// SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * 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
*/
/* 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 \
(is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \
(SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \
SKB_SMALL_HEAD_SIZE)
/* 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(offsetof(struct bio_vec, bv_page) ==
offsetof(skb_frag_t, netmem));
static_assert(sizeof_field(struct bio_vec, bv_page) ==
sizeof_field(skb_frag_t, netmem));
/** * 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, conststruct drop_reason_list *list)
{ if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE ||
subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return;
/* must point to statically allocated memory, so INIT is OK */
RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], list);
}
EXPORT_SYMBOL_GPL(drop_reasons_register_subsys);
/** * 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)
{ if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE ||
subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return;
/** * 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.
*/ staticvoid skb_panic(struct sk_buff *skb, unsignedint sz, void *addr, constchar msg[])
{
pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n",
msg, addr, skb->len, sz, skb->head, skb->data,
(unsignedlong)skb->tail, (unsignedlong)skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
/** * napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache * @skbs: pointer to an at least @n-sized array to fill with skb pointers * @n: number of entries to provide * * Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes * the pointers into the provided array @skbs. If there are less entries * available, tries to replenish the cache and bulk-allocates the diff from * the MM layer if needed. * The heads are being zeroed with either memset() or %__GFP_ZERO, so they are * ready for {,__}build_skb_around() and don't have any data buffers attached. * Must be called *only* from the BH context. * * Return: number of successfully allocated skbs (@n if no actual allocation * needed or kmem_cache_alloc_bulk() didn't fail).
*/
u32 napi_skb_cache_get_bulk(void **skbs, u32 n)
{ struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
u32 bulk, total = n;
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
if (nc->skb_count >= n) goto get;
/* No enough cached skbs. Try refilling the cache first */
bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK);
nc->skb_count += kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN, bulk,
&nc->skb_cache[nc->skb_count]); if (likely(nc->skb_count >= n)) goto get;
/* Still not enough. Bulk-allocate the missing part directly, zeroed */
n -= kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN,
n - nc->skb_count, &skbs[nc->skb_count]); if (likely(nc->skb_count >= n)) goto get;
/* kmem_cache didn't allocate the number we need, limit the output */
total -= n - nc->skb_count;
n = nc->skb_count;
get: for (u32 base = nc->skb_count - n, i = 0; i < n; i++) {
u32 cache_size = kmem_cache_size(net_hotdata.skbuff_cache);
/* Must find the allocation size (and grow it to match). */
*size = ksize(data); /* krealloc() will immediately return "data" when * "ksize(data)" is requested: it is the existing upper * bounds. As a result, GFP_ATOMIC will be ignored. Note * that this "new" pointer needs to be passed back to the * caller for use so the __alloc_size hinting will be * tracked correctly.
*/
resized = krealloc(data, *size, GFP_ATOMIC);
WARN_ON_ONCE(resized != data); return resized;
}
/* 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)
{ struct sk_buff *skb; unsignedint size;
skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL;
/* Caller must provide SKB that is memset cleared */ staticvoid __build_skb_around(struct sk_buff *skb, void *data, unsignedint frag_size)
{ unsignedint size = frag_size;
/* frag_size == 0 is considered deprecated now. Callers * using slab buffer should use slab_build_skb() instead.
*/ if (WARN_ONCE(size == 0, "Use slab_build_skb() instead"))
data = __slab_build_skb(data, &size);
__finalize_skb_around(skb, data, 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, unsignedint frag_size)
{ struct sk_buff *skb;
skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL;
/* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc
*/ struct sk_buff *build_skb(void *data, unsignedint frag_size)
{ struct sk_buff *skb = __build_skb(data, frag_size);
/** * 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, unsignedint frag_size)
{ if (unlikely(!skb)) return NULL;
/** * __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.
*/ staticstruct sk_buff *__napi_build_skb(void *data, unsignedint frag_size)
{ struct sk_buff *skb;
skb = napi_skb_cache_get(); if (unlikely(!skb)) return NULL;
/** * 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, unsignedint frag_size)
{ struct sk_buff *skb = __napi_build_skb(data, frag_size);
/* * 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
*/ staticvoid *kmalloc_reserve(unsignedint *size, gfp_t flags, int node, bool *pfmemalloc)
{ bool ret_pfmemalloc = false;
size_t obj_size; void *obj;
obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
!(flags & KMALLOC_NOT_NORMAL_BITS)) {
obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache,
flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
node);
*size = SKB_SMALL_HEAD_CACHE_SIZE; if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; /* Try again but now we are using pfmemalloc reserves */
ret_pfmemalloc = true;
obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out;
}
obj_size = kmalloc_size_roundup(obj_size); /* The following cast might truncate high-order bits of obj_size, this * is harmless because kmalloc(obj_size >= 2^32) will fail anyway.
*/
*size = (unsignedint)obj_size;
/* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail.
