// 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/if_vlan.h>#include <linux/mpls.h> #include <net/protocol.h>#include <net/dst.h>#include <net/sock.h>#include <net/checksum.h>#include <net/ip6_checksum.h>#include <net/xfrm.h>#include <net/mpls.h>#include <net/mptcp.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 "datagram.h" struct kmem_cache *skbuff_head_cache __ro_after_init;static struct kmem_cache *skbuff_fclone_cache __ro_after_init;#ifdef CONFIG_SKB_EXTENSIONSstatic struct kmem_cache *skbuff_ext_cache __ro_after_init;#endifint sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;EXPORT_SYMBOL(sysctl_max_skb_frags); /** * 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__);} /* * 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 */#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, bool *pfmemalloc){ void *obj; bool ret_pfmemalloc = false; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(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(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 skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; bool pfmemalloc; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); if (!skb) goto out; 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. */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) 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. */ size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + 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)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); skb->pfmemalloc = pfmemalloc; refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); 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); fclones->skb2.fclone = SKB_FCLONE_CLONE; }out: return skb;nodata: kmem_cache_free(cache, skb); skb = NULL; goto out;}EXPORT_SYMBOL(__alloc_skb); /* Caller must provide SKB that is memset cleared */static struct sk_buff *__build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size){ struct skb_shared_info *shinfo; unsigned int size = frag_size ? : ksize(data); 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->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); return skb;} /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if * @frag_size is 0, otherwise data should come from the page allocator * or vmalloc() * 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_head_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __build_skb_around(skb, data, frag_size);} /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc * This means that if @frag_size is not zero, then @data must be backed * by a page fragment, not kmalloc() or vmalloc() */struct sk_buff *build_skb(void *data, unsigned int frag_size){ struct sk_buff *skb = __build_skb(data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } 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, or 0 if head was kmalloced */struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size){ if (unlikely(!skb)) return NULL; skb = __build_skb_around(skb, data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb;}EXPORT_SYMBOL(build_skb_around); #define NAPI_SKB_CACHE_SIZE 64 struct napi_alloc_cache { struct page_frag_cache page; 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); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask){ struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); return page_frag_alloc(&nc->page, fragsz, gfp_mask);} void *napi_alloc_frag(unsigned int fragsz){ fragsz = SKB_DATA_ALIGN(fragsz); return __napi_alloc_frag(fragsz, GFP_ATOMIC);}EXPORT_SYMBOL(napi_alloc_frag); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */void *netdev_alloc_frag(unsigned int fragsz){ struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_irq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, fragsz, GFP_ATOMIC); } else { local_bh_disable(); data = __napi_alloc_frag(fragsz, GFP_ATOMIC); local_bh_enable(); } return data;}EXPORT_SYMBOL(netdev_alloc_frag); /** * __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 ((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_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_irq() || 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 = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb;Lines 1–500 of 6254. Load more
// 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/if_vlan.h> #include <linux/mpls.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.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 "datagram.h" struct kmem_cache *skbuff_head_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 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); /** * 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__); } /* * 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 */ #define kmalloc_reserve(size, gfp, node, pfmemalloc) \ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(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(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 skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; bool pfmemalloc; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); if (!skb) goto out; 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. */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) 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. */ size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + 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)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); skb->pfmemalloc = pfmemalloc; refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); 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); fclones->skb2.fclone = SKB_FCLONE_CLONE; } out: return skb; nodata: kmem_cache_free(cache, skb); skb = NULL; goto out; } EXPORT_SYMBOL(__alloc_skb); /* Caller must provide SKB that is memset cleared */ static struct sk_buff *__build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; unsigned int size = frag_size ? : ksize(data); 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->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); return skb; } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if * @frag_size is 0, otherwise data should come from the page allocator * or vmalloc() * 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_head_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __build_skb_around(skb, data, frag_size); } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc * This means that if @frag_size is not zero, then @data must be backed * by a page fragment, not kmalloc() or vmalloc() */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } 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, or 0 if head was kmalloced */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; skb = __build_skb_around(skb, data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; } EXPORT_SYMBOL(build_skb_around); #define NAPI_SKB_CACHE_SIZE 64 struct napi_alloc_cache { struct page_frag_cache page; 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); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); return page_frag_alloc(&nc->page, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) { fragsz = SKB_DATA_ALIGN(fragsz); return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ void *netdev_alloc_frag(unsigned int fragsz) { struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_irq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, fragsz, GFP_ATOMIC); } else { local_bh_disable(); data = __napi_alloc_frag(fragsz, GFP_ATOMIC); local_bh_enable(); } return data; } EXPORT_SYMBOL(netdev_alloc_frag); /** * __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 ((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_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_irq() || 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 = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb;