diff options
Diffstat (limited to 'include/linux/netfilter.h')
| -rw-r--r-- | include/linux/netfilter.h | 534 |
1 files changed, 352 insertions, 182 deletions
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index de70f7b45b68..efbbfa770d66 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETFILTER_H #define __LINUX_NETFILTER_H @@ -9,57 +10,174 @@ #include <linux/in6.h> #include <linux/wait.h> #include <linux/list.h> -#include <uapi/linux/netfilter.h> -#ifdef CONFIG_NETFILTER +#include <linux/static_key.h> +#include <linux/module.h> +#include <linux/netfilter_defs.h> +#include <linux/netdevice.h> +#include <linux/sockptr.h> +#include <net/net_namespace.h> + static inline int NF_DROP_GETERR(int verdict) { return -(verdict >> NF_VERDICT_QBITS); } +static __always_inline int +NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) +{ + BUILD_BUG_ON(err > 0xffff); + + kfree_skb_reason(skb, reason); + + return ((err << 16) | NF_STOLEN); +} + static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const unsigned long *ul1 = (const unsigned long *)a1; + const unsigned long *ul2 = (const unsigned long *)a2; + + return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; +#else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; +#endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, union nf_inet_addr *result, const union nf_inet_addr *mask) { +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const unsigned long *ua = (const unsigned long *)a1; + unsigned long *ur = (unsigned long *)result; + const unsigned long *um = (const unsigned long *)mask; + + ur[0] = ua[0] & um[0]; + ur[1] = ua[1] & um[1]; +#else result->all[0] = a1->all[0] & mask->all[0]; result->all[1] = a1->all[1] & mask->all[1]; result->all[2] = a1->all[2] & mask->all[2]; result->all[3] = a1->all[3] & mask->all[3]; +#endif } -extern int netfilter_init(void); - -/* Largest hook number + 1 */ -#define NF_MAX_HOOKS 8 +int netfilter_init(void); struct sk_buff; -typedef unsigned int nf_hookfn(unsigned int hooknum, +struct nf_hook_ops; + +struct sock; + +struct nf_hook_state { + u8 hook; + u8 pf; + struct net_device *in; + struct net_device *out; + struct sock *sk; + struct net *net; + int (*okfn)(struct net *, struct sock *, struct sk_buff *); +}; + +typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)); + const struct nf_hook_state *state); +enum nf_hook_ops_type { + NF_HOOK_OP_UNDEFINED, + NF_HOOK_OP_NF_TABLES, + NF_HOOK_OP_BPF, + NF_HOOK_OP_NFT_FT, +}; struct nf_hook_ops { - struct list_head list; + struct list_head list; + struct rcu_head rcu; /* User fills in from here down. */ - nf_hookfn *hook; - struct module *owner; - u_int8_t pf; - unsigned int hooknum; + nf_hookfn *hook; + struct net_device *dev; + void *priv; + u8 pf; + enum nf_hook_ops_type hook_ops_type:8; + unsigned int hooknum; /* Hooks are ordered in ascending priority. */ - int priority; + int priority; +}; + +struct nf_hook_entry { + nf_hookfn *hook; + void *priv; +}; + +struct nf_hook_entries_rcu_head { + struct rcu_head head; + void *allocation; }; +struct nf_hook_entries { + u16 num_hook_entries; + /* padding */ + struct nf_hook_entry hooks[]; + + /* trailer: pointers to original orig_ops of each hook, + * followed by rcu_head and scratch space used for freeing + * the structure via call_rcu. + * + * This is not part of struct nf_hook_entry since its only + * needed in slow path (hook register/unregister): + * const struct nf_hook_ops *orig_ops[] + * + * For the same reason, we store this at end -- its + * only needed when a hook is deleted, not during + * packet path processing: + * struct nf_hook_entries_rcu_head head + */ +}; + +#ifdef CONFIG_NETFILTER +static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) +{ + unsigned int n = e->num_hook_entries; + const void *hook_end; + + hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ + + return (struct nf_hook_ops **)hook_end; +} + +static inline int +nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, + struct nf_hook_state *state) +{ + return entry->hook(entry->priv, skb, state); +} + +static inline void nf_hook_state_init(struct nf_hook_state *p, + unsigned int hook, + u_int8_t pf, + struct net_device *indev, + struct net_device *outdev, + struct sock *sk, + struct net *net, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + p->hook = hook; + p->pf = pf; + p->in = indev; + p->out = outdev; + p->sk = sk; + p->net = net; + p->okfn = okfn; +} + + + struct nf_sockopt_ops { struct list_head list; @@ -68,82 +186,97 @@ struct nf_sockopt_ops { /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; - int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); -#ifdef CONFIG_COMPAT - int (*compat_set)(struct sock *sk, int optval, - void __user *user, unsigned int len); -#endif + int (*set)(struct sock *sk, int optval, sockptr_t arg, + unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); -#ifdef CONFIG_COMPAT - int (*compat_get)(struct sock *sk, int optval, - void __user *user, int *len); -#endif /* Use the module struct to lock set/get code in place */ struct module *owner; }; /* Function to register/unregister hook points. */ -int nf_register_hook(struct nf_hook_ops *reg); -void nf_unregister_hook(struct nf_hook_ops *reg); -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); -extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - -#if defined(CONFIG_JUMP_LABEL) -#include <linux/static_key.h> +#ifdef CONFIG_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) -{ - if (__builtin_constant_p(pf) && - __builtin_constant_p(hook)) - return static_key_false(&nf_hooks_needed[pf][hook]); - - return !list_empty(&nf_hooks[pf][hook]); -} -#else -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) -{ - return !list_empty(&nf_hooks[pf][hook]); -} #endif -int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb, - struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh); +int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, + const struct nf_hook_entries *e, unsigned int i); +void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, + const struct nf_hook_entries *e); /** - * nf_hook_thresh - call a netfilter hook - * + * nf_hook - call a netfilter hook + * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) -{ - if (nf_hooks_active(pf, hook)) - return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh); - return 1; -} - -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN); + struct nf_hook_entries *hook_head = NULL; + int ret = 1; + +#ifdef CONFIG_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return 1; +#endif + + rcu_read_lock(); + switch (pf) { + case NFPROTO_IPV4: + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + case NFPROTO_ARP: +#ifdef CONFIG_NETFILTER_FAMILY_ARP + if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) + break; + hook_head = rcu_dereference(net->nf.hooks_arp[hook]); +#endif + break; + case NFPROTO_BRIDGE: +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); +#endif + break; + default: + WARN_ON_ONCE(1); + break; + } + + if (hook_head) { + struct nf_hook_state state; + + nf_hook_state_init(&state, hook, pf, indev, outdev, + sk, net, okfn); + + ret = nf_hook_slow(skb, &state, hook_head, 0); + } + rcu_read_unlock(); + + return ret; } - + /* Activate hook; either okfn or kfree_skb called, unless a hook returns NF_STOLEN (in which case, it's up to the hook to deal with the consequences). @@ -162,147 +295,145 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, */ static inline int -NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *), int thresh) -{ - int ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, thresh); - if (ret == 1) - ret = okfn(skb); - return ret; -} - -static inline int -NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *), bool cond) +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) { int ret; if (!cond || - ((ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, INT_MIN)) == 1)) - ret = okfn(skb); + ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1)) + ret = okfn(net, sk, skb); return ret; } static inline int -NF_HOOK(uint8_t pf, unsigned int hook, struct sk_buff *skb, +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); + if (ret == 1) + ret = okfn(net, sk, skb); + return ret; +} + +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return NF_HOOK_THRESH(pf, hook, skb, in, out, okfn, INT_MIN); + struct nf_hook_entries *hook_head = NULL; + +#ifdef CONFIG_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return; +#endif + + rcu_read_lock(); + switch (pf) { + case NFPROTO_IPV4: + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + default: + WARN_ON_ONCE(1); + break; + } + + if (hook_head) { + struct nf_hook_state state; + + nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); + + nf_hook_slow_list(head, &state, hook_head); + } + rcu_read_unlock(); } /* Call setsockopt() */ -int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, +int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -#ifdef CONFIG_COMPAT -int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, unsigned int len); -int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int *len); -#endif - -/* Call this before modifying an existing packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); struct flowi; struct nf_queue_entry; -struct nf_afinfo { - unsigned short family; - __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - __sum16 (*checksum_partial)(struct sk_buff *skb, - unsigned int hook, - unsigned int dataoff, - unsigned int len, - u_int8_t protocol); - int (*route)(struct net *net, struct dst_entry **dst, - struct flowi *fl, bool strict); - void (*saveroute)(const struct sk_buff *skb, - struct nf_queue_entry *entry); - int (*reroute)(struct sk_buff *skb, - const struct nf_queue_entry *entry); - int route_key_size; -}; +__sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol, + unsigned short family); -extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; -static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) -{ - return rcu_dereference(nf_afinfo[family]); -} - -static inline __sum16 -nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, - u_int8_t protocol, unsigned short family) -{ - const struct nf_afinfo *afinfo; - __sum16 csum = 0; - - rcu_read_lock(); - afinfo = nf_get_afinfo(family); - if (afinfo) - csum = afinfo->checksum(skb, hook, dataoff, protocol); - rcu_read_unlock(); - return csum; -} +__sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, unsigned int len, + u_int8_t protocol, unsigned short family); +int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, + bool strict, unsigned short family); -static inline __sum16 -nf_checksum_partial(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol, unsigned short family) -{ - const struct nf_afinfo *afinfo; - __sum16 csum = 0; +#include <net/flow.h> - rcu_read_lock(); - afinfo = nf_get_afinfo(family); - if (afinfo) - csum = afinfo->checksum_partial(skb, hook, dataoff, len, - protocol); - rcu_read_unlock(); - return csum; -} +struct nf_conn; +enum nf_nat_manip_type; +struct nlattr; -extern int nf_register_afinfo(const struct nf_afinfo *afinfo); -extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo); +struct nf_nat_hook { + int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, + const struct nlattr *attr); + void (*decode_session)(struct sk_buff *skb, struct flowi *fl); + void (*remove_nat_bysrc)(struct nf_conn *ct); +}; -#include <net/flow.h> -extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); +extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { -#ifdef CONFIG_NF_NAT_NEEDED - void (*decodefn)(struct sk_buff *, struct flowi *); +#if IS_ENABLED(CONFIG_NF_NAT) + const struct nf_nat_hook *nat_hook; rcu_read_lock(); - decodefn = rcu_dereference(nf_nat_decode_session_hook); - if (decodefn) - decodefn(skb, fl); + nat_hook = rcu_dereference(nf_nat_hook); + if (nat_hook && nat_hook->decode_session) + nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) -#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) +static inline int +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) +{ + return okfn(net, sk, skb); +} + +static inline int +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + return okfn(net, sk, skb); +} + +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return okfn(skb); + /* nothing to do */ } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, + +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } @@ -313,28 +444,67 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #endif /*CONFIG_NETFILTER*/ -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; -extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <linux/netfilter/nf_conntrack_zones_common.h> + +void nf_ct_attach(struct sk_buff *, const struct sk_buff *); +void nf_ct_set_closing(struct nf_conntrack *nfct); +struct nf_conntrack_tuple; +bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb); +#else +static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} +struct nf_conntrack_tuple; +static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb) +{ + return false; +} +#endif struct nf_conn; +enum ip_conntrack_info; + +struct nf_ct_hook { + int (*update)(struct net *net, struct sk_buff *skb); + void (*destroy)(struct nf_conntrack *); + bool (*get_tuple_skb)(struct nf_conntrack_tuple *, + const struct sk_buff *); + void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); + void (*set_closing)(struct nf_conntrack *nfct); + int (*confirm)(struct sk_buff *skb); + u32 (*get_id)(const struct nf_conntrack *nfct); +}; +extern const struct nf_ct_hook __rcu *nf_ct_hook; + struct nlattr; -struct nfq_ct_hook { +struct nfnl_ct_hook { size_t (*build_size)(const struct nf_conn *ct); - int (*build)(struct sk_buff *skb, struct nf_conn *ct); + int (*build)(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); + int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report); + void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; +extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; -struct nfq_ct_nat_hook { - void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off); +struct nf_defrag_hook { + struct module *owner; + int (*enable)(struct net *net); + void (*disable)(struct net *net); }; -extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; -#else -static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} -#endif +extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook; +extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook; + +/* + * Contains bitmask of ctnetlink event subscribers, if any. + * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. + */ +extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ |
