Linux Kernel存储udp server的socket信息跟踪

前言

工作中遇到一个内核的bug，同事给内核增加了socket绑定设备接口id的功能，主要用在绑定VRF的时候，绑定特定的设备。最近测试发现了，加了这个补丁后，导致不同vlan的dhcp server不能同时工作，为了解决这个问题，我对linux kernel如何存储socket的相关功能进行了跟踪，记录如下。

应用层UDP Server创建

应用层调用socket, bind创建udp server

	socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
	bind(sock, (struct sockaddr *)&sa, len));

Kernel 路径跟踪

调用socket后会创建内核的struct sock结构体，也就是inet_create, 这个是在inet_init（）函数中注册的
(void)sock_register(&inet_family_ops); 针对TCP,UDP,RAW也有相应的回调函数注册的协议族。

SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
	int retval;
	struct socket *sock;
	int flags;

	/* Check the SOCK_* constants for consistency.  */
	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
	BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);

	flags = type & ~SOCK_TYPE_MASK;
	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;
	type &= SOCK_TYPE_MASK;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
   //创建内核struct sock结构体 以及必要填充数据结构，核心
	retval = sock_create(family, type, protocol, &sock);
	if (retval < 0)
		goto out;

	retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
	if (retval < 0)
		goto out_release;

out:
	/* It may be already another descriptor 8) Not kernel problem. */
	return retval;

out_release:
	sock_release(sock);
	return retval;
}

int __sock_create(struct net *net, int family, int type, int protocol,
			 struct socket **res, int kern)
{
	int err;
	struct socket *sock;
	const struct net_proto_family *pf;

	/*
	 *      Check protocol is in range
	 */
	if (family < 0 || family >= NPROTO)
		return -EAFNOSUPPORT;
	if (type < 0 || type >= SOCK_MAX)
		return -EINVAL;

	/* Compatibility.

	   This uglymoron is moved from INET layer to here to avoid
	   deadlock in module load.
	 */
	if (family == PF_INET && type == SOCK_PACKET) {
		static int warned;
		if (!warned) {
			warned = 1;
			printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n",
			       current->comm);
		}
		family = PF_PACKET;
	}

	err = security_socket_create(family, type, protocol, kern);
	if (err)
		return err;

	/*
	 *	Allocate the socket and allow the family to set things up. if
	 *	the protocol is 0, the family is instructed to select an appropriate
	 *	default.
	 */
	sock = sock_alloc();
	if (!sock) {
		net_warn_ratelimited("socket: no more sockets\n");
		return -ENFILE;	/* Not exactly a match, but its the
				   closest posix thing */
	}

	sock->type = type;

#ifdef CONFIG_MODULES
	/* Attempt to load a protocol module if the find failed.
	 *
	 * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user
	 * requested real, full-featured networking support upon configuration.
	 * Otherwise module support will break!
	 */
	if (rcu_access_pointer(net_families[family]) == NULL)
		request_module("net-pf-%d", family);
#endif

	rcu_read_lock();
	pf = rcu_dereference(net_families[family]);
	err = -EAFNOSUPPORT;
	if (!pf)
		goto out_release;

	/*
	 * We will call the ->create function, that possibly is in a loadable
	 * module, so we have to bump that loadable module refcnt first.
	 */
	if (!try_module_get(pf->owner))
		goto out_release;

	/* Now protected by module ref count */
	rcu_read_unlock();

   // 这里最终调用的是inet_create
	err = pf->create(net, sock, protocol, kern);
	if (err < 0)
		goto out_module_put;

	/*
	 * Now to bump the refcnt of the [loadable] module that owns this
	 * socket at sock_release time we decrement its refcnt.
	 */
	if (!try_module_get(sock->ops->owner))
		goto out_module_busy;

	/*
	 * Now that we're done with the ->create function, the [loadable]
	 * module can have its refcnt decremented
	 */
	module_put(pf->owner);
	err = security_socket_post_create(sock, family, type, protocol, kern);
	if (err)
		goto out_sock_release;
	*res = sock;

	return 0;

out_module_busy:
	err = -EAFNOSUPPORT;
out_module_put:
	sock->ops = NULL;
	module_put(pf->owner);
out_sock_release:
	sock_release(sock);
	return err;

out_release:
	rcu_read_unlock();
	goto out_sock_release;
}

    注册协议相关的结构体
	/* Register the socket-side information for inet_create. */
	for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r)
		INIT_LIST_HEAD(r);
	for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q)
		inet_register_protosw(q);

协议相关操作，以及inet相关操作
static struct inet_protosw inetsw_array[] =
{
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
			      INET_PROTOSW_ICSK,
	},

	{
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_UDP,
		.prot =       &udp_prot,
		.ops =        &inet_dgram_ops,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_PERMANENT,
       },

       {
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_ICMP,
		.prot =       &ping_prot,
		.ops =        &inet_dgram_ops,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_REUSE,
       },

       {
	       .type =       SOCK_RAW,
	       .protocol =   IPPROTO_IP,	/* wild card */
	       .prot =       &raw_prot,
	       .ops =        &inet_sockraw_ops,
	       .no_check =   UDP_CSUM_DEFAULT,
	       .flags =      INET_PROTOSW_REUSE,
       }
};

/*
 
 *	Create an inet socket.
 */

int inet_create(struct net *net, struct socket *sock, int protocol, int kern)
{
	struct sock *sk;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
	int try_loading_module = 0;
	int err;

	if (protocol < 0 || protocol >= IPPROTO_MAX)
		return -EINVAL;

	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
lookup_protocol:
	err = -ESOCKTNOSUPPORT;
	rcu_read_lock();
	list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {

		err = 0;
		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
		err = -EPROTONOSUPPORT;
	}

	if (unlikely(err)) {
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

	err = -EPERM;
	if (sock->type == SOCK_RAW && !kern &&
	    !ns_capable(net->user_ns, CAP_NET_RAW))
		goto out_rcu_unlock;

	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

	WARN_ON(answer_prot->slab == NULL);

	err = -ENOBUFS;
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
	if (sk == NULL)
		goto out;

	err = 0;
	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = SK_CAN_REUSE;

	inet = inet_sk(sk);
	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

	inet->nodefrag = 0;

	if (SOCK_RAW == sock->type) {
		inet->inet_num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->inet_id = 0;

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_protocol	   = protocol;
	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
	inet->mc_all	= 1;
	inet->mc_index	= 0;
	inet->mc_list	= NULL;
	inet->rcv_tos	= 0;

	sk_refcnt_debug_inc(sk);

	if (inet->inet_num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->inet_sport = htons(inet->inet_num);
		printk("Richard - %s(%d) - inet_sport=%d\n", __FUNCTION__, __LINE__, inet->inet_sport);
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {
		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}

bind函数相关的系统调用

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		err = move_addr_to_kernel(umyaddr, addrlen, &address);
		if (err >= 0) {
			err = security_socket_bind(sock,
						   (struct sockaddr *)&address,
						   addrlen);

            此处调用inet_bind做一些绑定
			if (!err)
				err = sock->ops->bind(sock,
						      (struct sockaddr *)
						      &address, addrlen);
		}
		fput_light(sock->file, fput_needed);
	}
	return err;
}



int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	printk("Richard - %s(%d)\n", __FUNCTION__, __LINE__);
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	unsigned short snum;
	int chk_addr_ret;
	u32 tb_id = RT_TABLE_LOCAL;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	if (addr->sin_family != AF_INET) {
		/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
		 * only if s_addr is INADDR_ANY.
		 */
		err = -EAFNOSUPPORT;
		if (addr->sin_family != AF_UNSPEC ||
		    addr->sin_addr.s_addr != htonl(INADDR_ANY))
			goto out;
	}

	tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
	chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
	    !(inet->freebind || inet->transparent) &&
	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	printk("Richard - %s(%d): snum=%d\n", __FUNCTION__, __LINE__, snum);
	err = -EACCES;
	if (snum && snum < PROT_SOCK &&
	    !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->inet_num)
		goto out_release_sock;

	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->inet_saddr = 0;  /* Use device */

    这里比较关键，会根据传输的端口号，进行相应的计算存储到struct sock的哈希链表中
	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
		inet->inet_saddr = inet->inet_rcv_saddr = 0;
		err = -EADDRINUSE;
		goto out_release_sock;
	}

	if (inet->inet_rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->inet_sport = htons(inet->inet_num);
	inet->inet_daddr = 0;
	inet->inet_dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}
EXPORT_SYMBOL(inet_bind);

关于bind的最核心的是看这里，内核是如何存储这个socket的, 比如dhcp server，传入的snum=67 就会根据这个值计算hash,如果多个接口都有，则根据sk_bound_dev_if来区分是哪个接口上的。最后加入hslot链表中。

/**
 *  udp_lib_get_port  -  UDP/-Lite port lookup for IPv4 and IPv6
 *
 *  @sk:          socket struct in question
 *  @snum:        port number to look up
 *  @saddr_comp:  AF-dependent comparison of bound local IP addresses
 *  @hash2_nulladdr: AF-dependent hash value in secondary hash chains,
 *                   with NULL address
 */
int udp_lib_get_port(struct sock *sk, unsigned short snum,
		       int (*saddr_comp)(const struct sock *sk1,
					 const struct sock *sk2),
		     unsigned int hash2_nulladdr)
{
	struct udp_hslot *hslot, *hslot2;
	struct udp_table *udptable = sk->sk_prot->h.udp_table;
	int    error = 1;
	struct net *net = sock_net(sk);

	printk("Richard - %s(%d) - snum=%d\n", __FUNCTION__, __LINE__, snum);
	if (!snum) {
		int low, high, remaining;
		unsigned int rand;
		unsigned short first, last;
		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);

		inet_get_local_port_range(&low, &high);
		remaining = (high - low) + 1;

		rand = net_random();
		first = (((u64)rand * remaining) >> 32) + low;
		/*
		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
		 */
		rand = (rand | 1) * (udptable->mask + 1);
		last = first + udptable->mask + 1;
		do {
			hslot = udp_hashslot(udptable, net, first);
			bitmap_zero(bitmap, PORTS_PER_CHAIN);
			spin_lock_bh(&hslot->lock);
			udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
					    saddr_comp, udptable->log);

			snum = first;
			/*
			 * Iterate on all possible values of snum for this hash.
			 * Using steps of an odd multiple of UDP_HTABLE_SIZE
			 * give us randomization and full range coverage.
			 */
			do {
				if (low <= snum && snum <= high &&
				    !test_bit(snum >> udptable->log, bitmap) &&
				    !inet_is_reserved_local_port(snum))
					goto found;
				snum += rand;
			} while (snum != first);
			spin_unlock_bh(&hslot->lock);
		} while (++first != last);
		goto fail;
	} else {
		hslot = udp_hashslot(udptable, net, snum);
		spin_lock_bh(&hslot->lock);
		if (hslot->count > 10) {
			int exist;
			unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;

			slot2          &= udptable->mask;
			hash2_nulladdr &= udptable->mask;

			hslot2 = udp_hashslot2(udptable, slot2);
			if (hslot->count < hslot2->count)
				goto scan_primary_hash;

			exist = udp_lib_lport_inuse2(net, snum, hslot2,
						     sk, saddr_comp);
			if (!exist && (hash2_nulladdr != slot2)) {
				hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
				exist = udp_lib_lport_inuse2(net, snum, hslot2,
							     sk, saddr_comp);
			}
			if (exist)
				goto fail_unlock;
			else
				goto found;
		}
scan_primary_hash:
		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk,
					saddr_comp, 0)) {
			printk("Richard - %s(%d) port inuse, fail_unlock\n", __FUNCTION__, __LINE__);
			goto fail_unlock;
		}
	}
found:
	inet_sk(sk)->inet_num = snum;
	udp_sk(sk)->udp_port_hash = snum;
	udp_sk(sk)->udp_portaddr_hash ^= snum;
	if (sk_unhashed(sk)) {
		sk_nulls_add_node_rcu(sk, &hslot->head);
		hslot->count++;
		
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);

		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
		spin_lock(&hslot2->lock);
		hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
					 &hslot2->head);
		hslot2->count++;
		spin_unlock(&hslot2->lock);
		
		printk("Richard - %s(%d) - snum=%d, sk=%p, hslot->count=%d, portaddr_hash=%d, hslot2->count=%d\n", 
			__FUNCTION__, __LINE__, snum, sk, hslot->count, udp_sk(sk)->udp_portaddr_hash, hslot2->count);
	}
	error = 0;
fail_unlock:
	spin_unlock_bh(&hslot->lock);
fail:
	return error;
}

udp客户端请求

OK, 到这里， socket， bind都看过了，如何存储的socket也知道了，那么接下来看看请求来的时候，这个是怎么处理的吧。

首先数据被接收了后进入udp 层处理 udp_rcv->__udp4_lib_rcv->__udp4_lib_mcast_deliver

/*
 *	Multicasts and broadcasts go to each listener.
 *
 *	Note: called only from the BH handler context.
 */
static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
				    struct udphdr  *uh,
				    __be32 saddr, __be32 daddr,
				    struct udp_table *udptable)
{
	printk("Richard - %s(%d) saddr=%pI4, daddr=%pI4\n", __FUNCTION__, __LINE__, &saddr, &daddr);
	struct sock *sk, *stack[256 / sizeof(struct sock *)];
	struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest));
	int dif;
	unsigned int i, count = 0;

	spin_lock(&hslot->lock);
	sk = sk_nulls_head(&hslot->head);
	dif = skb->dev->ifindex;
	int sdif = inet_sdif(skb);
	sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif, sdif);
	while (sk) {
		stack[count++] = sk;
		sk = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest,
				       daddr, uh->source, saddr, dif, sdif);
		if (unlikely(count == ARRAY_SIZE(stack))) {
			if (!sk) {
				printk("Richard -- break\n");
				break;
			}
			flush_stack(stack, count, skb, ~0);
			count = 0;
		}
	}
	/*
	 * before releasing chain lock, we must take a reference on sockets
	 */
	for (i = 0; i < count; i++)
		sock_hold(stack[i]);

	spin_unlock(&hslot->lock);

	/*
	 * do the slow work with no lock held
	 */
	if (count) {
		flush_stack(stack, count, skb, count - 1);

		for (i = 0; i < count; i++)
			sock_put(stack[i]);
	} else {
		
		kfree_skb(skb);
	}
	return 0;
}




static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
					     __be16 loc_port, __be32 loc_addr,
					     __be16 rmt_port, __be32 rmt_addr,
					     int dif, int sdif)
{
	struct hlist_nulls_node *node;
	struct sock *s = sk;
	unsigned short hnum = ntohs(loc_port);
	
	//这里遍历udp server socket的链表找相对应的，条件满足就可以了。
	sk_nulls_for_each_from(s, node) {
		struct inet_sock *inet = inet_sk(s);
		
		if (!net_eq(sock_net(s), net) ||
		    udp_sk(s)->udp_port_hash != hnum ||
		    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
		    (inet->inet_dport != rmt_port && inet->inet_dport) ||
		    (inet->inet_rcv_saddr &&
		     inet->inet_rcv_saddr != loc_addr) ||
		    ipv6_only_sock(s) ||
			(s->sk_bound_dev_if && s->sk_bound_dev_if != dif &&
			s->sk_bound_dev_if != sdif))

			continue;
		if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif, sdif))
			continue;
		
		goto found;
	}
	s = NULL;
found:
	return s;
}

总结

本来解决问题的时候我还有很多模棱两可的理解，写了这个文章发现，系统调用看socket.c就好了，到这里感觉对整体的理解又有点深入了。

udp server的socket的端口号，接口号是保存在哈希链表的。但是这个struct sock的结构体是保存在文件系统的。

static int sock_map_fd(struct socket *sock, int flags)
{
	struct file *newfile;
	int fd = get_unused_fd_flags(flags);
	if (unlikely(fd < 0))
		return fd;
	//结构体是放在这里面
	newfile = sock_alloc_file(sock, flags, NULL);
	if (likely(!IS_ERR(newfile))) {
		fd_install(fd, newfile);
		return fd;
	}

	put_unused_fd(fd);
	return PTR_ERR(newfile);
}