X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;ds=sidebyside;f=include%2Flinux%2Fskbuff.h;fp=include%2Flinux%2Fskbuff.h;h=c219f2f5f49b079dab075aeecbedd24ef3dbf51c;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=cc04f5cd2286953a16a66dbfd89fe96211b0026c;hpb=cee37fe97739d85991964371c1f3a745c00dd236;p=linux-2.6.git diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cc04f5cd2..c219f2f5f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -27,11 +27,11 @@ #include #include #include +#include #include #define HAVE_ALLOC_SKB /* For the drivers to know */ #define HAVE_ALIGNABLE_SKB /* Ditto 8) */ -#define SLAB_SKB /* Slabified skbuffs */ #define CHECKSUM_NONE 0 #define CHECKSUM_HW 1 @@ -133,9 +133,11 @@ struct skb_frag_struct { */ struct skb_shared_info { atomic_t dataref; - unsigned int nr_frags; + unsigned short nr_frags; unsigned short tso_size; unsigned short tso_segs; + unsigned short ufo_size; + unsigned int ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; }; @@ -154,16 +156,26 @@ struct skb_shared_info { #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) +struct skb_timeval { + u32 off_sec; + u32 off_usec; +}; + + +enum { + SKB_FCLONE_UNAVAILABLE, + SKB_FCLONE_ORIG, + SKB_FCLONE_CLONE, +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @list: List we are on * @sk: Socket we are owned by - * @stamp: Time we arrived + * @tstamp: Time we arrived * @dev: Device we arrived on/are leaving by * @input_dev: Device we arrived on - * @real_dev: The real device we are using * @h: Transport layer header * @nh: Network layer header * @mac: Link layer header @@ -178,11 +190,11 @@ struct skb_shared_info { * @cloned: Head may be cloned (check refcnt to be sure) * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class + * @fclone: skbuff clone status * @ip_summed: Driver fed us an IP checksum * @priority: Packet queueing priority * @users: User count - see {datagram,tcp}.c * @protocol: Packet protocol from driver - * @security: Security level of packet * @truesize: Buffer size * @head: Head of buffer * @data: Data head pointer @@ -190,15 +202,13 @@ struct skb_shared_info { * @end: End pointer * @destructor: Destruct function * @nfmark: Can be used for communication between hooks - * @nfcache: Cache info * @nfct: Associated connection, if any + * @ipvs_property: skbuff is owned by ipvs * @nfctinfo: Relationship of this skb to the connection - * @nf_debug: Netfilter debugging + * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c - * @private: Data which is private to the HIPPI implementation * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @tc_classid: traffic control classid */ struct sk_buff { @@ -206,12 +216,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - struct sk_buff_head *list; struct sock *sk; - struct timeval stamp; + struct skb_timeval tstamp; struct net_device *dev; struct net_device *input_dev; - struct net_device *real_dev; union { struct tcphdr *th; @@ -243,46 +251,39 @@ struct sk_buff { * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ - char cb[40]; + char cb[48]; unsigned int len, data_len, mac_len, csum; - unsigned char local_df, + __u32 priority; + __u8 local_df:1, cloned:1, + ip_summed:2, nohdr:1, - pkt_type, - ip_summed; - __u32 priority; - unsigned short protocol, - security; + nfctinfo:3; + __u8 pkt_type:3, + fclone:2, + ipvs_property:1; + __be16 protocol; void (*destructor)(struct sk_buff *skb); #ifdef CONFIG_NETFILTER - unsigned long nfmark; - __u32 nfcache; - __u32 nfctinfo; struct nf_conntrack *nfct; -#ifdef CONFIG_NETFILTER_DEBUG - unsigned int nf_debug; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + struct sk_buff *nfct_reasm; #endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif + __u32 nfmark; #endif /* CONFIG_NETFILTER */ -#if defined(CONFIG_HIPPI) - union { - __u32 ifield; - } private; -#endif #ifdef CONFIG_NET_SCHED - __u32 tc_index; /* traffic control index */ + __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT - __u32 tc_verd; /* traffic control verdict */ - __u32 tc_classid; /* traffic control classid */ + __u16 tc_verd; /* traffic control verdict */ #endif - #endif @@ -303,27 +304,80 @@ struct sk_buff { #include +extern void kfree_skb(struct sk_buff *skb); extern void __kfree_skb(struct sk_buff *skb); -extern struct sk_buff *alloc_skb(unsigned int size, int priority); +extern struct sk_buff *__alloc_skb(unsigned int size, + gfp_t priority, int fclone); +static inline struct sk_buff *alloc_skb(unsigned int size, + gfp_t priority) +{ + return __alloc_skb(size, priority, 0); +} + +static inline struct sk_buff *alloc_skb_fclone(unsigned int size, + gfp_t priority) +{ + return __alloc_skb(size, priority, 1); +} + extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, - unsigned int size, int priority); + unsigned int size, + gfp_t priority); extern void kfree_skbmem(struct sk_buff *skb); -extern struct sk_buff *skb_clone(struct sk_buff *skb, int priority); -extern struct sk_buff *skb_copy(const struct sk_buff *skb, int priority); -extern struct sk_buff *pskb_copy(struct sk_buff *skb, int gfp_mask); +extern struct sk_buff *skb_clone(struct sk_buff *skb, + gfp_t priority); +extern struct sk_buff *skb_copy(const struct sk_buff *skb, + gfp_t priority); +extern struct sk_buff *pskb_copy(struct sk_buff *skb, + gfp_t gfp_mask); extern int pskb_expand_head(struct sk_buff *skb, - int nhead, int ntail, int gfp_mask); + int nhead, int ntail, + gfp_t gfp_mask); extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, - int priority); + gfp_t priority); extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) kfree_skb(a) extern void skb_over_panic(struct sk_buff *skb, int len, void *here); extern void skb_under_panic(struct sk_buff *skb, int len, void *here); +extern void skb_truesize_bug(struct sk_buff *skb); + +static inline void skb_truesize_check(struct sk_buff *skb) +{ + if (unlikely((int)skb->truesize < sizeof(struct sk_buff) + skb->len)) + skb_truesize_bug(skb); +} + +extern int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, + int getfrag(void *from, char *to, int offset, + int len,int odd, struct sk_buff *skb), + void *from, int length); + +struct skb_seq_state +{ + __u32 lower_offset; + __u32 upper_offset; + __u32 frag_idx; + __u32 stepped_offset; + struct sk_buff *root_skb; + struct sk_buff *cur_skb; + __u8 *frag_data; +}; + +extern void skb_prepare_seq_read(struct sk_buff *skb, + unsigned int from, unsigned int to, + struct skb_seq_state *st); +extern unsigned int skb_seq_read(unsigned int consumed, const u8 **data, + struct skb_seq_state *st); +extern void skb_abort_seq_read(struct skb_seq_state *st); + +extern unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, + unsigned int to, struct ts_config *config, + struct ts_state *state); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)((SKB)->end)) @@ -357,22 +411,6 @@ static inline struct sk_buff *skb_get(struct sk_buff *skb) * atomic change. */ -/** - * kfree_skb - free an sk_buff - * @skb: buffer to free - * - * Drop a reference to the buffer and free it if the usage count has - * hit zero. - */ -static inline void kfree_skb(struct sk_buff *skb) -{ - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) - return; - __kfree_skb(skb); -} - /** * skb_cloned - is the buffer a clone * @skb: buffer to check @@ -446,7 +484,8 @@ static inline int skb_shared(const struct sk_buff *skb) * * NULL is returned on a memory allocation failure. */ -static inline struct sk_buff *skb_share_check(struct sk_buff *skb, int pri) +static inline struct sk_buff *skb_share_check(struct sk_buff *skb, + gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_shared(skb)) { @@ -477,7 +516,8 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, int pri) * * %NULL is returned on a memory allocation failure. */ -static inline struct sk_buff *skb_unshare(struct sk_buff *skb, int pri) +static inline struct sk_buff *skb_unshare(struct sk_buff *skb, + gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_cloned(skb)) { @@ -556,30 +596,46 @@ static inline void skb_queue_head_init(struct sk_buff_head *list) */ /** - * __skb_queue_head - queue a buffer at the list head + * __skb_queue_after - queue a buffer at the list head * @list: list to use + * @prev: place after this buffer * @newsk: buffer to queue * - * Queue a buffer at the start of a list. This function takes no locks + * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ -extern 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) +static inline void __skb_queue_after(struct sk_buff_head *list, + struct sk_buff *prev, + struct sk_buff *newsk) { - struct sk_buff *prev, *next; - - newsk->list = list; + struct sk_buff *next; list->qlen++; - prev = (struct sk_buff *)list; + next = prev->next; newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; } +/** + * __skb_queue_head - queue a buffer at the list head + * @list: list to use + * @newsk: buffer to queue + * + * Queue a buffer at the start of a list. This function takes no locks + * and you must therefore hold required locks before calling it. + * + * A buffer cannot be placed on two lists at the same time. + */ +extern 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); +} + /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use @@ -596,7 +652,6 @@ static inline void __skb_queue_tail(struct sk_buff_head *list, { struct sk_buff *prev, *next; - newsk->list = list; list->qlen++; next = (struct sk_buff *)list; prev = next->prev; @@ -629,7 +684,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) next->prev = prev; prev->next = next; result->next = result->prev = NULL; - result->list = NULL; } return result; } @@ -638,7 +692,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) /* * Insert a packet on a list. */ -extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk); +extern 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) @@ -646,24 +700,23 @@ static inline void __skb_insert(struct sk_buff *newsk, newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; - newsk->list = list; list->qlen++; } /* * Place a packet after a given packet in a list. */ -extern void skb_append(struct sk_buff *old, struct sk_buff *newsk); -static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk) +extern void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); +static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { - __skb_insert(newsk, old, old->next, old->list); + __skb_insert(newsk, old, old->next, list); } /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ -extern void skb_unlink(struct sk_buff *skb); +extern void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; @@ -672,7 +725,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; - skb->list = NULL; next->prev = prev; prev->next = next; } @@ -866,7 +918,7 @@ static inline int skb_tailroom(const struct sk_buff *skb) * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ -static inline void skb_reserve(struct sk_buff *skb, unsigned int len) +static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; @@ -896,6 +948,25 @@ static inline void skb_reserve(struct sk_buff *skb, unsigned int len) #define NET_IP_ALIGN 2 #endif +/* + * The networking layer reserves some headroom in skb data (via + * dev_alloc_skb). This is used to avoid having to reallocate skb data when + * the header has to grow. In the default case, if the header has to grow + * 16 bytes or less we avoid the reallocation. + * + * Unfortunately this headroom changes the DMA alignment of the resulting + * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive + * on some architectures. An architecture can override this value, + * perhaps setting it to a cacheline in size (since that will maintain + * cacheline alignment of the DMA). It must be a power of 2. + * + * Various parts of the networking layer expect at least 16 bytes of + * headroom, you should not reduce this. + */ +#ifndef NET_SKB_PAD +#define NET_SKB_PAD 16 +#endif + extern int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc); static inline void __skb_trim(struct sk_buff *skb, unsigned int len) @@ -983,11 +1054,11 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) * %NULL is returned in there is no free memory. */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, - int gfp_mask) + gfp_t gfp_mask) { - struct sk_buff *skb = alloc_skb(length + 16, gfp_mask); + struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask); if (likely(skb)) - skb_reserve(skb, 16); + skb_reserve(skb, NET_SKB_PAD); return skb; } #else @@ -1025,13 +1096,15 @@ static inline struct sk_buff *dev_alloc_skb(unsigned int length) */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { - int delta = (headroom > 16 ? headroom : 16) - skb_headroom(skb); + int delta = (headroom > NET_SKB_PAD ? headroom : NET_SKB_PAD) - + skb_headroom(skb); if (delta < 0) delta = 0; if (delta || skb_cloned(skb)) - return pskb_expand_head(skb, (delta + 15) & ~15, 0, GFP_ATOMIC); + return pskb_expand_head(skb, (delta + (NET_SKB_PAD-1)) & + ~(NET_SKB_PAD-1), 0, GFP_ATOMIC); return 0; } @@ -1096,8 +1169,8 @@ static inline int skb_can_coalesce(struct sk_buff *skb, int i, * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ -extern int __skb_linearize(struct sk_buff *skb, int gfp); -static inline int skb_linearize(struct sk_buff *skb, int gfp) +extern int __skb_linearize(struct sk_buff *skb, gfp_t gfp); +static inline int skb_linearize(struct sk_buff *skb, gfp_t gfp) { return __skb_linearize(skb, gfp); } @@ -1114,12 +1187,14 @@ static inline int skb_linearize(struct sk_buff *skb, int gfp) */ static inline void skb_postpull_rcsum(struct sk_buff *skb, - const void *start, int len) + const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_HW) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); } +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim @@ -1131,7 +1206,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { - if (len >= skb->len) + if (likely(len >= skb->len)) return 0; if (skb->ip_summed == CHECKSUM_HW) skb->ip_summed = CHECKSUM_NONE; @@ -1161,6 +1236,11 @@ static inline void