cregit-Linux how code gets into the kernel

Release 4.11 net/ipv4/ping.c

Directory: net/ipv4
/*
 * INET         An implementation of the TCP/IP protocol suite for the LINUX
 *              operating system.  INET is implemented using the  BSD Socket
 *              interface as the means of communication with the user level.
 *
 *              "Ping" sockets
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * Based on ipv4/udp.c code.
 *
 * Authors:     Vasiliy Kulikov / Openwall (for Linux 2.6),
 *              Pavel Kankovsky (for Linux 2.4.32)
 *
 * Pavel gave all rights to bugs to Vasiliy,
 * none of the bugs are Pavel's now.
 *
 */

#include <linux/uaccess.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/ping.h>
#include <net/udp.h>
#include <net/route.h>
#include <net/inet_common.h>
#include <net/checksum.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#include <linux/icmpv6.h>
#include <net/addrconf.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#endif


struct ping_table {
	
struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
	
rwlock_t		lock;
};


static struct ping_table ping_table;

struct pingv6_ops pingv6_ops;

EXPORT_SYMBOL_GPL(pingv6_ops);


static u16 ping_port_rover;




static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
{
	u32 res = (num + net_hash_mix(net)) & mask;

	pr_debug("hash(%u) = %u\n", num, res);
	return res;
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov3986.67%150.00%


Eric Dumazet613.33%150.00%


Total45100.00%2100.00%




EXPORT_SYMBOL_GPL(ping_hash);




static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
					     struct net *net, unsigned int num)
{
	return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}


Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov3897.44%150.00%


Eric Dumazet12.56%150.00%


Total39100.00%2100.00%






int ping_get_port(struct sock *sk, unsigned short ident)
{
	struct hlist_nulls_node *node;
	struct hlist_nulls_head *hlist;
	struct inet_sock *isk, *isk2;
	struct sock *sk2 = NULL;

	isk = inet_sk(sk);
	write_lock_bh(&ping_table.lock);
	if (ident == 0) {
		u32 i;
		u16 result = ping_port_rover + 1;

		for (i = 0; i < (1L << 16); i++, result++) {
			if (!result)
				result++; /* avoid zero */
			hlist = ping_hashslot(&ping_table, sock_net(sk),
					    result);
			ping_portaddr_for_each_entry(sk2, node, hlist) {
				isk2 = inet_sk(sk2);

				if (isk2->inet_num == result)
					goto next_port;
			}

			/* found */
			ping_port_rover = ident = result;
			break;
next_port:
			;
		}
		if (i >= (1L << 16))
			goto fail;
	} else {
		hlist = ping_hashslot(&ping_table, sock_net(sk), ident);
		ping_portaddr_for_each_entry(sk2, node, hlist) {
			isk2 = inet_sk(sk2);

			/* BUG? Why is this reuse and not reuseaddr? ping.c
                         * doesn't turn off SO_REUSEADDR, and it doesn't expect
                         * that other ping processes can steal its packets.
                         */
			if ((isk2->inet_num == ident) &&
			    (sk2 != sk) &&
			    (!sk2->sk_reuse || !sk->sk_reuse))
				goto fail;
		}
	}

	pr_debug("found port/ident = %d\n", ident);
	isk->inet_num = ident;
	if (sk_unhashed(sk)) {
		pr_debug("was not hashed\n");
		sock_hold(sk);
		hlist_nulls_add_head(&sk->sk_nulls_node, hlist);
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
	}
	write_unlock_bh(&ping_table.lock);
	return 0;

fail:
	write_unlock_bh(&ping_table.lock);
	return 1;
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov31599.37%150.00%


Lorenzo Colitti20.63%150.00%


Total317100.00%2100.00%




EXPORT_SYMBOL_GPL(ping_get_port);




int ping_hash(struct sock *sk)
{
	pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
	BUG(); /* "Please do not press this button again." */

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov2379.31%133.33%


Craig Gallek413.79%133.33%


Lorenzo Colitti26.90%133.33%


Total29100.00%3100.00%






void ping_unhash(struct sock *sk)
{
	struct inet_sock *isk = inet_sk(sk);

	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
	write_lock_bh(&ping_table.lock);
	if (sk_hashed(sk)) {
		hlist_nulls_del(&sk->sk_nulls_node);
		sk_nulls_node_init(&sk->sk_nulls_node);
		sock_put(sk);
		isk->inet_num = 0;
		isk->inet_sport = 0;
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
	}
	write_unlock_bh(&ping_table.lock);
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov8379.81%120.00%


Eric Dumazet1110.58%240.00%


David S. Miller87.69%120.00%


Lorenzo Colitti21.92%120.00%


Total104100.00%5100.00%




EXPORT_SYMBOL_GPL(ping_unhash);




static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
	struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
	struct sock *sk = NULL;
	struct inet_sock *isk;
	struct hlist_nulls_node *hnode;
	int dif = skb->dev->ifindex;

	if (skb->protocol == htons(ETH_P_IP)) {
		pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
			 (int)ident, &ip_hdr(skb)->daddr, dif);
#if IS_ENABLED(CONFIG_IPV6)
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
			 (int)ident, &ipv6_hdr(skb)->daddr, dif);
#endif
	}

	read_lock_bh(&ping_table.lock);

	ping_portaddr_for_each_entry(sk, hnode, hslot) {
		isk = inet_sk(sk);

		pr_debug("iterate\n");
		if (isk->inet_num != ident)
			continue;

		if (skb->protocol == htons(ETH_P_IP) &&
		    sk->sk_family == AF_INET) {
			pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
				 (int) isk->inet_num, &isk->inet_rcv_saddr,
				 sk->sk_bound_dev_if);

			if (isk->inet_rcv_saddr &&
			    isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
				continue;
#if IS_ENABLED(CONFIG_IPV6)
		} else if (skb->protocol == htons(ETH_P_IPV6) &&
			   sk->sk_family == AF_INET6) {

			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
				 (int) isk->inet_num,
				 &sk->sk_v6_rcv_saddr,
				 sk->sk_bound_dev_if);

			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
			    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
					     &ipv6_hdr(skb)->daddr))
				continue;
#endif
		} else {
			continue;
		}

		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
			continue;

		sock_hold(sk);
		goto exit;
	}

	sk = NULL;
exit:
	read_unlock_bh(&ping_table.lock);

	return sk;
}


Contributors
PersonTokensPropCommitsCommitProp
Lorenzo Colitti18551.68%116.67%


Vasiliy Kulikov16044.69%116.67%


Eric Dumazet92.51%350.00%


Jane Zhou41.12%116.67%


Total358100.00%6100.00%






static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
					  kgid_t *high)
{
	kgid_t *data = net->ipv4.ping_group_range.range;
	unsigned int seq;

	do {
		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);

		*low = data[0];
		*high = data[1];
	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
}



Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov6880.00%120.00%


Eric W. Biedermann1112.94%240.00%


Américo Wang55.88%120.00%


Eric Dumazet11.18%120.00%


Total85100.00%5100.00%






int ping_init_sock(struct sock *sk)
{
	struct net *net = sock_net(sk);
	kgid_t group = current_egid();
	struct group_info *group_info;
	int i;
	kgid_t low, high;
	int ret = 0;

	if (sk->sk_family == AF_INET6)
		sk->sk_ipv6only = 1;

	inet_get_ping_group_range_net(net, &low, &high);
	if (gid_lte(low, group) && gid_lte(group, high))
		return 0;

	group_info = get_current_groups();
	for (i = 0; i < group_info->ngroups; i++) {
		kgid_t gid = group_info->gid[i];

		if (gid_lte(low, gid) && gid_lte(gid, high))
			goto out_release_group;
	}

	ret = -EACCES;

out_release_group:
	put_group_info(group_info);
	return ret;
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov7246.75%116.67%


Eric W. Biedermann4126.62%233.33%


Wang, Xiaoming2516.23%116.67%


Lorenzo Colitti149.09%116.67%


Alexey Dobriyan21.30%116.67%


Total154100.00%6100.00%




EXPORT_SYMBOL_GPL(ping_init_sock);




void ping_close(struct sock *sk, long timeout)
{
	pr_debug("ping_close(sk=%p,sk->num=%u)\n",
		 inet_sk(sk), inet_sk(sk)->inet_num);
	pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter);

	sk_common_release(sk);
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov46100.00%1100.00%


Total46100.00%1100.00%




EXPORT_SYMBOL_GPL(ping_close);

/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */



static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
				struct sockaddr *uaddr, int addr_len) {
	struct net *net = sock_net(sk);
	if (sk->sk_family == AF_INET) {
		struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
		int chk_addr_ret;

		if (addr_len < sizeof(*addr))
			return -EINVAL;

		if (addr->sin_family != AF_INET &&
		    !(addr->sin_family == AF_UNSPEC &&
		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
			return -EAFNOSUPPORT;

		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));

		chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);

		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
			chk_addr_ret = RTN_LOCAL;

		if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 &&
		    isk->freebind == 0 && isk->transparent == 0 &&
		     chk_addr_ret != RTN_LOCAL) ||
		    chk_addr_ret == RTN_MULTICAST ||
		    chk_addr_ret == RTN_BROADCAST)
			return -EADDRNOTAVAIL;

#if IS_ENABLED(CONFIG_IPV6)
	} else if (sk->sk_family == AF_INET6) {
		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
		int addr_type, scoped, has_addr;
		struct net_device *dev = NULL;

		if (addr_len < sizeof(*addr))
			return -EINVAL;

		if (addr->sin6_family != AF_INET6)
			return -EAFNOSUPPORT;

		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));

		addr_type = ipv6_addr_type(&addr->sin6_addr);
		scoped = __ipv6_addr_needs_scope_id(addr_type);
		if ((addr_type != IPV6_ADDR_ANY &&
		     !(addr_type & IPV6_ADDR_UNICAST)) ||
		    (scoped && !addr->sin6_scope_id))
			return -EINVAL;

		rcu_read_lock();
		if (addr->sin6_scope_id) {
			dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
			if (!dev) {
				rcu_read_unlock();
				return -ENODEV;
			}
		}
		has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
						    scoped);
		rcu_read_unlock();

		if (!(net->ipv6.sysctl.ip_nonlocal_bind ||
		      isk->freebind || isk->transparent || has_addr ||
		      addr_type == IPV6_ADDR_ANY))
			return -EADDRNOTAVAIL;

		if (scoped)
			sk->sk_bound_dev_if = addr->sin6_scope_id;
#endif
	} else {
		return -EAFNOSUPPORT;
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Lorenzo Colitti36983.48%228.57%


Vasiliy Kulikov4911.09%114.29%


Hannes Frederic Sowa112.49%114.29%


Tom Herbert81.81%114.29%


Vincent Bernat40.90%114.29%


Fengguang Wu10.23%114.29%


Total442100.00%7100.00%






static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
{
	if (saddr->sa_family == AF_INET) {
		struct inet_sock *isk = inet_sk(sk);
		struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
		isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
#if IS_ENABLED(CONFIG_IPV6)
	} else if (saddr->sa_family == AF_INET6) {
		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
		struct ipv6_pinfo *np = inet6_sk(sk);
		sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
#endif
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Lorenzo Colitti11297.39%133.33%


Eric Dumazet21.74%133.33%


Fengguang Wu10.87%133.33%


Total115100.00%3100.00%






static void ping_clear_saddr(struct sock *sk, int dif)
{
	sk->sk_bound_dev_if = dif;
	if (sk->sk_family == AF_INET) {
		struct inet_sock *isk = inet_sk(sk);
		isk->inet_rcv_saddr = isk->inet_saddr = 0;
#if IS_ENABLED(CONFIG_IPV6)
	} else if (sk->sk_family == AF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);
		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
		memset(&np->saddr, 0, sizeof(np->saddr));
#endif
	}
}

Contributors
PersonTokensPropCommitsCommitProp
Lorenzo Colitti10895.58%133.33%


Eric Dumazet43.54%133.33%


Fengguang Wu10.88%133.33%


Total113100.00%3100.00%



/*
 * We need our own bind because there are no privileged id's == local ports.
 * Moreover, we don't allow binding to multi- and broadcast addresses.
 */




int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *isk = inet_sk(sk);
	unsigned short snum;
	int err;
	int dif = sk->sk_bound_dev_if;

	err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
	if (err)
		return err;

	lock_sock(sk);

	err = -EINVAL;
	if (isk->inet_num != 0)
		goto out;

	err = -EADDRINUSE;
	ping_set_saddr(sk, uaddr);
	snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
	if (ping_get_port(sk, snum) != 0) {
		ping_clear_saddr(sk, dif);
		goto out;
	}

	pr_debug("after bind(): num = %hu, dif = %d\n",
		 isk->inet_num,
		 sk->sk_bound_dev_if);

	err = 0;
	if (sk->sk_family == AF_INET && isk->inet_rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr))
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
#endif

	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	isk->inet_sport = htons(isk->inet_num);
	isk->inet_daddr = 0;
	isk->inet_dport = 0;

#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
#endif

	sk_dst_reset(sk);
out:
	release_sock(sk);
	pr_debug("ping_v4_bind -> %d\n", err);
	return err;
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov14751.04%116.67%