*/
obj = kmalloc_node_track_caller(obj_size,
flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
node); if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out;
/* Try again but now we are using pfmemalloc reserves */
ret_pfmemalloc = true;
obj = kmalloc_node_track_caller(obj_size, flags, node);
out: if (pfmemalloc)
*pfmemalloc = ret_pfmemalloc;
return obj;
}
/* 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(unsignedint size, gfp_t gfp_mask, int flags, int node)
{ struct kmem_cache *cache; struct sk_buff *skb; bool pfmemalloc;
u8 *data;
if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
gfp_mask |= __GFP_MEMALLOC;
/* Get the HEAD */ if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI &&
likely(node == NUMA_NO_NODE || node == numa_mem_id()))
skb = napi_skb_cache_get(); else
skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); if (unlikely(!skb)) return NULL;
prefetchw(skb);
/* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned.
*/
data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation.
*/
prefetchw(data + SKB_WITH_OVERHEAD(size));
/* * Only clear those fields we need to clear, not those that we will * actually initialise below. Hence, don't put any more fields after * the tail pointer in struct sk_buff!
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, size);
skb->pfmemalloc = pfmemalloc;
if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones;
/** * __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, unsignedint len,
gfp_t gfp_mask)
{ struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data;
len += NET_SKB_PAD;
/* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation.
*/ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) ||
len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success;
}
len = SKB_HEAD_ALIGN(len);
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
/** * 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, unsignedint len)
{
gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN; struct napi_alloc_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data;
DEBUG_NET_WARN_ON_ONCE(!in_softirq());
len += NET_SKB_PAD + NET_IP_ALIGN;
/* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation.
*/ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) ||
len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI,
NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success;
}
len = SKB_HEAD_ALIGN(len);
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsignedint truesize)
{
DEBUG_NET_WARN_ON_ONCE(size > truesize);
/** * 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.
*/ staticint skb_pp_frag_ref(struct sk_buff *skb)
{ struct skb_shared_info *shinfo;
netmem_ref head_netmem; int i;
if (!skb->pp_recycle) return -EINVAL;
shinfo = skb_shinfo(skb);
for (i = 0; i < shinfo->nr_frags; i++) {
head_netmem = netmem_compound_head(shinfo->frags[i].netmem); if (likely(netmem_is_pp(head_netmem)))
page_pool_ref_netmem(head_netmem); else
page_ref_inc(netmem_to_page(head_netmem));
} return 0;
}
if (skb_zcopy(skb)) { bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS;
skb_zcopy_clear(skb, true); if (skip_unref) goto free_head;
}
for (i = 0; i < shinfo->nr_frags; i++)
__skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
free_head: if (shinfo->frag_list)
kfree_skb_list_reason(shinfo->frag_list, reason);
skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have * additional references to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling
*/
skb->pp_recycle = 0;
}
/* * Free an skbuff by memory without cleaning the state.
*/ staticvoid kfree_skbmem(struct sk_buff *skb)
{ struct sk_buff_fclones *fclones;
switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE:
kmem_cache_free(net_hotdata.skbuff_cache, skb); return;
case SKB_FCLONE_ORIG:
fclones = container_of(skb, struct sk_buff_fclones, skb1);
/* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good.
*/ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break;
/* Free everything but the sk_buff shell. */ staticvoid skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason)
{
skb_release_head_state(skb); if (likely(skb->head))
skb_release_data(skb, 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
*/
/** * 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)
{ if (__sk_skb_reason_drop(sk, skb, reason))
__kfree_skb(skb);
}
EXPORT_SYMBOL(sk_skb_reason_drop);
staticvoid kfree_skb_add_bulk(struct sk_buff *skb, struct skb_free_array *sa, enum skb_drop_reason reason)
{ /* if SKB is a clone, don't handle this case */ if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) {
__kfree_skb(skb); return;
}
/** * 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)
{ if (skb) {
skb_zcopy_downgrade_managed(skb);
skb_zcopy_clear(skb, true);
}
}
EXPORT_SYMBOL(skb_tx_error);
#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)
{ if (!skb_unref(skb)) return;
/** * __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)
{
trace_consume_skb(skb, __builtin_return_address(0));
skb_release_data(skb, SKB_CONSUMED);
kfree_skbmem(skb);
}
if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
kasan_mempool_unpoison_object(nc->skb_cache[i],
kmem_cache_size(net_hotdata.skbuff_cache));
void napi_consume_skb(struct sk_buff *skb, int budget)
{ /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) {
dev_consume_skb_any(skb); return;
}
DEBUG_NET_WARN_ON_ONCE(!in_softirq());
if (!skb_unref(skb)) return;
/* if reaching here SKB is ready to free */
trace_consume_skb(skb, __builtin_return_address(0));
/* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) {
__kfree_skb(skb); return;
}
/* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) \
BUILD_BUG_ON(offsetof(struct sk_buff, field) != \
offsetof(struct sk_buff, headers.field)); \
/* Note : this field could be in the headers group. * It is not yet because we do not want to have a 16 bit hole
*/
new->queue_mapping = old->queue_mapping;
/* * You should not add any new code to this function. Add it to * __copy_skb_header above instead.
*/ staticstruct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
{ #define C(x) n->x = skb->x
/** * 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)
{ struct sk_buff *n;
n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL;
/** * 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)
{
skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src);
}
EXPORT_SYMBOL_GPL(skb_morph);
struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem)
{ if (uarg) { struct ubuf_info_msgzc *uarg_zc; const u32 byte_limit = 1 << 19; /* limit to a few TSO */
u32 bytelen, next;
/* there might be non MSG_ZEROCOPY users */ if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL;
/* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized
*/ if (!sock_owned_by_user(sk)) {
WARN_ON_ONCE(1); return NULL;
}
uarg_zc = uarg_to_msgzc(uarg);
bytelen = uarg_zc->bytelen + size; if (uarg_zc->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL;
}
next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg_zc->id + uarg_zc->len) == next) { if (likely(!devmem) &&
mm_account_pinned_pages(&uarg_zc->mmp, size)) return NULL;
uarg_zc->len++;
uarg_zc->bytelen = bytelen;
atomic_set(&sk->sk_zckey, ++next);
/* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM)
net_zcopy_get(uarg);
/* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification
*/ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release;
len = uarg->len;
lo = uarg->id;
hi = uarg->id + len - 1;
is_zerocopy = uarg->zerocopy;
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding)
{ int err, orig_len = skb->len;
if (uarg->ops->link_skb) {
err = uarg->ops->link_skb(skb, uarg); if (err) return err;
} else { struct ubuf_info *orig_uarg = skb_zcopy(skb);
/* An skb can only point to one uarg. This edge case happens * when TCP appends to an skb, but zerocopy_realloc triggered * a new alloc.
*/ if (orig_uarg && uarg != orig_uarg) return -EEXIST;
}
void __skb_zcopy_downgrade_managed(struct sk_buff *skb)
{ int i;
skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i);
}
EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed);
staticint skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
gfp_t gfp_mask)
{ if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) {
WARN_ON_ONCE(1); return -ENOMEM;
} if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO;
}
skb_zcopy_set(nskb, skb_uarg(orig), NULL);
} return 0;
}
/** * 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)
{ int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, order, psize, new_frags;
u32 d_off;
if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL;
if (!skb_frags_readable(skb)) return -EFAULT;
if (!num_frags) goto release;
/* We might have to allocate high order pages, so compute what minimum * page order is needed.
*/
order = 0; while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb))
order++;
psize = (PAGE_SIZE << order);
new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order); for (i = 0; i < new_frags; i++) {
page = alloc_pages(gfp_mask | __GFP_COMP, order); if (!page) { while (head) { struct page *next = (struct page *)page_private(head);
put_page(head);
head = next;
} return -ENOMEM;
}
set_page_private(page, (unsignedlong)head);
head = page;
}
page = head;
d_off = 0; for (i = 0; i < num_frags; i++) {
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
u32 p_off, p_len, copied; struct page *p;
u8 *vaddr;
/** * 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.
*/
void skb_headers_offset_update(struct sk_buff *skb, int off)
{ /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */
skb->transport_header += off;
skb->network_header += off; if (skb_mac_header_was_set(skb))
skb->mac_header += off;
skb->inner_transport_header += off;
skb->inner_network_header += off;
skb->inner_mac_header += off;
}
EXPORT_SYMBOL(skb_headers_offset_update);
/** * 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.
*/
/** * __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.
*/
/* Set the data pointer */
skb_reserve(n, headroom); /* Set the tail pointer and length */
skb_put(n, skb_headlen(skb)); /* Copy the bytes */
skb_copy_from_linear_data(skb, n->data, n->len);
/** * 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)
{ unsignedint osize = skb_end_offset(skb); unsignedint size = osize + nhead + ntail; long off;
u8 *data; int i;
BUG_ON(nhead < 0);
BUG_ON(skb_shared(skb));
skb_zcopy_downgrade_managed(skb);
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata;
size = SKB_WITH_OVERHEAD(size);
/* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void.
*/
memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head);
/* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values
*/ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb))
refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i);
if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
/* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket).
*/ if (!skb->sk || skb->destructor == sock_edemux)
skb->truesize += size - osize;
/* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
{ unsignedint saved_end_offset, saved_truesize; struct skb_shared_info *shinfo; int res;
res = pskb_expand_head(skb, 0, 0, pri); if (res) return res;
skb->truesize = saved_truesize;
if (likely(skb_end_offset(skb) == saved_end_offset)) return 0;
/* We can not change skb->end if the original or new value * is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head().
*/ if (saved_end_offset == SKB_SMALL_HEAD_HEADROOM ||
skb_end_offset(skb) == SKB_SMALL_HEAD_HEADROOM) { /* We think this path should not be taken. * Add a temporary trace to warn us just in case.
*/
pr_err_once("__skb_unclone_keeptruesize() skb_end_offset() %u -> %u\n",
saved_end_offset, skb_end_offset(skb));
WARN_ON_ONCE(1); return 0;
}
shinfo = skb_shinfo(skb);
/* We are about to change back skb->end, * we need to move skb_shinfo() to its new location.
*/
memmove(skb->head + saved_end_offset,
shinfo,
offsetof(struct skb_shared_info, frags[shinfo->nr_frags]));
skb_set_end_offset(skb, saved_end_offset);
return 0;
}
/** * 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.
