1 files changed, 96 insertions, 145 deletions

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 3183413ebc6c..006c1f0ed8b4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -85,22 +85,21 @@ struct raw_frag_vec {
 	int hlen;
 };
 
-struct raw_hashinfo raw_v4_hashinfo = {
-	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
-};
+struct raw_hashinfo raw_v4_hashinfo;
 EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
 
 int raw_hash_sk(struct sock *sk)
 {
 	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
-	struct hlist_head *head;
+	struct hlist_nulls_head *hlist;
 
-	head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];
+	hlist = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];
 
-	write_lock_bh(&h->lock);
-	sk_add_node(sk, head);
+	spin_lock(&h->lock);
+	__sk_nulls_add_node_rcu(sk, hlist);
+	sock_set_flag(sk, SOCK_RCU_FREE);
+	spin_unlock(&h->lock);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-	write_unlock_bh(&h->lock);
 
 	return 0;
 }
@@ -110,31 +109,26 @@ void raw_unhash_sk(struct sock *sk)
 {
 	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
 
-	write_lock_bh(&h->lock);
-	if (sk_del_node_init(sk))
+	spin_lock(&h->lock);
+	if (__sk_nulls_del_node_init_rcu(sk))
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-	write_unlock_bh(&h->lock);
+	spin_unlock(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_unhash_sk);
 
-struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
-			     unsigned short num, __be32 raddr, __be32 laddr,
-			     int dif, int sdif)
+bool raw_v4_match(struct net *net, struct sock *sk, unsigned short num,
+		  __be32 raddr, __be32 laddr, int dif, int sdif)
 {
-	sk_for_each_from(sk) {
-		struct inet_sock *inet = inet_sk(sk);
-
-		if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
-		    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
-		    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
-		    raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
-			goto found; /* gotcha */
-	}
-	sk = NULL;
-found:
-	return sk;
+	struct inet_sock *inet = inet_sk(sk);
+
+	if (net_eq(sock_net(sk), net) && inet->inet_num == num	&&
+	    !(inet->inet_daddr && inet->inet_daddr != raddr) 	&&
+	    !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
+	    raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
+		return true;
+	return false;
 }
-EXPORT_SYMBOL_GPL(__raw_v4_lookup);
+EXPORT_SYMBOL_GPL(raw_v4_match);
 
 /*
  *	0 - deliver
@@ -168,23 +162,20 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
  */
 static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 {
+	struct net *net = dev_net(skb->dev);
+	struct hlist_nulls_head *hlist;
+	struct hlist_nulls_node *hnode;
 	int sdif = inet_sdif(skb);
 	int dif = inet_iif(skb);
-	struct sock *sk;
-	struct hlist_head *head;
 	int delivered = 0;
-	struct net *net;
-
-	read_lock(&raw_v4_hashinfo.lock);
-	head = &raw_v4_hashinfo.ht[hash];
-	if (hlist_empty(head))
-		goto out;
-
-	net = dev_net(skb->dev);
-	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
-			     iph->saddr, iph->daddr, dif, sdif);
+	struct sock *sk;
 
-	while (sk) {
+	hlist = &raw_v4_hashinfo.ht[hash];
+	rcu_read_lock();
+	sk_nulls_for_each(sk, hnode, hlist) {
+		if (!raw_v4_match(net, sk, iph->protocol,
+				  iph->saddr, iph->daddr, dif, sdif))
+			continue;
 		delivered = 1;
 		if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
 		    ip_mc_sf_allow(sk, iph->daddr, iph->saddr,
@@ -195,31 +186,16 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 			if (clone)
 				raw_rcv(sk, clone);
 		}
-		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
-				     iph->saddr, iph->daddr,
-				     dif, sdif);
 	}
-out:
-	read_unlock(&raw_v4_hashinfo.lock);
+	rcu_read_unlock();
 	return delivered;
 }
 
 int raw_local_deliver(struct sk_buff *skb, int protocol)
 {
-	int hash;
-	struct sock *raw_sk;
-
-	hash = protocol & (RAW_HTABLE_SIZE - 1);
-	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
-
-	/* If there maybe a raw socket we must check - if not we
-	 * don't care less
-	 */
-	if (raw_sk && !raw_v4_input(skb, ip_hdr(skb), hash))
-		raw_sk = NULL;
-
-	return raw_sk != NULL;
+	int hash = protocol & (RAW_HTABLE_SIZE - 1);
 
+	return raw_v4_input(skb, ip_hdr(skb), hash);
 }
 
 static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
@@ -260,11 +236,12 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 		err = EHOSTUNREACH;
 		if (code > NR_ICMP_UNREACH)
 			break;
-		err = icmp_err_convert[code].errno;
-		harderr = icmp_err_convert[code].fatal;
 		if (code == ICMP_FRAG_NEEDED) {
 			harderr = inet->pmtudisc != IP_PMTUDISC_DONT;
 			err = EMSGSIZE;
+		} else {
+			err = icmp_err_convert[code].errno;
+			harderr = icmp_err_convert[code].fatal;
 		}
 	}
 
@@ -279,37 +256,33 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 
 	if (inet->recverr || harderr) {
 		sk->sk_err = err;
-		sk->sk_error_report(sk);
+		sk_error_report(sk);
 	}
 }
 
 void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 {
-	int hash;
-	struct sock *raw_sk;
+	struct net *net = dev_net(skb->dev);
+	struct hlist_nulls_head *hlist;
+	struct hlist_nulls_node *hnode;
+	int dif = skb->dev->ifindex;
+	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
-	struct net *net;
+	struct sock *sk;
+	int hash;
 
 	hash = protocol & (RAW_HTABLE_SIZE - 1);
+	hlist = &raw_v4_hashinfo.ht[hash];
 
-	read_lock(&raw_v4_hashinfo.lock);
-	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
-	if (raw_sk) {
-		int dif = skb->dev->ifindex;
-		int sdif = inet_sdif(skb);
-
+	rcu_read_lock();
+	sk_nulls_for_each(sk, hnode, hlist) {
 		iph = (const struct iphdr *)skb->data;
-		net = dev_net(skb->dev);
-
-		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
-						iph->daddr, iph->saddr,
-						dif, sdif)) != NULL) {
-			raw_err(raw_sk, skb, info);
-			raw_sk = sk_next(raw_sk);
-			iph = (const struct iphdr *)skb->data;
-		}
+		if (!raw_v4_match(net, sk, iph->protocol,
+				  iph->daddr, iph->saddr, dif, sdif))
+			continue;
+		raw_err(sk, skb, info);
 	}
-	read_unlock(&raw_v4_hashinfo.lock);
+	rcu_read_unlock();
 }
 
 static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
@@ -478,7 +451,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
 			skb->csum = csum_block_add(
 				skb->csum,
 				csum_partial_copy_nocheck(rfv->hdr.c + offset,
-							  to, copy, 0),
+							  to, copy),
 				odd);
 
 		odd = 0;
@@ -610,7 +583,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	} else if (!ipc.oif) {
 		ipc.oif = inet->uc_index;
 	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
-		/* oif is set, packet is to local broadcast and
+		/* oif is set, packet is to local broadcast
 		 * and uc_index is set. oif is most likely set
 		 * by sk_bound_dev_if. If uc_index != oif check if the
 		 * oif is an L3 master and uc_index is an L3 slave.
@@ -639,7 +612,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			goto done;
 	}
 
-	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
@@ -716,30 +689,34 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+	struct net *net = sock_net(sk);
 	u32 tb_id = RT_TABLE_LOCAL;
 	int ret = -EINVAL;
 	int chk_addr_ret;
 
+	lock_sock(sk);
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
 		goto out;
 
 	if (sk->sk_bound_dev_if)
-		tb_id = l3mdev_fib_table_by_index(sock_net(sk),
-						 sk->sk_bound_dev_if) ? : tb_id;
+		tb_id = l3mdev_fib_table_by_index(net,
+						  sk->sk_bound_dev_if) ? : tb_id;
 
-	chk_addr_ret = inet_addr_type_table(sock_net(sk), addr->sin_addr.s_addr,
-					    tb_id);
+	chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
 
 	ret = -EADDRNOTAVAIL;
-	if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
-	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
+	if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr,
+					 chk_addr_ret))
 		goto out;
+
 	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 */
 	sk_dst_reset(sk);
 	ret = 0;
-out:	return ret;
+out:
+	release_sock(sk);
+	return ret;
 }
 
 /*
@@ -748,7 +725,7 @@ out:	return ret;
  */
 
 static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
-		       int noblock, int flags, int *addr_len)
+		       int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	size_t copied = 0;
@@ -764,7 +741,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
@@ -778,7 +755,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (err)
 		goto done;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_recv_cmsgs(msg, sk, skb);
 
 	/* Copy the address. */
 	if (sin) {
@@ -809,11 +786,11 @@ static int raw_sk_init(struct sock *sk)
 	return 0;
 }
 
-static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
+static int raw_seticmpfilter(struct sock *sk, sockptr_t optval, int optlen)
 {
 	if (optlen > sizeof(struct icmp_filter))
 		optlen = sizeof(struct icmp_filter);
-	if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
+	if (copy_from_sockptr(&raw_sk(sk)->filter, optval, optlen))
 		return -EFAULT;
 	return 0;
 }
@@ -838,7 +815,7 @@ out:	return ret;
 }
 
 static int do_raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			     sockptr_t optval, unsigned int optlen)
 {
 	if (optname == ICMP_FILTER) {
 		if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
@@ -850,23 +827,13 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname,
 }
 
 static int raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
+			  sockptr_t optval, unsigned int optlen)
 {
 	if (level != SOL_RAW)
 		return ip_setsockopt(sk, level, optname, optval, optlen);
 	return do_raw_setsockopt(sk, level, optname, optval, optlen);
 }
 
-#ifdef CONFIG_COMPAT
-static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, unsigned int optlen)
-{
-	if (level != SOL_RAW)
-		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
-	return do_raw_setsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
 static int do_raw_getsockopt(struct sock *sk, int level, int optname,
 			  char __user *optval, int __user *optlen)
 {
@@ -887,16 +854,6 @@ static int raw_getsockopt(struct sock *sk, int level, int optname,
 	return do_raw_getsockopt(sk, level, optname, optval, optlen);
 }
 
-#ifdef CONFIG_COMPAT
-static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, int __user *optlen)
-{
-	if (level != SOL_RAW)
-		return compat_ip_getsockopt(sk, level, optname, optval, optlen);
-	return do_raw_getsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
 static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -948,7 +905,7 @@ int raw_abort(struct sock *sk, int err)
 	lock_sock(sk);
 
 	sk->sk_err = err;
-	sk->sk_error_report(sk);
+	sk_error_report(sk);
 	__udp_disconnect(sk, 0);
 
 	release_sock(sk);
@@ -980,52 +937,47 @@ struct proto raw_prot = {
 	.usersize	   = sizeof_field(struct raw_sock, filter),
 	.h.raw_hash	   = &raw_v4_hashinfo,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_raw_setsockopt,
-	.compat_getsockopt = compat_raw_getsockopt,
 	.compat_ioctl	   = compat_raw_ioctl,
 #endif
 	.diag_destroy	   = raw_abort,
 };
 
 #ifdef CONFIG_PROC_FS
-static struct sock *raw_get_first(struct seq_file *seq)
+static struct sock *raw_get_first(struct seq_file *seq, int bucket)
 {
-	struct sock *sk;
-	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
+	struct raw_hashinfo *h = pde_data(file_inode(seq->file));
 	struct raw_iter_state *state = raw_seq_private(seq);
+	struct hlist_nulls_head *hlist;
+	struct hlist_nulls_node *hnode;
+	struct sock *sk;
 
-	for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
+	for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE;
 			++state->bucket) {
-		sk_for_each(sk, &h->ht[state->bucket])
+		hlist = &h->ht[state->bucket];
+		sk_nulls_for_each(sk, hnode, hlist) {
 			if (sock_net(sk) == seq_file_net(seq))
-				goto found;
+				return sk;
+		}
 	}
-	sk = NULL;
-found:
-	return sk;
+	return NULL;
 }
 
 static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
 {
-	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
 	struct raw_iter_state *state = raw_seq_private(seq);
 
 	do {
-		sk = sk_next(sk);
-try_again:
-		;
+		sk = sk_nulls_next(sk);
 	} while (sk && sock_net(sk) != seq_file_net(seq));
 
-	if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
-		sk = sk_head(&h->ht[state->bucket]);
-		goto try_again;
-	}
+	if (!sk)
+		return raw_get_first(seq, state->bucket + 1);
 	return sk;
 }
 
 static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
 {
-	struct sock *sk = raw_get_first(seq);
+	struct sock *sk = raw_get_first(seq, 0);
 
 	if (sk)
 		while (pos && (sk = raw_get_next(seq, sk)) != NULL)
@@ -1034,10 +986,9 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 void *raw_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU)
 {
-	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
-
-	read_lock(&h->lock);
+	rcu_read_lock();
 	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
 EXPORT_SYMBOL_GPL(raw_seq_start);
@@ -1047,7 +998,7 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct sock *sk;
 
 	if (v == SEQ_START_TOKEN)
-		sk = raw_get_first(seq);
+		sk = raw_get_first(seq, 0);
 	else
 		sk = raw_get_next(seq, v);
 	++*pos;
@@ -1056,10 +1007,9 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 EXPORT_SYMBOL_GPL(raw_seq_next);
 
 void raw_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
 {
-	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
-
-	read_unlock(&h->lock);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(raw_seq_stop);
 
@@ -1121,6 +1071,7 @@ static __net_initdata struct pernet_operations raw_net_ops = {
 
 int __init raw_proc_init(void)
 {
+
 	return register_pernet_subsys(&raw_net_ops);
 }