skb管理函数之alloc_skb、dev_alloc_skb、kfree_skb、dev_kfree_skb、consume_skb

alloc_skb

–分配skb，进行基本的初始化；

 static inline struct sk_buff *alloc_skb(unsigned int size,
                     gfp_t priority)
 {
     return __alloc_skb(size, priority, , NUMA_NO_NODE);
 }

 /**
  *    __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;

     /* 得到分配使用的高速缓存 */
     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 */
     /* 分配skb */
     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.
      */
     /* 数据对齐 */
     size = SKB_DATA_ALIGN(size);
     /* 对齐后的数据加上skb_shared_info对齐后的大小 */
     size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));

     //分配数据区
     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.
      */
     /* 除了skb_shared_info以外的数据大小 */
     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, , offsetof(struct sk_buff, tail));
     /* Account for allocated memory : skb + skb->head */
     /* 总长度= skb大小+  数据大小+  skb_shared_info大小 */
     skb->truesize = SKB_TRUESIZE(size);
     /* PFMEMALLOC分配标记 */
     skb->pfmemalloc = pfmemalloc;
     /* 设置引用计数为1 */
     atomic_set(&skb->users, );
     /*head data tail均指向数据区头部*/
     skb->head = data;
     skb->data = data;
     skb_reset_tail_pointer(skb);

     /* end指向数据区尾部 */
     skb->end = skb->tail + size;
     /* 初始化默认各层header偏移值 */
     skb->mac_header = (typeof(skb->mac_header))~0U;
     skb->transport_header = (typeof(skb->transport_header))~0U;

     /* make sure we initialize shinfo sequentially */
     /* 从end开始的区域为skb_shared_info */
     shinfo = skb_shinfo(skb);
     memset(shinfo, , offsetof(struct skb_shared_info, dataref));
     /* 设置引用计数为1 */
     atomic_set(&shinfo->dataref, );
     kmemcheck_annotate_variable(shinfo->destructor_arg);

     /* 如果有克隆标记 */
     if (flags & SKB_ALLOC_FCLONE) {
         struct sk_buff_fclones *fclones;

         /* 得到clone结构 */
         fclones = container_of(skb, struct sk_buff_fclones, skb1);

         kmemcheck_annotate_bitfield(&fclones->skb2, flags1);

         /* 设置克隆标记 */
         skb->fclone = SKB_FCLONE_ORIG;

         /* 设置引用为1 */
         atomic_set(&fclones->fclone_ref, );

         /* 设置skb2的克隆标记 */
         fclones->skb2.fclone = SKB_FCLONE_CLONE;
     }
 out:
     return skb;
 nodata:
     kmem_cache_free(cache, skb);
     skb = NULL;
     goto out;
 }

dev_alloc_skb

–分配skb，通常被设备驱动用在中断上下文中，它是alloc_skb的封装函数，因为在中断处理函数中被调用，因此要求原子操作(GFP_ATOMIC)；

 /* legacy helper around netdev_alloc_skb() */
 static inline struct sk_buff *dev_alloc_skb(unsigned int length)
 {
     return netdev_alloc_skb(NULL, length);
 }

 /**
  *    netdev_alloc_skb - allocate an skbuff for rx on a specific device
  *    @dev: network device to receive on
  *    @length: length to allocate
  *
  *    Allocate a new &sk_buff and assign it a usage count of one. The
  *    buffer has unspecified headroom built in. Users should allocate
  *    the headroom they think they need without accounting for the
  *    built in space. The built in space is used for optimisations.
  *
  *    %NULL is returned if there is no free memory. Although this function
  *    allocates memory it can be called from an interrupt.
  */
 static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev,
                            unsigned int length)
 {
     return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
 }

 /**
  *    __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;
     unsigned long flags;
     struct sk_buff *skb;
     bool pfmemalloc;
     void *data;

     len += NET_SKB_PAD;

     /*
         分配长度+ skb_shared_info长度> 一页
         有__GFP_DIRECT_RECLAIM | GFP_DMA 标记
     */
     if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
         (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
         /* 通过__alloc_skb分配内存*/
         skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
         if (!skb)
             goto skb_fail;

         /* 分配成功 */
         goto skb_success;
     }

     /* 分配长度+ skb_shared_info长度*/
     len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
     /* 对整个长度进行对齐 */
     len = SKB_DATA_ALIGN(len);

     if (sk_memalloc_socks())
         gfp_mask |= __GFP_MEMALLOC;

     /* 保存中断 */
     local_irq_save(flags);

     nc = this_cpu_ptr(&netdev_alloc_cache);
     /* 分配空间 */
     data = page_frag_alloc(nc, len, gfp_mask);
     pfmemalloc = nc->pfmemalloc;

     /* 恢复中断 */
     local_irq_restore(flags);

     if (unlikely(!data))
         return NULL;

     /* 构建skb */
     skb = __build_skb(data, len);
     if (unlikely(!skb)) {
         skb_free_frag(data);
         return NULL;
     }

     /* use OR instead of assignment to avoid clearing of bits in mask */
     /* 设置PFMEMALLOC标记 */
     if (pfmemalloc)
         skb->pfmemalloc = ;

     //打内存分配标记
     skb->head_frag = ;

 skb_success:
     /* 保留空间 */
     skb_reserve(skb, NET_SKB_PAD);
     /* 设置输入设备 */
     skb->dev = dev;

 skb_fail:
     return skb;
 }

kfree_skb

–减少skb引用，为0则释放，用于出错丢包时释放skb使用；

 /**
  *    kfree_skb - free an sk_buff
  *    @skb: buffer to free
  *
  *    Drop a reference to the buffer and free it if the usage count has
  *    hit zero.
  */
 /*
     释放skb
 */
 void kfree_skb(struct sk_buff *skb)
 {
     if (unlikely(!skb))
         return;
     /* 引用为1，可直接释放 */
     if (likely(atomic_read(&skb->users) == ))
         smp_rmb();
     /*
         对引用减1，并且判断，如果结果不为0
         说明还有引用，返回
     */
     else if (likely(!atomic_dec_and_test(&skb->users)))
         return;
     trace_kfree_skb(skb, __builtin_return_address());

     //真正的skb释放
     __kfree_skb(skb);
 }

 /**
  *    __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
  */
 /* 释放skb */
 void __kfree_skb(struct sk_buff *skb)
 {
     /* 释放skb附带的所有数据 */
     skb_release_all(skb);
     /* 释放skb */
     kfree_skbmem(skb);
 }

dev_kfree_skb && consume_skb

–减少skb引用，为0则释放，成功状态下释放skb使用；

 /**
  *    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
  */
 /* 释放skb，与kfree_skb区别是，kfree_skb用于失败时丢包释放 */
 void consume_skb(struct sk_buff *skb)
 {
     if (unlikely(!skb))
         return;
     if (likely(atomic_read(&skb->users) == ))
         smp_rmb();
     else if (likely(!atomic_dec_and_test(&skb->users)))
         return;
     trace_consume_skb(skb);
     __kfree_skb(skb);
 }

 #define dev_kfree_skb(a)    consume_skb(a)