Lorenzo Colitti11941.32%116.67%


Eric Dumazet217.29%350.00%


Gao Feng10.35%116.67%


Total288100.00%6100.00%




EXPORT_SYMBOL_GPL(ping_bind);

/*
 * Is this a supported type of ICMP message?
 */




static inline int ping_supported(int family, int type, int code)
{
	return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
	       (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
}


Contributors
PersonTokensPropCommitsCommitProp
Lorenzo Colitti2351.11%150.00%


Vasiliy Kulikov2248.89%150.00%


Total45100.00%2100.00%



/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.
 */




void ping_err(struct sk_buff *skb, int offset, u32 info)
{
	int family;
	struct icmphdr *icmph;
	struct inet_sock *inet_sock;
	int type;
	int code;
	struct net *net = dev_net(skb->dev);
	struct sock *sk;
	int harderr;
	int err;

	if (skb->protocol == htons(ETH_P_IP)) {
		family = AF_INET;
		type = icmp_hdr(skb)->type;
		code = icmp_hdr(skb)->code;
		icmph = (struct icmphdr *)(skb->data + offset);
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		family = AF_INET6;
		type = icmp6_hdr(skb)->icmp6_type;
		code = icmp6_hdr(skb)->icmp6_code;
		icmph = (struct icmphdr *) (skb->data + offset);
	} else {
		BUG();
	}

	/* We assume the packet has already been checked by icmp_unreach */

	if (!ping_supported(family, icmph->type, icmph->code))
		return;

	pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
		 skb->protocol, type, code, ntohs(icmph->un.echo.id),
		 ntohs(icmph->un.echo.sequence));

	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
	if (!sk) {
		pr_debug("no socket, dropping\n");
		return;	/* No socket for error */
	}
	pr_debug("err on socket %p\n", sk);

	err = 0;
	harderr = 0;
	inet_sock = inet_sk(sk);

	if (skb->protocol == htons(ETH_P_IP)) {
		switch (type) {
		default:
		case ICMP_TIME_EXCEEDED:
			err = EHOSTUNREACH;
			break;
		case ICMP_SOURCE_QUENCH:
			/* This is not a real error but ping wants to see it.
                         * Report it with some fake errno.
                         */
			err = EREMOTEIO;
			break;
		case ICMP_PARAMETERPROB:
			err = EPROTO;
			harderr = 1;
			break;
		case ICMP_DEST_UNREACH:
			if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
				ipv4_sk_update_pmtu(skb, sk, info);
				if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
					err = EMSGSIZE;
					harderr = 1;
					break;
				}
				goto out;
			}
			err = EHOSTUNREACH;
			if (code <= NR_ICMP_UNREACH) {
				harderr = icmp_err_convert[code].fatal;
				err = icmp_err_convert[code].errno;
			}
			break;
		case ICMP_REDIRECT:
			/* See ICMP_SOURCE_QUENCH */
			ipv4_sk_redirect(skb, sk);
			err = EREMOTEIO;
			break;
		}
#if IS_ENABLED(CONFIG_IPV6)
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
#endif
	}

	/*
         *      RFC1122: OK.  Passes ICMP errors back to application, as per
         *      4.1.3.3.
         */
	if ((family == AF_INET && !inet_sock->recverr) ||
	    (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
			goto out;
	} else {
		if (family == AF_INET) {
			ip_icmp_error(sk, skb, err, 0 /* no remote port */,
				      info, (u8 *)icmph);
#if IS_ENABLED(CONFIG_IPV6)
		} else if (family == AF_INET6) {
			pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
						   info, (u8 *)icmph);
#endif
		}
	}
	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

Contributors
PersonTokensPropCommitsCommitProp
Vasiliy Kulikov32255.33%120.00%


Lorenzo Colitti24341.75%120.00%


David S. Miller162.75%240.00%


Ian Morris10.17%120.00%


Total582100.00%5100.00%




EXPORT_SYMBOL_GPL(ping_err);

/*
 *      Copy and checksum an ICMP Echo packet from user space into a buffer
 *      starting from the payload.
 */




int ping_getfrag(void *from, char *to,
		 int offset, int fraglen, int odd, struct sk_buff *skb)
{
	struct pingfakehdr *pfh = (struct pingfakehdr *)from;

	if (offset == 0) {
		fraglen -= sizeof(struct icmphdr);
		if (fraglen < 0)
			BUG();
		if (!csum_and_copy_from_iter_full(to + sizeof(struct icmphdr),
			    fraglen, &pfh->wcheck,
			    &pfh->msg->msg_iter))
			return -EFAULT;
	} else if (offset < sizeof(struct icmphdr)) {