diff options
65 files changed, 646 insertions, 680 deletions
diff --git a/Documentation/networking/netfilter-sysctl.txt b/Documentation/networking/netfilter-sysctl.txt new file mode 100644 index 000000000000..55791e50e169 --- /dev/null +++ b/Documentation/networking/netfilter-sysctl.txt @@ -0,0 +1,10 @@ +/proc/sys/net/netfilter/* Variables: + +nf_log_all_netns - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + By default, only init_net namespace can log packets into kernel log + with LOG target; this aims to prevent containers from flooding host + kernel log. If enabled, this target also works in other network + namespaces. This variable is only accessible from init_net. diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5117e4d2ddfa..be378cf47fcc 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -167,6 +167,7 @@ struct xt_match { const char *table; unsigned int matchsize; + unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif @@ -207,6 +208,7 @@ struct xt_target { const char *table; unsigned int targetsize; + unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif @@ -287,6 +289,13 @@ int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); +int xt_match_to_user(const struct xt_entry_match *m, + struct xt_entry_match __user *u); +int xt_target_to_user(const struct xt_entry_target *t, + struct xt_entry_target __user *u); +int xt_data_to_user(void __user *dst, const void *src, + int usersize, int size); + void *xt_copy_counters_from_user(const void __user *user, unsigned int len, struct xt_counters_info *info, bool compat); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f63b7e2ac11..c6a78e1892b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -585,7 +585,6 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header - * @nfctinfo: Relationship of this skb to the connection * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs @@ -598,7 +597,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function - * @nfct: Associated connection, if any + * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index @@ -671,7 +670,7 @@ struct sk_buff { struct sec_path *sp; #endif #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - struct nf_conntrack *nfct; + unsigned long _nfct; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info *nf_bridge; @@ -724,7 +723,6 @@ struct sk_buff { __u8 pkt_type:3; __u8 pfmemalloc:1; __u8 ignore_df:1; - __u8 nfctinfo:3; __u8 nf_trace:1; __u8 ip_summed:2; @@ -841,6 +839,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) +#define SKB_NFCT_PTRMASK ~(7UL) /** * skb_dst - returns skb dst_entry * @skb: buffer @@ -3558,6 +3557,15 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, skb->csum = csum_add(skb->csum, delta); } +static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + return (void *)(skb->_nfct & SKB_NFCT_PTRMASK); +#else + return NULL; +#endif +} + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) @@ -3586,8 +3594,8 @@ static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) static inline void nf_reset(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put(skb->nfct); - skb->nfct = NULL; + nf_conntrack_put(skb_nfct(skb)); + skb->_nfct = 0; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nf_bridge_put(skb->nf_bridge); @@ -3607,10 +3615,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - dst->nfct = src->nfct; - nf_conntrack_get(src->nfct); - if (copy) - dst->nfctinfo = src->nfctinfo; + dst->_nfct = src->_nfct; + nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dst->nf_bridge = src->nf_bridge; @@ -3625,7 +3631,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put(dst->nfct); + nf_conntrack_put(skb_nfct(dst)); #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nf_bridge_put(dst->nf_bridge); @@ -3657,9 +3663,7 @@ static inline bool skb_irq_freeable(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_XFRM) !skb->sp && #endif -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - !skb->nfct && -#endif + !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index cd6018a9ee24..7bdfa7d78363 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1421,7 +1421,7 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest) static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) { - if (atomic_dec_return(&dest->refcnt) < 0) + if (atomic_dec_and_test(&dest->refcnt)) kfree(dest); } @@ -1554,10 +1554,12 @@ static inline void ip_vs_notrack(struct sk_buff *skb) struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (!ct || !nf_ct_is_untracked(ct)) { - nf_conntrack_put(skb->nfct); - skb->nfct = &nf_ct_untracked_get()->ct_general; - skb->nfctinfo = IP_CT_NEW; - nf_conntrack_get(skb->nfct); + struct nf_conn *untracked; + + nf_conntrack_put(&ct->ct_general); + untracked = nf_ct_untracked_get(); + nf_conntrack_get(&untracked->ct_general); + nf_ct_set(skb, untracked, IP_CT_NEW); } #endif } diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 919e4e8af327..6ff32815641b 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -14,6 +14,7 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; #ifdef CONFIG_NF_CT_PROTO_DCCP extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4; diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index eaea968f8657..c59b82456f89 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -5,6 +5,7 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; #ifdef CONFIG_NF_CT_PROTO_DCCP extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5916aa9ab3f0..f540f9ad2af4 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -34,6 +34,7 @@ union nf_conntrack_proto { struct ip_ct_sctp sctp; struct ip_ct_tcp tcp; struct nf_ct_gre gre; + unsigned int tmpl_padto; }; union nf_conntrack_expect_proto { @@ -75,7 +76,7 @@ struct nf_conn { /* Usage count in here is 1 for hash table, 1 per skb, * plus 1 for any connection(s) we are `master' for * - * Hint, SKB address this struct and refcnt via skb->nfct and + * Hint, SKB address this struct and refcnt via skb->_nfct and * helpers nf_conntrack_get() and nf_conntrack_put(). * Helper nf_ct_put() equals nf_conntrack_put() by dec refcnt, * beware nf_ct_get() is different and don't inc refcnt. @@ -162,12 +163,16 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, int nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack); +#define NFCT_INFOMASK 7UL +#define NFCT_PTRMASK ~(NFCT_INFOMASK) + /* Return conntrack_info and tuple hash for given skb. */ static inline struct nf_conn * nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) { - *ctinfo = skb->nfctinfo; - return (struct nf_conn *)skb->nfct; + *ctinfo = skb->_nfct & NFCT_INFOMASK; + + return (struct nf_conn *)(skb->_nfct & NFCT_PTRMASK); } /* decrement reference count on a conntrack */ @@ -341,6 +346,12 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, gfp_t flags); void nf_ct_tmpl_free(struct nf_conn *tmpl); +static inline void +nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) +{ + skb->_nfct = (unsigned long)ct | info; +} + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 62e17d1319ff..84ec7ca5f195 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -62,7 +62,7 @@ int __nf_conntrack_confirm(struct sk_buff *skb); /* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int nf_conntrack_confirm(struct sk_buff *skb) { - struct nf_conn *ct = (struct nf_conn *)skb->nfct; + struct nf_conn *ct = (struct nf_conn *)skb_nfct(skb); int ret = NF_ACCEPT; if (ct && !nf_ct_is_untracked(ct)) { diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index e7b836590f0b..85e993e278d5 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -55,7 +55,7 @@ struct nf_conntrack_l4proto { void (*destroy)(struct nf_conn *ct); int (*error)(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info *ctinfo, + unsigned int dataoff, u_int8_t pf, unsigned int hooknum); /* Print out the per-protocol part of the tuple. Return like seq_* */ diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 450f87f95415..42e0696f38d8 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -51,6 +51,9 @@ struct nf_logger { struct module *me; }; +/* sysctl_nf_log_all_netns - allow LOG target in all network namespaces */ +extern int sysctl_nf_log_all_netns; + /* Function to register/unregister log function. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger); void nf_log_unregister(struct nf_logger *logger); diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index cf799fc3fdec..17724c62de97 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -69,19 +69,6 @@ struct nf_sctp_net { }; #endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE -enum udplite_conntrack { - UDPLITE_CT_UNREPLIED, - UDPLITE_CT_REPLIED, - UDPLITE_CT_MAX -}; - -struct nf_udplite_net { - struct nf_proto_net pn; - unsigned int timeouts[UDPLITE_CT_MAX]; -}; -#endif - struct nf_ip_net { struct nf_generic_net generic; struct nf_tcp_net tcp; @@ -94,9 +81,6 @@ struct nf_ip_net { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net sctp; #endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE - struct nf_udplite_net udplite; -#endif }; struct ct_pcpu { diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e3f27e09eb2b..7b730cab99bd 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -860,6 +860,10 @@ enum nft_rt_attributes { * @NFT_CT_PROTOCOL: conntrack layer 4 protocol * @NFT_CT_PROTO_SRC: conntrack layer 4 protocol source * @NFT_CT_PROTO_DST: conntrack layer 4 protocol destination + * @NFT_CT_LABELS: conntrack labels + * @NFT_CT_PKTS: conntrack packets + * @NFT_CT_BYTES: conntrack bytes + * @NFT_CT_AVGPKT: conntrack average bytes per packet */ enum nft_ct_keys { NFT_CT_STATE, @@ -878,6 +882,7 @@ enum nft_ct_keys { NFT_CT_LABELS, NFT_CT_PKTS, NFT_CT_BYTES, + NFT_CT_AVGPKT, }; /** diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c index 517e78befcb2..61a9f1be1263 100644 --- a/net/bridge/netfilter/ebt_limit.c +++ b/net/bridge/netfilter/ebt_limit.c @@ -105,6 +105,7 @@ static struct xt_match ebt_limit_mt_reg __read_mostly = { .match = ebt_limit_mt, .checkentry = ebt_limit_mt_check, .matchsize = sizeof(struct ebt_limit_info), + .usersize = offsetof(struct ebt_limit_info, prev), #ifdef CONFIG_COMPAT .compatsize = sizeof(struct ebt_compat_limit_info), #endif diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index e88bd4827ac1..98b9c8e8615e 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -78,7 +78,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, unsigned int bitmask; /* FIXME: Disabled from containers until syslog ns is supported */ - if (!net_eq(net, &init_net)) + if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns) return; spin_lock_bh(&ebt_log_lock); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 537e3d506fc2..79b69917f521 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1346,56 +1346,72 @@ static int update_counters(struct net *net, const void __user *user, hlp.num_counters, user, len); } -static inline int ebt_make_matchname(const struct ebt_entry_match *m, - const char *base, char __user *ubase) +static inline int ebt_obj_to_user(char __user *um, const char *_name, + const char *data, int entrysize, + int usersize, int datasize) { - char __user *hlp = ubase + ((char *)m - base); - char name[EBT_FUNCTION_MAXNAMELEN] = {}; + char name[EBT_FUNCTION_MAXNAMELEN] = {0}; /* ebtables expects 32 bytes long names but xt_match names are 29 bytes * long. Copy 29 bytes and fill remaining bytes with zeroes. */ - strlcpy(name, m->u.match->name, sizeof(name)); - if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) + strlcpy(name, _name, sizeof(name)); + if (copy_to_user(um, name, EBT_FUNCTION_MAXNAMELEN) || + put_user(datasize, (int __user *)(um + EBT_FUNCTION_MAXNAMELEN)) || + xt_data_to_user(um + entrysize, data, usersize, datasize)) return -EFAULT; + return 0; } -static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, - const char *base, char __user *ubase) +static inline int ebt_match_to_user(const struct ebt_entry_match *m, + const char *base, char __user *ubase) { - char __user *hlp = ubase + ((char *)w - base); - char name[EBT_FUNCTION_MAXNAMELEN] = {}; + return ebt_obj_to_user(ubase + ((char *)m - base), + m->u.match->name, m->data, sizeof(*m), + m->u.match->usersize, m->match_size); +} - strlcpy(name, w->u.watcher->name, sizeof(name)); - if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) - return -EFAULT; - r |