连接跟踪conntrack是状态防火墙和NAT的基础，每个经过conntrack处理的数据包的skb->nfctinfo都会设置如下值之一，后续流程中NAT模块根据此值做不同的处理，filter模块可以在扩展匹配中指定state进行不同的处理。
enum ip_conntrack_info {
/* Part of an established connection (either direction). */
//收到双向报文，连接已经建立，对original方向报文设置此标志
IP_CT_ESTABLISHED,
/* Like NEW, but related to an existing connection, or ICMP error
(in either direction). */
IP_CT_RELATED,
/* Started a new connection to track (only
IP_CT_DIR_ORIGINAL); may be a retransmission. */
//收到original方向数据包，连接还未建立
IP_CT_NEW,
/* >= this indicates reply direction */
//收到reply方向数据包，说明连接建立
IP_CT_IS_REPLY,
IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY,
IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY,
IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY,
/* Number of distinct IP_CT types (no NEW in reply dirn). */
IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
};
nf hook函数注册
跟连接跟踪相关的hook函数包含下面两个：重组相关的和conntrack处理相关的。
注册报文重组hook函数。
static struct nf_hook_ops ipv4_defrag_ops[] = {
{
.hook = ipv4_conntrack_defrag,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_DEFRAG,
},
{
.hook = ipv4_conntrack_defrag,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_CONNTRACK_DEFRAG,
},
};
static int __init nf_defrag_init(void)
{
return nf_register_hooks(ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops));
}
module_init(nf_defrag_init);
注册conntrack hook函数。
/* Connection tracking may drop packets, but never alters them, so
make it the first hook. */
static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
{
.hook = ipv4_conntrack_in,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_CONNTRACK,
},
{
.hook = ipv4_conntrack_local,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_CONNTRACK,
},
{
.hook = ipv4_helper,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_HELPER,
},
{
.hook = ipv4_confirm,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
},
{
.hook = ipv4_helper,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_CONNTRACK_HELPER,
},
{
.hook = ipv4_confirm,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
},
};
static int __init nf_conntrack_l3proto_ipv4_init(void)
{
...
ret = nf_register_hooks(ipv4_conntrack_ops,
ARRAY_SIZE(ipv4_conntrack_ops));
...
}
上面的hook函数会注册到二维数组nf_hook中。
enum nf_inet_hooks {
NF_INET_PRE_ROUTING,
NF_INET_LOCAL_IN,
NF_INET_FORWARD,
NF_INET_LOCAL_OUT,
NF_INET_POST_ROUTING,
NF_INET_NUMHOOKS
};
enum {
NFPROTO_UNSPEC = 0,
NFPROTO_INET = 1,
NFPROTO_IPV4 = 2,
NFPROTO_ARP = 3,
NFPROTO_BRIDGE = 7,
NFPROTO_IPV6 = 10,
NFPROTO_DECNET = 12,
NFPROTO_NUMPROTO,
};
extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n)
{
unsigned int i;
for (i = 0; i < n; i++) {
nf_register_hook(®[i]);
}
}
int nf_register_hook(struct nf_hook_ops *reg)
{
struct nf_hook_ops *elem;
mutex_lock(&nf_hook_mutex);
list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) {
if (reg->priority < elem->priority)
break;
}
list_add_rcu(®->list, elem->list.prev);
mutex_unlock(&nf_hook_mutex);
#ifdef HAVE_JUMP_LABEL
static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
#endif
return 0;
}
重组和conntrack hook注册成功后，nf_hook内容如下标黄，这也是ipv4的连接跟踪模块用到的hook函数，小括号中的数字是hook函数的优先级。在同一个hook点上，数字越小优先级越高。
image.png
发送给本机的数据会经过 NF_INET_PRE_ROUTING 和 NF_INET_LOCAL_IN 两个hook点，所以hook函数调用顺序为：
ipv4_conntrack_defrag -> ipv4_conntrack_in -> ipv4_helper -> ipv4_confirm。
由本机转发的数据会经过 NF_INET_PRE_ROUTING 和 NF_INET_FORWARD 和 NF_INET_POST_ROUTING 三个hook点，所以hook函数调用顺序为:
ipv4_conntrack_defrag -> ipv4_conntrack_in -> ipv4_helper -> ipv4_confirm。
