blob: edbbef563d4d913dafd4be4287373fb77670e826 [file] [log] [blame]
// 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
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/sctp.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/splice.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/scatterlist.h>
#include <linux/errqueue.h>
#include <linux/prefetch.h>
#include <linux/bitfield.h>
#include <linux/if_vlan.h>
#include <linux/mpls.h>
#include <linux/kcov.h>
#include <linux/iov_iter.h>
#include <net/protocol.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/gso.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/mpls.h>
#include <net/mptcp.h>
#include <net/mctp.h>
#include <net/page_pool/helpers.h>
#include <net/dropreason.h>
#include <linux/uaccess.h>
#include <trace/events/skb.h>
#include <linux/highmem.h>
#include <linux/capability.h>
#include <linux/user_namespace.h>
#include <linux/indirect_call_wrapper.h>
#include <linux/textsearch.h>
#include "dev.h"
#include "sock_destructor.h"
struct kmem_cache *skbuff_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
#ifdef CONFIG_SKB_EXTENSIONS
static struct kmem_cache *skbuff_ext_cache __ro_after_init;
#endif
static struct kmem_cache *skb_small_head_cache __ro_after_init;
#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER)
/* 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)
#define SKB_SMALL_HEAD_HEADROOM \
SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE)
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
#undef FN
#define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
static const char * const drop_reasons[] = {
[SKB_CONSUMED] = "CONSUMED",
DEFINE_DROP_REASON(FN, FN)
};
static const struct drop_reason_list drop_reasons_core = {
.reasons = drop_reasons,
.n_reasons = ARRAY_SIZE(drop_reasons),
};
const struct drop_reason_list __rcu *
drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = {
[SKB_DROP_REASON_SUBSYS_CORE] = RCU_INITIALIZER(&drop_reasons_core),
};
EXPORT_SYMBOL(drop_reasons_by_subsys);
/**
* drop_reasons_register_subsys - register another drop reason subsystem
* @subsys: the subsystem to register, must not be the core
* @list: the list of drop reasons within the subsystem, must point to
* a statically initialized list
*/
void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys,
const struct drop_reason_list *list)
{
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;
RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], NULL);
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(drop_reasons_unregister_subsys);
/**
* skb_panic - private function for out-of-line support
* @skb: buffer
* @sz: size
* @addr: address
* @msg: skb_over_panic or skb_under_panic
*
* Out-of-line support for skb_put() and skb_push().
* Called via the wrapper skb_over_panic() or skb_under_panic().
* Keep out of line to prevent kernel bloat.
* __builtin_return_address is not used because it is not always reliable.
*/
static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr,
const char msg[])
{
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,
(unsigned long)skb->tail, (unsigned long)skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
skb_panic(skb, sz, addr, __func__);
}
static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
skb_panic(skb, sz, addr, __func__);
}
#define NAPI_SKB_CACHE_SIZE 64
#define NAPI_SKB_CACHE_BULK 16
#define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2)
#if PAGE_SIZE == SZ_4K
#define NAPI_HAS_SMALL_PAGE_FRAG 1
#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc)
/* specialized page frag allocator using a single order 0 page
* and slicing it into 1K sized fragment. Constrained to systems
* with a very limited amount of 1K fragments fitting a single
* page - to avoid excessive truesize underestimation
*/
struct page_frag_1k {
void *va;
u16 offset;
bool pfmemalloc;
};
static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp)
{
struct page *page;
int offset;
offset = nc->offset - SZ_1K;
if (likely(offset >= 0))
goto use_frag;
page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
if (!page)
return NULL;
nc->va = page_address(page);
nc->pfmemalloc = page_is_pfmemalloc(page);
offset = PAGE_SIZE - SZ_1K;
page_ref_add(page, offset / SZ_1K);
use_frag:
nc->offset = offset;
return nc->va + offset;
}
#else
/* the small page is actually unused in this build; add dummy helpers
* to please the compiler and avoid later preprocessor's conditionals
*/
#define NAPI_HAS_SMALL_PAGE_FRAG 0
#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false
struct page_frag_1k {
};
static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask)
{
return NULL;
}
#endif
struct napi_alloc_cache {
struct page_frag_cache page;
struct page_frag_1k page_small;
unsigned int skb_count;
void *skb_cache[NAPI_SKB_CACHE_SIZE];
};
static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
/* Double check that napi_get_frags() allocates skbs with
* skb->head being backed by slab, not a page fragment.
* This is to make sure bug fixed in 3226b158e67c
* ("net: avoid 32 x truesize under-estimation for tiny skbs")
* does not accidentally come back.
*/
void napi_get_frags_check(struct napi_struct *napi)
{
struct sk_buff *skb;
local_bh_disable();
skb = napi_get_frags(napi);
WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag);
napi_free_frags(napi);
local_bh_enable();
}
void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
fragsz = SKB_DATA_ALIGN(fragsz);
return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
}
EXPORT_SYMBOL(__napi_alloc_frag_align);
void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
{
void *data;
fragsz = SKB_DATA_ALIGN(fragsz);
if (in_hardirq() || irqs_disabled()) {
struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask);
} else {
struct napi_alloc_cache *nc;
local_bh_disable();
nc = this_cpu_ptr(&napi_alloc_cache);
data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
local_bh_enable();
}
return data;
}
EXPORT_SYMBOL(__netdev_alloc_frag_align);
static struct sk_buff *napi_skb_cache_get(void)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
struct sk_buff *skb;
if (unlikely(!nc->skb_count)) {
nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache,
GFP_ATOMIC,
NAPI_SKB_CACHE_BULK,
nc->skb_cache);
if (unlikely(!nc->skb_count))
return NULL;
}
skb = nc->skb_cache[--nc->skb_count];
kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache));
return skb;
}
static inline void __finalize_skb_around(struct sk_buff *skb, void *data,
unsigned int size)
{
struct skb_shared_info *shinfo;
size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
/* Assumes caller memset cleared SKB */
skb->truesize = SKB_TRUESIZE(size);
refcount_set(&skb->users, 1);
skb->head = data;
skb->data = data;
skb_reset_tail_pointer(skb);
skb_set_end_offset(skb, size);
skb->mac_header = (typeof(skb->mac_header))~0U;
skb->transport_header = (typeof(skb->transport_header))~0U;
skb->alloc_cpu = raw_smp_processor_id();
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
skb_set_kcov_handle(skb, kcov_common_handle());
}
static inline void *__slab_build_skb(struct sk_buff *skb, void *data,
unsigned int *size)
{
void *resized;
/* 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;
unsigned int size;
skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
data = __slab_build_skb(skb, data, &size);
__finalize_skb_around(skb, data, size);
return skb;
}
EXPORT_SYMBOL(slab_build_skb);
/* Caller must provide SKB that is memset cleared */
static void __build_skb_around(struct sk_buff *skb, void *data,
unsigned int frag_size)
{
unsigned int 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(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, unsigned int frag_size)
{
struct sk_buff *skb;
skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, frag_size);
return skb;
}
/* build_skb() is wrapper over __build_skb(), that specifically
* takes care of skb->head and skb->pfmemalloc
*/
struct sk_buff *build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb = __build_skb(data, frag_size);
if (likely(skb && frag_size)) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(build_skb);
/**
* build_skb_around - build a network buffer around provided skb
* @skb: sk_buff provide by caller, must be memset cleared
* @data: data buffer provided by caller
* @frag_size: size of data
*/
struct sk_buff *build_skb_around(struct sk_buff *skb,
void *data, unsigned int frag_size)
{
if (unlikely(!skb))
return NULL;
__build_skb_around(skb, data, frag_size);
if (frag_size) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(build_skb_around);
/**
* __napi_build_skb - build a network buffer
* @data: data buffer provided by caller
* @frag_size: size of data
*
* Version of __build_skb() that uses NAPI percpu caches to obtain
* skbuff_head instead of inplace allocation.
*
* Returns a new &sk_buff on success, %NULL on allocation failure.
*/
static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb;
skb = napi_skb_cache_get();
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, frag_size);
return skb;
}
/**
* napi_build_skb - build a network buffer
* @data: data buffer provided by caller
* @frag_size: size of data
*
* Version of __napi_build_skb() that takes care of skb->head_frag
* and skb->pfmemalloc when the data is a page or page fragment.
*
* Returns a new &sk_buff on success, %NULL on allocation failure.
*/
struct sk_buff *napi_build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb = __napi_build_skb(data, frag_size);
if (likely(skb) && frag_size) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(napi_build_skb);
/*
* kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
* the caller if emergency pfmemalloc reserves are being used. If it is and
* the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
* may be used. Otherwise, the packet data may be discarded until enough
* memory is free
*/
static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
bool *pfmemalloc)
{
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(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(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 = (unsigned int)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(unsigned int size, gfp_t gfp_mask,
int flags, int node)
{
struct kmem_cache *cache;
struct sk_buff *skb;
bool pfmemalloc;
u8 *data;
cache = (flags & SKB_ALLOC_FCLONE)
? skbuff_fclone_cache : skbuff_cache;
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;
fclones = container_of(skb, struct sk_buff_fclones, skb1);
skb->fclone = SKB_FCLONE_ORIG;
refcount_set(&fclones->fclone_ref, 1);
}
return skb;
nodata:
kmem_cache_free(cache, skb);
return NULL;
}
EXPORT_SYMBOL(__alloc_skb);
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
* @len: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
*
* Allocate a new &sk_buff and assign it a usage count of one. The
* buffer has NET_SKB_PAD headroom built in. Users should allocate
* the headroom they think they need without accounting for the
* built in space. The built in space is used for optimisations.
*
* %NULL is returned if there is no free memory.
*/
struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
gfp_t gfp_mask)
{
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(1024) ||
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;
if (in_hardirq() || irqs_disabled()) {
nc = this_cpu_ptr(&netdev_alloc_cache);
data = page_frag_alloc(nc, len, gfp_mask);
pfmemalloc = nc->pfmemalloc;
} else {
local_bh_disable();
nc = this_cpu_ptr(&napi_alloc_cache.page);
data = page_frag_alloc(nc, len, gfp_mask);
pfmemalloc = nc->pfmemalloc;
local_bh_enable();
}
if (unlikely(!data))
return NULL;
skb = __build_skb(data, len);
if (unlikely(!skb)) {
skb_free_frag(data);
return NULL;
}
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
skb_success:
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
skb_fail:
return skb;
}
EXPORT_SYMBOL(__netdev_alloc_skb);
/**
* __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
* @napi: napi instance this buffer was allocated for
* @len: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
*
* Allocate a new sk_buff for use in NAPI receive. This buffer will
* attempt to allocate the head from a special reserved region used
* only for NAPI Rx allocation. By doing this we can save several
* CPU cycles by avoiding having to disable and re-enable IRQs.
*
* %NULL is returned if there is no free memory.
*/
struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
gfp_t gfp_mask)
{
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.
* When the small frag allocator is available, prefer it over kmalloc
* for small fragments
*/
if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) ||
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;
}
nc = this_cpu_ptr(&napi_alloc_cache);
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) {
/* we are artificially inflating the allocation size, but
* that is not as bad as it may look like, as:
* - 'len' less than GRO_MAX_HEAD makes little sense
* - On most systems, larger 'len' values lead to fragment
* size above 512 bytes
* - kmalloc would use the kmalloc-1k slab for such values
* - Builds with smaller GRO_MAX_HEAD will very likely do
* little networking, as that implies no WiFi and no
* tunnels support, and 32 bits arches.
*/
len = SZ_1K;
data = page_frag_alloc_1k(&nc->page_small, gfp_mask);
pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small);
} else {
len = SKB_HEAD_ALIGN(len);
data = page_frag_alloc(&nc->page, len, gfp_mask);
pfmemalloc = nc->page.pfmemalloc;
}
if (unlikely(!data))
return NULL;
skb = __napi_build_skb(data, len);
if (unlikely(!skb)) {
skb_free_frag(data);
return NULL;
}
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
skb_success:
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
skb->dev = napi->dev;
skb_fail:
return skb;
}
EXPORT_SYMBOL(__napi_alloc_skb);
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size, unsigned int truesize)
{
DEBUG_NET_WARN_ON_ONCE(size > truesize);
skb_fill_page_desc(skb, i, page, off, size);
skb->len += size;
skb->data_len += size;
skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_add_rx_frag);
void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
unsigned int truesize)
{
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
DEBUG_NET_WARN_ON_ONCE(size > truesize);
skb_frag_size_add(frag, size);
skb->len += size;
skb->data_len += size;
skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_coalesce_rx_frag);
static void skb_drop_list(struct sk_buff **listp)
{
kfree_skb_list(*listp);
*listp = NULL;
}
static inline void skb_drop_fraglist(struct sk_buff *skb)
{
skb_drop_list(&skb_shinfo(skb)->frag_list);
}
static void skb_clone_fraglist(struct sk_buff *skb)
{
struct sk_buff *list;
skb_walk_frags(skb, list)
skb_get(list);
}
static bool is_pp_page(struct page *page)
{
return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
}
#if IS_ENABLED(CONFIG_PAGE_POOL)
bool napi_pp_put_page(struct page *page, bool napi_safe)
{
bool allow_direct = false;
struct page_pool *pp;
page = compound_head(page);
/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
* in order to preserve any existing bits, such as bit 0 for the
* head page of compound page and bit 1 for pfmemalloc page, so
* mask those bits for freeing side when doing below checking,
* and page_is_pfmemalloc() is checked in __page_pool_put_page()
* to avoid recycling the pfmemalloc page.
*/
if (unlikely(!is_pp_page(page)))
return false;
pp = page->pp;
/* Allow direct recycle if we have reasons to believe that we are
* in the same context as the consumer would run, so there's
* no possible race.
* __page_pool_put_page() makes sure we're not in hardirq context
* and interrupts are enabled prior to accessing the cache.
*/
if (napi_safe || in_softirq()) {
const struct napi_struct *napi = READ_ONCE(pp->p.napi);
allow_direct = napi &&
READ_ONCE(napi->list_owner) == smp_processor_id();
}
/* Driver set this to memory recycling info. Reset it on recycle.
* This will *not* work for NIC using a split-page memory model.
* The page will be returned to the pool here regardless of the
* 'flipped' fragment being in use or not.
*/
page_pool_put_full_page(pp, page, allow_direct);
return true;
}
EXPORT_SYMBOL(napi_pp_put_page);
#endif
static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
{
if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
return false;
return napi_pp_put_page(virt_to_page(data), napi_safe);
}
/**
* skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
* @skb: page pool aware skb
*
* Increase the fragment reference count (pp_ref_count) of a skb. This is
* intended to gain fragment references only for page pool aware skbs,
* i.e. when skb->pp_recycle is true, and not for fragments in a
* non-pp-recycling skb. It has a fallback to increase references on normal
* pages, as page pool aware skbs may also have normal page fragments.
*/
static int skb_pp_frag_ref(struct sk_buff *skb)
{
struct skb_shared_info *shinfo;
struct page *head_page;
int i;
if (!skb->pp_recycle)
return -EINVAL;
shinfo = skb_shinfo(skb);
for (i = 0; i < shinfo->nr_frags; i++) {
head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
if (likely(is_pp_page(head_page)))
page_pool_ref_page(head_page);
else
page_ref_inc(head_page);
}
return 0;
}
static void skb_kfree_head(void *head, unsigned int end_offset)
{
if (end_offset == SKB_SMALL_HEAD_HEADROOM)
kmem_cache_free(skb_small_head_cache, head);
else
kfree(head);
}
static void skb_free_head(struct sk_buff *skb, bool napi_safe)
{
unsigned char *head = skb->head;
if (skb->head_frag) {
if (skb_pp_recycle(skb, head, napi_safe))
return;
skb_free_frag(head);
} else {
skb_kfree_head(head, skb_end_offset(skb));
}
}
static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason,
bool napi_safe)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
int i;
if (skb->cloned &&
atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&shinfo->dataref))
goto exit;
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++)
napi_frag_unref(&shinfo->frags[i], skb->pp_recycle, napi_safe);
free_head:
if (shinfo->frag_list)
kfree_skb_list_reason(shinfo->frag_list, reason);
skb_free_head(skb, napi_safe);
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.
*/
static void kfree_skbmem(struct sk_buff *skb)
{
struct sk_buff_fclones *fclones;
switch (skb->fclone) {
case SKB_FCLONE_UNAVAILABLE:
kmem_cache_free(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;
default: /* SKB_FCLONE_CLONE */
fclones = container_of(skb, struct sk_buff_fclones, skb2);
break;
}
if (!refcount_dec_and_test(&fclones->fclone_ref))
return;
fastpath:
kmem_cache_free(skbuff_fclone_cache, fclones);
}
void skb_release_head_state(struct sk_buff *skb)
{
skb_dst_drop(skb);
if (skb->destructor) {
DEBUG_NET_WARN_ON_ONCE(in_hardirq());
skb->destructor(skb);
}
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb_nfct(skb));
#endif
skb_ext_put(skb);
}
/* Free everything but the sk_buff shell. */
static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason,
bool napi_safe)
{
skb_release_head_state(skb);
if (likely(skb->head))
skb_release_data(skb, reason, napi_safe);
}
/**
* __kfree_skb - private function
* @skb: buffer
*
* Free an sk_buff. Release anything attached to the buffer.
* Clean the state. This is an internal helper function. Users should
* always call kfree_skb
*/
void __kfree_skb(struct sk_buff *skb)
{
skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED, false);
kfree_skbmem(skb);
}
EXPORT_SYMBOL(__kfree_skb);
static __always_inline
bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
{
if (unlikely(!skb_unref(skb)))
return false;
DEBUG_NET_WARN_ON_ONCE(reason == SKB_NOT_DROPPED_YET ||
u32_get_bits(reason,
SKB_DROP_REASON_SUBSYS_MASK) >=
SKB_DROP_REASON_SUBSYS_NUM);
if (reason == SKB_CONSUMED)
trace_consume_skb(skb, __builtin_return_address(0));
else
trace_kfree_skb(skb, __builtin_return_address(0), reason);
return true;
}
/**
* kfree_skb_reason - free an sk_buff with special reason
* @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 drop reason to 'kfree_skb'
* tracepoint.
*/
void __fix_address
kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
{
if (__kfree_skb_reason(skb, reason))
__kfree_skb(skb);
}
EXPORT_SYMBOL(kfree_skb_reason);
#define KFREE_SKB_BULK_SIZE 16
struct skb_free_array {
unsigned int skb_count;
void *skb_array[KFREE_SKB_BULK_SIZE];
};
static void 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_release_all(skb, reason, false);
sa->skb_array[sa->skb_count++] = skb;
if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) {
kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE,
sa->skb_array);
sa->skb_count = 0;
}
}
void __fix_address
kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason)
{
struct skb_free_array sa;
sa.skb_count = 0;
while (segs) {
struct sk_buff *next = segs->next;
if (__kfree_skb_reason(segs, reason)) {
skb_poison_list(segs);
kfree_skb_add_bulk(segs, &sa, reason);
}
segs = next;
}
if (sa.skb_count)
kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array);
}
EXPORT_SYMBOL(kfree_skb_list_reason);
/* Dump skb information and contents.
*
* Must only be called from net_ratelimit()-ed paths.
*
* Dumps whole packets if full_pkt, only headers otherwise.
*/
void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
{
struct skb_shared_info *sh = skb_shinfo(skb);
struct net_device *dev = skb->dev;
struct sock *sk = skb->sk;
struct sk_buff *list_skb;
bool has_mac, has_trans;
int headroom, tailroom;
int i, len, seg_len;
if (full_pkt)
len = skb->len;
else
len = min_t(int, skb->len, MAX_HEADER + 128);
headroom = skb_headroom(skb);
tailroom = skb_tailroom(skb);
has_mac = skb_mac_header_was_set(skb);
has_trans = skb_transport_header_was_set(skb);
printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n"
"mac=(%d,%d) net=(%d,%d) trans=%d\n"
"shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n"
"csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n"
"hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n",
level, skb->len, headroom, skb_headlen(skb), tailroom,
has_mac ? skb->mac_header : -1,
has_mac ? skb_mac_header_len(skb) : -1,
skb->network_header,
has_trans ? skb_network_header_len(skb) : -1,
has_trans ? skb->transport_header : -1,
sh->tx_flags, sh->nr_frags,
sh->gso_size, sh->gso_type, sh->gso_segs,
skb->csum, skb->ip_summed, skb->csum_complete_sw,
skb->csum_valid, skb->csum_level,
skb->hash, skb->sw_hash, skb->l4_hash,
ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
if (dev)
printk("%sdev name=%s feat=%pNF\n",
level, dev->name, &dev->features);
if (sk)
printk("%ssk family=%hu type=%u proto=%u\n",
level, sk->sk_family, sk->sk_type, sk->sk_protocol);
if (full_pkt && headroom)
print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET,
16, 1, skb->head, headroom, false);
seg_len = min_t(int, skb_headlen(skb), len);
if (seg_len)
print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET,
16, 1, skb->data, seg_len, false);
len -= seg_len;
if (full_pkt && tailroom)
print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET,
16, 1, skb_tail_pointer(skb), tailroom, false);
for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
skb_frag_foreach_page(frag, skb_frag_off(frag),
skb_frag_size(frag), p, p_off, p_len,
copied) {
seg_len = min_t(int, p_len, len);
vaddr = kmap_atomic(p);
print_hex_dump(level, "skb frag: ",
DUMP_PREFIX_OFFSET,
16, 1, vaddr + p_off, seg_len, false);
kunmap_atomic(vaddr);
len -= seg_len;
if (!len)
break;
}
}
if (full_pkt && skb_has_frag_list(skb)) {
printk("skb fraglist:\n");
skb_walk_frags(skb, list_skb)
skb_dump(level, list_skb, true);
}
}
EXPORT_SYMBOL(skb_dump);
/**
* 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;
trace_consume_skb(skb, __builtin_return_address(0));
__kfree_skb(skb);
}
EXPORT_SYMBOL(consume_skb);
#endif
/**
* __consume_stateless_skb - free an skbuff, assuming it is stateless
* @skb: buffer to free
*
* Alike consume_skb(), but this variant assumes that this is the last
* skb reference and all the head states have been already dropped
*/
void __consume_stateless_skb(struct sk_buff *skb)
{
trace_consume_skb(skb, __builtin_return_address(0));
skb_release_data(skb, SKB_CONSUMED, false);
kfree_skbmem(skb);
}
static void napi_skb_cache_put(struct sk_buff *skb)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
u32 i;
if (!kasan_mempool_poison_object(skb))
return;
nc->skb_cache[nc->skb_count++] = 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(skbuff_cache));
kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
nc->skb_cache + NAPI_SKB_CACHE_HALF);
nc->skb_count = NAPI_SKB_CACHE_HALF;
}
}
void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason)
{
skb_release_all(skb, reason, true);
napi_skb_cache_put(skb);
}
void napi_skb_free_stolen_head(struct sk_buff *skb)
{
if (unlikely(skb->slow_gro)) {
nf_reset_ct(skb);
skb_dst_drop(skb);
skb_ext_put(skb);
skb_orphan(skb);
skb->slow_gro = 0;
}
napi_skb_cache_put(skb);
}
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;
}
skb_release_all(skb, SKB_CONSUMED, !!budget);
napi_skb_cache_put(skb);
}
EXPORT_SYMBOL(napi_consume_skb);
/* 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)); \
static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
new->tstamp = old->tstamp;
/* We do not copy old->sk */
new->dev = old->dev;
memcpy(new->cb, old->cb, sizeof(old->cb));
skb_dst_copy(new, old);
__skb_ext_copy(new, old);
__nf_copy(new, old, false);
/* 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;
memcpy(&new->headers, &old->headers, sizeof(new->headers));
CHECK_SKB_FIELD(protocol);
CHECK_SKB_FIELD(csum);
CHECK_SKB_FIELD(hash);
CHECK_SKB_FIELD(priority);
CHECK_SKB_FIELD(skb_iif);
CHECK_SKB_FIELD(vlan_proto);
CHECK_SKB_FIELD(vlan_tci);
CHECK_SKB_FIELD(transport_header);
CHECK_SKB_FIELD(network_header);
CHECK_SKB_FIELD(mac_header);
CHECK_SKB_FIELD(inner_protocol);
CHECK_SKB_FIELD(inner_transport_header);
CHECK_SKB_FIELD(inner_network_header);
CHECK_SKB_FIELD(inner_mac_header);
CHECK_SKB_FIELD(mark);
#ifdef CONFIG_NETWORK_SECMARK
CHECK_SKB_FIELD(secmark);
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
CHECK_SKB_FIELD(napi_id);
#endif
CHECK_SKB_FIELD(alloc_cpu);
#ifdef CONFIG_XPS
CHECK_SKB_FIELD(sender_cpu);
#endif
#ifdef CONFIG_NET_SCHED
CHECK_SKB_FIELD(tc_index);
#endif
}
/*
* You should not add any new code to this function. Add it to
* __copy_skb_header above instead.
*/
static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
{
#define C(x) n->x = skb->x
n->next = n->prev = NULL;
n->sk = NULL;
__copy_skb_header(n, skb);
C(len);
C(data_len);
C(mac_len);
n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
n->cloned = 1;
n->nohdr = 0;
n->peeked = 0;
C(pfmemalloc);
C(pp_recycle);
n->destructor = NULL;
C(tail);
C(end);
C(head);
C(head_frag);
C(data);
C(truesize);
refcount_set(&n->users, 1);
atomic_inc(&(skb_shinfo(skb)->dataref));
skb->cloned = 1;
return n;
#undef C
}
/**
* 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;
n->len = first->len;
n->data_len = first->len;
n->truesize = first->truesize;
skb_shinfo(n)->frag_list = first;
__copy_skb_header(n, first);
n->destructor = NULL;
return n;
}
EXPORT_SYMBOL_GPL(alloc_skb_for_msg);
/**
* 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, false);
return __skb_clone(dst, src);
}
EXPORT_SYMBOL_GPL(skb_morph);
int mm_account_pinned_pages(struct mmpin *mmp, size_t size)
{
unsigned long max_pg, num_pg, new_pg, old_pg, rlim;
struct user_struct *user;
if (capable(CAP_IPC_LOCK) || !size)
return 0;
rlim = rlimit(RLIMIT_MEMLOCK);
if (rlim == RLIM_INFINITY)
return 0;
num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */
max_pg = rlim >> PAGE_SHIFT;
user = mmp->user ? : current_user();
old_pg = atomic_long_read(&user->locked_vm);
do {
new_pg = old_pg + num_pg;
if (new_pg > max_pg)
return -ENOBUFS;
} while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg));
if (!mmp->user) {
mmp->user = get_uid(user);
mmp->num_pg = num_pg;
} else {
mmp->num_pg += num_pg;
}
return 0;
}
EXPORT_SYMBOL_GPL(mm_account_pinned_pages);
void mm_unaccount_pinned_pages(struct mmpin *mmp)
{
if (mmp->user) {
atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm);
free_uid(mmp->user);
}
}
EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
{
struct ubuf_info_msgzc *uarg;
struct sk_buff *skb;
WARN_ON_ONCE(!in_task());
skb = sock_omalloc(sk, 0, GFP_KERNEL);
if (!skb)
return NULL;
BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb));
uarg = (void *)skb->cb;
uarg->mmp.user = NULL;
if (mm_account_pinned_pages(&uarg->mmp, size)) {
kfree_skb(skb);
return NULL;
}
uarg->ubuf.callback = msg_zerocopy_callback;
uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1;
uarg->len = 1;
uarg->bytelen = size;
uarg->zerocopy = 1;
uarg->ubuf.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
refcount_set(&uarg->ubuf.refcnt, 1);
sock_hold(sk);
return &uarg->ubuf;
}
static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg)
{
return container_of((void *)uarg, struct sk_buff, cb);
}
struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
struct ubuf_info *uarg)
{
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->callback != msg_zerocopy_callback)
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 (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);
return uarg;
}
}
new_alloc:
return msg_zerocopy_alloc(sk, size);
}
EXPORT_SYMBOL_GPL(msg_zerocopy_realloc);
static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
u32 old_lo, old_hi;
u64 sum_len;
old_lo = serr->ee.ee_info;
old_hi = serr->ee.ee_data;
sum_len = old_hi - old_lo + 1ULL + len;
if (sum_len >= (1ULL << 32))
return false;
if (lo != old_hi + 1)
return false;
serr->ee.ee_data += len;
return true;
}
static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg)
{
struct sk_buff *tail, *skb = skb_from_uarg(uarg);
struct sock_exterr_skb *serr;
struct sock *sk = skb->sk;
struct sk_buff_head *q;
unsigned long flags;
bool is_zerocopy;
u32 lo, hi;
u16 len;
mm_unaccount_pinned_pages(&uarg->mmp);
/* 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;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = 0;
serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY;
serr->ee.ee_data = hi;
serr->ee.ee_info = lo;
if (!is_zerocopy)
serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED;
q = &sk->sk_error_queue;
spin_lock_irqsave(&q->lock, flags);
tail = skb_peek_tail(q);
if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY ||
!skb_zerocopy_notify_extend(tail, lo, len)) {
__skb_queue_tail(q, skb);
skb = NULL;
}
spin_unlock_irqrestore(&q->lock, flags);
sk_error_report(sk);
release:
consume_skb(skb);
sock_put(sk);
}
void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
bool success)
{
struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg);
uarg_zc->zerocopy = uarg_zc->zerocopy & success;
if (refcount_dec_and_test(&uarg->refcnt))
__msg_zerocopy_callback(uarg_zc);
}
EXPORT_SYMBOL_GPL(msg_zerocopy_callback);
void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
struct sock *sk = skb_from_uarg(uarg_to_msgzc(uarg))->sk;
atomic_dec(&sk->sk_zckey);
uarg_to_msgzc(uarg)->len--;
if (have_uref)
msg_zerocopy_callback(NULL, uarg, true);
}
EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort);
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
struct ubuf_info *uarg)
{
struct ubuf_info *orig_uarg = skb_zcopy(skb);
int err, orig_len = skb->len;
/* 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;
err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
struct sock *save_sk = skb->sk;
/* Streams do not free skb on error. Reset to prev state. */
iov_iter_revert(&msg->msg_iter, skb->len - orig_len);
skb->sk = sk;
___pskb_trim(skb, orig_len);
skb->sk = save_sk;
return err;
}
skb_zcopy_set(skb, uarg, NULL);
return skb->len - orig_len;
}
EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
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);
static int 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 (!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, (unsigned long)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_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f),
p, p_off, p_len, copied) {
u32 copy, done = 0;
vaddr = kmap_atomic(p);
while (done < p_len) {
if (d_off == psize) {
d_off = 0;
page = (struct page *)page_private(page);
}
copy = min_t(u32, psize - d_off, p_len - done);
memcpy(page_address(page) + d_off,
vaddr + p_off + done, copy);
done += copy;
d_off += copy;
}
kunmap_atomic(vaddr);
}
}
/* skb frags release userspace buffers */
for (i = 0; i < num_frags; i++)
skb_frag_unref(skb, i);
/* skb frags point to kernel buffers */
for (i = 0; i < new_frags - 1; i++) {
__skb_fill_page_desc(skb, i, head, 0, psize);
head = (struct page *)page_private(head);
}
__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
skb_shinfo(skb)->nr_frags = new_frags;
release:
skb_zcopy_clear(skb, false);
return 0;
}
EXPORT_SYMBOL_GPL(skb_copy_ubufs);
/**
* skb_clone - duplicate an sk_buff
* @skb: buffer to clone
* @gfp_mask: allocation priority
*
* Duplicate an &sk_buff. The new one is not owned by a socket. Both
* copies share the same packet data but not structure. The new
* buffer has a reference count of 1. If the allocation fails the
* function returns %NULL otherwise the new buffer is returned.
*
* If this function is called from an interrupt gfp_mask() must be
* %GFP_ATOMIC.
*/
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff_fclones *fclones = container_of(skb,
struct sk_buff_fclones,
skb1);
struct sk_buff *n;
if (skb_orphan_frags(skb, gfp_mask))
return NULL;
if (skb->fclone == SKB_FCLONE_ORIG &&
refcount_read(&fclones->fclone_ref) == 1) {
n = &fclones->skb2;
refcount_set(&fclones->fclone_ref, 2);
n->fclone = SKB_FCLONE_CLONE;
} else {
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
n = kmem_cache_alloc(skbuff_cache, gfp_mask);
if (!n)
return NULL;
n->fclone = SKB_FCLONE_UNAVAILABLE;
}
return __skb_clone(n, skb);
}
EXPORT_SYMBOL(skb_clone);
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);
void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
{
__copy_skb_header(new, old);
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
EXPORT_SYMBOL(skb_copy_header);
static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
{
if (skb_pfmemalloc(skb))
return SKB_ALLOC_RX;
return 0;
}
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data. This is used when the
* caller wishes to modify the data and needs a private copy of the
* data to alter. Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* As by-product this function converts non-linear &sk_buff to linear
* one, so that &sk_buff becomes completely private and caller is allowed
* to modify all the data of returned buffer. This means that this
* function is not recommended for use in circumstances when only
* header is going to be modified. Use pskb_copy() instead.
*/
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
unsigned int size = skb_end_offset(skb) + skb->data_len;
struct sk_buff *n = __alloc_skb(size, gfp_mask,
skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
/* Set the data pointer */
skb_reserve(n, headerlen);
/* Set the tail pointer and length */
skb_put(n, skb->len);
BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
skb_copy_header(n, skb);
return n;
}
EXPORT_SYMBOL(skb_copy);
/**
* __pskb_copy_fclone - create copy of an sk_buff with private head.
* @skb: buffer to copy
* @headroom: headroom of new skb
* @gfp_mask: allocation priority
* @fclone: if true allocate the copy of the skb from the fclone
* cache instead of the head cache; it is recommended to set this
* to true for the cases where the copy will likely be cloned
*
* Make a copy of both an &sk_buff and part of its data, located
* in header. Fragmented data remain shared. This is used when
* the caller wishes to modify only header of &sk_buff and needs
* private copy of the header to alter. Returns %NULL on failure
* or the pointer to the buffer on success.
* The returned buffer has a reference count of 1.
*/
struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
gfp_t gfp_mask, bool fclone)
{
unsigned int size = skb_headlen(skb) + headroom;
int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0);
struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE);
if (!n)
goto out;
/* 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);
n->truesize += skb->data_len;
n->data_len = skb->data_len;
n->len = skb->len;
if (skb_shinfo(skb)->nr_frags) {
int i;
if (skb_orphan_frags(skb, gfp_mask) ||
skb_zerocopy_clone(n, skb, gfp_mask)) {
kfree_skb(n);
n = NULL;
goto out;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
skb_frag_ref(skb, i);
}
skb_shinfo(n)->nr_frags = i;
}
if (skb_has_frag_list(skb)) {
skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
skb_clone_fraglist(n);
}
skb_copy_header(n, skb);
out:
return n;
}
EXPORT_SYMBOL(__pskb_copy_fclone);
/**
* 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)
{
unsigned int osize = skb_end_offset(skb);
unsigned int 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);
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb),
offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags]));
/*
* 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);
skb_release_data(skb, SKB_CONSUMED, false);
} else {
skb_free_head(skb, false);
}
off = (data + nhead) - skb->head;
skb->head = data;
skb->head_frag = 0;
skb->data += off;
skb_set_end_offset(skb, size);
#ifdef NET_SKBUFF_DATA_USES_OFFSET
off = nhead;
#endif
skb->tail += off;
skb_headers_offset_update(skb, nhead);
skb->cloned = 0;
skb->hdr_len = 0;
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
skb_metadata_clear(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;
return 0;
nofrags:
skb_kfree_head(data, size);
nodata:
return -ENOMEM;
}
EXPORT_SYMBOL(pskb_expand_head);
/* Make private copy of skb with writable head and some headroom */
struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
{
struct sk_buff *skb2;
int delta = headroom - skb_headroom(skb);
if (delta <= 0)
skb2 = pskb_copy(skb, GFP_ATOMIC);
else {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
GFP_ATOMIC)) {
kfree_skb(skb2);
skb2 = NULL;
}
}
return skb2;
}
EXPORT_SYMBOL(skb_realloc_headroom);
/* Note: We plan to rework this in linux-6.4 */
int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
{
unsigned int saved_end_offset, saved_truesize;
struct skb_shared_info *shinfo;
int res;
saved_end_offset = skb_end_offset(skb);
saved_truesize = skb->truesize;
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.