*/
/** * 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(conststruct sk_buff *skb, int newheadroom, int newtailroom,
gfp_t gfp_mask)
{ /* * Allocate the copy buffer
*/ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom;
if (!skb_frags_readable(skb)) return NULL;
if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL;
oldheadroom = skb_headroom(skb);
n = __alloc_skb(newheadroom + skb->len + newtailroom,
gfp_mask, skb_alloc_rx_flag(skb),
NUMA_NO_NODE); if (!n) return NULL;
skb_reserve(n, newheadroom);
/* Set the tail pointer and length */
skb_put(n, skb->len);
/** * __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)
{ int err; int ntail;
/* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
memset(skb->data+skb->len, 0, pad); return 0;
}
ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) {
err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb;
}
/* FIXME: The use of this function with non-linear skb's really needs * to be audited.
*/
err = skb_linearize(skb); if (unlikely(err)) goto free_skb;
memset(skb->data + skb->len, 0, pad); return 0;
free_skb: if (free_on_error)
kfree_skb(skb); return err;
}
EXPORT_SYMBOL(__skb_pad);
/** * 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.
*/
/** * 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, unsignedint len)
{ void *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, __builtin_return_address(0)); return tmp;
}
EXPORT_SYMBOL(skb_put);
/** * 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, unsignedint len)
{
skb->data -= len;
skb->len += len; if (unlikely(skb->data < skb->head))
skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data;
}
EXPORT_SYMBOL(skb_push);
/** * 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, unsignedint len)
{ return skb_pull_inline(skb, len);
}
EXPORT_SYMBOL(skb_pull);
/** * 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)
{ void *data = skb->data;
if (skb->len < len) return NULL;
skb_pull(skb, len);
return data;
}
EXPORT_SYMBOL(skb_pull_data);
/** * 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, unsignedint len)
{ if (skb->len > len)
__skb_trim(skb, len);
}
EXPORT_SYMBOL(skb_trim);
/* Trims skb to length len. It can change skb pointers.
*/
int ___pskb_trim(struct sk_buff *skb, unsignedint len)
{ struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err;
/* Note : use pskb_trim_rcsum() instead of calling this directly
*/ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsignedint len)
{ if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len;
/** * __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)
{ /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned.
*/ int i, k, eat = (skb->tail + delta) - skb->end;
/* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb.
*/ if (!skb_has_frag_list(skb)) goto pull_pages;
/* Estimate size of pulled pages. */
eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (size >= eat) goto pull_pages;
eat -= size;
}
/* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8)
*/ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL;
do { if (list->len <= eat) { /* Eaten as whole. */
eat -= list->len;
list = list->next;
insp = list;
} else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag &&
skb_headlen(list))
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */
clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL;
insp = list->next;
list = clone;
} else { /* This may be pulled without
* problems. */
insp = list;
} if (!pskb_pull(list, eat)) {
kfree_skb(clone); return NULL;
} break;
}
} while (eat);
/* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) {
skb_shinfo(skb)->frag_list = list->next;
consume_skb(list);
} /* And insert new clone at head. */ if (clone) {
clone->next = list;
skb_shinfo(skb)->frag_list = clone;
}
} /* Success! Now we may commit changes to skb data. */
pull_pages:
eat = delta;
k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
/** * 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(conststruct sk_buff *skb, int offset, void *to, int len)
{ int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy;
if (offset > (int)skb->len - len) goto fault;
/* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len)
copy = len;
skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0;
offset += copy;
to += copy;
}
if (!skb_frags_readable(skb)) goto fault;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end;
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(f); if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied; struct page *p;
u8 *vaddr;
/* * 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.
*/ staticvoid sock_spd_release(struct splice_pipe_desc *spd, unsignedint i)
{
put_page(spd->pages[i]);
}
/* * Fill page/offset/length into spd, if it can hold more pages.
*/ staticbool spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsignedint *len, unsignedint offset, bool linear, struct sock *sk)
{ if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) returntrue;
/* * 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.
*/ staticbool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsignedint *offset, unsignedint *len, struct splice_pipe_desc *spd, struct sock *sk)
{ struct sk_buff *iter; int seg;
/* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page.
*/ if (__splice_segment(virt_to_page(skb->data),
(unsignedlong) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
offset, len, spd,
skb_head_is_locked(skb),
sk)) returntrue;
/* * then map the fragments
*/ if (!skb_frags_readable(skb)) returnfalse;
for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
skb_walk_frags(skb, iter) { if (*offset >= iter->len) {
*offset -= iter->len; continue;
} /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case.
*/ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) returntrue;
}
returnfalse;
}
/* * 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, unsignedint offset, struct pipe_inode_info *pipe, unsignedint tlen, unsignedint flags)
{ struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.nr_pages_max = MAX_SKB_FRAGS,
.ops = &nosteal_pipe_buf_ops,
.spd_release = sock_spd_release,
}; int ret = 0;
iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error;
offset += ret;
len -= ret;
}
/* All the data was skb head? */ if (!len) goto out;
/* Make offset relative to start of frags */
offset -= skb_headlen(skb);
/* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
if (offset < skb_frag_size(frag)) break;
offset -= skb_frag_size(frag);
}
for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
error: return orig_len == len ? ret : orig_len - len;
}
/* 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)
{ return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags)
{ return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags);
/* 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)
{ return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0);
}
/** * 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, constvoid *from, int len)
{ int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy;
if (offset > (int)skb->len - len) goto fault;
if ((copy = start - offset) > 0) { if (copy > len)
copy = len;
skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0;
offset += copy;
from += copy;
}
if (!skb_frags_readable(skb)) goto fault;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied; struct page *p;
u8 *vaddr;
__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
{
__sum16 sum;
sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev, skb);
} if (!skb_shared(skb))
skb->csum_valid = !sum; return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete_head);
/* 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)
{
__wsum csum;
__sum16 sum;
csum = skb_checksum(skb, 0, skb->len, 0);
sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around.
*/ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev, skb);
}
if (!skb_shared(skb)) { /* Save full packet checksum */
skb->csum = csum;
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum_complete_sw = 1;
skb->csum_valid = !sum;
}
/** * 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)
{ int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsignedint offset;
BUG_ON(!from->head_frag && !hlen);
/* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len); if (plen) {
page = virt_to_head_page(from->head);
offset = from->data - (unsignedchar *)page_address(page);
__skb_fill_netmem_desc(to, 0, page_to_netmem(page),
offset, plen);
get_page(page);
j = 1;
len -= plen;
}
}
/** * 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.
*/
/** * 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)
{ unsignedlong flags; struct sk_buff *result;
/** * 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)
{ struct sk_buff_head tmp; unsignedlong flags;
/** * 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).
*/ unsignedint skb_rbtree_purge(struct rb_root *root)
{ struct rb_node *p = rb_first(root); unsignedint sum = 0;
/** * 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)
{ unsignedlong flags;
/** * 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)
{ unsignedlong flags;
/** * 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)
{ unsignedlong flags;
/** * 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)
{ unsignedlong flags;
skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len),
pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (pos + size > len) {
skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this.
*/
skb_frag_ref(skb, i);
skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos);
skb_shinfo(skb)->nr_frags++;
}
k++;
} else
skb_shinfo(skb)->nr_frags++;
pos += size;
}
skb_shinfo(skb1)->nr_frags = k;
skb1->unreadable = skb->unreadable;
}
/** * 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)
{ int pos = skb_headlen(skb); constint zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY;
skb_zcopy_downgrade_managed(skb);
skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags;
skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */
skb_split_inside_header(skb, skb1, len, pos); else/* Second chunk has no header, nothing to copy. */
skb_split_no_header(skb, skb1, len, pos);
}
EXPORT_SYMBOL(skb_split);
/* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here!
*/ staticint skb_prepare_for_shift(struct sk_buff *skb)
{ return skb_unclone_keeptruesize(skb, GFP_ATOMIC);
}
/** * 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)
{ int from, to, merge, todo;
skb_frag_t *fragfrom, *fragto;
BUG_ON(shiftlen > skb->len);
if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0;
todo = shiftlen;
from = 0;
to = skb_shinfo(tgt)->nr_frags;
fragfrom = &skb_shinfo(skb)->frags[from];
/* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes
*/ if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
skb_frag_off(fragfrom))) {
merge = -1;
} else {
merge = to - 1;
todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) ||
skb_prepare_for_shift(tgt)) return 0;
/* All previous frag pointers might be stale! */
fragfrom = &skb_shinfo(skb)->frags[from];
fragto = &skb_shinfo(tgt)->frags[merge];
/* Reposition in the original skb */
to = 0; while (from < skb_shinfo(skb)->nr_frags)
skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
skb_shinfo(skb)->nr_frags = to;
BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);
onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent
*/
tgt->ip_summed = CHECKSUM_PARTIAL;
skb->ip_summed = CHECKSUM_PARTIAL;
/** * 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, unsignedint from, unsignedint to, struct skb_seq_state *st)
{
st->lower_offset = from;
st->upper_offset = to;
st->root_skb = st->cur_skb = skb;
st->frag_idx = st->stepped_offset = 0;
st->frag_data = NULL;
st->frag_off = 0;
}
EXPORT_SYMBOL(skb_prepare_seq_read);
/** * 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.
*/ unsignedint skb_seq_read(unsignedint consumed, const u8 **data, struct skb_seq_state *st)
{ unsignedint block_limit, abs_offset = consumed + st->lower_offset;
skb_frag_t *frag;
if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) {
kunmap_atomic(st->frag_data);
st->frag_data = NULL;
} return 0;
}
/** * 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)
{ if (st->frag_data)
kunmap_atomic(st->frag_data);
}
EXPORT_SYMBOL(skb_abort_seq_read);
/** * 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)
{ const u8 *data;
u32 sqlen;
for (;;) {
sqlen = skb_seq_read(offset, &data, st); if (sqlen == 0) return -EINVAL; if (sqlen >= len) {
memcpy(to, data, len); return 0;
}
memcpy(to, data, sqlen);
to += sqlen;
offset += sqlen;
len -= sqlen;
}
}
EXPORT_SYMBOL(skb_copy_seq_read);
/** * 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.