本机发送的数据会经过 NF_INET_LOCAL_OUT 和NF_INET_POST_ROUTING 两个hook点，所以hook函数调用顺序为:
ipv4_conntrack_defrag -> ipv4_conntrack_local -> ipv4_helper -> ipv4_confirm。
可看到不管数据包从哪来到哪去，经过的连接跟踪模块处理基本是一样的，唯一的区别是ipv4_conntrack_in和ipv4_conntrack_local，后者增加了对数据包长度的校验，即只有从本机发出去的报文才需要校验长度。
static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb);
}
static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb);
}
hook函数执行
下面分别分析这四个hook函数。
- ipv4_conntrack_defrag
重组分片报文。重组完整前不让数据包进行下一步
static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(skb->sk);
//对于PF_INET类型的socket，并且inet->nodefrag置位了，则
//不允许重组，返回NF_ACCEPT
if (sk && (sk->sk_family == PF_INET) &&
inet->nodefrag)
return NF_ACCEPT;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#if !IS_ENABLED(CONFIG_NF_NAT)
/* Previously seen (loopback)? Ignore. Do this before
fragment check. */
//nfct不为空，并且没有IPS_TEMPLATE_BIT标志，说明此ct是
//在raw表匹配到target为notrack的规则。
if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
return NF_ACCEPT;
#endif
#endif
/* Gather fragments. */
//如果是分片报文，只处理分片报文
if (ip_is_fragment(ip_hdr(skb))) {
//获取重组的user。user表示谁来执行重组，或者说在哪个
//模块哪个阶段重组
enum ip_defrag_users user =
nf_ct_defrag_user(ops->hooknum, skb);
//返回值为非零表示未完成重组(只收到第一片或者某几
//片)，需要将skb保存到队列，或者重组过程出错，此时
//需要释放skb。
if (nf_ct_ipv4_gather_frags(skb, user))
return NF_STOLEN;
}
return NF_ACCEPT;
}
- nf_conntrack_in
连接跟踪处理的主函数nf_conntrack_in，其会用到l3proto和l4proto函数，先看一下这两组函数的注册。
注册l3proto Ipv4的处理函数。
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
.l3proto = PF_INET,
.name = "ipv4",
.pkt_to_tuple = ipv4_pkt_to_tuple, //获取源目的ip
.invert_tuple = ipv4_invert_tuple, //源目的ip调换
.print_tuple = ipv4_print_tuple, //打印出源目的ip
.get_l4proto = ipv4_get_l4proto, //获取ip报文总长度和四层协议号
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = ipv4_tuple_to_nlattr,
.nlattr_tuple_size = ipv4_nlattr_tuple_size,
.nlattr_to_tuple = ipv4_nlattr_to_tuple,
.nla_policy = ipv4_nla_policy,
#endif
#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
.ctl_table_path = "net/ipv4/netfilter",
#endif
.init_net = ipv4_init_net,
.me = THIS_MODULE,
};
static int __init nf_conntrack_l3proto_ipv4_init(void)
ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto)
{
int ret = 0;
struct nf_conntrack_l3proto *old;
if (proto->l3proto >= AF_MAX)
return -EBUSY;
if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size)
return -EINVAL;
mutex_lock(&nf_ct_proto_mutex);
old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
lockdep_is_held(&nf_ct_proto_mutex));
if (proto->nlattr_tuple_size)
proto->nla_size = 3 * proto->nlattr_tuple_size();
rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto);
}
注册l4proto处理函数
int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto)
rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], l4proto);
//ipv4的l4注册了tcp,udp和icmp这三种协议
static int __init nf_conntrack_l3proto_ipv4_init(void)
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4);
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4);
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp);
//以udp为例说明
struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
{
.l3proto = PF_INET,
.l4proto = IPPROTO_UDP,
.name = "udp",
.pkt_to_tuple = udp_pkt_to_tuple, //获取源目的port
.invert_tuple = udp_invert_tuple,//源目的port调换
.print_tuple = udp_print_tuple,//打印源目的port
.packet = udp_packet, //更新ct中定时器超时时间并更新统计计数
.get_timeouts = udp_get_timeouts, //获取ct超时时间
.new = udp_new, //创建新ct时调用
.error = udp_error,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nla_policy = nf_ct_port_nla_policy,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
.ctnl_timeout = {
.nlattr_to_obj = udp_timeout_nlattr_to_obj,
.obj_to_nlattr = udp_timeout_obj_to_nlattr,
.nlattr_max = CTA_TIMEOUT_UDP_MAX,
.obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX,
.nla_policy = udp_timeout_nla_policy,
},
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
.init_net = udp_init_net,
.get_net_proto = udp_get_net_proto,
};
nf_conntrack_in 会用到上面注册的l3proto和l4proto函数
unsigned int
nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
struct sk_buff *skb)
{
struct nf_conn *ct, *tmpl = NULL;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_l3proto *l3proto;
struct nf_conntrack_l4proto *l4proto;
unsigned int *timeouts;
unsigned int dataoff;
u_int8_t protonum;
int set_reply = 0;
int ret;
//如果skb已经有ct了，并且有template标志
//IPS_TEMPLATE_BIT，说明报文在raw表经过了
//notrack处理，不用记录在连接跟踪表，可以直接返回。
//如果有template标志IPS_TEMPLATE_BIT，说明是helper相关
//的处理，保存tmpl，将skb->nfct置空，后面重新给它分配ct
if (skb->nfct) {
/* Previously seen (loopback or untracked)? Ignore. */
tmpl = (struct nf_conn *)skb->nfct;
if (!nf_ct_is_template(tmpl)) {
NF_CT_STAT_INC_ATOMIC(net, ignore);
return NF_ACCEPT;
}
skb->nfct = NULL;
}
/* rcu_read_lock()ed by nf_hook_slow */
//根据pf到nf_ct_l3protos获取l3proto
//对于ipv4，l3proto为nf_conntrack_l3proto_ipv4，用于获取三层源目的ip。
l3proto = __nf_ct_l3proto_find(pf);
ret = l3proto->get_l4proto(skb, skb_network_offset(skb),
&dataoff, &protonum);
if (ret <= 0) {
pr_debug("not prepared to track yet or error occurred\n");
NF_CT_STAT_INC_ATOMIC(net, error);
NF_CT_STAT_INC_ATOMIC(net, invalid);
ret = -ret;
goto out;
}
//根据pf和四层协议号到nf_ct_protos找l4proto。
//对于udp协议来说，l4proto就是nf_conntrack_l4proto_udp4，
//用于获取四层源目的端口号等信息。
l4proto = __nf_ct_l4proto_find(pf, protonum);
/* It may be an special packet, error, unclean...
* inverse of the return code tells to the netfilter
* core what to do with the packet. */
if (l4proto->error != NULL) {
ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo,
pf, hooknum);
if (ret <= 0) {
NF_CT_STAT_INC_ATOMIC(net, error);
NF_CT_STAT_INC_ATOMIC(net, invalid);
ret = -ret;
goto out;
}
/* ICMP[v6] protocol trackers may assign one conntrack. */
if (skb->nfct)
goto out;
}
ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
l3proto, l4proto, &set_reply, &ctinfo);
if (!ct) {
/* Not valid part of a connection */
NF_CT_STAT_INC_ATOMIC(net, invalid);
ret = NF_ACCEPT;
goto out;
}
if (IS_ERR(ct)) {
/* Too stressed to deal. */
NF_CT_STAT_INC_ATOMIC(net, drop);
ret = NF_DROP;
goto out;
}
NF_CT_ASSERT(skb->nfct);
/* Decide what timeout policy we want to apply to this flow. */
//不同的四层协议根据各自特点提供了不同的超时时间，udp提供如下两种
//static unsigned int udp_timeouts[UDP_CT_MAX] = {
// [UDP_CT_UNREPLIED] = 30*HZ,
// [UDP_CT_REPLIED] = 180*HZ,
//};
timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
//对于udp来说，调用udp_packet->nf_ct_refresh_acct更新ct超
//时时间，保证此条数据流不断，ct就不会被删除。并且更新统
//计计数到acct中。
ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
if (ret <= 0) {
/* Invalid: inverse of the return code tells
* the netfilter core what to do */
pr_debug("nf_conntrack_in: Can't track with proto module\n");
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
NF_CT_STAT_INC_ATOMIC(net, invalid);
if (ret == -NF_DROP)
NF_CT_STAT_INC_ATOMIC(net, drop);
ret = -ret;
goto out;
}
//对于一个新创建的连接跟踪项后，当第一次收到reply方向的数
//据包后，则会设置nf_conn->status的IPS_SEEN_REPLY_BIT
//位为1，当设置成功且IPS_SEEN_REPLY_BIT位的原来值为0
//时，则调用nf_conntrack_event_cache ，由nfnetlink模块处理
//状态改变的事件。
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_REPLY, ct);
out:
if (tmpl) {
/* Special case: we have to repeat this hook, assign the
* template again to this packet. We assume that this packet
* has no conntrack assigned. This is used by nf_ct_tcp. */
if (ret == NF_REPEAT)
skb->nfct = (struct nf_conntrack *)tmpl;
else
nf_ct_put(tmpl);
}
return ret;
}
/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
static inline struct nf_conn *
resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int dataoff,
u_int16_t l3num,
u_int8_t protonum,
struct nf_conntrack_l3proto *l3proto,
struct nf_conntrack_l4proto *l4proto,
int *set_reply,
enum ip_conntrack_info *ctinfo)
{
struct nf_conntrack_tuple tuple;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
u32 hash;
//获取五元组信息
if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
dataoff, l3num, protonum, &tuple, l3proto,
l4proto)) {
pr_debug("resolve_normal_ct: Can't get tuple\n");
return NULL;
}
/* look for tuple match */
hash = hash_conntrack_raw(&tuple, zone);
//到全局confirm表net->ct.hash中查找是否已经存在此条流
h = __nf_conntrack_find_get(net, zone, &tuple, hash);
if (!h) {
//如果查找不到，需要分配一个ct。根据tuple获取反方向的
//reply tuple，将他俩赋值给ct的tuplehash。并将original
//的tuplehash挂到 net.ct.pcpu_lists->unconfirmed表中
h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
skb, dataoff, hash);
if (!h)
return NULL;
if (IS_ERR(h))
return (void *)h;
}
ct = nf_ct_tuplehash_to_ctrack(h);
//如果是reply方向的数据包，设置 ctinfo =
//IP_CT_ESTABLISHED_REPLY，
//如果是original方向的数据包，分为如下几种情况：
//a. original方向第一个数据包，则设置ctinfo = IP_CT_NEW
//b. original方向的非第一个数据包，并且已经收到reply的数据
//包，则设置ctinfo = IP_CT_ESTABLISHED
//c.original方向的数据包，并且是其他连接的期望连接，则设置ctinfo = IP_CT_RELATED
//d. original方向的非第一个数据包，但是还没有收到reply包，也设置ctinfo = IP_CT_NEW
/* It exists; we have (non-exclusive) reference. */
if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
*ctinfo = IP_CT_ESTABLISHED_REPLY;
/* Please set reply bit if this packet OK */
*set_reply = 1;
} else {
/* Once we've had two way comms, always ESTABLISHED. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
pr_debug("nf_conntrack_in: normal packet for %p\n", ct);
*ctinfo = IP_CT_ESTABLISHED;
} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
pr_debug("nf_conntrack_in: related packet for %p\n",
ct);
*ctinfo = IP_CT_RELATED;
} else {
pr_debug("nf_conntrack_in: new packet for %p\n", ct);
*ctinfo = IP_CT_NEW;
}
*set_reply = 0;
}
//将ct和ctinfo保存到数据包
skb->nfct = &ct->ct_general;
skb->nfctinfo = *ctinfo;
return ct;
}
//只有original方向的报文才会执行此函数
//分配ct
/* Allocate a new conntrack: we return -ENOMEM if classification
failed due to stress. Otherwise it really is unclassifiable. */
static struct nf_conntrack_tuple_hash *
init_conntrack(struct net *net, struct nf_conn *tmpl,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_l3proto *l3proto,
struct nf_conntrack_l4proto *l4proto,
struct sk_buff *skb,
unsigned int dataoff, u32 hash)
{
struct nf_conn *ct;
struct nf_conn_help *help;
struct nf_conntrack_tuple repl_tuple;
struct nf_conntrack_ecache *ecache;
struct nf_conntrack_expect *exp = NULL;
u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
struct nf_conn_timeout *timeout_ext;
unsigned int *timeouts;
//由tuple获取reply方向的tuple
if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
pr_debug("Can't invert tuple.\n");
return NULL;
}
ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
hash);
if (IS_ERR(ct))
return (struct nf_conntrack_tuple_hash *)ct;
if (tmpl && nfct_synproxy(tmpl)) {
nfct_seqadj_ext_add(ct);
