +371,12 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, + nla_total_size(sizeof(u_int32_t))); /* gid */ } + if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { + seclen = nfqnl_get_sk_secctx(entskb, &secdata); + if (seclen) + size += nla_total_size(seclen); + } + skb = nfnetlink_alloc_skb(net, size, queue->peer_portid, GFP_ATOMIC); if (!skb) { @@ -479,6 +504,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nfqnl_put_sk_uidgid(skb, entskb->sk) < 0) goto nla_put_failure; + if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata)) + goto nla_put_failure; + if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) goto nla_put_failure; @@ -806,8 +834,6 @@ nfqnl_dev_drop(struct net *net, int ifindex) rcu_read_unlock(); } -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) @@ -824,6 +850,27 @@ static struct notifier_block nfqnl_dev_notifier = { .notifier_call = nfqnl_rcv_dev_event, }; +static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long ops_ptr) +{ + return entry->elem == (struct nf_hook_ops *)ops_ptr; +} + +static void nfqnl_nf_hook_drop(struct net *net, struct nf_hook_ops *hook) +{ + struct nfnl_queue_net *q = nfnl_queue_pernet(net); + int i; + + rcu_read_lock(); + for (i = 0; i < INSTANCE_BUCKETS; i++) { + struct nfqnl_instance *inst; + struct hlist_head *head = &q->instance_table[i]; + + hlist_for_each_entry_rcu(inst, head, hlist) + nfqnl_flush(inst, nf_hook_cmp, (unsigned long)hook); + } + rcu_read_unlock(); +} + static int nfqnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) @@ -1031,7 +1078,8 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { }; static const struct nf_queue_handler nfqh = { - .outfn = &nfqnl_enqueue_packet, + .outfn = &nfqnl_enqueue_packet, + .nf_hook_drop = &nfqnl_nf_hook_drop, }; static int @@ -1142,7 +1190,12 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, ret = -EOPNOTSUPP; goto err_out_unlock; } - +#if !IS_ENABLED(CONFIG_NETWORK_SECMARK) + if (flags & mask & NFQA_CFG_F_SECCTX) { + ret = -EOPNOTSUPP; + goto err_out_unlock; + } +#endif spin_lock_bh(&queue->lock); queue->flags &= ~mask; queue->flags |= flags & mask; @@ -1257,7 +1310,7 @@ static int seq_show(struct seq_file *s, void *v) inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); - return seq_has_overflowed(s); + return 0; } static const struct seq_operations nfqnl_seq_ops = { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 7f29cfc76..66def315e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -161,6 +161,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, par->hook_mask = 0; } par->family = ctx->afi->family; + par->nft_compat = true; } static void target_compat_from_user(struct xt_target *t, void *in, void *out) @@ -377,6 +378,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, par->hook_mask = 0; } par->family = ctx->afi->family; + par->nft_compat = true; } static void match_compat_from_user(struct xt_match *m, void *in, void *out) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 51a459c3c..d324fe712 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -658,35 +658,23 @@ EXPORT_SYMBOL_GPL(xt_compat_target_to_user); struct xt_table_info *xt_alloc_table_info(unsigned int size) { - struct xt_table_info *newinfo; - int cpu; + struct xt_table_info *info = NULL; + size_t sz = sizeof(*info) + size; /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; - newinfo = kzalloc(XT_TABLE_INFO_SZ, GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_possible_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, - cpu_to_node(cpu)); - - if (newinfo->entries[cpu] == NULL) { - xt_free_table_info(newinfo); + if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!info) { + info = vmalloc(sz); + if (!info) return NULL; - } } - - return newinfo; + memset(info, 0, sizeof(*info)); + info->size = size; + return info; } EXPORT_SYMBOL(xt_alloc_table_info); @@ -694,9 +682,6 @@ void xt_free_table_info(struct xt_table_info *info) { int cpu; - for_each_possible_cpu(cpu) - kvfree(info->entries[cpu]); - if (info->jumpstack != NULL) { for_each_possible_cpu(cpu) kvfree(info->jumpstack[cpu]); @@ -705,7 +690,7 @@ void xt_free_table_info(struct xt_table_info *info) free_percpu(info->stackptr); - kfree(info); + kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); @@ -947,11 +932,9 @@ static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); - if (strlen(table->name)) { + if (*table->name) seq_printf(seq, "%s\n", table->name); - return seq_has_overflowed(seq); - } else - return 0; + return 0; } static const struct seq_operations xt_table_seq_ops = { @@ -1087,10 +1070,8 @@ static int xt_match_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); - if (*match->name == '\0') - return 0; - seq_printf(seq, "%s\n", match->name); - return seq_has_overflowed(seq); + if (*match->name) + seq_printf(seq, "%s\n", match->name); } return 0; } @@ -1142,10 +1123,8 @@ static int xt_target_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); - if (*target->name == '\0') - return 0; - seq_printf(seq, "%s\n", target->name); - return seq_has_overflowed(seq); + if (*target->name) + seq_printf(seq, "%s\n", target->name); } return 0; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 75747aecd..f3377ce1f 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -184,7 +184,6 @@ out: static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { - struct nf_conntrack_tuple t; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -202,11 +201,11 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err1; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); - ret = PTR_ERR(ct); - if (IS_ERR(ct)) + ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); + if (!ct) { + ret = -ENOMEM; goto err2; + } ret = 0; if ((info->ct_events || info->exp_events) && @@ -227,14 +226,14 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err3; } - - nf_conntrack_tmpl_insert(par->net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; err3: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err2: nf_ct_l3proto_module_put(par->family); err1: diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f407ebc13..29d2c31f4 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -126,6 +126,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index e762de5ee..8c3190e2f 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -277,6 +277,9 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par) "FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } + if (par->nft_compat) + return 0; + xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; @@ -299,6 +302,9 @@ static int tcpmss_tg6_check(const struct xt_tgchk_param *par) "FORWARD, OUTPUT and POSTROUTING hooks\n"); return -EINVAL; } + if (par->nft_compat) + return 0; + xt_ematch_foreach(ematch, e) if (find_syn_match(ematch)) return 0; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 292934d23..a747eb475 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,6 +152,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.daddr = info->gw.in6; fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index fab6eea1b..5b4743cc0 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -73,7 +73,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (dev == NULL && rt->rt6i_flags & RTF_LOCAL) ret |= XT_ADDRTYPE_LOCAL; - if (rt->rt6i_flags & RTF_ANYCAST) + if (ipv6_anycast_destination((struct dst_entry *)rt, addr)) ret |= XT_ADDRTYPE_ANYCAST; dst_release(&rt->dst); diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index 233452387..ebd41dc50 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -23,6 +23,7 @@ MODULE_ALIAS("ipt_mark"); MODULE_ALIAS("ip6t_mark"); MODULE_ALIAS("ipt_MARK"); MODULE_ALIAS("ip6t_MARK"); +MODULE_ALIAS("arpt_MARK"); static unsigned int mark_tg(struct sk_buff *skb, const struct xt_action_param *par) diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 89045982e..5669e5b45 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -9,14 +9,16 @@ */ /* Kernel module which implements the set match and SET target - * for netfilter/iptables. */ + * for netfilter/iptables. + */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> -#include <linux/netfilter/xt_set.h> +#include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_timeout.h> +#include <uapi/linux/netfilter/xt_set.