Linux中TCP listen套接字的查找的变化

时间 2019-11-16

标签 linux tcp listen 查找变化栏目 Linux 繁體版

原文原文链接

内核TCP在收到SYN报文时，会根据报文的目的IP和Port，在本地匹配处于LISTEN状态的套接字进行握手过程。linux

4.17版本之前的listen套接字查找

The current listener hashtable is hashed by port only. When a process is listening at many IP addresses with the same port (e.g.[IP1]:443, [IP2]:443... [IPN]:443), the inet[6]_lookup_listener() performance is degraded to a link list. It is prone to syn attack.

4.17版本以前，TCP的listener socket是按port进行hash，而后插入到对应的冲突链表中的。这就使得若是不少个listen套接字都侦听同一个port，就会使得链表拉得比较长, 这种状况在3.9版本引入REUSEPORT以后更加严重git

举个栗子，主机上启动了6个listener,它们都侦听21端口，所以被放到同一条链表上(其中sk_B使用了REUSEPORT)。若是此时收到一个目标位1.1.1.4:21的SYN链接请求,内核在查找listenr的时候，始终会从头开始遍历到尾，直到找到匹配的sk_D。socket

4.17版本：在两个hashtable中查找

4.17版本增长了一个新的hashtable(lhash2)来组织listen套接字，这个lhash2是按port+addr做为key进行hash的，而原来按port进行hash的hashtable保持不变。换句话说，同一个listen套接字会同时放到两个hashtable中(例外状况是，若是它绑定的本地地址是0.0.0.0,则只会放到原来的hashtable中)tcp

lhash2增长了addr做为key，也就增长hash的随机性。仍是以上面的例子为例，此时，原来的sk_A~C可能就被hash到其余冲突链了,固然与此同时，也有可能有原来在其余冲突链上的sk_E被hash到lhash2[0]这条冲突链。spa

所以在listen套接字的查找时，内核会根据SYN报文中的port+addr，同时计算出知足条件的套接字应该在两个hashtable中所属的链表，而后比较这两个链表的长度，若是在1st链表长度不长或者小于2nd链表的长度，则仍是以原来的方式，在1st链表中进行查找，不然就在2nd链表中进行查找。3d

struct inet_hashinfo *hashinfo,
                     struct sk_buff *skb, int doff,
@@ -217,10 +306,42 @@ struct sock *__inet_lookup_listener(struct net *net,
     unsigned int hash = inet_lhashfn(net, hnum);
     struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
     bool exact_dif = inet_exact_dif_match(net, skb);
+    struct inet_listen_hashbucket *ilb2;
     struct sock *sk, *result = NULL;
     int score, hiscore = 0;
+    unsigned int hash2;
     u32 phash = 0;
 
+    if (ilb->count <= 10 || !hashinfo->lhash2)
+        goto port_lookup;
+
+    /* Too many sk in the ilb bucket (which is hashed by port alone).
+     * Try lhash2 (which is hashed by port and addr) instead.
+     */
+
+    hash2 = ipv4_portaddr_hash(net, daddr, hnum);
+    ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+    if (ilb2->count > ilb->count)
+        goto port_lookup;
+
+    result = inet_lhash2_lookup(net, ilb2, skb, doff,
+                    saddr, sport, daddr, hnum,
+                    dif, sdif);
+    if (result)
+        return result;
+
+    /* Lookup lhash2 with INADDR_ANY */
+
+    hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
+    ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+    if (ilb2->count > ilb->count)
+        goto port_lookup;
+
+    return inet_lhash2_lookup(net, ilb2, skb, doff,
+                  saddr, sport, daddr, hnum,
+                  dif, sdif);
+
+port_lookup:
     sk_for_each_rcu(sk, &ilb->head) {
         score = compute_score(sk, net, hnum, daddr,
                       dif, sdif, exact_dif);

5.0版本：只在2nd hashtable中查找

内核在5.0版本又将查找方式改成了只在2nd hashtable中进行查找。这样修改的缘由是按原来的查找方式，若是选择了在1st hashtable中进行查找，可能发生在通配地址(0.0.0.0)和特定地址(好比1.1.1.1)都侦听同一个Port时，反而匹配上通配地址的listener的问题。这其实不是4.17版本的锅，而是在3.9版本引入SO_PORTREUSE就已经存在了！code

来看看怎么回事：orm

设置了SO_REUSEPORT的sk_A和sk_B同时侦听21端口，若是sk_A是后启动，那么它将添加到链表头，这样当收到一个1.1.1.2:21的报文时，内核会发现sk_A就已经匹配了，它就不会再去尝试匹配更精确的sk_B！这显然很差，要知道在SO_REUSEPORT进入内核以前，内核会遍历整个链表，对每一个套接字进行匹配程度打分(compute_score)。blog

5.0版本修改成只在2nd hashtable中进行查找，而且修改了compute_score的实现方式，若是侦听地址与报文的目的地址不相同，则直接算匹配失败。而在以前，通配地址是能够直接经过这项检查的。ip

查找方式的修改：

struct sock *__inet_lookup_listener(struct net *net,
                     const __be32 daddr, const unsigned short hnum,
                     const int dif, const int sdif)
 {
-    unsigned int hash = inet_lhashfn(net, hnum);
-    struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-    bool exact_dif = inet_exact_dif_match(net, skb);
     struct inet_listen_hashbucket *ilb2;
-    struct sock *sk, *result = NULL;
-    int score, hiscore = 0;
+    struct sock *result = NULL;
     unsigned int hash2;
-    u32 phash = 0;
-
-    if (ilb->count <= 10 || !hashinfo->lhash2)
-        goto port_lookup;
-
-    /* Too many sk in the ilb bucket (which is hashed by port alone).
-     * Try lhash2 (which is hashed by port and addr) instead.
-     */
 
     hash2 = ipv4_portaddr_hash(net, daddr, hnum);
     ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-    if (ilb2->count > ilb->count)
-        goto port_lookup;
 
     result = inet_lhash2_lookup(net, ilb2, skb, doff,
                     saddr, sport, daddr, hnum,
@@ -335,34 +313,12 @@ struct sock *__inet_lookup_listener(struct net *net,
         goto done;
 
     /* Lookup lhash2 with INADDR_ANY */
-
     hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
     ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-    if (ilb2->count > ilb->count)
-        goto port_lookup;
 
     result = inet_lhash2_lookup(net, ilb2, skb, doff,
-                    saddr, sport, daddr, hnum,
+                    saddr, sport, htonl(INADDR_ANY), hnum,
                     dif, sdif);
-    goto done;
-
-port_lookup:
-    sk_for_each_rcu(sk, &ilb->head) {
-        score = compute_score(sk, net, hnum, daddr,
-                      dif, sdif, exact_dif);
-        if (score > hiscore) {
-            if (sk->sk_reuseport) {
-                phash = inet_ehashfn(net, daddr, hnum,
-                             saddr, sport);
-                result = reuseport_select_sock(sk, phash,
-                                   skb, doff);
-                if (result)
-                    goto done;
-            }
-            result = sk;
-            hiscore = score;
-        }
-    }

打分部分的修改

@@ -234,24 +234,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
                 const int dif, const int sdif, bool exact_dif)
 {
     int score = -1;
-    struct inet_sock *inet = inet_sk(sk);
-    bool dev_match;
 
-    if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
+    if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
             !ipv6_only_sock(sk)) {
-        __be32 rcv_saddr = inet->inet_rcv_saddr;
-        score = sk->sk_family == PF_INET ? 2 : 1;
-        if (rcv_saddr) {
-            if (rcv_saddr != daddr)
-                return -1;
-            score += 4;
-        }
-        dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
-                         dif, sdif);
-        if (!dev_match)
+        if (sk->sk_rcv_saddr != daddr)
+            return -1;
+
+        if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
             return -1;
-        score += 4;
 
+        score = sk->sk_family == PF_INET ? 2 : 1;
         if (sk->sk_incoming_cpu == raw_smp_processor_id())
             score++;
     }

附录:完整补丁

inet: Add a 2nd listener hashtable (port+addr) inet_connection_sock.h
inet: Add a 2nd listener hashtable (port+addr) inet_hashtables.h
inet: Add a 2nd listener hashtable (port+addr) inet_hashtables.c
net: tcp: prefer listeners bound to an address inet_hashtables.c