*/ unsignedint skb_find_text(struct sk_buff *skb, unsignedint from, unsignedint to, struct ts_config *config)
{ unsignedint patlen = config->ops->get_pattern_len(config); struct ts_state state; unsignedint ret;
/** * 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, unsignedint len)
{ unsignedchar *data = skb->data;
/** * 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)
{ struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsignedint mss = skb_shinfo(head_skb)->gso_size; unsignedint doffset = head_skb->data - skb_mac_header(head_skb); unsignedint offset = doffset; unsignedint tnl_hlen = skb_tnl_header_len(head_skb); unsignedint partial_segs = 0; unsignedint headroom; unsignedint len = head_skb->len; struct sk_buff *frag_skb;
skb_frag_t *frag;
__be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos;
for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG.
*/
features &= ~NETIF_F_SG; break;
}
}
}
__skb_push(head_skb, doffset);
proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL);
if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsignedint frag_len;
if (!list_skb ||
!net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal;
/* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length.
*/
frag_len = list_skb->len;
skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal;
len -= iter->len;
}
if (len != frag_len) goto normal;
}
/* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS.
*/
partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1)
mss *= partial_segs; else
partial_segs = 0;
}
/* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example)
*/
segs->prev = tail;
if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsignedshort gso_size = skb_shinfo(head_skb)->gso_size;
/* Update type to add partial and then remove dodgy if set */
type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL;
type &= ~SKB_GSO_DODGY;
/* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols.
*/ for (iter = segs; iter; iter = iter->next) {
skb_shinfo(iter)->gso_size = gso_size;
skb_shinfo(iter)->gso_segs = partial_segs;
skb_shinfo(iter)->gso_type = type;
SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset;
}
/* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment.
*/ if (head_skb->destructor == sock_wfree) {
swap(tail->truesize, head_skb->truesize);
swap(tail->destructor, head_skb->destructor);
swap(tail->sk, head_skb->sk);
} return segs;
/* 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 SLAB_NO_MERGE #else/* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */ #define FLAG_SKB_NO_MERGE 0 #endif
void __init skb_init(void)
{
net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|
FLAG_SKB_NO_MERGE,
offsetof(struct sk_buff, cb),
sizeof_field(struct sk_buff, cb),
NULL);
net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL); /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user.
*/
net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
SKB_SMALL_HEAD_CACHE_SIZE,
0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC,
0,
SKB_SMALL_HEAD_HEADROOM,
NULL);
skb_extensions_init();
}
staticint
__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsignedint recursion_level)
{ int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0;
if (unlikely(recursion_level >= 24)) return -EMSGSIZE;
if (copy > 0) { if (copy > len)
copy = len;
sg_set_buf(sg, skb->data + offset, copy);
elt++; if ((len -= copy) == 0) return elt;
offset += copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE;
/** * 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)
{ int nsg = __skb_to_sgvec(skb, sg, offset, len, 0);
if (nsg <= 0) return nsg;
sg_mark_end(&sg[nsg - 1]);
return nsg;
}
EXPORT_SYMBOL_GPL(skb_to_sgvec);
/* 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)
{ return __skb_to_sgvec(skb, sg, offset, len, 0);
}
EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
/** * 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)
{ int copyflag; int elt; struct sk_buff *skb1, **skb_p;
/* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous).
*/ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
!__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM;
/* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more
* space, 128 bytes is fair. */
staticvoid skb_set_err_queue(struct sk_buff *skb)
{ /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. * So, it is safe to (mis)use it to mark skbs on the error queue.
*/
skb->pkt_type = PACKET_OUTGOING;
BUILD_BUG_ON(PACKET_OUTGOING == 0);
}
/* * Note: We dont mem charge error packets (no sk_forward_alloc changes)
*/ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{ if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsignedint)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM;
/** * 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)
{ struct sock *sk = skb->sk; struct sk_buff *clone;
if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL;
/* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero.
*/ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
sock_put(sk); return;
}
staticbool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, int tstype)
{ switch (tstype) { case SCM_TSTAMP_SCHED: return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP; case SCM_TSTAMP_SND: return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
SKBTX_SW_TSTAMP); case SCM_TSTAMP_ACK: return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK; case SCM_TSTAMP_COMPLETION: return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP;
}
returnfalse;
}
staticvoid skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype)
{ int op;
switch (tstype) { case SCM_TSTAMP_SCHED:
op = BPF_SOCK_OPS_TSTAMP_SCHED_CB; break; case SCM_TSTAMP_SND: if (hwtstamps) {
op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB;
*skb_hwtstamps(skb) = *hwtstamps;
} else {
op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
} break; case SCM_TSTAMP_ACK:
op = BPF_SOCK_OPS_TSTAMP_ACK_CB; break; default: return;
}
/* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero.
*/ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
err = sock_queue_err_skb(sk, skb);
sock_put(sk);
} if (err)
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); #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)
{
u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
u32 csum_start = skb_headroom(skb) + (u32)start;
/* 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 256
len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp;
err = skb_maybe_pull_tail(skb,
off + sizeof(struct ipv6_opt_hdr),
MAX_IPV6_HDR_LEN); if (err < 0) goto out;
hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
nexthdr = hp->nexthdr;
off += ipv6_optlen(hp); break;
} case IPPROTO_AH: { struct ip_auth_hdr *hp;
err = skb_maybe_pull_tail(skb,
off + sizeof(struct ip_auth_hdr),
MAX_IPV6_HDR_LEN); if (err < 0) goto out;
hp = OPT_HDR(struct ip_auth_hdr, skb, off);
nexthdr = hp->nexthdr;
off += ipv6_authlen(hp); break;
} case IPPROTO_FRAGMENT: { struct frag_hdr *hp;
err = skb_maybe_pull_tail(skb,
off + sizeof(struct frag_hdr),
MAX_IPV6_HDR_LEN); if (err < 0) goto out;
hp = OPT_HDR(struct frag_hdr, skb, off);
if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
fragment = true;
/** * 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)
{ int err;
switch (skb->protocol) { case htons(ETH_P_IP):
err = skb_checksum_setup_ipv4(skb, recalculate); break;
case htons(ETH_P_IPV6):
err = skb_checksum_setup_ipv6(skb, recalculate); break;
default:
err = -EPROTO; break;
}
return err;
}
EXPORT_SYMBOL(skb_checksum_setup);
/** * 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.
*/ staticstruct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsignedint transport_len)
{ struct sk_buff *skb_chk; unsignedint len = skb_transport_offset(skb) + transport_len; int ret;
skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL;
ret = pskb_trim_rcsum(skb_chk, len); if (ret) {
kfree_skb(skb_chk); return NULL;
}
return skb_chk;
}
/** * 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, unsignedint transport_len,
__sum16(*skb_chkf)(struct sk_buff *skb))
{ struct sk_buff *skb_chk; unsignedint offset = skb_transport_offset(skb);
__sum16 ret;
skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err;
if (!pskb_may_pull(skb_chk, offset)) goto err;
skb_pull_rcsum(skb_chk, offset);
ret = skb_chkf(skb_chk);
skb_push_rcsum(skb_chk, offset);
if (ret) goto err;
return skb_chk;
err: if (skb_chk && skb_chk != skb)
kfree_skb(skb_chk);
return NULL;
}
EXPORT_SYMBOL(skb_checksum_trimmed);
void __skb_warn_lro_forwarding(conststruct sk_buff *skb)
{
net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
skb->dev->name);
}
EXPORT_SYMBOL(__skb_warn_lro_forwarding);
/** * 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)
{ struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len;
*fragstolen = false;
if (skb_cloned(to)) returnfalse;
/* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. In theory we could take full * references if @from is cloned and !@to->pp_recycle but its * tricky (due to potential race with the clone disappearing) and * rare, so not worth dealing with.
*/ if (to->pp_recycle != from->pp_recycle) returnfalse;
if (skb_frags_readable(from) != skb_frags_readable(to)) returnfalse;
if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len)
BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
*delta_truesize = 0; returntrue;
}
to_shinfo = skb_shinfo(to);
from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) returnfalse; if (skb_zcopy(to) || skb_zcopy(from)) returnfalse;
if (skb_headlen(from) != 0) { struct page *page; unsignedint offset;
if (to_shinfo->nr_frags +
from_shinfo->nr_frags >= MAX_SKB_FRAGS) returnfalse;
/* if the skb is not cloned this does nothing * since we set nr_frags to 0.
*/ if (skb_pp_frag_ref(from)) { for (i = 0; i < from_shinfo->nr_frags; i++)
__skb_frag_ref(&from_shinfo->frags[i]);
}
/** * 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)
{
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
skb_dst_drop(skb);
skb_ext_reset(skb);
nf_reset_ct(skb);
nf_reset_trace(skb);
if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb;
}
skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsignedshort)))) goto err_free;
int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
{ int needed_headroom = dev->needed_headroom; int needed_tailroom = dev->needed_tailroom;
/* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later.
*/ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
needed_tailroom += ETH_ZLEN - skb->len; /* skb_headroom() returns unsigned int... */
needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) /* No reallocation needed, yay! */ return 0;
/* 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)
{ int offset = skb->data - skb_mac_header(skb); int err;
if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n",
offset)) { return -EINVAL;
}
err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err;
if (skb_network_offset(skb) < ETH_HLEN)
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_len(skb);
return err;
}
EXPORT_SYMBOL(__skb_vlan_pop);
/* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header.