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); @@ -52,6 +54,7 @@ static bool set_match_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_set_info_match_v0 *info = par->matchinfo; + ADT_OPT(opt, par->family, info->match_set.u.compat.dim, info->match_set.u.compat.flags, 0, UINT_MAX); @@ -68,10 +71,10 @@ compat_flags(struct xt_set_info_v0 *info) info->u.compat.dim = IPSET_DIM_ZERO; if (info->u.flags[0] & IPSET_MATCH_INV) info->u.compat.flags |= IPSET_INV_MATCH; - for (i = 0; i < IPSET_DIM_MAX-1 && info->u.flags[i]; i++) { + for (i = 0; i < IPSET_DIM_MAX - 1 && info->u.flags[i]; i++) { info->u.compat.dim++; if (info->u.flags[i] & IPSET_SRC) - info->u.compat.flags |= (1<<info->u.compat.dim); + info->u.compat.flags |= (1 << info->u.compat.dim); } } @@ -88,7 +91,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par) info->match_set.index); return -ENOENT; } - if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) { + if (info->match_set.u.flags[IPSET_DIM_MAX - 1] != 0) { pr_warn("Protocol error: set match dimension is over the limit!\n"); ip_set_nfnl_put(par->net, info->match_set.index); return -ERANGE; @@ -114,6 +117,7 @@ static bool set_match_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_set_info_match_v1 *info = par->matchinfo; + ADT_OPT(opt, par->family, info->match_set.dim, info->match_set.flags, 0, UINT_MAX); @@ -178,9 +182,10 @@ static bool set_match_v3(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_set_info_match_v3 *info = par->matchinfo; + int ret; + ADT_OPT(opt, par->family, info->match_set.dim, info->match_set.flags, info->flags, UINT_MAX); - int ret; if (info->packets.op != IPSET_COUNTER_NONE || info->bytes.op != IPSET_COUNTER_NONE) @@ -224,9 +229,10 @@ static bool set_match_v4(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_set_info_match_v4 *info = par->matchinfo; + int ret; + ADT_OPT(opt, par->family, info->match_set.dim, info->match_set.flags, info->flags, UINT_MAX); - int ret; if (info->packets.op != IPSET_COUNTER_NONE || info->bytes.op != IPSET_COUNTER_NONE) @@ -252,6 +258,7 @@ static unsigned int set_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v0 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.u.compat.dim, info->add_set.u.compat.flags, 0, UINT_MAX); ADT_OPT(del_opt, par->family, info->del_set.u.compat.dim, @@ -290,8 +297,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) return -ENOENT; } } - if (info->add_set.u.flags[IPSET_DIM_MAX-1] != 0 || - info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) { + if (info->add_set.u.flags[IPSET_DIM_MAX - 1] != 0 || + info->del_set.u.flags[IPSET_DIM_MAX - 1] != 0) { pr_warn("Protocol error: SET target dimension is over the limit!\n"); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); @@ -324,6 +331,7 @@ static unsigned int set_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v1 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.dim, info->add_set.flags, 0, UINT_MAX); ADT_OPT(del_opt, par->family, info->del_set.dim, @@ -392,6 +400,7 @@ static unsigned int set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v2 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.dim, info->add_set.flags, info->flags, info->timeout); ADT_OPT(del_opt, par->family, info->del_set.dim, @@ -399,8 +408,8 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) /* Normalize to fit into jiffies */ if (add_opt.ext.timeout != IPSET_NO_TIMEOUT && - add_opt.ext.timeout > UINT_MAX/MSEC_PER_SEC) - add_opt.ext.timeout = UINT_MAX/MSEC_PER_SEC; + add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC) + add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); if (info->del_set.index != IPSET_INVALID_ID) @@ -418,6 +427,8 @@ static unsigned int set_target_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v3 *info = par->targinfo; + int ret; + ADT_OPT(add_opt, par->family, info->add_set.dim, info->add_set.flags, info->flags, info->timeout); ADT_OPT(del_opt, par->family, info->del_set.dim, @@ -425,12 +436,10 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par) ADT_OPT(map_opt, par->family, info->map_set.dim, info->map_set.flags, 0, UINT_MAX); - int ret; - /* Normalize to fit into jiffies */ if (add_opt.ext.timeout != IPSET_NO_TIMEOUT && - add_opt.ext.timeout > UINT_MAX/MSEC_PER_SEC) - add_opt.ext.timeout = UINT_MAX/MSEC_PER_SEC; + add_opt.ext.timeout > UINT_MAX / MSEC_PER_SEC) + add_opt.ext.timeout = UINT_MAX / MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); if (info->del_set.index != IPSET_INVALID_ID) @@ -456,7 +465,6 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } - static int set_target_v3_checkentry(const struct xt_tgchk_param *par) { @@ -496,8 +504,7 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) !(par->hook_mask & (1 << NF_INET_FORWARD | 1 << NF_INET_LOCAL_OUT | 1 << NF_INET_POST_ROUTING))) { - pr_warn("mapping of prio or/and queue is allowed only" - "from OUTPUT/FORWARD/POSTROUTING chains\n"); + pr_warn("mapping of prio or/and queue is allowed only from OUTPUT/FORWARD/POSTROUTING chains\n"); return -EINVAL; } index = ip_set_nfnl_get_byindex(par->net, @@ -518,8 +525,7 @@ set_target_v3_checkentry(const struct xt_tgchk_param *par) if (info->add_set.dim > IPSET_DIM_MAX || info->del_set.dim > IPSET_DIM_MAX || info->map_set.dim > IPSET_DIM_MAX) { - pr_warn("Protocol error: SET target dimension " - "is over the limit!\n"); + pr_warn("Protocol error: SET target dimension is over the limit!\n"); if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(par->net, info->add_set.index); if (info->del_set.index != IPSET_INVALID_ID) @@ -545,7 +551,6 @@ set_target_v3_destroy(const struct xt_tgdtor_param *par) ip_set_nfnl_put(par->net, info->map_set.index); } - static struct xt_match set_matches[] __read_mostly = { { .name = "set", diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index e092cb046..43e26c881 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -205,6 +205,7 @@ static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { + struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (!sk) @@ -226,6 +227,10 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_TRANSPARENT) transparent = xt_socket_sk_is_transparent(sk); + if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && + transparent) + pskb->mark = sk->sk_mark; + if (sk != skb->sk) sock_gen_put(sk); @@ -247,7 +252,7 @@ socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) } static bool -socket_mt4_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } @@ -371,9 +376,10 @@ static struct sock *xt_socket_lookup_slow_v6(const struct sk_buff *skb, } static bool -socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) +socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; + struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (!sk) @@ -395,6 +401,10 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_TRANSPARENT) transparent = xt_socket_sk_is_transparent(sk); + if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && + transparent) + pskb->mark = sk->sk_mark; + if (sk != skb->sk) sock_gen_put(sk); @@ -428,6 +438,19 @@ static int socket_mt_v2_check(const struct xt_mtchk_param *par) return 0; } +static int socket_mt_v3_check(const struct xt_mtchk_param *par) +{ + const struct xt_socket_mtinfo3 *info = + (struct xt_socket_mtinfo3 *)par->matchinfo; + + if (info->flags & ~XT_SOCKET_FLAGS_V3) { + pr_info("unknown flags 0x%x\n", + info->flags & ~XT_SOCKET_FLAGS_V3); + return -EINVAL; + } + return 0; +} + static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", @@ -442,7 +465,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, - .match = socket_mt4_v1_v2, + .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | @@ -454,7 +477,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 1, .family = NFPROTO_IPV6, - .match = socket_mt6_v1_v2, + .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | @@ -466,7 +489,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 2, .family = NFPROTO_IPV4, - .match = socket_mt4_v1_v2, + .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v2_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | @@ -478,7 +501,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .name = "socket", .revision = 2, .family = NFPROTO_IPV6, - .match = socket_mt6_v1_v2, + .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v2_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | @@ -486,6 +509,30 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .me = THIS_MODULE, }, #endif + { + .name = "socket", + .revision = 3, + .family = NFPROTO_IPV4, + .match = socket_mt4_v1_v2_v3, + .checkentry = socket_mt_v3_check, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +#ifdef XT_SOCKET_HAVE_IPV6 + { + .name = "socket", + .revision = 3, + .family = NFPROTO_IPV6, + .match = socket_mt6_v1_v2_v3, + .checkentry = socket_mt_v3_check, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +#endif }; static int __init socket_mt_init(void) |