nfct_synproxy_ext_add(ct);
}
timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
if (timeout_ext)
timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
else
timeouts = l4proto->get_timeouts(net);
if (!l4proto->new(ct, skb, dataoff, timeouts)) {
nf_conntrack_free(ct);
pr_debug("init conntrack: can't track with proto module\n");
return NULL;
}
if (timeout_ext)
nf_ct_timeout_ext_add(ct, timeout_ext->timeout, GFP_ATOMIC);
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
nf_ct_labels_ext_add(ct);
ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
ecache ? ecache->expmask : 0,
GFP_ATOMIC);
local_bh_disable();
//如果有了期望连接，则需要到net->ct.expect_hash查找自己是
//否是期望连接，如果是，需要设置 IPS_EXPECTED_BIT，并
//将 ct->master 指向主连接
if (net->ct.expect_count) {
spin_lock(&nf_conntrack_expect_lock);
exp = nf_ct_find_expectation(net, zone, tuple);
if (exp) {
pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
ct, exp);
/* Welcome, Mr. Bond. We've been expecting you... */
__set_bit(IPS_EXPECTED_BIT, &ct->status);
/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
ct->master = exp->master;
if (exp->helper) {
help = nf_ct_helper_ext_add(ct, exp->helper,
GFP_ATOMIC);
if (help)
rcu_assign_pointer(help->helper, exp->helper);
}
#ifdef CONFIG_NF_CONNTRACK_MARK
ct->mark = exp->master->mark;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
ct->secmark = exp->master->secmark;
#endif
NF_CT_STAT_INC(net, expect_new);
}
spin_unlock(&nf_conntrack_expect_lock);
}
if (!exp) {
__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
NF_CT_STAT_INC(net, new);
}
/* Now it is inserted into the unconfirmed list, bump refcount */
nf_conntrack_get(&ct->ct_general);
//暂时将ct保存到本cpu的unconfirm链表中
nf_ct_add_to_unconfirmed_list(ct);
local_bh_enable();
if (exp) {
if (exp->expectfn)
exp->expectfn(ct, exp);
nf_ct_expect_put(exp);
}
return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
}
- ipv4_help
ipv4_help主要是执行匹配到的helper函数，进行一些扩展操作，比如ftp的数据通道建立，nat的转换。可参考ftp提供的helper：help
static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_conn_help *help;
const struct nf_conntrack_helper *helper;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
return NF_ACCEPT;
//从ct的扩展区域尝试获取helper
help = nfct_help(ct);
if (!help)
return NF_ACCEPT;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
return NF_ACCEPT;
return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
}
- ipv4_confirm
ipv4_confirm是优先级最低的hook函数，数据包能走到这里就肯定不会被netfilter丢弃，所以可以将它的ct从uncomfirm(per-cpu)转到confirm(全局的)链表上。
static unsigned int ipv4_confirm(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
goto out;
/* adjust seqs for loopback traffic only in outgoing direction */
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
!nf_is_loopback_packet(skb)) {
if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
}
}
out:
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(skb);
}
/* Confirm a connection: returns NF_DROP if packet must be dropped. */
static inline int nf_conntrack_confirm(struct sk_buff *skb)
{
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
int ret = NF_ACCEPT;
if (ct && !nf_ct_is_untracked(ct)) {
if (!nf_ct_is_confirmed(ct))
//将 ct->tuplehash[IP_CT_DIR_ORIGINAL] 从
//unconfirm hash链上删除，并将ct-
//>tuplehash[IP_CT_DIR_ORIGINAL]
//和ct->tuplehash[IP_CT_DIR_REPLY]根据hash同时
//添加到全局confirm hash链上
ret = __nf_conntrack_confirm(skb);
if (likely(ret == NF_ACCEPT))
//调用通知链上的函数通知netlink模块
nf_ct_deliver_cached_events(ct);
}
return ret;
}
连接跟踪是个基础模块，总结如下图，其他利用它实现功能的模块在其他文章中记录。
image.png
网友评论