*/
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
{
int delta = headroom - skb_headroom(skb);
int osize = skb_end_offset(skb);
struct sock *sk = skb->sk;
if (WARN_ONCE(delta <= 0,
"%s is expecting an increase in the headroom", __func__))
return skb;
delta = SKB_DATA_ALIGN(delta);
/* pskb_expand_head() might crash, if skb is shared. */
if (skb_shared(skb) || !is_skb_wmem(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb))
goto fail;
if (sk)
skb_set_owner_w(nskb, sk);
consume_skb(skb);
skb = nskb;
}
if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
goto fail;
if (sk && is_skb_wmem(skb)) {
delta = skb_end_offset(skb) - osize;
refcount_add(delta, &sk->sk_wmem_alloc);
skb->truesize += delta;
}
return skb;
fail:
kfree_skb(skb);
return NULL;
}
EXPORT_SYMBOL(skb_expand_head);
/**
* skb_copy_expand - copy and expand sk_buff
* @skb: buffer to copy
* @newheadroom: new free bytes at head
* @newtailroom: new free bytes at tail
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data and while doing so
* allocate additional space.
*
* This is used when the caller wishes to modify the data and needs a
* private copy of the data to alter as well as more space for new fields.
* Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* You must pass %GFP_ATOMIC as the allocation priority if this function
* is called from an interrupt.
*/
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
int newheadroom, int newtailroom,
gfp_t gfp_mask)
{
/*
* Allocate the copy buffer
*/
struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
gfp_mask, skb_alloc_rx_flag(skb),
NUMA_NO_NODE);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
if (!n)
return NULL;
skb_reserve(n, newheadroom);
/* Set the tail pointer and length */
skb_put(n, skb->len);
head_copy_len = oldheadroom;
head_copy_off = 0;
if (newheadroom <= head_copy_len)
head_copy_len = newheadroom;
else
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
skb->len + head_copy_len));
skb_copy_header(n, skb);
skb_headers_offset_update(n, newheadroom - oldheadroom);
return n;
}
EXPORT_SYMBOL(skb_copy_expand);
/**
* __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.
*/
void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
{
if (tail != skb) {
skb->data_len += len;
skb->len += len;
}
return skb_put(tail, len);
}
EXPORT_SYMBOL_GPL(pskb_put);
/**
* skb_put - add data to a buffer
* @skb: buffer to use
* @len: amount of data to add
*
* This function extends the used data area of the buffer. If this would
* exceed the total buffer size the kernel will panic. A pointer to the
* first byte of the extra data is returned.
*/
void *skb_put(struct sk_buff *skb, unsigned int len)
{
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, unsigned int 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, unsigned int 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, unsigned int 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, unsigned int 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;
if (skb_cloned(skb) &&
unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
return err;
i = 0;
if (offset >= len)
goto drop_pages;
for (; i < nfrags; i++) {
int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (end < len) {
offset = end;
continue;
}
skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset);
drop_pages:
skb_shinfo(skb)->nr_frags = i;
for (; i < nfrags; i++)
skb_frag_unref(skb, i);
if (skb_has_frag_list(skb))
skb_drop_fraglist(skb);
goto done;
}
for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp);
fragp = &frag->next) {
int end = offset + frag->len;
if (skb_shared(frag)) {
struct sk_buff *nfrag;
nfrag = skb_clone(frag, GFP_ATOMIC);
if (unlikely(!nfrag))
return -ENOMEM;
nfrag->next = frag->next;
consume_skb(frag);
frag = nfrag;
*fragp = frag;
}
if (end < len) {
offset = end;
continue;
}
if (end > len &&
unlikely((err = pskb_trim(frag, len - offset))))
return err;
if (frag->next)
skb_drop_list(&frag->next);
break;
}
done:
if (len > skb_headlen(skb)) {
skb->data_len -= skb->len - len;
skb->len = len;
} else {
skb->len = len;
skb->data_len = 0;
skb_set_tail_pointer(skb, len);
}
if (!skb->sk || skb->destructor == sock_edemux)
skb_condense(skb);
return 0;
}
EXPORT_SYMBOL(___pskb_trim);
/* Note : use pskb_trim_rcsum() instead of calling this directly
*/
int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
int delta = skb->len - len;
skb->csum = csum_block_sub(skb->csum,
skb_checksum(skb, len, delta, 0),
len);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len;
int offset = skb_checksum_start_offset(skb) + skb->csum_offset;
if (offset + sizeof(__sum16) > hdlen)
return -EINVAL;
}
return __pskb_trim(skb, len);
}
EXPORT_SYMBOL(pskb_trim_rcsum_slow);
/**
* __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;
if (eat > 0 || skb_cloned(skb)) {
if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
GFP_ATOMIC))
return NULL;
}
BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
skb_tail_pointer(skb), delta));
/* 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]);
if (size <= eat) {
skb_frag_unref(skb, i);
eat -= size;
} else {
skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
*frag = skb_shinfo(skb)->frags[i];
if (eat) {
skb_frag_off_add(frag, eat);
skb_frag_size_sub(frag, eat);
if (!i)
goto end;
eat = 0;
}
k++;
}
}
skb_shinfo(skb)->nr_frags = k;
end:
skb->tail += delta;
skb->data_len -= delta;
if (!skb->data_len)
skb_zcopy_clear(skb, false);
return skb_tail_pointer(skb);
}
EXPORT_SYMBOL(__pskb_pull_tail);
/**
* skb_copy_bits - copy bits from skb to kernel buffer
* @skb: source skb
* @offset: offset in source
* @to: destination buffer
* @len: number of bytes to copy
*
* Copy the specified number of bytes from the source skb to the
* destination buffer.
*
* CAUTION ! :
* If its prototype is ever changed,
* check arch/{*}/net/{*}.S files,
* since it is called from BPF assembly code.
*/
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
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;
}
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;
if (copy > len)
copy = len;
skb_frag_foreach_page(f,
skb_frag_off(f) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
memcpy(to + copied, vaddr + p_off, p_len);
kunmap_atomic(vaddr);
}
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_bits(frag_iter, offset - start, to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
if (!len)
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_bits);
/*
* Callback from splice_to_pipe(), if we need to release some pages
* at the end of the spd in case we error'ed out in filling the pipe.
*/
static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
{
put_page(spd->pages[i]);
}
static struct page *linear_to_page(struct page *page, unsigned int *len,
unsigned int *offset,
struct sock *sk)
{
struct page_frag *pfrag = sk_page_frag(sk);
if (!sk_page_frag_refill(sk, pfrag))
return NULL;
*len = min_t(unsigned int, *len, pfrag->size - pfrag->offset);
memcpy(page_address(pfrag->page) + pfrag->offset,
page_address(page) + *offset, *len);
*offset = pfrag->offset;
pfrag->offset += *len;
return pfrag->page;
}
static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
struct page *page,
unsigned int offset)
{
return spd->nr_pages &&
spd->pages[spd->nr_pages - 1] == page &&
(spd->partial[spd->nr_pages - 1].offset +
spd->partial[spd->nr_pages - 1].len == offset);
}
/*
* Fill page/offset/length into spd, if it can hold more pages.
*/
static bool spd_fill_page(struct splice_pipe_desc *spd,
struct pipe_inode_info *pipe, struct page *page,
unsigned int *len, unsigned int offset,
bool linear,
struct sock *sk)
{
if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
return true;
if (linear) {
page = linear_to_page(page, len, &offset, sk);
if (!page)
return true;
}
if (spd_can_coalesce(spd, page, offset)) {
spd->partial[spd->nr_pages - 1].len += *len;
return false;
}
get_page(page);
spd->pages[spd->nr_pages] = page;
spd->partial[spd->nr_pages].len = *len;
spd->partial[spd->nr_pages].offset = offset;
spd->nr_pages++;
return false;
}
static bool __splice_segment(struct page *page, unsigned int poff,
unsigned int plen, unsigned int *off,
unsigned int *len,
struct splice_pipe_desc *spd, bool linear,
struct sock *sk,
struct pipe_inode_info *pipe)
{
if (!*len)
return true;
/* skip this segment if already processed */
if (*off >= plen) {
*off -= plen;
return false;
}
/* ignore any bits we already processed */
poff += *off;
plen -= *off;
*off = 0;
do {
unsigned int flen = min(*len, plen);
if (spd_fill_page(spd, pipe, page, &flen, poff,
linear, sk))
return true;
poff += flen;
plen -= flen;
*len -= flen;
} while (*len && plen);
return false;
}
/*
* Map linear and fragment data from the skb to spd. It reports true if the
* pipe is full or if we already spliced the requested length.
*/
static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
unsigned int *offset, unsigned int *len,
struct splice_pipe_desc *spd, struct sock *sk)
{
int seg;
struct sk_buff *iter;
/* 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),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
offset, len, spd,
skb_head_is_locked(skb),
sk, pipe))
return true;
/*
* then map the fragments
*/
for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
if (__splice_segment(skb_frag_page(f),
skb_frag_off(f), skb_frag_size(f),
offset, len, spd, false, sk, pipe))
return true;
}
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))
return true;
}
return false;
}
/*
* Map data from the skb to a pipe. Should handle both the linear part,
* the fragments, and the frag list.
*/
int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
unsigned int flags)
{
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;
__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk);
if (spd.nr_pages)
ret = splice_to_pipe(pipe, &spd);
return ret;
}
EXPORT_SYMBOL_GPL(skb_splice_bits);
static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
size_t size = msg_data_left(msg);
if (!sock)
return -EINVAL;
if (!sock->ops->sendmsg_locked)
return sock_no_sendmsg_locked(sk, msg, size);
return sock->ops->sendmsg_locked(sk, msg, size);
}
static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
if (!sock)
return -EINVAL;
return sock_sendmsg(sock, msg);
}
typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
int len, sendmsg_func sendmsg)
{
unsigned int orig_len = len;
struct sk_buff *head = skb;
unsigned short fragidx;
int slen, ret;
do_frag_list:
/* Deal with head data */
while (offset < skb_headlen(skb) && len) {
struct kvec kv;
struct msghdr msg;
slen = min_t(int, len, skb_headlen(skb) - offset);
kv.iov_base = skb->data + offset;
kv.iov_len = slen;
memset(&msg, 0, sizeof(msg));
msg.msg_flags = MSG_DONTWAIT;
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];
slen = min_t(size_t, len, skb_frag_size(frag) - offset);
while (slen) {
struct bio_vec bvec;
struct msghdr msg = {
.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
};
bvec_set_page(&bvec, skb_frag_page(frag), slen,
skb_frag_off(frag) + offset);
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
slen);
ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
len -= ret;
offset += ret;
slen -= ret;
}
offset = 0;
}
if (len) {
/* Process any frag lists */
if (skb == head) {
if (skb_has_frag_list(skb)) {
skb = skb_shinfo(skb)->frag_list;
goto do_frag_list;
}
} else if (skb->next) {
skb = skb->next;
goto do_frag_list;
}
}
out:
return orig_len - len;
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);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);