diff options
Diffstat (limited to 'include/linux/skbuff.h')
| -rw-r--r-- | include/linux/skbuff.h | 335 |
1 files changed, 259 insertions, 76 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0d1b2c3f127b..6d58fa8a65fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -245,6 +245,7 @@ struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; +struct skb_ext; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { @@ -254,7 +255,6 @@ struct nf_conntrack { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { - refcount_t use; enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, @@ -327,26 +327,49 @@ struct skb_frag_struct { #endif }; +/** + * skb_frag_size - Returns the size of a skb fragment + * @frag: skb fragment + */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->size; } +/** + * skb_frag_size_set - Sets the size of a skb fragment + * @frag: skb fragment + * @size: size of fragment + */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->size = size; } +/** + * skb_frag_size_add - Incrementes the size of a skb fragment by %delta + * @frag: skb fragment + * @delta: value to add + */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->size += delta; } +/** + * skb_frag_size_sub - Decrements the size of a skb fragment by %delta + * @frag: skb fragment + * @delta: value to subtract + */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->size -= delta; } +/** + * skb_frag_must_loop - Test if %p is a high memory page + * @p: fragment's page + */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) @@ -481,10 +504,11 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg) } void sock_zerocopy_put(struct ubuf_info *uarg); -void sock_zerocopy_put_abort(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); +int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); @@ -589,7 +613,7 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** +/** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list @@ -615,6 +639,8 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @offload_fwd_mark: Packet was L2-forwarded in hardware + * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @tc_redirected: packet was redirected by a tc action @@ -631,8 +657,8 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices - * @xmit_more: More SKBs are pending for this queue * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -644,7 +670,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB - * @napi_id: id of the NAPI struct this skb came from + * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark * @vlan_proto: vlan encapsulation protocol @@ -662,6 +688,7 @@ typedef unsigned char *sk_buff_data_t; * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c + * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { @@ -709,15 +736,9 @@ struct sk_buff { struct list_head tcp_tsorted_anchor; }; -#ifdef CONFIG_XFRM - struct sec_path *sp; -#endif #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - struct nf_bridge_info *nf_bridge; -#endif unsigned int len, data_len; __u16 mac_len, @@ -742,9 +763,10 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - xmit_more:1, pfmemalloc:1; - +#ifdef CONFIG_SKB_EXTENSIONS + __u8 active_extensions; +#endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -777,6 +799,14 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#else +#define PKT_VLAN_PRESENT_BIT 0 +#endif +#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + __u8 __pkt_vlan_present_offset[0]; + __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; @@ -784,13 +814,13 @@ struct sk_buff { #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif - __u8 ipvs_property:1; + __u8 ipvs_property:1; __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; - __u8 offload_mr_fwd_mark:1; + __u8 offload_l3_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; @@ -858,6 +888,11 @@ struct sk_buff { *data; unsigned int truesize; refcount_t users; + +#ifdef CONFIG_SKB_EXTENSIONS + /* only useable after checking ->active_extensions != 0 */ + struct skb_ext *extensions; +#endif }; #ifdef __KERNEL__ @@ -869,7 +904,10 @@ struct sk_buff { #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 -/* Returns true if the skb was allocated from PFMEMALLOC reserves */ +/** + * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves + * @skb: buffer + */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); @@ -891,7 +929,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { - /* If refdst was not refcounted, check we still are in a + /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && @@ -938,6 +976,10 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } +/** + * skb_rtable - Returns the skb &rtable + * @skb: buffer + */ static inline struct rtable *skb_rtable(const struct sk_buff *skb) { return (struct rtable *)skb_dst(skb); @@ -952,6 +994,10 @@ static inline bool skb_pkt_type_ok(u32 ptype) return ptype <= PACKET_OTHERHOST; } +/** + * skb_napi_id - Returns the skb's NAPI id + * @skb: buffer + */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL @@ -961,7 +1007,12 @@ static inline unsigned int skb_napi_id(const struct sk_buff *skb) #endif } -/* decrement the reference count and return true if we can free the skb */ +/** + * skb_unref - decrement the skb's reference count + * @skb: buffer + * + * Returns true if we can free the skb. + */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) @@ -991,6 +1042,16 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); +struct sk_buff *build_skb_around(struct sk_buff *skb, + void *data, unsigned int frag_size); + +/** + * alloc_skb - allocate a network buffer + * @size: size to allocate + * @priority: allocation mask + * + * This function is a convenient wrapper around __alloc_skb(). + */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { @@ -1033,6 +1094,13 @@ static inline bool skb_fclone_busy(const struct sock *sk, fclones->skb2.sk == sk; } +/** + * alloc_skb_fclone - allocate a network buffer from fclone cache + * @size: size to allocate + * @priority: allocation mask + * + * This function is a convenient wrapper around __alloc_skb(). + */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { @@ -1190,11 +1258,19 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); #ifdef CONFIG_NET +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); #else +static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { @@ -1207,7 +1283,12 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif -bool __skb_flow_dissect(const struct sk_buff *skb, +struct bpf_flow_dissector; +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen); + +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -1217,8 +1298,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, @@ -1226,18 +1307,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_dissector, flow, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, + flow, NULL, 0, 0, 0, flags); } static inline bool -skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic(const struct net *net, + const struct sk_buff *skb, struct flow_keys_basic *flow, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -1317,10 +1399,14 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, + bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { - sock_zerocopy_get(uarg); + if (unlikely(have_ref && *have_ref)) + *have_ref = false; + else + sock_zerocopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } @@ -1365,7 +1451,7 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - sock_zerocopy_put_abort(uarg); + sock_zerocopy_put_abort(uarg, false); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } @@ -1741,8 +1827,6 @@ static inline void skb_queue_head_init_class(struct sk_buff_head *list, * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ -void skb_insert(struct sk_buff *old, struct sk_buff *newsk, - struct sk_buff_head *list); static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) @@ -1868,12 +1952,12 @@ static inline void __skb_queue_before(struct sk_buff_head *list, * * A buffer cannot be placed on two lists at the same time. */ -void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } +void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail @@ -1885,12 +1969,12 @@ static inline void __skb_queue_head(struct sk_buff_head *list, * * A buffer cannot be placed on two lists at the same time. */ -void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } +void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with @@ -1917,7 +2001,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ -struct sk_buff *skb_dequeue(struct sk_buff_head *list); static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); @@ -1925,6 +2008,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) __skb_unlink(skb, list); return skb; } +struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue @@ -1934,7 +2018,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ -struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); @@ -1942,6 +2025,7 @@ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) __skb_unlink(skb, list); return skb; } +struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) @@ -2027,8 +2111,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); -#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags) -#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb)) #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET @@ -2408,18 +2490,16 @@ static inline void skb_pop_mac_header(struct sk_buff *skb) skb->mac_header = skb->network_header; } -static inline void skb_probe_transport_header(struct sk_buff *skb, - const int offset_hint) +static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); - else - skb_set_transport_header(skb, offset_hint); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) @@ -2524,10 +2604,8 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { - if (unlikely(skb_is_nonlinear(skb))) { - WARN_ON(1); + if (WARN_ON(skb_is_nonlinear(skb))) return; - } skb->len = len; skb_set_tail_pointer(skb, len); } @@ -2634,13 +2712,13 @@ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ -void skb_queue_purge(struct sk_buff_head *list); static inline void __skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb(skb); } +void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); @@ -3009,7 +3087,7 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) } /** - * skb_put_padto - increase size and pad an skbuff up to a minimal size + * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error @@ -3204,6 +3282,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. + * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) @@ -3301,17 +3380,17 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err); + int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, @@ -3325,6 +3404,9 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); +int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len, + struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); @@ -3345,7 +3427,6 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); -int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, @@ -3464,16 +3545,25 @@ static inline ktime_t skb_get_ktime(const struct sk_buff *skb) /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from - * @stamp: pointer to struct timeval to store stamp in + * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, - struct timeval *stamp) + struct __kernel_old_timeval *stamp) +{ + *stamp = ns_to_kernel_old_timeval(skb->tstamp); +} + +static inline void skb_get_new_timestamp(const struct sk_buff *skb, + struct __kernel_sock_timeval *stamp) { - *stamp = ktime_to_timeval(skb->tstamp); + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, @@ -3482,6 +3572,15 @@ static inline void skb_get_timestampns(const struct sk_buff *skb, *stamp = ktime_to_timespec(skb->tstamp); } +static inline void skb_get_new_timestampns(const struct sk_buff *skb, + struct __kernel_timespec *stamp) +{ + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_nsec = ts.tv_nsec; +} + static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); @@ -3886,18 +3985,97 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) atomic_inc(&nfct->use); } #endif + +#ifdef CONFIG_SKB_EXTENSIONS +enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) + SKB_EXT_BRIDGE_NF, +#endif +#ifdef CONFIG_XFRM + SKB_EXT_SEC_PATH, +#endif + SKB_EXT_NUM, /* must be last */ +}; + +/** + * struct skb_ext - sk_buff extensions + * @refcnt: 1 on allocation, deallocated on 0 + * @offset: offset to add to @data to obtain extension address + * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units + * @data: start of extension data, variable sized + * + * Note: offsets/lengths are stored in chunks of 8 bytes, this allows + * to use 'u8' types while allowing up to 2kb worth of extension data. + */ +struct skb_ext { + refcount_t refcnt; + u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ + u8 chunks; /* same */ + char data[0] __aligned(8); +}; + +void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); +void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); +void __skb_ext_put(struct skb_ext *ext); + +static inline void skb_ext_put(struct sk_buff *skb) +{ + if (skb->active_extensions) + __skb_ext_put(skb->extensions); +} + +static inline void __skb_ext_copy(struct sk_buff *dst, + const struct sk_buff *src) +{ + dst->active_extensions = src->active_extensions; + + if (src->active_extensions) { + struct skb_ext *ext = src->extensions; + + refcount_inc(&ext->refcnt); + dst->extensions = ext; + } +} + +static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) +{ + skb_ext_put(dst); + __skb_ext_copy(dst, src); +} + +static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) +{ + return !!ext->offset[i]; +} + +static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) +{ + return skb->active_extensions & (1 << id); +} + +static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { - if (nf_bridge && refcount_dec_and_test(&nf_bridge->use)) - kfree(nf_bridge); + if (skb_ext_exist(skb, id)) + __skb_ext_del(skb, id); } -static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) + +static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { - if (nf_bridge) - refcount_inc(&nf_bridge->use); + if (skb_ext_exist(skb, id)) { + struct skb_ext *ext = skb->extensions; + + return (void *)ext + (ext->offset[id] << 3); + } + + return NULL; } -#endif /* CONFIG_BRIDGE_NETFILTER */ +#else +static inline void skb_ext_put(struct sk_buff *skb) {} +static inline void skb_ext_del(struct sk_buff *skb, int unused) {} +static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} +static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} +#endif /* CONFIG_SKB_EXTENSIONS */ + static inline void nf_reset(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) @@ -3905,8 +4083,7 @@ static inline void nf_reset(struct sk_buff *skb) skb->_nfct = 0; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - nf_bridge_put(skb->nf_bridge); - skb->nf_bridge = NULL; + skb_ext_del(skb, SKB_EXT_BRIDGE_NF); #endif } @@ -3924,7 +4101,7 @@ static inline void ipvs_reset(struct sk_buff *skb) #endif } -/* Note: This doesn't put any conntrack and bridge info in dst. */ +/* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { @@ -3932,10 +4109,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - dst->nf_bridge = src->nf_bridge; - nf_bridge_get(src->nf_bridge); -#endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; @@ -3947,9 +4120,6 @@ 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(skb_nfct(dst)); #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - nf_bridge_put(dst->nf_bridge); -#endif __nf_copy(dst, src, true); } @@ -3971,12 +4141,19 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline int secpath_exists(const struct sk_buff *skb) +{ +#ifdef CONFIG_XFRM + return skb_ext_exist(skb, SKB_EXT_SEC_PATH); +#else + return 0; +#endif +} + static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && -#if IS_ENABLED(CONFIG_XFRM) - !skb->sp && -#endif + !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); @@ -4022,10 +4199,10 @@ static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) return skb->dst_pending_confirm != 0; } -static inline struct sec_path *skb_sec_path(struct sk_buff *skb) +static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM - return skb->sp; + return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif @@ -4117,6 +4294,12 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } +/* Note: Should be called only if skb_is_gso(skb) is true */ +static inline bool skb_is_gso_tcp(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); +} + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; @@ -4202,7 +4385,7 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. - * See Documentation/networking/checksum-offloads.txt for + * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. |