1 files changed, 79 insertions, 109 deletions

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 409ec2a1f95b..ad56588107cc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -49,21 +49,14 @@
 #include <net/transp_v6.h>
 #endif
 
-#define ping_portaddr_for_each_entry(__sk, node, list) \
-	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
-#define ping_portaddr_for_each_entry_rcu(__sk, node, list) \
-	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
-
 struct ping_table {
-	struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
+	struct hlist_head	hash[PING_HTABLE_SIZE];
 	spinlock_t		lock;
 };
 
 static struct ping_table ping_table;
 struct pingv6_ops pingv6_ops;
-EXPORT_SYMBOL_GPL(pingv6_ops);
-
-static u16 ping_port_rover;
+EXPORT_IPV6_MOD_GPL(pingv6_ops);
 
 static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
 {
@@ -72,33 +65,33 @@ static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
 	pr_debug("hash(%u) = %u\n", num, res);
 	return res;
 }
-EXPORT_SYMBOL_GPL(ping_hash);
 
-static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
-					     struct net *net, unsigned int num)
+static inline struct hlist_head *ping_hashslot(struct ping_table *table,
+					       struct net *net, unsigned int num)
 {
 	return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
 }
 
 int ping_get_port(struct sock *sk, unsigned short ident)
 {
-	struct hlist_nulls_node *node;
-	struct hlist_nulls_head *hlist;
+	struct net *net = sock_net(sk);
 	struct inet_sock *isk, *isk2;
+	struct hlist_head *hlist;
 	struct sock *sk2 = NULL;
 
 	isk = inet_sk(sk);
 	spin_lock(&ping_table.lock);
 	if (ident == 0) {
+		u16 result = net->ipv4.ping_port_rover + 1;
 		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) {
+				continue; /* avoid zero */
+			hlist = ping_hashslot(&ping_table, net, result);
+			sk_for_each(sk2, hlist) {
+				if (!net_eq(sock_net(sk2), net))
+					continue;
 				isk2 = inet_sk(sk2);
 
 				if (isk2->inet_num == result)
@@ -106,7 +99,7 @@ int ping_get_port(struct sock *sk, unsigned short ident)
 			}
 
 			/* found */
-			ping_port_rover = ident = result;
+			net->ipv4.ping_port_rover = ident = result;
 			break;
 next_port:
 			;
@@ -114,8 +107,10 @@ 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) {
+		hlist = ping_hashslot(&ping_table, net, ident);
+		sk_for_each(sk2, hlist) {
+			if (!net_eq(sock_net(sk2), net))
+				continue;
 			isk2 = inet_sk(sk2);
 
 			/* BUG? Why is this reuse and not reuseaddr? ping.c
@@ -133,10 +128,9 @@ next_port:
 	isk->inet_num = ident;
 	if (sk_unhashed(sk)) {
 		pr_debug("was not hashed\n");
-		sock_hold(sk);
+		sk_add_node_rcu(sk, hlist);
 		sock_set_flag(sk, SOCK_RCU_FREE);
-		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, hlist);
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+		sock_prot_inuse_add(net, sk->sk_prot, 1);
 	}
 	spin_unlock(&ping_table.lock);
 	return 0;
@@ -145,15 +139,7 @@ fail:
 	spin_unlock(&ping_table.lock);
 	return -EADDRINUSE;
 }
-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;
-}
+EXPORT_IPV6_MOD_GPL(ping_get_port);
 
 void ping_unhash(struct sock *sk)
 {
@@ -161,24 +147,21 @@ void ping_unhash(struct sock *sk)
 
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
 	spin_lock(&ping_table.lock);
-	if (sk_hashed(sk)) {
-		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
-		sock_put(sk);
+	if (sk_del_node_init_rcu(sk)) {
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	}
 	spin_unlock(&ping_table.lock);
 }
-EXPORT_SYMBOL_GPL(ping_unhash);
+EXPORT_IPV6_MOD_GPL(ping_unhash);
 
 /* Called under rcu_read_lock() */
 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 hlist_head *hslot = ping_hashslot(&ping_table, net, ident);
 	struct sock *sk = NULL;
 	struct inet_sock *isk;
-	struct hlist_nulls_node *hnode;
 	int dif, sdif;
 
 	if (skb->protocol == htons(ETH_P_IP)) {
@@ -197,7 +180,9 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 		return NULL;
 	}
 
-	ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) {
+	sk_for_each_rcu(sk, hslot) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
 		isk = inet_sk(sk);
 
 		pr_debug("iterate\n");
@@ -289,7 +274,7 @@ out_release_group:
 	put_group_info(group_info);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(ping_init_sock);
+EXPORT_IPV6_MOD_GPL(ping_init_sock);
 
 void ping_close(struct sock *sk, long timeout)
 {
@@ -299,9 +284,9 @@ void ping_close(struct sock *sk, long timeout)
 
 	sk_common_release(sk);
 }
-EXPORT_SYMBOL_GPL(ping_close);
+EXPORT_IPV6_MOD_GPL(ping_close);
 
-static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+static int ping_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
 			    int addr_len)
 {
 	/* This check is replicated from __ip4_datagram_connect() and
@@ -311,12 +296,12 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (addr_len < sizeof(struct sockaddr_in))
 		return -EINVAL;
 
-	return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
+	return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len);
 }
 
 /* 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 sockaddr_unsized *uaddr, int addr_len)
 {
 	struct net *net = sock_net(sk);
 	if (sk->sk_family == AF_INET) {
@@ -402,7 +387,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 	return 0;
 }
 
-static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
+static void ping_set_saddr(struct sock *sk, struct sockaddr_unsized *saddr)
 {
 	if (saddr->sa_family == AF_INET) {
 		struct inet_sock *isk = inet_sk(sk);
@@ -422,7 +407,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
  * Moreover, we don't allow binding to multi- and broadcast addresses.
  */
 
-int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len)
 {
 	struct inet_sock *isk = inet_sk(sk);
 	unsigned short snum;
@@ -477,7 +462,7 @@ out:
 	pr_debug("ping_v4_bind -> %d\n", err);
 	return err;
 }
-EXPORT_SYMBOL_GPL(ping_bind);
+EXPORT_IPV6_MOD_GPL(ping_bind);
 
 /*
  * Is this a supported type of ICMP message?
@@ -561,7 +546,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info)
 		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) {
+				if (READ_ONCE(inet_sock->pmtudisc) != IP_PMTUDISC_DONT) {
 					err = EMSGSIZE;
 					harderr = 1;
 					break;
@@ -590,8 +575,8 @@ void ping_err(struct sk_buff *skb, int offset, u32 info)
 	 *      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 ((family == AF_INET && !inet_test_bit(RECVERR, sk)) ||
+	    (family == AF_INET6 && !inet6_test_bit(RECVERR6, sk))) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
 	} else {
@@ -610,7 +595,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info)
 out:
 	return;
 }
-EXPORT_SYMBOL_GPL(ping_err);
+EXPORT_IPV6_MOD_GPL(ping_err);
 
 /*
  *	Copy and checksum an ICMP Echo packet from user space into a buffer
@@ -640,7 +625,7 @@ int ping_getfrag(void *from, char *to,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ping_getfrag);
+EXPORT_IPV6_MOD_GPL(ping_getfrag);
 
 static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 				       struct flowi4 *fl4)
@@ -701,7 +686,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ping_common_sendmsg);
+EXPORT_IPV6_MOD_GPL(ping_common_sendmsg);
 
 static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
@@ -715,7 +700,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ip_options_data opt_copy;
 	int free = 0;
 	__be32 saddr, daddr, faddr;
-	u8  tos;
+	u8 scope;
 	int err;
 
 	pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -778,25 +763,20 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 		faddr = ipc.opt->opt.faddr;
 	}
-	tos = get_rttos(&ipc, inet);
-	if (sock_flag(sk, SOCK_LOCALROUTE) ||
-	    (msg->msg_flags & MSG_DONTROUTE) ||
-	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
-		tos |= RTO_ONLINK;
-	}
+	scope = ip_sendmsg_scope(inet, &ipc, msg);
 
 	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
-			ipc.oif = inet->mc_index;
+			ipc.oif = READ_ONCE(inet->mc_index);
 		if (!saddr)
-			saddr = inet->mc_addr;
+			saddr = READ_ONCE(inet->mc_addr);
 	} else if (!ipc.oif)
-		ipc.oif = inet->uc_index;
+		ipc.oif = READ_ONCE(inet->uc_index);
 
-	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
-			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
-			   sk->sk_uid);
+	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
+			   ipc.tos & INET_DSCP_MASK, scope,
+			   sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
+			   saddr, 0, 0, sk_uid(sk));
 
 	fl4.fl4_icmp_type = user_icmph.type;
 	fl4.fl4_icmp_code = user_icmph.code;
@@ -909,12 +889,11 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 			*addr_len = sizeof(*sin);
 		}
 
-		if (isk->cmsg_flags)
+		if (inet_cmsg_flags(isk))
 			ip_cmsg_recv(msg, skb);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct ipv6hdr *ip6 = ipv6_hdr(skb);
 		DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 
@@ -923,7 +902,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 			sin6->sin6_port = 0;
 			sin6->sin6_addr = ip6->saddr;
 			sin6->sin6_flowinfo = 0;
-			if (np->sndflow)
+			if (inet6_test_bit(SNDFLOW, sk))
 				sin6->sin6_flowinfo = ip6_flowinfo(ip6);
 			sin6->sin6_scope_id =
 				ipv6_iface_scope_id(&sin6->sin6_addr,
@@ -936,7 +915,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 		if (skb->protocol == htons(ETH_P_IPV6) &&
 		    inet6_sk(sk)->rxopt.all)
 			pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb);
-		else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags)
+		else if (skb->protocol == htons(ETH_P_IP) &&
+			 inet_cmsg_flags(isk))
 			ip_cmsg_recv(msg, skb);
 #endif
 	} else {
@@ -951,7 +931,7 @@ out:
 	pr_debug("ping_recvmsg -> %d\n", err);
 	return err;
 }
-EXPORT_SYMBOL_GPL(ping_recvmsg);
+EXPORT_IPV6_MOD_GPL(ping_recvmsg);
 
 static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk,
 						 struct sk_buff *skb)
@@ -961,7 +941,7 @@ static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk,
 	pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
 		 inet_sk(sk), inet_sk(sk)->inet_num, skb);
 	if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
-		kfree_skb_reason(skb, reason);
+		sk_skb_reason_drop(sk, skb, reason);
 		pr_debug("ping_queue_rcv_skb -> failed\n");
 		return reason;
 	}
@@ -972,7 +952,7 @@ int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	return __ping_queue_rcv_skb(sk, skb) ? -1 : 0;
 }
-EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
+EXPORT_IPV6_MOD_GPL(ping_queue_rcv_skb);
 
 
 /*
@@ -981,10 +961,9 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
 
 enum skb_drop_reason ping_rcv(struct sk_buff *skb)
 {
-	enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET;
-	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
 	struct icmphdr *icmph = icmp_hdr(skb);
+	struct sock *sk;
 
 	/* We assume the packet has already been checked by icmp_rcv */
 
@@ -995,22 +974,13 @@ enum skb_drop_reason ping_rcv(struct sk_buff *skb)
 	skb_push(skb, skb->data - (u8 *)icmph);
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
-	if (sk) {
-		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
-
-		pr_debug("rcv on socket %p\n", sk);
-		if (skb2)
-			reason = __ping_queue_rcv_skb(sk, skb2);
-		else
-			reason = SKB_DROP_REASON_NOMEM;
-	}
-
-	if (reason)
-		pr_debug("no socket, dropping\n");
+	if (sk)
+		return __ping_queue_rcv_skb(sk, skb);
 
-	return reason;
+	kfree_skb_reason(skb, SKB_DROP_REASON_NO_SOCKET);
+	return SKB_DROP_REASON_NO_SOCKET;
 }
-EXPORT_SYMBOL_GPL(ping_rcv);
+EXPORT_IPV6_MOD_GPL(ping_rcv);
 
 struct proto ping_prot = {
 	.name =		"PING",
@@ -1027,13 +997,12 @@ struct proto ping_prot = {
 	.bind =		ping_bind,
 	.backlog_rcv =	ping_queue_rcv_skb,
 	.release_cb =	ip4_datagram_release_cb,
-	.hash =		ping_hash,
 	.unhash =	ping_unhash,
 	.get_port =	ping_get_port,
 	.put_port =	ping_unhash,
 	.obj_size =	sizeof(struct inet_sock),
 };
-EXPORT_SYMBOL(ping_prot);
+EXPORT_IPV6_MOD(ping_prot);
 
 #ifdef CONFIG_PROC_FS
 
@@ -1045,15 +1014,14 @@ static struct sock *ping_get_first(struct seq_file *seq, int start)
 
 	for (state->bucket = start; state->bucket < PING_HTABLE_SIZE;
 	     ++state->bucket) {
-		struct hlist_nulls_node *node;
-		struct hlist_nulls_head *hslot;
+		struct hlist_head *hslot;
 
 		hslot = &ping_table.hash[state->bucket];
 
-		if (hlist_nulls_empty(hslot))
+		if (hlist_empty(hslot))
 			continue;
 
-		sk_nulls_for_each(sk, node, hslot) {
+		sk_for_each(sk, hslot) {
 			if (net_eq(sock_net(sk), net) &&
 			    sk->sk_family == state->family)
 				goto found;
@@ -1070,7 +1038,7 @@ static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk)
 	struct net *net = seq_file_net(seq);
 
 	do {
-		sk = sk_nulls_next(sk);
+		sk = sk_next(sk);
 	} while (sk && (!net_eq(sock_net(sk), net)));
 
 	if (!sk)
@@ -1089,17 +1057,17 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
-	__acquires(RCU)
+	__acquires(ping_table.lock)
 {
 	struct ping_iter_state *state = seq->private;
 	state->bucket = 0;
 	state->family = family;
 
-	rcu_read_lock();
+	spin_lock(&ping_table.lock);
 
 	return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
 }
-EXPORT_SYMBOL_GPL(ping_seq_start);
+EXPORT_IPV6_MOD_GPL(ping_seq_start);
 
 static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
 {
@@ -1118,14 +1086,14 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	return sk;
 }
-EXPORT_SYMBOL_GPL(ping_seq_next);
+EXPORT_IPV6_MOD_GPL(ping_seq_next);
 
 void ping_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU)
+	__releases(ping_table.lock)
 {
-	rcu_read_unlock();
+	spin_unlock(&ping_table.lock);
 }
-EXPORT_SYMBOL_GPL(ping_seq_stop);
+EXPORT_IPV6_MOD_GPL(ping_seq_stop);
 
 static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
 		int bucket)
@@ -1142,10 +1110,10 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
 		sk_wmem_alloc_get(sp),
 		sk_rmem_alloc_get(sp),
 		0, 0L, 0,
-		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
+		from_kuid_munged(seq_user_ns(f), sk_uid(sp)),
 		0, sock_i_ino(sp),
 		refcount_read(&sp->sk_refcnt), sp,
-		atomic_read(&sp->sk_drops));
+		sk_drops_read(sp));
 }
 
 static int ping_v4_seq_show(struct seq_file *seq, void *v)
@@ -1176,6 +1144,8 @@ static int __net_init ping_v4_proc_init_net(struct net *net)
 	if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops,
 			sizeof(struct ping_iter_state)))
 		return -ENOMEM;
+
+	net->ipv4.ping_port_rover = get_random_u16();
 	return 0;
 }
 
@@ -1206,6 +1176,6 @@ void __init ping_init(void)
 	int i;
 
 	for (i = 0; i < PING_HTABLE_SIZE; i++)
-		INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i);
+		INIT_HLIST_HEAD(&ping_table.hash[i]);
 	spin_lock_init(&ping_table.lock);
 }