*/ int skb_vlan_pop(struct sk_buff *skb)
{
u16 vlan_tci;
__be16 vlan_proto; int err;
if (likely(skb_vlan_tag_present(skb))) {
__vlan_hwaccel_clear_tag(skb);
} else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0;
err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err;
} /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0;
/* 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)
{ if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err;
if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n",
offset)) { return -EINVAL;
}
err = __vlan_insert_tag(skb, skb->vlan_proto,
skb_vlan_tag_get(skb)); if (err) return err;
/** * 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)
{ if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
skb_network_offset(skb) < ETH_HLEN) return -EPROTO;
/** * 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, constunsignedchar *dst, constunsignedchar *src)
{ struct ethhdr *eth; int err;
if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO;
err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err;
/** * 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)
{ struct mpls_shim_hdr *lse; int err;
if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL;
/* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL;
err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err;
if (!skb->inner_protocol) {
skb_set_inner_network_header(skb, skb_network_offset(skb));
skb_set_inner_protocol(skb, skb->protocol);
}
/** * 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)
{ int err;
if (unlikely(!eth_p_mpls(skb->protocol))) return 0;
err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err;
/** * 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(unsignedlong header_len, unsignedlong data_len, int order, int *errcode,
gfp_t gfp_mask)
{ unsignedlong chunk; struct sk_buff *skb; struct page *page; int nr_frags = 0;
/* carve out the first off bytes from skb when off < headlen */ staticint pskb_carve_inside_header(struct sk_buff *skb, const u32 off, constint headlen, gfp_t gfp_mask)
{ int i; unsignedint size = skb_end_offset(skb); int new_hlen = headlen - off;
u8 *data;
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM;
size = SKB_WITH_OVERHEAD(size);
/* Copy real data, and all frags */
skb_copy_from_linear_data_offset(skb, off, data, new_hlen);
skb->len -= off;
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb),
offsetof(struct skb_shared_info,
frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) {
skb_kfree_head(data, size); return -ENOMEM;
} for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i); if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
skb_release_data(skb, SKB_CONSUMED);
} else { /* we can reuse existing recount- all we did was * relocate values
*/
skb_free_head(skb);
}
/* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve()
*/ staticint pskb_carve_frag_list(struct skb_shared_info *shinfo, int eat,
gfp_t gfp_mask)
{ struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL;
do { if (!list) {
pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT;
} if (list->len <= eat) { /* Eaten as whole. */
eat -= list->len;
list = list->next;
insp = list;
} else { /* Eaten partially. */ if (skb_shared(list)) {
clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM;
insp = list->next;
list = clone;
} else { /* This may be pulled without problems. */
insp = list;
} if (pskb_carve(list, eat, gfp_mask) < 0) {
kfree_skb(clone); return -ENOMEM;
} break;
}
} while (eat);
/* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) {
shinfo->frag_list = list->next;
consume_skb(list);
} /* And insert new clone at head. */ if (clone) {
clone->next = list;
shinfo->frag_list = clone;
} return 0;
}
/* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb
*/ staticint pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask)
{ int i, k = 0; unsignedint size = skb_end_offset(skb);
u8 *data; constint nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo;
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM;
size = SKB_WITH_OVERHEAD(size);
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) {
skb_kfree_head(data, size); return -ENOMEM;
}
shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (pos + fsize > off) {
shinfo->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this.
*/
skb_frag_off_add(&shinfo->frags[0], off - pos);
skb_frag_size_sub(&shinfo->frags[0], off - pos);
}
skb_frag_ref(skb, i);
k++;
}
pos += fsize;
}
shinfo->nr_frags = k; if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
/* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb))
kfree_skb_list(skb_shinfo(skb)->frag_list);
skb_kfree_head(data, size); return -ENOMEM;
}
skb_release_data(skb, SKB_CONSUMED);
/* remove len bytes from the beginning of the skb */ staticint pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp)
{ int headlen = skb_headlen(skb);
/* 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)
{ struct sk_buff *clone = skb_clone(skb, gfp);
/** * 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)
{ if (skb->data_len) { if (skb->data_len > skb->end - skb->tail ||
skb_cloned(skb) || !skb_frags_readable(skb)) return;
/* Nice, we can free page frag(s) right now */
__pskb_pull_tail(skb, skb->data_len);
} /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize.
*/
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
}
EXPORT_SYMBOL(skb_condense);
/** * __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)
{ struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags);
if (new) {
memset(new->offset, 0, sizeof(new->offset));
refcount_set(&new->refcnt, 1);
}
/** * 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)
{ struct skb_ext *new, *old = NULL; unsignedint newlen, newoff;
if (skb->active_extensions) {
old = skb->extensions;
new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL;
void __skb_ext_put(struct skb_ext *ext)
{ /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op.
*/ if (refcount_read(&ext->refcnt) == 1) goto free_now;
if (!refcount_dec_and_test(&ext->refcnt)) return;
free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif #ifdef CONFIG_MCTP_FLOWS if (__skb_ext_exist(ext, SKB_EXT_MCTP))
skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP)); #endif
staticvoid kfree_skb_napi_cache(struct sk_buff *skb)
{ /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) {
__kfree_skb(skb); return;
}
/** * 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)
{ int cpu = skb->alloc_cpu; struct softnet_data *sd; unsignedint defer_max; bool kick;
spin_lock_bh(&sd->defer_lock); /* Send an IPI every time queue reaches half capacity. */
kick = sd->defer_count == (defer_max >> 1); /* Paired with the READ_ONCE() few lines above */
WRITE_ONCE(sd->defer_count, sd->defer_count + 1);
skb->next = sd->defer_list; /* Paired with READ_ONCE() in skb_defer_free_flush() */
WRITE_ONCE(sd->defer_list, skb);
spin_unlock_bh(&sd->defer_lock);
/* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely).
*/ if (unlikely(kick))
kick_defer_list_purge(sd, cpu);
}
/** * 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 * * 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)
{
size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags); struct page *pages[8], **ppages = pages;
ssize_t spliced = 0, ret = 0; unsignedint i;
¤ Diese beiden folgenden Angebotsgruppen bietet das Unternehmen0.222Angebot
(Wie Sie bei der Firma Beratungs- und Dienstleistungen beauftragen können 2026-04-25)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.