kunmap_skb_frag(void *vaddr) prefetch(skb->next), (skb != (struct sk_buff *)(queue)); \ skb = skb->next) +#define skb_queue_reverse_walk(queue, skb) \ + for (skb = (queue)->prev; \ + prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ + skb = skb->prev) + extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); @@ -1169,11 +1249,12 @@ extern unsigned int datagram_poll(struct file *file, struct socket *sock, extern int skb_copy_datagram_iovec(const struct sk_buff *from, int offset, struct iovec *to, int size); -extern int skb_copy_and_csum_datagram_iovec(const - struct sk_buff *skb, +extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen, struct iovec *iov); extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb); +extern void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, + unsigned int flags); extern unsigned int skb_checksum(const struct sk_buff *skb, int offset, int len, unsigned int csum); extern int skb_copy_bits(const struct sk_buff *skb, int offset, @@ -1187,12 +1268,14 @@ extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); +extern void skb_release_data(struct sk_buff *skb); + static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { int hlen = skb_headlen(skb); - if (offset + len <= hlen) + if (hlen - offset >= len) return skb->data + offset; if (skb_copy_bits(skb, offset, buffer, len) < 0) @@ -1204,6 +1287,64 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, extern void skb_init(void); extern void skb_add_mtu(int mtu); +/** + * skb_get_timestamp - get timestamp from a skb + * @skb: skb to get stamp from + * @stamp: pointer to struct 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) +{ + stamp->tv_sec = skb->tstamp.off_sec; + stamp->tv_usec = skb->tstamp.off_usec; +} + +/** + * skb_set_timestamp - set timestamp of a skb + * @skb: skb to set stamp of + * @stamp: pointer to struct timeval to get stamp from + * + * Timestamps are stored in the skb as offsets to a base timestamp. + * This function converts a struct timeval to an offset and stores + * it in the skb. + */ +static inline void skb_set_timestamp(struct sk_buff *skb, const struct timeval *stamp) +{ + skb->tstamp.off_sec = stamp->tv_sec; + skb->tstamp.off_usec = stamp->tv_usec; +} + +extern void __net_timestamp(struct sk_buff *skb); + +extern unsigned int __skb_checksum_complete(struct sk_buff *skb); + +/** + * skb_checksum_complete - Calculate checksum of an entire packet + * @skb: packet to process + * + * This function calculates the checksum over the entire packet plus + * the value of skb->csum. The latter can be used to supply the + * checksum of a pseudo header as used by TCP/UDP. It returns the + * checksum. + * + * For protocols that contain complete checksums such as ICMP/TCP/UDP, + * this function can be used to verify that checksum on received + * packets. In that case the function should return zero if the + * checksum is correct. In particular, this function will return zero + * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the + * hardware has already verified the correctness of the checksum. + */ +static inline unsigned int skb_checksum_complete(struct sk_buff *skb) +{ + return skb->ip_summed != CHECKSUM_UNNECESSARY && + __skb_checksum_complete(skb); +} + +struct tux_req_struct; + #ifdef CONFIG_NETFILTER static inline void nf_conntrack_put(struct nf_conntrack *nfct) { @@ -1215,21 +1356,18 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) if (nfct) atomic_inc(&nfct->use); } -static inline void nf_reset(struct sk_buff *skb) +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +static inline void nf_conntrack_get_reasm(struct sk_buff *skb) { - nf_conntrack_put(skb->nfct); - skb->nfct = NULL; -#ifdef CONFIG_NETFILTER_DEBUG - skb->nf_debug = 0; -#endif + if (skb) + atomic_inc(&skb->users); } -static inline void nf_reset_debug(struct sk_buff *skb) +static inline void nf_conntrack_put_reasm(struct sk_buff *skb) { -#ifdef CONFIG_NETFILTER_DEBUG - skb->nf_debug = 0; -#endif + if (skb) + kfree_skb(skb); } - +#endif #ifdef CONFIG_BRIDGE_NETFILTER static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { @@ -1242,6 +1380,20 @@ static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) atomic_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ +static inline void nf_reset(struct sk_buff *skb) +{ + nf_conntrack_put(skb->nfct); + skb->nfct = NULL; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + nf_conntrack_put_reasm(skb->nfct_reasm); + skb->nfct_reasm = NULL; +#endif +#ifdef CONFIG_BRIDGE_NETFILTER + nf_bridge_put(skb->nf_bridge); + skb->nf_bridge = NULL; +#endif +} + #else /* CONFIG_NETFILTER */ static inline void nf_reset(struct sk_buff *skb) {} #endif /* CONFIG_NETFILTER */