内核hlist的使用

 struct hlist_head {
         struct hlist_node *first;
 };

 struct hlist_node {
         struct hlist_node *next, **pprev;
 };

hlist_head表示哈希表的头结点，是hash数组的一个元素。

哈希表中每一个entry(hlist_head)所对应的都是一个链表（hlist)，该链表的结点由hlist_node表示。

hlist_head结构体只有一个域，即first。 first指针指向该hlist链表的第一个节点。

hlist_node结构体有两个域，next 和pprev。 next指针很容易理解，它指向下个hlist_node结点，倘若该节点是链表的最后一个节点，next指向NULL。

pprev是一个二级指针， 它指向前一个节点的next指针。为什么我们需要这样一个指针呢？它的好处是什么？

在回答这个问题之前，我们先研究另一个问题：为什么散列表的实现需要两个不同的数据结构？

散列表的目的是为了方便快速的查找，所以散列表通常是一个比较大的数组，否则“冲突”的概率会非常大， 这样也就失去了散列表的意义。如何做到既能维护一张大表，又能不使用过多的内存呢？就只能从数据结构上下功夫了。所以对于散列表的每个entry，它的结构体中只存放一个指针，解决了占用空间的问题。

现在又出现了另一个问题：数据结构不一致。显然，如果hlist_node采用传统的next,prev指针， 对于第一个节点和后面其他节点的处理会不一致。这样并不优雅，而且效率上也有损失。

hlist_node巧妙地将pprev指向上一个节点的next指针的地址，由于hlist_head和hlist_node指向的下一个节点的指针类型相同，这样就解决了通用性！

以IP分片时hlist使用为例，说明一下hlist的使用。

  /**
 32  * struct inet_frag_queue - fragment queue
 33  *
 34  * @lock: spinlock protecting the queue
 35  * @timer: queue expiration timer
 36  * @list: hash bucket list
 37  * @refcnt: reference count of the queue
 38  * @fragments: received fragments head
 39  * @fragments_tail: received fragments tail
 40  * @stamp: timestamp of the last received fragment
 41  * @len: total length of the original datagram
 42  * @meat: length of received fragments so far
 43  * @flags: fragment queue flags
 44  * @max_size: maximum received fragment size
 45  * @net: namespace that this frag belongs to
 46  * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
 47  */
  struct inet_frag_queue {
          spinlock_t              lock;
          struct timer_list       timer;
          struct hlist_node       list;   //hash节点
          atomic_t                refcnt;
          struct sk_buff          *fragments;
          struct sk_buff          *fragments_tail;
          ktime_t                 stamp;
          int                     len;
          int                     meat;
          __u8                    flags;
          u16                     max_size;
          struct netns_frags      *net;
          struct hlist_node       list_evictor;
  };

  #define INETFRAGS_HASHSZ        1024  //hash数组的大小

  /* averaged:
 67  * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
 68  *             rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
 69  *             struct frag_queue))
 70  */
  #define INETFRAGS_MAXDEPTH      128

  struct inet_frag_bucket {
          struct hlist_head       chain;  //hash冲突链表
          spinlock_t              chain_lock;
  };

  struct inet_frags {
          struct inet_frag_bucket hash[INETFRAGS_HASHSZ];  //hash数组

          struct work_struct      frags_work;
          unsigned int next_bucket;
          unsigned long last_rebuild_jiffies;
          bool rebuild;

          /* The first call to hashfn is responsible to initialize
 87          * rnd. This is best done with net_get_random_once.
 88          *
 89          * rnd_seqlock is used to let hash insertion detect
 90          * when it needs to re-lookup the hash chain to use.
 91          */
          u32                     rnd;
          seqlock_t               rnd_seqlock;
          int                     qsize;

          unsigned int            (*hashfn)(const struct inet_frag_queue *);
          bool                    (*match)(const struct inet_frag_queue *q,
                                           const void *arg);
          void                    (*constructor)(struct inet_frag_queue *q,
                                                const void *arg);
         void                    (*destructor)(struct inet_frag_queue *);
         void                    (*skb_free)(struct sk_buff *);
         void                    (*frag_expire)(unsigned long data);
         struct kmem_cache       *frags_cachep;
         const char              *frags_cache_name;
 };

   /*
  2  * inet fragments management
  3  *
  4  *              This program is free software; you can redistribute it and/or
  5  *              modify it under the terms of the GNU General Public License
  6  *              as published by the Free Software Foundation; either version
  7  *              2 of the License, or (at your option) any later version.
  8  *
  9  *              Authors:        Pavel Emelyanov <xemul@openvz.org>
 10  *                              Started as consolidation of ipv4/ip_fragment.c,
 11  *                              ipv6/reassembly. and ipv6 nf conntrack reassembly
 12  */

  #include <linux/list.h>
  #include <linux/spinlock.h>
  #include <linux/module.h>
  #include <linux/timer.h>
  #include <linux/mm.h>
  #include <linux/random.h>
  #include <linux/skbuff.h>
  #include <linux/rtnetlink.h>
  #include <linux/slab.h>

  #include <net/sock.h>
  #include <net/inet_frag.h>
  #include <net/inet_ecn.h>

  #define INETFRAGS_EVICT_BUCKETS   128
  #define INETFRAGS_EVICT_MAX       512

  /* don't rebuild inetfrag table with new secret more often than this */
  #define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)

  /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
 35  * Value : 0xff if frame should be dropped.
 36  *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
 37  */
  const u8 ip_frag_ecn_table[] = {
          /* at least one fragment had CE, and others ECT_0 or ECT_1 */
          [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0]                      = INET_ECN_CE,
          [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1]                      = INET_ECN_CE,
          [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1]   = INET_ECN_CE,

          /* invalid combinations : drop frame */
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
          [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
  };
  EXPORT_SYMBOL(ip_frag_ecn_table);

  static unsigned int   //hash函数
  inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
  {
          return f->hashfn(q) & (INETFRAGS_HASHSZ - );
  }

  static bool inet_frag_may_rebuild(struct inet_frags *f)
  {
          return time_after(jiffies,
                 f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
  }

  static void inet_frag_secret_rebuild(struct inet_frags *f)
  {
          int i;

          write_seqlock_bh(&f->rnd_seqlock);

          if (!inet_frag_may_rebuild(f))
                  goto out;

          get_random_bytes(&f->rnd, sizeof(u32));

          for (i = ; i < INETFRAGS_HASHSZ; i++) {
                  struct inet_frag_bucket *hb;
                  struct inet_frag_queue *q;
                  struct hlist_node *n;

                  hb = &f->hash[i];
                  spin_lock(&hb->chain_lock);

                  hlist_for_each_entry_safe(q, n, &hb->chain, list) {//安全遍历所有hash冲突链表
                          unsigned int hval = inet_frag_hashfn(f, q);  //计算hash值

                          if (hval != i) {
                                  struct inet_frag_bucket *hb_dest;

                                  hlist_del(&q->list);

                                  /* Relink to new hash chain. */
                                  hb_dest = &f->hash[hval];  //hash冲突链表

                                  /* This is the only place where we take
 98                                  * another chain_lock while already holding
 99                                  * one.  As this will not run concurrently,
100                                  * we cannot deadlock on hb_dest lock below, if its
101                                  * already locked it will be released soon since
102                                  * other caller cannot be waiting for hb lock
103                                  * that we've taken above.
104                                  */
                                 spin_lock_nested(&hb_dest->chain_lock,
                                                  SINGLE_DEPTH_NESTING);

　　　　　　　　　　　　　　　　　　　　　//把节点list加入到hash冲突链表chain里面
                                 hlist_add_head(&q->list, &hb_dest->chain);
                                 spin_unlock(&hb_dest->chain_lock);
                         }
                 }
                 spin_unlock(&hb->chain_lock);
         }

         f->rebuild = false;
         f->last_rebuild_jiffies = jiffies;
 out:
         write_sequnlock_bh(&f->rnd_seqlock);
 }

 static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
 {
         return q->net->low_thresh ==  ||
                frag_mem_limit(q->net) >= q->net->low_thresh;
 }

 static unsigned int
 inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
 {
         struct inet_frag_queue *fq;
         struct hlist_node *n;
         unsigned int evicted = ;
         HLIST_HEAD(expired);

