/* * 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 #include #include #include #include #include #include #define HAVE_ALLOC_SKB /* For the drivers to know */ #define HAVE_ALIGNABLE_SKB /* Ditto 8) */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 #define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \ ~(SMP_CACHE_BYTES - 1)) #define SKB_WITH_OVERHEAD(X) \ (((X) - sizeof(struct skb_shared_info)) & \ ~(SMP_CACHE_BYTES - 1)) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* A. Checksumming of received packets by device. * * NONE: device failed to checksum this packet. * skb->csum is undefined. * * UNNECESSARY: device parsed packet and wouldbe verified checksum. * skb->csum is undefined. * It is bad option, but, unfortunately, many of vendors do this. * Apparently with secret goal to sell you new device, when you * will add new protocol to your host. F.e. IPv6. 8) * * COMPLETE: the most generic way. Device supplied checksum of _all_ * the packet as seen by netif_rx in skb->csum. * NOTE: Even if device supports only some protocols, but * is able to produce some skb->csum, it MUST use COMPLETE, * not UNNECESSARY. * * PARTIAL: identical to the case for output below. This may occur * on a packet received directly from another Linux OS, e.g., * a virtualised Linux kernel on the same host. The packet can * be treated in the same way as UNNECESSARY except that on * output (i.e., forwarding) the checksum must be filled in * by the OS or the hardware. * * B. Checksumming on output. * * NONE: skb is checksummed by protocol or csum is not required. * * PARTIAL: device is required to csum packet as seen by hard_start_xmit * from skb->csum_start to the end and to record the checksum * at skb->csum_start + skb->csum_offset. * * Device must show its capabilities in dev->features, set * at device setup time. * NETIF_F_HW_CSUM - it is clever device, it is able to checksum * everything. * NETIF_F_NO_CSUM - loopback or reliable single hop media. * NETIF_F_IP_CSUM - device is dumb. It is able to csum only * TCP/UDP over IPv4. Sigh. Vendors like this * way by an unknown reason. Though, see comment above * about CHECKSUM_UNNECESSARY. 8) * NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead. * * Any questions? No questions, good. --ANK */ struct net_device; struct scatterlist; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { atomic_t use; }; #endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info { atomic_t use; struct net_device *physindev; struct net_device *physoutdev; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) struct net_device *netoutdev; #endif unsigned int mask; unsigned long data[32 / sizeof(unsigned long)]; }; #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; /* To allow 64K frame to be packed as single skb without frag_list */ #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2) typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { struct page *page; __u32 page_offset; __u32 size; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; unsigned short gso_type; __be32 ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; }; /* We divide dataref into two halves. The higher 16 bits hold references * to the payload part of skb->data. The lower 16 bits hold references to * the entire skb->data. A clone of a headerless skb holds the length of * the header in skb->hdr_len. * * All users must obey the rule that the skb->data reference count must be * greater than or equal to the payload reference count. * * Holding a reference to the payload part means that the user does not * care about modifications to the header part of skb->data. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, SKB_FCLONE_ORIG, SKB_FCLONE_CLONE, }; enum { SKB_GSO_TCPV4 = 1 << 0, SKB_GSO_UDP = 1 << 1, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 2, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @sk: Socket we are owned by * @tstamp: Time we arrived * @dev: Device we arrived on/are leaving by * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @dst: destination entry * @sp: the security path, used for xfrm * @cb: Control buffer. Free for use by every layer. Put private vars here * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @local_df: allow local fragmentation * @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 * @truesize: Buffer size * @head: Head of buffer * @data: Data head pointer * @tail: Tail pointer * @end: End pointer * @destructor: Destruct function * @mark: Generic packet mark * @nfct: Associated connection, if any * @ipvs_property: skbuff is owned by ipvs * @nf_trace: netfilter packet trace flag * @nfctinfo: Relationship of this skb to the connection * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @iif: ifindex of device we arrived on * @queue_mapping: Queue mapping for multiqueue devices * @tc_index: Traffic control index * @tc_verd: traffic control verdict * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions * @secmark: security marking */ struct sk_buff { /* These two members must be first. */ struct sk_buff *next; struct sk_buff *prev; struct sock *sk; ktime_t tstamp; struct net_device *dev; struct dst_entry *dst; struct sec_path *sp; /* * 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, data_len; __u16 mac_len, hdr_len; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; __u8 local_df:1, cloned:1, ip_summed:2, nohdr:1, nfctinfo:3; __u8 pkt_type:3, fclone:2, ipvs_property:1, nf_trace:1; __be16 protocol; void (*destructor)(struct sk_buff *skb); #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack *nfct; struct sk_buff *nfct_reasm; #endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif int iif; __u16 queue_mapping; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT __u16 tc_verd; /* traffic control verdict */ #endif #endif /* 2 byte hole */ #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif __u32 mark; sk_buff_data_t transport_header; sk_buff_data_t network_header; sk_buff_data_t mac_header; /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; atomic_t users; }; #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #include #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, gfp_t priority, int fclone, int node); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, -1); } static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 1, -1); } extern void kfree_skbmem(struct sk_buff *skb); extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); 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, 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, gfp_t priority); extern int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); extern int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); extern int 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); #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } #endif /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) /** * 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(const 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. */ /** * 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(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } /** * skb_header_release - release reference to header * @skb: buffer to operate on * * Drop a reference to the header part of the buffer. This is done * by acquiring a payload reference. You must not read from the header * part of skb->data after this. */ static inline void skb_header_release(struct sk_buff *skb) { BUG_ON(skb->nohdr); skb->nohdr = 1; atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref); } /** * 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(const 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, gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); kfree_skb(skb); skb = 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, gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); kfree_skb(skb); /* Free our shared copy */ skb = nskb; } return skb; } /** * 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(const struct sk_buff_head *list_) { return list_->qlen; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * 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_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * 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. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { struct sk_buff *next; list->qlen++; 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 * @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. */ extern 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) { struct sk_buff *prev, *next; list->qlen++; next = (struct sk_buff *)list; prev = next->prev; newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; } /** * __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. */ extern 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 *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 = result->prev = NULL; } return result; } /* * Insert a packet on a list. */ 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) { newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; list->qlen++; } /* * Place a packet after a given packet in a list. */ 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, list); } /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ 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; list->qlen--; next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; next->prev = prev; prev->next = next; } /* 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. */ extern 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); if (skb) __skb_unlink(skb, list); return skb; } static inline int skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline int skb_pagelen(const struct sk_buff *skb) { int i, len = 0; for (i = (int)skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) len += skb_shinfo(skb)->frags[i].size; return len + skb_headlen(skb); } static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; frag->page = page; frag->page_offset = off; frag->size = size; skb_shinfo(skb)->nr_frags = i + 1; } #define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags) #define SKB_FRAG_ASSERT(skb) BUG_ON(skb_shinfo(skb)->frag_list) #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ /* * Add data to an sk_buff */ static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len) { unsigned char *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); 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_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(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 (unlikely(skb->datahead)) skb_under_panic(skb, len, current_text_addr()); return skb->data; } static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; BUG_ON(skb->len < skb->data_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) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } extern unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb_headlen(skb) && !__pskb_pull_tail(skb, len-skb_headlen(skb))) return NULL; skb->len -= len; return skb->data += len; } static inline unsigned char *pskb_pull(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) return 1; if (unlikely(len > skb->len)) return 0; return __pskb_pull_tail(skb, len-skb_headlen(skb)) != NULL; } /** * 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_is_nonlinear(skb) ? 0 : 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, int len) { skb->data += len; skb->tail += len; } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { skb->transport_header = skb->data - skb->head; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { skb->network_header = skb->data - skb->head; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { return skb->head + skb->mac_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != ~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data - skb->head; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { skb->transport_header = skb->data; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb->transport_header = skb->data + offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { skb->network_header = skb->data; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb->network_header = skb->data + offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { return skb->mac_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != NULL; } static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb->mac_header = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { return skb->transport_header - skb->network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #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); static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { if (unlikely(skb->data_len)) { WARN_ON(1); return; } skb->len = len; skb_set_tail_pointer(skb, 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. * The skb must be linear. */ static inline void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } /** * 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_queue_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. */ extern 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); } /** * __dev_alloc_skb - allocate an skbuff for receiving * @length: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * 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 if there is no free memory. */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask); if (likely(skb)) skb_reserve(skb, NET_SKB_PAD); return skb; } /** * dev_alloc_skb - allocate an skbuff for receiving * @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 if 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) { return __dev_alloc_skb(length, GFP_ATOMIC); } extern struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @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 if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(struct sk_buff *skb, int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom < NET_SKB_PAD) headroom = NET_SKB_PAD; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len-size); } static inline int skb_add_data(struct sk_buff *skb, char __user *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { int err = 0; __wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy), copy, 0, &err); if (!err) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (!copy_from_user(skb_put(skb, copy), from, copy)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline int skb_can_coalesce(struct sk_buff *skb, int i, struct page *page, int off) { if (i) { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; return page == frag->page && off == frag->page_offset + frag->size; } return 0; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) 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 * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __pskb_trim(skb, len); } #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ prefetch(skb->next), (skb != (struct sk_buff *)(queue)); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = 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); extern unsigned int datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); 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(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 __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); extern int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); extern int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); extern __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); 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 struct sk_buff *skb_segment(struct sk_buff *skb, int features); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { int hlen = skb_headlen(skb); if (hlen - offset >= len) return skb->data + offset; if (skb_copy_bits(skb, offset, buffer, len) < 0) return NULL; return buffer; } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } extern void skb_init(void); /** * 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 = ktime_to_timeval(skb->tstamp); } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline ktime_t net_invalid_timestamp(void) { return ktime_set(0, 0); } extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); extern __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return skb->ip_summed & CHECKSUM_UNNECESSARY; } /** * 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 __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) extern void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && atomic_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) atomic_inc(&nfct->use); } static inline void nf_conntrack_get_reasm(struct sk_buff *skb) { if (skb) atomic_inc(&skb->users); } static inline void nf_conntrack_put_reasm(struct sk_buff *skb) { if (skb) kfree_skb(skb); } #endif #ifdef CONFIG_BRIDGE_NETFILTER static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { if (nf_bridge && atomic_dec_and_test(&nf_bridge->use)) kfree(nf_bridge); } static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) { if (nf_bridge) atomic_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ 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_reasm(skb->nfct_reasm); skb->nfct_reasm = NULL; #endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); skb->nf_bridge = NULL; #endif } /* Note: This doesn't put any conntrack and bridge info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->nfct = src->nfct; nf_conntrack_get(src->nfct); dst->nfctinfo = src->nfctinfo; dst->nfct_reasm = src->nfct_reasm; nf_conntrack_get_reasm(src->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif } 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_reasm(dst->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(dst->nf_bridge); #endif __nf_copy(dst, src); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { #ifdef CONFIG_NETDEVICES_MULTIQUEUE skb->queue_mapping = queue_mapping; #endif } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_NETDEVICES_MULTIQUEUE to->queue_mapping = from->queue_mapping; #endif } static inline int skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */