fib_hash.c

linux 内核源代码

out_free_new_fa:
	kmem_cache_free(fn_alias_kmem, new_fa);
out:
	fib_release_info(fi);
	return err;
}


static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg)
{
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;
	struct fib_node *f;
	struct fib_alias *fa, *fa_to_delete;
	struct fn_zone *fz;
	__be32 key;

	if (cfg->fc_dst_len > 32)
		return -EINVAL;

	if ((fz  = table->fn_zones[cfg->fc_dst_len]) == NULL)
		return -ESRCH;

	key = 0;
	if (cfg->fc_dst) {
		if (cfg->fc_dst & ~FZ_MASK(fz))
			return -EINVAL;
		key = fz_key(cfg->fc_dst, fz);
	}

	f = fib_find_node(fz, key);

	if (!f)
		fa = NULL;
	else
		fa = fib_find_alias(&f->fn_alias, cfg->fc_tos, 0);
	if (!fa)
		return -ESRCH;

	fa_to_delete = NULL;
	fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
	list_for_each_entry_continue(fa, &f->fn_alias, fa_list) {
		struct fib_info *fi = fa->fa_info;

		if (fa->fa_tos != cfg->fc_tos)
			break;

		if ((!cfg->fc_type ||
		     fa->fa_type == cfg->fc_type) &&
		    (cfg->fc_scope == RT_SCOPE_NOWHERE ||
		     fa->fa_scope == cfg->fc_scope) &&
		    (!cfg->fc_protocol ||
		     fi->fib_protocol == cfg->fc_protocol) &&
		    fib_nh_match(cfg, fi) == 0) {
			fa_to_delete = fa;
			break;
		}
	}

	if (fa_to_delete) {
		int kill_fn;

		fa = fa_to_delete;
		rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len,
			  tb->tb_id, &cfg->fc_nlinfo, 0);

		kill_fn = 0;
		write_lock_bh(&fib_hash_lock);
		list_del(&fa->fa_list);
		if (list_empty(&f->fn_alias)) {
			hlist_del(&f->fn_hash);
			kill_fn = 1;
		}
		fib_hash_genid++;
		write_unlock_bh(&fib_hash_lock);

		if (fa->fa_state & FA_S_ACCESSED)
			rt_cache_flush(-1);
		fn_free_alias(fa);
		if (kill_fn) {
			fn_free_node(f);
			fz->fz_nent--;
		}

		return 0;
	}
	return -ESRCH;
}

static int fn_flush_list(struct fn_zone *fz, int idx)
{
	struct hlist_head *head = &fz->fz_hash[idx];
	struct hlist_node *node, *n;
	struct fib_node *f;
	int found = 0;

	hlist_for_each_entry_safe(f, node, n, head, fn_hash) {
		struct fib_alias *fa, *fa_node;
		int kill_f;

		kill_f = 0;
		list_for_each_entry_safe(fa, fa_node, &f->fn_alias, fa_list) {
			struct fib_info *fi = fa->fa_info;

			if (fi && (fi->fib_flags&RTNH_F_DEAD)) {
				write_lock_bh(&fib_hash_lock);
				list_del(&fa->fa_list);
				if (list_empty(&f->fn_alias)) {
					hlist_del(&f->fn_hash);
					kill_f = 1;
				}
				fib_hash_genid++;
				write_unlock_bh(&fib_hash_lock);

				fn_free_alias(fa);
				found++;
			}
		}
		if (kill_f) {
			fn_free_node(f);
			fz->fz_nent--;
		}
	}
	return found;
}

static int fn_hash_flush(struct fib_table *tb)
{
	struct fn_hash *table = (struct fn_hash *) tb->tb_data;
	struct fn_zone *fz;
	int found = 0;

	for (fz = table->fn_zone_list; fz; fz = fz->fz_next) {
		int i;

		for (i = fz->fz_divisor - 1; i >= 0; i--)
			found += fn_flush_list(fz, i);
	}
	return found;
}


static inline int
fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb,
		     struct fib_table *tb,
		     struct fn_zone *fz,
		     struct hlist_head *head)
{
	struct hlist_node *node;
	struct fib_node *f;
	int i, s_i;

	s_i = cb->args[4];
	i = 0;
	hlist_for_each_entry(f, node, head, fn_hash) {
		struct fib_alias *fa;

		list_for_each_entry(fa, &f->fn_alias, fa_list) {
			if (i < s_i)
				goto next;

			if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid,
					  cb->nlh->nlmsg_seq,
					  RTM_NEWROUTE,
					  tb->tb_id,
					  fa->fa_type,
					  fa->fa_scope,
					  f->fn_key,
					  fz->fz_order,
					  fa->fa_tos,
					  fa->fa_info,
					  NLM_F_MULTI) < 0) {
				cb->args[4] = i;
				return -1;
			}
		next:
			i++;
		}
	}
	cb->args[4] = i;
	return skb->len;
}

static inline int
fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb,
		   struct fib_table *tb,
		   struct fn_zone *fz)
{
	int h, s_h;

	if (fz->fz_hash == NULL)
		return skb->len;
	s_h = cb->args[3];
	for (h = s_h; h < fz->fz_divisor; h++) {
		if (hlist_empty(&fz->fz_hash[h]))
			continue;
		if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h]) < 0) {
			cb->args[3] = h;
			return -1;
		}
		memset(&cb->args[4], 0,
		       sizeof(cb->args) - 4*sizeof(cb->args[0]));
	}
	cb->args[3] = h;
	return skb->len;
}

static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb)
{
	int m, s_m;
	struct fn_zone *fz;
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;

	s_m = cb->args[2];
	read_lock(&fib_hash_lock);
	for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) {
		if (m < s_m) continue;
		if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) {
			cb->args[2] = m;
			read_unlock(&fib_hash_lock);
			return -1;
		}
		memset(&cb->args[3], 0,
		       sizeof(cb->args) - 3*sizeof(cb->args[0]));
	}
	read_unlock(&fib_hash_lock);
	cb->args[2] = m;
	return skb->len;
}

#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_table * fib_hash_init(u32 id)
#else
struct fib_table * __init fib_hash_init(u32 id)
#endif
{
	struct fib_table *tb;

	if (fn_hash_kmem == NULL)
		fn_hash_kmem = kmem_cache_create("ip_fib_hash",
						 sizeof(struct fib_node),
						 0, SLAB_HWCACHE_ALIGN,
						 NULL);

	if (fn_alias_kmem == NULL)
		fn_alias_kmem = kmem_cache_create("ip_fib_alias",
						  sizeof(struct fib_alias),
						  0, SLAB_HWCACHE_ALIGN,
						  NULL);

	tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash),
		     GFP_KERNEL);
	if (tb == NULL)
		return NULL;

	tb->tb_id = id;
	tb->tb_lookup = fn_hash_lookup;
	tb->tb_insert = fn_hash_insert;
	tb->tb_delete = fn_hash_delete;
	tb->tb_flush = fn_hash_flush;
	tb->tb_select_default = fn_hash_select_default;
	tb->tb_dump = fn_hash_dump;
	memset(tb->tb_data, 0, sizeof(struct fn_hash));
	return tb;
}

/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS

struct fib_iter_state {
	struct fn_zone	*zone;
	int		bucket;
	struct hlist_head *hash_head;
	struct fib_node *fn;
	struct fib_alias *fa;
	loff_t pos;
	unsigned int genid;
	int valid;
};

static struct fib_alias *fib_get_first(struct seq_file *seq)
{
	struct fib_iter_state *iter = seq->private;
	struct fn_hash *table = (struct fn_hash *) ip_fib_main_table->tb_data;

	iter->bucket    = 0;
	iter->hash_head = NULL;
	iter->fn        = NULL;
	iter->fa        = NULL;
	iter->pos	= 0;
	iter->genid	= fib_hash_genid;
	iter->valid	= 1;

	for (iter->zone = table->fn_zone_list; iter->zone;
	     iter->zone = iter->zone->fz_next) {
		int maxslot;

		if (!iter->zone->fz_nent)
			continue;

		iter->hash_head = iter->zone->fz_hash;
		maxslot = iter->zone->fz_divisor;

		for (iter->bucket = 0; iter->bucket < maxslot;
		     ++iter->bucket, ++iter->hash_head) {
			struct hlist_node *node;
			struct fib_node *fn;

			hlist_for_each_entry(fn,node,iter->hash_head,fn_hash) {
				struct fib_alias *fa;

				list_for_each_entry(fa,&fn->fn_alias,fa_list) {
					iter->fn = fn;
					iter->fa = fa;
					goto out;
				}
			}
		}
	}
out:
	return iter->fa;
}

static struct fib_alias *fib_get_next(struct seq_file *seq)
{
	struct fib_iter_state *iter = seq->private;
	struct fib_node *fn;
	struct fib_alias *fa;

	/* Advance FA, if any. */
	fn = iter->fn;
	fa = iter->fa;
	if (fa) {
		BUG_ON(!fn);
		list_for_each_entry_continue(fa, &fn->fn_alias, fa_list) {
			iter->fa = fa;
			goto out;
		}
	}

	fa = iter->fa = NULL;

	/* Advance FN. */
	if (fn) {
		struct hlist_node *node = &fn->fn_hash;
		hlist_for_each_entry_continue(fn, node, fn_hash) {
			iter->fn = fn;

			list_for_each_entry(fa, &fn->fn_alias, fa_list) {
				iter->fa = fa;
				goto out;
			}
		}
	}

	fn = iter->fn = NULL;

	/* Advance hash chain. */
	if (!iter->zone)
		goto out;

	for (;;) {
		struct hlist_node *node;
		int maxslot;

		maxslot = iter->zone->fz_divisor;

		while (++iter->bucket < maxslot) {
			iter->hash_head++;

			hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) {
				list_for_each_entry(fa, &fn->fn_alias, fa_list) {
					iter->fn = fn;
					iter->fa = fa;
					goto out;
				}
			}
		}

		iter->zone = iter->zone->fz_next;

		if (!iter->zone)
			goto out;

		iter->bucket = 0;
		iter->hash_head = iter->zone->fz_hash;

		hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) {
			list_for_each_entry(fa, &fn->fn_alias, fa_list) {
				iter->fn = fn;
				iter->fa = fa;
				goto out;
			}
		}
	}
out:
	iter->pos++;
	return fa;
}

static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos)
{
	struct fib_iter_state *iter = seq->private;
	struct fib_alias *fa;

	if (iter->valid && pos >= iter->pos && iter->genid == fib_hash_genid) {
		fa   = iter->fa;
		pos -= iter->pos;
	} else
		fa = fib_get_first(seq);

	if (fa)
		while (pos && (fa = fib_get_next(seq)))
			--pos;
	return pos ? NULL : fa;
}

static void *fib_seq_start(struct seq_file *seq, loff_t *pos)
{
	void *v = NULL;

	read_lock(&fib_hash_lock);
	if (ip_fib_main_table)
		v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
	return v;
}

static void *fib_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return v == SEQ_START_TOKEN ? fib_get_first(seq) : fib_get_next(seq);
}

static void fib_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&fib_hash_lock);
}

static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi)
{
	static const unsigned type2flags[RTN_MAX + 1] = {
		[7] = RTF_REJECT, [8] = RTF_REJECT,
	};
	unsigned flags = type2flags[type];

	if (fi && fi->fib_nh->nh_gw)
		flags |= RTF_GATEWAY;
	if (mask == htonl(0xFFFFFFFF))
		flags |= RTF_HOST;
	flags |= RTF_UP;
	return flags;
}

/*
 *	This outputs /proc/net/route.
 *
 *	It always works in backward compatibility mode.
 *	The format of the file is not supposed to be changed.
 */
static int fib_seq_show(struct seq_file *seq, void *v)
{
	struct fib_iter_state *iter;
	char bf[128];
	__be32 prefix, mask;
	unsigned flags;
	struct fib_node *f;
	struct fib_alias *fa;
	struct fib_info *fi;

	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway "
			   "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU"
			   "\tWindow\tIRTT");
		goto out;
	}

	iter	= seq->private;
	f	= iter->fn;
	fa	= iter->fa;
	fi	= fa->fa_info;
	prefix	= f->fn_key;
	mask	= FZ_MASK(iter->zone);
	flags	= fib_flag_trans(fa->fa_type, mask, fi);
	if (fi)
		snprintf(bf, sizeof(bf),
			 "%s\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
			 fi->fib_dev ? fi->fib_dev->name : "*", prefix,
			 fi->fib_nh->nh_gw, flags, 0, 0, fi->fib_priority,
			 mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0),
			 fi->fib_window,
			 fi->fib_rtt >> 3);
	else
		snprintf(bf, sizeof(bf),
			 "*\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
			 prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0);
	seq_printf(seq, "%-127s\n", bf);
out:
	return 0;
}

static const struct seq_operations fib_seq_ops = {
	.start  = fib_seq_start,
	.next   = fib_seq_next,
	.stop   = fib_seq_stop,
	.show   = fib_seq_show,
};

static int fib_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &fib_seq_ops,
			sizeof(struct fib_iter_state));
}

static const struct file_operations fib_seq_fops = {
	.owner		= THIS_MODULE,
	.open           = fib_seq_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release	= seq_release_private,
};

int __init fib_proc_init(void)
{
	if (!proc_net_fops_create(&init_net, "route", S_IRUGO, &fib_seq_fops))
		return -ENOMEM;
	return 0;
}

void __init fib_proc_exit(void)
{
	proc_net_remove(&init_net, "route");
}
#endif /* CONFIG_PROC_FS */