         spin_lock(&hb->chain_lock);

         hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
                 if (!inet_fragq_should_evict(fq))
                         continue;

                 if (!del_timer(&fq->timer))
                         continue;

                 hlist_add_head(&fq->list_evictor, &expired);
                 ++evicted;
         }

         spin_unlock(&hb->chain_lock);

         hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
                 f->frag_expire((unsigned long) fq);

         return evicted;
 }

 static void inet_frag_worker(struct work_struct *work)
 {
         unsigned int budget = INETFRAGS_EVICT_BUCKETS;
         unsigned int i, evicted = ;
         struct inet_frags *f;

         f = container_of(work, struct inet_frags, frags_work);

         BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);

         local_bh_disable();

         for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
                 evicted += inet_evict_bucket(f, &f->hash[i]);
                 i = (i + ) & (INETFRAGS_HASHSZ - );
                 if (evicted > INETFRAGS_EVICT_MAX)
                         break;
         }

         f->next_bucket = i;

         local_bh_enable();

         if (f->rebuild && inet_frag_may_rebuild(f))
                 inet_frag_secret_rebuild(f);
 }

 static void inet_frag_schedule_worker(struct inet_frags *f)
 {
         if (unlikely(!work_pending(&f->frags_work)))
                 schedule_work(&f->frags_work);
 }

 int inet_frags_init(struct inet_frags *f)
 {
         int i;

         INIT_WORK(&f->frags_work, inet_frag_worker);

         for (i = ; i < INETFRAGS_HASHSZ; i++) { //初始化hash数组中所有的元素
                 struct inet_frag_bucket *hb = &f->hash[i];

                 spin_lock_init(&hb->chain_lock);  //初始化一个hash冲突链表
                 INIT_HLIST_HEAD(&hb->chain);
         }

         seqlock_init(&f->rnd_seqlock);
         f->last_rebuild_jiffies = ;
         f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, , ,
                                             NULL);
         if (!f->frags_cachep)
                 return -ENOMEM;

         return ;
 }
 EXPORT_SYMBOL(inet_frags_init);

 void inet_frags_init_net(struct netns_frags *nf)
 {
         init_frag_mem_limit(nf);
 }
 EXPORT_SYMBOL(inet_frags_init_net);

 void inet_frags_fini(struct inet_frags *f)
 {
         cancel_work_sync(&f->frags_work);
         kmem_cache_destroy(f->frags_cachep);
 }
 EXPORT_SYMBOL(inet_frags_fini);

 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 {
         unsigned int seq;
         int i;

         nf->low_thresh = ;

 evict_again:
         local_bh_disable();
         seq = read_seqbegin(&f->rnd_seqlock);

         for (i = ; i < INETFRAGS_HASHSZ ; i++)
                 inet_evict_bucket(f, &f->hash[i]);

         local_bh_enable();
         cond_resched();

         if (read_seqretry(&f->rnd_seqlock, seq) ||
             percpu_counter_sum(&nf->mem))
                 goto evict_again;

         percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);

 static struct inet_frag_bucket *
 get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
 __acquires(hb->chain_lock)
 {
         struct inet_frag_bucket *hb;
         unsigned int seq, hash;

  restart:
         seq = read_seqbegin(&f->rnd_seqlock);

         hash = inet_frag_hashfn(f, fq);
         hb = &f->hash[hash];

         spin_lock(&hb->chain_lock);
         if (read_seqretry(&f->rnd_seqlock, seq)) {
                 spin_unlock(&hb->chain_lock);
                 goto restart;
         }

         return hb;
 }

 static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
 {
         struct inet_frag_bucket *hb;

         hb = get_frag_bucket_locked(fq, f);
         hlist_del(&fq->list);
         fq->flags |= INET_FRAG_COMPLETE;
         spin_unlock(&hb->chain_lock);
 }

 void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
 {
         if (del_timer(&fq->timer))
                 atomic_dec(&fq->refcnt);

         if (!(fq->flags & INET_FRAG_COMPLETE)) {
                 fq_unlink(fq, f);
                 atomic_dec(&fq->refcnt);
         }
 }
 EXPORT_SYMBOL(inet_frag_kill);

 static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
                                   struct sk_buff *skb)
 {
         if (f->skb_free)
                 f->skb_free(skb);
         kfree_skb(skb);
 }

 void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 {
         struct sk_buff *fp;
         struct netns_frags *nf;
         unsigned int sum, sum_truesize = ;

         WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
         WARN_ON(del_timer(&q->timer) != );

         /* Release all fragment data. */
         fp = q->fragments;
         nf = q->net;
         while (fp) {
                 struct sk_buff *xp = fp->next;

                 sum_truesize += fp->truesize;
                 frag_kfree_skb(nf, f, fp);
                 fp = xp;
         }
         sum = sum_truesize + f->qsize;

         if (f->destructor)
                 f->destructor(q);
         kmem_cache_free(f->frags_cachep, q);

         sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);

 static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
                                                 struct inet_frag_queue *qp_in,
                                                 struct inet_frags *f,
                                                 void *arg)
 {
         struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
         struct inet_frag_queue *qp;

 #ifdef CONFIG_SMP
         /* With SMP race we have to recheck hash table, because
341          * such entry could have been created on other cpu before
342          * we acquired hash bucket lock.
343          */
         hlist_for_each_entry(qp, &hb->chain, list) {
                 if (qp->net == nf && f->match(qp, arg)) {
                         atomic_inc(&qp->refcnt);
                         spin_unlock(&hb->chain_lock);
                         qp_in->flags |= INET_FRAG_COMPLETE;
                         inet_frag_put(qp_in, f);
                         return qp;
                 }
         }
 #endif
         qp = qp_in;
         if (!mod_timer(&qp->timer, jiffies + nf->timeout))
                 atomic_inc(&qp->refcnt);

         atomic_inc(&qp->refcnt);
         hlist_add_head(&qp->list, &hb->chain);

         spin_unlock(&hb->chain_lock);

         return qp;
 }

 static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
                                                struct inet_frags *f,
                                                void *arg)
 {
         struct inet_frag_queue *q;

         if (frag_mem_limit(nf) > nf->high_thresh) {
                 inet_frag_schedule_worker(f);
                 return NULL;
         }

         q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
         if (!q)
                 return NULL;

         q->net = nf;
         f->constructor(q, arg);
         add_frag_mem_limit(nf, f->qsize);

         setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
         spin_lock_init(&q->lock);
         atomic_set(&q->refcnt, );

         return q;
 }

 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
                                                 struct inet_frags *f,
                                                 void *arg)
 {
         struct inet_frag_queue *q;

         q = inet_frag_alloc(nf, f, arg);
         if (!q)
                 return NULL;

         return inet_frag_intern(nf, q, f, arg);
 }

 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
                                        struct inet_frags *f, void *key,
                                        unsigned int hash)
 {
         struct inet_frag_bucket *hb;
         struct inet_frag_queue *q;
         int depth = ;

         if (frag_mem_limit(nf) > nf->low_thresh)
                 inet_frag_schedule_worker(f);

         hash &= (INETFRAGS_HASHSZ - );
         hb = &f->hash[hash];

         spin_lock(&hb->chain_lock);
         hlist_for_each_entry(q, &hb->chain, list) {
                 if (q->net == nf && f->match(q, key)) {
                         atomic_inc(&q->refcnt);
                         spin_unlock(&hb->chain_lock);
                         return q;
                 }
                 depth++;
         }
         spin_unlock(&hb->chain_lock);

         if (depth <= INETFRAGS_MAXDEPTH)
                 return inet_frag_create(nf, f, key);

         if (inet_frag_may_rebuild(f)) {
                 if (!f->rebuild)
                         f->rebuild = true;
                 inet_frag_schedule_worker(f);
         }

         return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);

 void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
                                    const char *prefix)
 {
         static const char msg[] = "inet_frag_find: Fragment hash bucket"
                 " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
                 ". Dropping fragment.\n";

         if (PTR_ERR(q) == -ENOBUFS)
                 net_dbg_ratelimited("%s%s", prefix, msg);
 }
 EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);