/* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, * Florian La Roche, * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include #include #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 #define CHECKSUM_UNNECESSARY 2 #ifdef __i386__ #define NET_CALLER(arg) (*(((void**)&arg)-1)) #else #define NET_CALLER(arg) __builtin_return_address(0) #endif #ifdef CONFIG_NETFILTER struct nf_conntrack { atomic_t use; void (*destroy)(struct nf_conntrack *); }; struct nf_ct_info { struct nf_conntrack *master; }; #endif struct sk_buff_head { /* These two members must be first. */ struct sk_buff * next; struct sk_buff * prev; __u32 qlen; spinlock_t lock; }; struct sk_buff { /* These two members must be first. */ struct sk_buff * next; /* Next buffer in list */ struct sk_buff * prev; /* Previous buffer in list */ struct sk_buff_head * list; /* List we are on */ struct sock *sk; /* Socket we are owned by */ struct timeval stamp; /* Time we arrived */ struct net_device *dev; /* Device we arrived on/are leaving by */ struct net_device *rx_dev; /* Transport layer header */ union { struct tcphdr *th; struct udphdr *uh; struct icmphdr *icmph; struct igmphdr *igmph; struct iphdr *ipiph; struct spxhdr *spxh; unsigned char *raw; } h; /* Network layer header */ union { struct iphdr *iph; struct ipv6hdr *ipv6h; struct arphdr *arph; struct ipxhdr *ipxh; unsigned char *raw; } nh; /* Link layer header */ union { struct ethhdr *ethernet; unsigned char *raw; } mac; struct dst_entry *dst; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * 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[48]; unsigned int len; /* Length of actual data */ unsigned int csum; /* Checksum */ volatile char used; /* Data moved to user and not MSG_PEEK */ unsigned char is_clone, /* We are a clone */ cloned, /* head may be cloned (check refcnt to be sure). */ pkt_type, /* Packet class */ ip_summed; /* Driver fed us an IP checksum */ __u32 priority; /* Packet queueing priority */ atomic_t users; /* User count - see datagram.c,tcp.c */ unsigned short protocol; /* Packet protocol from driver. */ unsigned short security; /* Security level of packet */ unsigned int truesize; /* Buffer size */ unsigned char *head; /* Head of buffer */ unsigned char *data; /* Data head pointer */ unsigned char *tail; /* Tail pointer */ unsigned char *end; /* End pointer */ void (*destructor)(struct sk_buff *); /* Destruct function */ #ifdef CONFIG_NETFILTER /* Can be used for communication between hooks. */ unsigned long nfmark; /* Cache info */ __u32 nfcache; /* Associated connection, if any */ struct nf_ct_info *nfct; #ifdef CONFIG_NETFILTER_DEBUG unsigned int nf_debug; #endif #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_HIPPI) union{ __u32 ifield; } private; #endif #ifdef CONFIG_NET_SCHED __u32 tc_index; /* traffic control index */ #endif }; /* These are just the default values. This is run time configurable. * FIXME: Probably the config option should go away. -- erics */ #ifdef CONFIG_SKB_LARGE #define SK_WMEM_MAX 65535 #define SK_RMEM_MAX 65535 #else #define SK_WMEM_MAX 32767 #define SK_RMEM_MAX 32767 #endif #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #include #include extern void __kfree_skb(struct sk_buff *skb); extern struct sk_buff * skb_peek_copy(struct sk_buff_head *list); extern struct sk_buff * alloc_skb(unsigned int size, int 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 * skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, int priority); #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); /* Backwards compatibility */ #define skb_realloc_headroom(skb, nhr) skb_copy_expand(skb, nhr, skb_tailroom(skb), GFP_ATOMIC) /* Internal */ static inline atomic_t *skb_datarefp(struct sk_buff *skb) { return (atomic_t *)(skb->end); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(struct sk_buff_head *list) { return (list->next == (struct sk_buff *) list); } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { atomic_inc(&skb->users); return skb; } /* * If users==1, we are the only owner and are can avoid redundant * 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 (atomic_read(&skb->users) == 1 || atomic_dec_and_test(&skb->users)) __kfree_skb(skb); } /* Use this if you didn't touch the skb state [for fast switching] */ static inline void kfree_skb_fast(struct sk_buff *skb) { if (atomic_read(&skb->users) == 1 || atomic_dec_and_test(&skb->users)) kfree_skbmem(skb); } /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(struct sk_buff *skb) { return skb->cloned && atomic_read(skb_datarefp(skb)) != 1; } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(struct sk_buff *skb) { return (atomic_read(&skb->users) != 1); } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, int pri) { if (skb_shared(skb)) { struct sk_buff *nskb; nskb = skb_clone(skb, pri); kfree_skb(skb); return nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet thats being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, int pri) { struct sk_buff *nskb; if(!skb_cloned(skb)) return skb; nskb=skb_copy(skb, pri); kfree_skb(skb); /* Free our shared copy */ return nskb; } /** * skb_peek * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(struct sk_buff_head *list_) { struct sk_buff *list = ((struct sk_buff *)list_)->next; if (list == (struct sk_buff *)list_) list = NULL; return list; } /** * skb_peek_tail * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(struct sk_buff_head *list_) { struct sk_buff *list = ((struct sk_buff *)list_)->prev; if (list == (struct sk_buff *)list_) list = NULL; return list; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(struct sk_buff_head *list_) { return(list_->qlen); } static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); list->prev = (struct sk_buff *)list; list->next = (struct sk_buff *)list; list->qlen = 0; } /* * Insert an sk_buff at the start of a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ /** * __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. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { struct sk_buff *prev, *next; newsk->list = list; list->qlen++; prev = (struct sk_buff *)list; next = prev->next; newsk->next = next; newsk->prev = prev; next->prev = newsk; 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 the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ static inline void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end 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. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { struct sk_buff *prev, *next; newsk->list = list; list->qlen++; next = (struct sk_buff *)list; prev = next->prev; newsk->next = next; newsk->prev = prev; next->prev = newsk; prev->next = newsk; } /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ static inline void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *next, *prev, *result; prev = (struct sk_buff *) list; next = prev->next; result = NULL; if (next != prev) { result = next; next = next->next; list->qlen--; next->prev = prev; prev->next = next; result->next = NULL; result->prev = NULL; result->list = NULL; } return result; } /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *skb_dequeue(struct sk_buff_head *list) { long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } /* * Insert a packet on a list. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff * prev, struct sk_buff *next, struct sk_buff_head * list) { newsk->next = next; newsk->prev = prev; next->prev = newsk; prev->next = newsk; newsk->list = list; list->qlen++; } /** * skb_insert - insert a buffer * @old: buffer to insert before * @newsk: buffer to insert * * Place a packet before a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls * A buffer cannot be placed on two lists at the same time. */ static inline void skb_insert(struct sk_buff *old, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&old->list->lock, flags); __skb_insert(newsk, old->prev, old, old->list); spin_unlock_irqrestore(&old->list->lock, flags); } /* * Place a packet after a given packet in a list. */ static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk) { __skb_insert(newsk, old, old->next, old->list); } /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ static inline void skb_append(struct sk_buff *old, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&old->list->lock, flags); __skb_append(old, newsk); spin_unlock_irqrestore(&old->list->lock, flags); } /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff * next, * prev; list->qlen--; next = skb->next; prev = skb->prev; skb->next = NULL; skb->prev = NULL; skb->list = NULL; next->prev = prev; prev->next = next; } /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls * * Works even without knowing the list it is sitting on, which can be * handy at times. It also means that THE LIST MUST EXIST when you * unlink. Thus a list must have its contents unlinked before it is * destroyed. */ static inline void skb_unlink(struct sk_buff *skb) { struct sk_buff_head *list = skb->list; if(list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); if(skb->list == list) __skb_unlink(skb, skb->list); spin_unlock_irqrestore(&list->lock, flags); } } /* XXX: more streamlined implementation */ /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } /* * Add data to an sk_buff */ static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len) { unsigned char *tmp=skb->tail; skb->tail+=len; skb->len+=len; return tmp; } /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ static inline unsigned char *skb_put(struct sk_buff *skb, unsigned int len) { unsigned char *tmp=skb->tail; skb->tail+=len; skb->len+=len; if(skb->tail>skb->end) { skb_over_panic(skb, len, current_text_addr()); } return tmp; } static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len) { skb->data-=len; skb->len+=len; return skb->data; } /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ static inline unsigned char *skb_push(struct sk_buff *skb, unsigned int len) { skb->data-=len; skb->len+=len; if(skb->datahead) { skb_under_panic(skb, len, current_text_addr()); } return skb->data; } static inline char *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len-=len; return skb->data+=len; } /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ static inline unsigned char * skb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb->len) return NULL; return __skb_pull(skb,len); } /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline int skb_headroom(const struct sk_buff *skb) { return skb->data-skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb->end-skb->tail; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * 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) { skb->data+=len; skb->tail+=len; } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { skb->len = len; skb->tail = skb->data+len; } /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. */ static inline void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) { __skb_trim(skb, len); } } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } /** * skb_purge - empty a list * @list: list to empty * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ static inline void skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb=skb_dequeue(list))!=NULL) kfree_skb(skb); } /** * __skb_purge - empty a list * @list: list to empty * * Delete all buffers on an &sk_buff list. Each buffer is removed from * 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. */ static inline void __skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb=__skb_dequeue(list))!=NULL) kfree_skb(skb); } /** * dev_alloc_skb - allocate an skbuff for sending * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned in there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { struct sk_buff *skb; skb = alloc_skb(length+16, GFP_ATOMIC); if (skb) skb_reserve(skb,16); return skb; } /** * skb_cow - copy a buffer if need be * @skb: buffer to copy * @headroom: needed headroom * * If the buffer passed lacks sufficient headroom or is a clone then * it is copied and the additional headroom made available. If there * is no free memory %NULL is returned. The new buffer is returned if * a copy was made (and the old one dropped a reference). The existing * buffer is returned otherwise. * * This function primarily exists to avoid making two copies when making * a writable copy of a buffer and then growing the headroom. */ static inline struct sk_buff * skb_cow(struct sk_buff *skb, unsigned int headroom) { headroom = (headroom+15)&~15; if ((unsigned)skb_headroom(skb) < headroom || skb_cloned(skb)) { struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); kfree_skb(skb); skb = skb2; } return skb; } extern struct sk_buff * skb_recv_datagram(struct sock *sk,unsigned flags,int noblock, int *err); extern unsigned int datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); extern int skb_copy_datagram(struct sk_buff *from, int offset, char *to,int size); extern int skb_copy_datagram_iovec(struct sk_buff *from, int offset, struct iovec *to,int size); extern void skb_free_datagram(struct sock * sk, struct sk_buff *skb); extern void skb_init(void); extern void skb_add_mtu(int mtu); #ifdef CONFIG_NETFILTER static inline void nf_conntrack_put(struct nf_ct_info *nfct) { if (nfct && atomic_dec_and_test(&nfct->master->use)) nfct->master->destroy(nfct->master); } static inline void nf_conntrack_get(struct nf_ct_info *nfct) { if (nfct) atomic_inc(&nfct->master->use); } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */