// SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <[email protected]> * Florian La Roche <[email protected]> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) … #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/bitfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <linux/iov_iter.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <net/mctp.h> #include <net/page_pool/helpers.h> #include <net/dropreason.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include <linux/textsearch.h> #include "dev.h" #include "netmem_priv.h" #include "sock_destructor.h" #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif #define SKB_SMALL_HEAD_SIZE … /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique * size, and we can differentiate heads from skb_small_head_cache * vs system slabs by looking at their size (skb_end_offset()). */ #define SKB_SMALL_HEAD_CACHE_SIZE … #define SKB_SMALL_HEAD_HEADROOM … /* kcm_write_msgs() relies on casting paged frags to bio_vec to use * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the * netmem is a page. */ static_assert(…); static_assert(…); static_assert(…); static_assert(…); static_assert(…); static_assert(…); #undef FN #define FN(reason) … static const char * const drop_reasons[] = …; static const struct drop_reason_list drop_reasons_core = …; const struct drop_reason_list __rcu * drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = …; EXPORT_SYMBOL(…); /** * drop_reasons_register_subsys - register another drop reason subsystem * @subsys: the subsystem to register, must not be the core * @list: the list of drop reasons within the subsystem, must point to * a statically initialized list */ void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys, const struct drop_reason_list *list) { … } EXPORT_SYMBOL_GPL(…); /** * drop_reasons_unregister_subsys - unregister a drop reason subsystem * @subsys: the subsystem to remove, must not be the core * * Note: This will synchronize_rcu() to ensure no users when it returns. */ void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys) { … } EXPORT_SYMBOL_GPL(…); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { … } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { … } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { … } #define NAPI_SKB_CACHE_SIZE … #define NAPI_SKB_CACHE_BULK … #define NAPI_SKB_CACHE_HALF … #if PAGE_SIZE == SZ_4K #define NAPI_HAS_SMALL_PAGE_FRAG … #define NAPI_SMALL_PAGE_PFMEMALLOC(nc) … /* specialized page frag allocator using a single order 0 page * and slicing it into 1K sized fragment. Constrained to systems * with a very limited amount of 1K fragments fitting a single * page - to avoid excessive truesize underestimation */ struct page_frag_1k { … }; static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) { … } #else /* the small page is actually unused in this build; add dummy helpers * to please the compiler and avoid later preprocessor's conditionals */ #define NAPI_HAS_SMALL_PAGE_FRAG … #define NAPI_SMALL_PAGE_PFMEMALLOC … struct page_frag_1k { }; static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) { return NULL; } #endif struct napi_alloc_cache { … }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = …; /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. * This is to make sure bug fixed in 3226b158e67c * ("net: avoid 32 x truesize under-estimation for tiny skbs") * does not accidentally come back. */ void napi_get_frags_check(struct napi_struct *napi) { … } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { … } EXPORT_SYMBOL(…); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { … } EXPORT_SYMBOL(…); static struct sk_buff *napi_skb_cache_get(void) { … } static inline void __finalize_skb_around(struct sk_buff *skb, void *data, unsigned int size) { … } static inline void *__slab_build_skb(struct sk_buff *skb, void *data, unsigned int *size) { … } /* build_skb() variant which can operate on slab buffers. * Note that this should be used sparingly as slab buffers * cannot be combined efficiently by GRO! */ struct sk_buff *slab_build_skb(void *data) { … } EXPORT_SYMBOL(…); /* Caller must provide SKB that is memset cleared */ static void __build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { … } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data (must not be 0) * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated from the page * allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc() * allocation is deprecated, and callers should use slab_build_skb() * instead.) * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { … } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { … } EXPORT_SYMBOL(…); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { … } EXPORT_SYMBOL(…); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { … } /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { … } EXPORT_SYMBOL(…); /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { … } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { … } EXPORT_SYMBOL(…); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: 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 NET_SKB_PAD 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. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); /** * napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) { … } EXPORT_SYMBOL(…); void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize) { … } EXPORT_SYMBOL(…); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { … } EXPORT_SYMBOL(…); static void skb_drop_list(struct sk_buff **listp) { … } static inline void skb_drop_fraglist(struct sk_buff *skb) { … } static void skb_clone_fraglist(struct sk_buff *skb) { … } static bool is_pp_netmem(netmem_ref netmem) { … } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { … } EXPORT_SYMBOL(…); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog) { … } EXPORT_SYMBOL(…); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(netmem_ref netmem) { … } EXPORT_SYMBOL(…); #endif static bool skb_pp_recycle(struct sk_buff *skb, void *data) { … } /** * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb * @skb: page pool aware skb * * Increase the fragment reference count (pp_ref_count) of a skb. This is * intended to gain fragment references only for page pool aware skbs, * i.e. when skb->pp_recycle is true, and not for fragments in a * non-pp-recycling skb. It has a fallback to increase references on normal * pages, as page pool aware skbs may also have normal page fragments. */ static int skb_pp_frag_ref(struct sk_buff *skb) { … } static void skb_kfree_head(void *head, unsigned int end_offset) { … } static void skb_free_head(struct sk_buff *skb) { … } static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { … } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { … } void skb_release_head_state(struct sk_buff *skb) { … } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { … } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); static __always_inline bool __sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { … } /** * sk_skb_reason_drop - free an sk_buff with special reason * @sk: the socket to receive @skb, or NULL if not applicable * @skb: buffer to free * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has hit * zero. Meanwhile, pass the receiving socket and drop reason to * 'kfree_skb' tracepoint. */ void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { … } EXPORT_SYMBOL(…); #define KFREE_SKB_BULK_SIZE … struct skb_free_array { … }; static void kfree_skb_add_bulk(struct sk_buff *skb, struct skb_free_array *sa, enum skb_drop_reason reason) { … } void __fix_address kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) { … } EXPORT_SYMBOL(…); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { … } EXPORT_SYMBOL(…); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); #endif /** * __consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { … } static void napi_skb_cache_put(struct sk_buff *skb) { … } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) { … } void napi_skb_free_stolen_head(struct sk_buff *skb) { … } void napi_consume_skb(struct sk_buff *skb, int budget) { … } EXPORT_SYMBOL(…); /* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) … \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { … } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { … } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { … } EXPORT_SYMBOL_GPL(…); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { … } EXPORT_SYMBOL_GPL(…); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { … } EXPORT_SYMBOL_GPL(…); void mm_unaccount_pinned_pages(struct mmpin *mmp) { … } EXPORT_SYMBOL_GPL(…); static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { … } static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg) { … } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg) { … } EXPORT_SYMBOL_GPL(…); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { … } static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg) { … } static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { … } void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { … } EXPORT_SYMBOL_GPL(…); const struct ubuf_info_ops msg_zerocopy_ubuf_ops = …; EXPORT_SYMBOL_GPL(…); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) { … } EXPORT_SYMBOL_GPL(…); void __skb_zcopy_downgrade_managed(struct sk_buff *skb) { … } EXPORT_SYMBOL_GPL(…); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { … } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { … } EXPORT_SYMBOL_GPL(…); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); void skb_headers_offset_update(struct sk_buff *skb, int off) { … } EXPORT_SYMBOL(…); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { … } EXPORT_SYMBOL(…); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { … } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { … } EXPORT_SYMBOL(…); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { … } EXPORT_SYMBOL(…); /* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { … } /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { … } EXPORT_SYMBOL(…); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { … } EXPORT_SYMBOL(…); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { … } EXPORT_SYMBOL_GPL(…); /** * 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. */ void *skb_put(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /** * 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. */ void *skb_push(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /** * 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. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /** * skb_pull_data - remove data from the start of a buffer returning its * original position. * @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 original data in the buffer * is returned after checking if there is enough data to pull. Once the * data has been pulled future pushes will overwrite the old data. */ void *skb_pull_data(struct sk_buff *skb, size_t len) { … } EXPORT_SYMBOL(…); /** * 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. */ void skb_trim(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL(…); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { … } EXPORT_SYMBOL(…); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { … } EXPORT_SYMBOL(…); /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { … } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { … } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { … } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { … } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) { … } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { … } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { … } EXPORT_SYMBOL_GPL(…); static int sendmsg_locked(struct sock *sk, struct msghdr *msg) { … } static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg) { … } sendmsg_func; static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len, sendmsg_func sendmsg) { … } /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { … } EXPORT_SYMBOL_GPL(…); /* Send skb data on a socket. Socket must be unlocked. */ int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) { … } /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { … } EXPORT_SYMBOL(…); /* Checksum skb data. */ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops) { … } EXPORT_SYMBOL(…); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { … } EXPORT_SYMBOL(…); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { … } EXPORT_SYMBOL(…); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { … } EXPORT_SYMBOL(…); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) { … } static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, int offset, int len) { … } static const struct skb_checksum_ops default_crc32c_ops = …; const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = …; EXPORT_SYMBOL(…); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { … } EXPORT_SYMBOL_GPL(…); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { … } EXPORT_SYMBOL_GPL(…); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { … } EXPORT_SYMBOL(…); /** * 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. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { … } EXPORT_SYMBOL(…); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail 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. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { … } EXPORT_SYMBOL(…); /** * skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * 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. */ void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { … } EXPORT_SYMBOL(…); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { … } void skb_errqueue_purge(struct sk_buff_head *list) { … } EXPORT_SYMBOL(…); /** * 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. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { … } EXPORT_SYMBOL(…); /** * 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. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { … } EXPORT_SYMBOL(…); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { … } EXPORT_SYMBOL(…); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * 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. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { … } EXPORT_SYMBOL(…); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { … } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { … } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { … } EXPORT_SYMBOL(…); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { … } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { … } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { … } EXPORT_SYMBOL(…); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { … } EXPORT_SYMBOL(…); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { … } EXPORT_SYMBOL(…); /** * skb_copy_seq_read() - copy from a skb_seq_state to a buffer * @st: source skb_seq_state * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy @len bytes from @offset bytes into the source @st to the destination * buffer @to. `offset` should increase (or be unchanged) with each subsequent * call to this function. If offset needs to decrease from the previous use `st` * should be reset first. * * Return: 0 on success or -EINVAL if the copy ended early */ int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len) { … } EXPORT_SYMBOL(…); #define TS_SKB_CB(state) … static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { … } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { … } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { … } EXPORT_SYMBOL(…); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags) { … } EXPORT_SYMBOL_GPL(…); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { … } EXPORT_SYMBOL_GPL(…); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { … } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { … } EXPORT_SYMBOL_GPL(…); /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { … } EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE … #define SKB_EXT_CHUNKSIZEOF(x) … static const u8 skb_ext_type_len[] = …; static __always_inline unsigned int skb_ext_total_length(void) { … } static void skb_extensions_init(void) { … } #else static void skb_extensions_init(void) {} #endif /* The SKB kmem_cache slab is critical for network performance. Never * merge/alias the slab with similar sized objects. This avoids fragmentation * that hurts performance of kmem_cache_{alloc,free}_bulk APIs. */ #ifndef CONFIG_SLUB_TINY #define FLAG_SKB_NO_MERGE … #else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */ #define FLAG_SKB_NO_MERGE … #endif void __init skb_init(void) { … } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { … } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { … } EXPORT_SYMBOL_GPL(…); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { … } EXPORT_SYMBOL_GPL(…); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { … } EXPORT_SYMBOL_GPL(…); static void sock_rmem_free(struct sk_buff *skb) { … } static void skb_set_err_queue(struct sk_buff *skb) { … } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { … } EXPORT_SYMBOL(…); static bool is_icmp_err_skb(const struct sk_buff *skb) { … } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { … } EXPORT_SYMBOL(…); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { … } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { … } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { … } EXPORT_SYMBOL_GPL(…); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { … } EXPORT_SYMBOL_GPL(…); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { … } EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_WIRELESS void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { … } EXPORT_SYMBOL_GPL(…); #endif /* CONFIG_WIRELESS */ /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { … } EXPORT_SYMBOL_GPL(…); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { … } #define MAX_TCP_HDR_LEN … static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { … } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN … static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { … } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN … #define OPT_HDR(type, skb, off) … static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { … } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { … } EXPORT_SYMBOL(…); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { … } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { … } EXPORT_SYMBOL(…); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { … } EXPORT_SYMBOL(…); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { … } EXPORT_SYMBOL(…); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { … } EXPORT_SYMBOL(…); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { … } EXPORT_SYMBOL_GPL(…); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { … } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) { … } EXPORT_SYMBOL(…); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) { … } EXPORT_SYMBOL(…); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { … } EXPORT_SYMBOL(…); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { … } EXPORT_SYMBOL(…); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { … } EXPORT_SYMBOL(…); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { … } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { … } EXPORT_SYMBOL_GPL(…); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { … } EXPORT_SYMBOL_GPL(…); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { … } EXPORT_SYMBOL_GPL(…); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { … } EXPORT_SYMBOL_GPL(…); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int order, int *errcode, gfp_t gfp_mask) { … } EXPORT_SYMBOL(…); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { … } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct sk_buff *skb, struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { … } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { … } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { … } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { … } EXPORT_SYMBOL(…); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { … } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { … } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { … } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { … } /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { … } #endif #ifdef CONFIG_MCTP_FLOWS static void skb_ext_put_mctp(struct mctp_flow *flow) { … } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { … } EXPORT_SYMBOL(…); void __skb_ext_put(struct skb_ext *ext) { … } EXPORT_SYMBOL(…); #endif /* CONFIG_SKB_EXTENSIONS */ static void kfree_skb_napi_cache(struct sk_buff *skb) { … } /** * skb_attempt_defer_free - queue skb for remote freeing * @skb: buffer * * Put @skb in a per-cpu list, using the cpu which * allocated the skb/pages to reduce false sharing * and memory zone spinlock contention. */ void skb_attempt_defer_free(struct sk_buff *skb) { … } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, size_t offset, size_t len) { … } /** * skb_splice_from_iter - Splice (or copy) pages to skbuff * @skb: The buffer to add pages to * @iter: Iterator representing the pages to be added * @maxsize: Maximum amount of pages to be added * @gfp: Allocation flags * * This is a common helper function for supporting MSG_SPLICE_PAGES. It * extracts pages from an iterator and adds them to the socket buffer if * possible, copying them to fragments if not possible (such as if they're slab * pages). * * Returns the amount of data spliced/copied or -EMSGSIZE if there's * insufficient space in the buffer to transfer anything. */ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp) { … } EXPORT_SYMBOL(…); static __always_inline size_t memcpy_from_iter_csum(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { … } static __always_inline size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { … } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux