Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller: "Highlights: 1) Support SPI based w5100 devices, from Akinobu Mita. 2) Partial Segmentation Offload, from Alexander Duyck. 3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE. 4) Allow cls_flower stats offload, from Amir Vadai. 5) Implement bpf blinding, from Daniel Borkmann. 6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is actually using FASYNC these atomics are superfluous. From Eric Dumazet. 7) Run TCP more preemptibly, also from Eric Dumazet. 8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e driver, from Gal Pressman. 9) Allow creating ppp devices via rtnetlink, from Guillaume Nault. 10) Improve BPF usage documentation, from Jesper Dangaard Brouer. 11) Support tunneling offloads in qed, from Manish Chopra. 12) aRFS offloading in mlx5e, from Maor Gottlieb. 13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo Leitner. 14) Add MSG_EOR support to TCP, this allows controlling packet coalescing on application record boundaries for more accurate socket timestamp sampling. From Martin KaFai Lau. 15) Fix alignment of 64-bit netlink attributes across the board, from Nicolas Dichtel. 16) Per-vlan stats in bridging, from Nikolay Aleksandrov. 17) Several conversions of drivers to ethtool ksettings, from Philippe Reynes. 18) Checksum neutral ILA in ipv6, from Tom Herbert. 19) Factorize all of the various marvell dsa drivers into one, from Vivien Didelot 20) Add VF support to qed driver, from Yuval Mintz" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits) Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m" Revert "phy dp83867: Make rgmii parameters optional" r8169: default to 64-bit DMA on recent PCIe chips phy dp83867: Make rgmii parameters optional phy dp83867: Fix compilation with CONFIG_OF_MDIO=m bpf: arm64: remove callee-save registers use for tmp registers asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions switchdev: pass pointer to fib_info instead of copy net_sched: close another race condition in tcf_mirred_release() tipc: fix nametable publication field in nl compat drivers: net: Don't print unpopulated net_device name qed: add support for dcbx. ravb: Add missing free_irq() calls to ravb_close() qed: Remove a stray tab net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings net: ethernet: fec-mpc52xx: use phydev from struct net_device bpf, doc: fix typo on bpf_asm descriptions stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings net: ethernet: fs-enet: use phydev from struct net_device ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2016-05-18 02:26:30 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2016-05-18 02:26:30 +0300
commit: a7fd20d1c476af4563e66865213474a2f9f473a4 (patch)
tree: fb1399e2f82842450245fb058a8fb23c52865f43 /net/ipv4/udp.c
parent: b80fed9595513384424cd141923c9161c4b5021b (diff)
parent: 917fa5353da05e8a0045b8acacba8d50400d5b12 (diff)
download: linux-a7fd20d1c476af4563e66865213474a2f9f473a4.tar.xz
1 files changed, 155 insertions, 273 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a2e7f55a1f61..2e3ebfe5549e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -143,10 +143,9 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 			       unsigned int log)
 {
 	struct sock *sk2;
-	struct hlist_nulls_node *node;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_nulls_for_each(sk2, node, &hslot->head) {
+	sk_for_each(sk2, &hslot->head) {
 		if (net_eq(sock_net(sk2), net) &&
 		    sk2 != sk &&
 		    (bitmap || udp_sk(sk2)->udp_port_hash == num) &&
@@ -177,12 +176,11 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 						  bool match_wildcard))
 {
 	struct sock *sk2;
-	struct hlist_nulls_node *node;
 	kuid_t uid = sock_i_uid(sk);
 	int res = 0;
 
 	spin_lock(&hslot2->lock);
-	udp_portaddr_for_each_entry(sk2, node, &hslot2->head) {
+	udp_portaddr_for_each_entry(sk2, &hslot2->head) {
 		if (net_eq(sock_net(sk2), net) &&
 		    sk2 != sk &&
 		    (udp_sk(sk2)->udp_port_hash == num) &&
@@ -207,11 +205,10 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot,
 						    bool match_wildcard))
 {
 	struct net *net = sock_net(sk);
-	struct hlist_nulls_node *node;
 	kuid_t uid = sock_i_uid(sk);
 	struct sock *sk2;
 
-	sk_nulls_for_each(sk2, node, &hslot->head) {
+	sk_for_each(sk2, &hslot->head) {
 		if (net_eq(sock_net(sk2), net) &&
 		    sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
@@ -333,22 +330,23 @@ found:
 			goto fail_unlock;
 		}
 
-		sk_nulls_add_node_rcu(sk, &hslot->head);
+		sk_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);
 		if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
-			sk->sk_family == AF_INET6)
-			hlist_nulls_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
-						 &hslot2->head);
+		    sk->sk_family == AF_INET6)
+			hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
+					   &hslot2->head);
 		else
-			hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
-						 &hslot2->head);
+			hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+					   &hslot2->head);
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	error = 0;
 fail_unlock:
 	spin_unlock_bh(&hslot->lock);
@@ -502,37 +500,27 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		struct sk_buff *skb)
 {
 	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	int score, badness, matches = 0, reuseport = 0;
-	bool select_ok = true;
 	u32 hash = 0;
 
-begin:
 	result = NULL;
 	badness = 0;
-	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score2(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
-			result = sk;
-			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
-
-					sk2 = reuseport_select_sock(sk, hash, skb,
+				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-					if (sk2) {
-						result = sk2;
-						select_ok = false;
-						goto found;
-					}
-				}
+				if (result)
+					return result;
 				matches = 1;
 			}
+			badness = score;
+			result = sk;
 		} else if (score == badness && reuseport) {
 			matches++;
 			if (reciprocal_scale(hash, matches) == 0)
@@ -540,23 +528,6 @@ begin:
 			hash = next_pseudo_random32(hash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot2)
-		goto begin;
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(compute_score2(result, net, saddr, sport,
-				  daddr, hnum, dif) < badness)) {
-			sock_put(result);
-			goto begin;
-		}
-	}
 	return result;
 }
 
@@ -568,15 +539,12 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		int dif, struct udp_table *udptable, struct sk_buff *skb)
 {
 	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
 	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
 	int score, badness, matches = 0, reuseport = 0;
-	bool select_ok = true;
 	u32 hash = 0;
 
-	rcu_read_lock();
 	if (hslot->count > 10) {
 		hash2 = udp4_portaddr_hash(net, daddr, hnum);
 		slot2 = hash2 & udptable->mask;
@@ -598,35 +566,27 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 						  htonl(INADDR_ANY), hnum, dif,
 						  hslot2, slot2, skb);
 		}
-		rcu_read_unlock();
 		return result;
 	}
 begin:
 	result = NULL;
 	badness = 0;
-	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, saddr, hnum, sport,
 				      daddr, dport, dif);
 		if (score > badness) {
-			result = sk;
-			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
-
-					sk2 = reuseport_select_sock(sk, hash, skb,
+				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-					if (sk2) {
-						result = sk2;
-						select_ok = false;
-						goto found;
-					}
-				}
+				if (result)
+					return result;
 				matches = 1;
 			}
+			result = sk;
+			badness = score;
 		} else if (score == badness && reuseport) {
 			matches++;
 			if (reciprocal_scale(hash, matches) == 0)
@@ -634,25 +594,6 @@ begin:
 			hash = next_pseudo_random32(hash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot)
-		goto begin;
-
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(compute_score(result, net, saddr, hnum, sport,
-				  daddr, dport, dif) < badness)) {
-			sock_put(result);
-			goto begin;
-		}
-	}
-	rcu_read_unlock();
 	return result;
 }
 EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
@@ -663,18 +604,36 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 {
 	const struct iphdr *iph = ip_hdr(skb);
 
-	return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
+	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
 				 iph->daddr, dport, inet_iif(skb),
 				 udptable, skb);
 }
 
+struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+				 __be16 sport, __be16 dport)
+{
+	return __udp4_lib_lookup_skb(skb, sport, dport, &udp_table);
+}
+EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
+
+/* Must be called under rcu_read_lock().
+ * Does increment socket refcount.
+ */
+#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
+    IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif)
 {
-	return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif,
-				 &udp_table, NULL);
+	struct sock *sk;
+
+	sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
+			       dif, &udp_table, NULL);
+	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+	return sk;
 }
 EXPORT_SYMBOL_GPL(udp4_lib_lookup);
+#endif
 
 static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 				       __be16 loc_port, __be32 loc_addr,
@@ -723,7 +682,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 			iph->saddr, uh->source, skb->dev->ifindex, udptable,
 			NULL);
 	if (!sk) {
-		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
+		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;	/* No socket for error */
 	}
 
@@ -776,7 +735,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
-	sock_put(sk);
+	return;
 }
 
 void udp_err(struct sk_buff *skb, u32 info)
@@ -917,13 +876,13 @@ send:
 	err = ip_send_skb(sock_net(sk), skb);
 	if (err) {
 		if (err == -ENOBUFS && !inet->recverr) {
-			UDP_INC_STATS_USER(sock_net(sk),
-					   UDP_MIB_SNDBUFERRORS, is_udplite);
+			UDP_INC_STATS(sock_net(sk),
+				      UDP_MIB_SNDBUFERRORS, is_udplite);
 			err = 0;
 		}
 	} else
-		UDP_INC_STATS_USER(sock_net(sk),
-				   UDP_MIB_OUTDATAGRAMS, is_udplite);
+		UDP_INC_STATS(sock_net(sk),
+			      UDP_MIB_OUTDATAGRAMS, is_udplite);
 	return err;
 }
 
@@ -1032,15 +991,13 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		 */
 		connected = 1;
 	}
-	ipc.addr = inet->inet_saddr;
 
+	ipc.sockc.tsflags = sk->sk_tsflags;
+	ipc.addr = inet->inet_saddr;
 	ipc.oif = sk->sk_bound_dev_if;
 
-	sock_tx_timestamp(sk, &ipc.tx_flags);
-
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
-				   sk->sk_family == AF_INET6);
+		err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
 		if (unlikely(err)) {
 			kfree(ipc.opt);
 			return err;
@@ -1065,6 +1022,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
+	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
+
 	if (ipc.opt && ipc.opt->opt.srr) {
 		if (!daddr)
 			return -EINVAL;
@@ -1192,8 +1151,8 @@ out:
 	 * seems like overkill.
 	 */
 	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-		UDP_INC_STATS_USER(sock_net(sk),
-				UDP_MIB_SNDBUFERRORS, is_udplite);
+		UDP_INC_STATS(sock_net(sk),
+			      UDP_MIB_SNDBUFERRORS, is_udplite);
 	}
 	return err;
 
@@ -1277,10 +1236,10 @@ static unsigned int first_packet_length(struct sock *sk)
 	spin_lock_bh(&rcvq->lock);
 	while ((skb = skb_peek(rcvq)) != NULL &&
 		udp_lib_checksum_complete(skb)) {
-		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS,
-				 IS_UDPLITE(sk));
-		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
-				 IS_UDPLITE(sk));
+		__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
+				IS_UDPLITE(sk));
+		__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
+				IS_UDPLITE(sk));
 		atomic_inc(&sk->sk_drops);
 		__skb_unlink(skb, rcvq);
 		__skb_queue_tail(&list_kill, skb);
@@ -1316,14 +1275,6 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 	{
 		unsigned int amount = first_packet_length(sk);
 
-		if (amount)
-			/*
-			 * We will only return the amount
-			 * of this packet since that is all
-			 * that will be read.
-			 */
-			amount -= sizeof(struct udphdr);
-
 		return put_user(amount, (int __user *)arg);
 	}
 
@@ -1347,7 +1298,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 	unsigned int ulen, copied;
-	int peeked, off = 0;
+	int peeked, peeking, off;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	bool checksum_valid = false;
@@ -1357,15 +1308,16 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
+	peeking = off = sk_peek_offset(sk, flags);
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
 				  &peeked, &off, &err);
 	if (!skb)
-		goto out;
+		return err;
 
-	ulen = skb->len - sizeof(struct udphdr);
+	ulen = skb->len;
 	copied = len;
-	if (copied > ulen)
-		copied = ulen;
+	if (copied > ulen - off)
+		copied = ulen - off;
 	else if (copied < ulen)
 		msg->msg_flags |= MSG_TRUNC;
 
@@ -1375,18 +1327,16 @@ try_again:
 	 * coverage checksum (UDP-Lite), do it before the copy.
 	 */
 
-	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
+	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov || peeking) {
 		checksum_valid = !udp_lib_checksum_complete(skb);
 		if (!checksum_valid)
 			goto csum_copy_err;
 	}
 
 	if (checksum_valid || skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
-					    msg, copied);
+		err = skb_copy_datagram_msg(skb, off, msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr),
-						     msg);
+		err = skb_copy_and_csum_datagram_msg(skb, off, msg);
 
 		if (err == -EINVAL)
 			goto csum_copy_err;
@@ -1396,15 +1346,16 @@ try_again:
 		trace_kfree_skb(skb, udp_recvmsg);
 		if (!peeked) {
 			atomic_inc(&sk->sk_drops);
-			UDP_INC_STATS_USER(sock_net(sk),
-					   UDP_MIB_INERRORS, is_udplite);
+			UDP_INC_STATS(sock_net(sk),
+				      UDP_MIB_INERRORS, is_udplite);
 		}
-		goto out_free;
+		skb_free_datagram_locked(sk, skb);
+		return err;
 	}
 
 	if (!peeked)
-		UDP_INC_STATS_USER(sock_net(sk),
-				UDP_MIB_INDATAGRAMS, is_udplite);
+		UDP_INC_STATS(sock_net(sk),
+			      UDP_MIB_INDATAGRAMS, is_udplite);
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
@@ -1417,22 +1368,20 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr) + off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
 		err = ulen;
 
-out_free:
-	skb_free_datagram_locked(sk, skb);
-out:
+	__skb_free_datagram_locked(sk, skb, peeking ? -err : err);
 	return err;
 
 csum_copy_err:
 	slow = lock_sock_fast(sk);
 	if (!skb_kill_datagram(sk, skb, flags)) {
-		UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
-		UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+		UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
+		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	}
 	unlock_sock_fast(sk, slow);
 
@@ -1479,13 +1428,13 @@ void udp_lib_unhash(struct sock *sk)
 		spin_lock_bh(&hslot->lock);
 		if (rcu_access_pointer(sk->sk_reuseport_cb))
 			reuseport_detach_sock(sk);
-		if (sk_nulls_del_node_init_rcu(sk)) {
+		if (sk_del_node_init_rcu(sk)) {
 			hslot->count--;
 			inet_sk(sk)->inet_num = 0;
 			sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
 			spin_lock(&hslot2->lock);
-			hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+			hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
 			hslot2->count--;
 			spin_unlock(&hslot2->lock);
 		}
@@ -1518,12 +1467,12 @@ void udp_lib_rehash(struct sock *sk, u16 newhash)
 
 			if (hslot2 != nhslot2) {
 				spin_lock(&hslot2->lock);
-				hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+				hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
 				hslot2->count--;
 				spin_unlock(&hslot2->lock);
 
 				spin_lock(&nhslot2->lock);
-				hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+				hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
 							 &nhslot2->head);
 				nhslot2->count++;
 				spin_unlock(&nhslot2->lock);
@@ -1553,15 +1502,15 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sk_incoming_cpu_update(sk);
 	}
 
-	rc = sock_queue_rcv_skb(sk, skb);
+	rc = __sock_queue_rcv_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
 
 		/* Note that an ENOMEM error is charged twice */
 		if (rc == -ENOMEM)
-			UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
-					 is_udplite);
-		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+			UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+					is_udplite);
+		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 		kfree_skb(skb);
 		trace_udp_fail_queue_rcv_skb(rc, sk);
 		return -1;
@@ -1625,9 +1574,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
-				UDP_INC_STATS_BH(sock_net(sk),
-						 UDP_MIB_INDATAGRAMS,
-						 is_udplite);
+				__UDP_INC_STATS(sock_net(sk),
+						UDP_MIB_INDATAGRAMS,
+						is_udplite);
 				return -ret;
 			}
 		}
@@ -1669,13 +1618,17 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
-	if (rcu_access_pointer(sk->sk_filter) &&
-	    udp_lib_checksum_complete(skb))
-		goto csum_error;
+	if (rcu_access_pointer(sk->sk_filter)) {
+		if (udp_lib_checksum_complete(skb))
+			goto csum_error;
+		if (sk_filter(sk, skb))
+			goto drop;
+	}
 
+	udp_csum_pull_header(skb);
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
-		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
-				 is_udplite);
+		__UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+				is_udplite);
 		goto drop;
 	}
 
@@ -1694,43 +1647,14 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return rc;
 
 csum_error:
-	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
+	__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
-	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+	__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	atomic_inc(&sk->sk_drops);
 	kfree_skb(skb);
 	return -1;
 }
 
-static void flush_stack(struct sock **stack, unsigned int count,
-			struct sk_buff *skb, unsigned int final)
-{
-	unsigned int i;
-	struct sk_buff *skb1 = NULL;
-	struct sock *sk;
-
-	for (i = 0; i < count; i++) {
-		sk = stack[i];
-		if (likely(!skb1))
-			skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
-
-		if (!skb1) {
-			atomic_inc(&sk->sk_drops);
-			UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
-					 IS_UDPLITE(sk));
-			UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
-					 IS_UDPLITE(sk));
-		}
-
-		if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0)
-			skb1 = NULL;
-
-		sock_put(sk);
-	}
-	if (unlikely(skb1))
-		kfree_skb(skb1);
-}
-
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
@@ -1754,14 +1678,14 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 				    struct udp_table *udptable,
 				    int proto)
 {
-	struct sock *sk, *stack[256 / sizeof(struct sock *)];
-	struct hlist_nulls_node *node;
+	struct sock *sk, *first = NULL;
 	unsigned short hnum = ntohs(uh->dest);
 	struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
-	int dif = skb->dev->ifindex;
-	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
-	bool inner_flushed = false;
+	unsigned int offset = offsetof(typeof(*sk), sk_node);
+	int dif = skb->dev->ifindex;
+	struct hlist_node *node;
+	struct sk_buff *nskb;
 
 	if (use_hash2) {
 		hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
@@ -1772,23 +1696,28 @@ start_lookup:
 		offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
 	}
 
-	spin_lock(&hslot->lock);
-	sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) {
-		if (__udp_is_mcast_sock(net, sk,
-					uh->dest, daddr,
-					uh->source, saddr,
-					dif, hnum)) {
-			if (unlikely(count == ARRAY_SIZE(stack))) {
-				flush_stack(stack, count, skb, ~0);
-				inner_flushed = true;
-				count = 0;
-			}
-			stack[count++] = sk;
-			sock_hold(sk);
+	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
+		if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr,
+					 uh->source, saddr, dif, hnum))
+			continue;
+
+		if (!first) {
+			first = sk;
+			continue;
 		}
-	}
+		nskb = skb_clone(skb, GFP_ATOMIC);
 
-	spin_unlock(&hslot->lock);
+		if (unlikely(!nskb)) {
+			atomic_inc(&sk->sk_drops);
+			__UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
+					IS_UDPLITE(sk));
+			__UDP_INC_STATS(net, UDP_MIB_INERRORS,
+					IS_UDPLITE(sk));
+			continue;
+		}
+		if (udp_queue_rcv_skb(sk, nskb) > 0)
+			consume_skb(nskb);
+	}
 
 	/* Also lookup *:port if we are using hash2 and haven't done so yet. */
 	if (use_hash2 && hash2 != hash2_any) {
@@ -1796,16 +1725,13 @@ start_lookup:
 		goto start_lookup;
 	}
 
-	/*
-	 * do the slow work with no lock held
-	 */
-	if (count) {
-		flush_stack(stack, count, skb, count - 1);
+	if (first) {
+		if (udp_queue_rcv_skb(first, skb) > 0)
+			consume_skb(skb);
 	} else {
-		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
-		consume_skb(skb);
+		kfree_skb(skb);
+		__UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI,
+				proto == IPPROTO_UDPLITE);
 	}
 	return 0;
 }
@@ -1902,7 +1828,6 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 						 inet_compute_pseudo);
 
 		ret = udp_queue_rcv_skb(sk, skb);
-		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but
 		 * it wants the return to be -protocol, or 0
@@ -1920,7 +1845,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp_lib_checksum_complete(skb))
 		goto csum_error;
 
-	UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
+	__UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 	/*
@@ -1947,9 +1872,9 @@ csum_error:
 			    proto == IPPROTO_UDPLITE ? "Lite" : "",
 			    &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
 			    ulen);
-	UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
+	__UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 drop:
-	UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
+	__UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
 	kfree_skb(skb);
 	return 0;
 }
@@ -1963,49 +1888,24 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 						  int dif)
 {
 	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(loc_port);
-	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
+	unsigned int slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
 	/* Do not bother scanning a too big list */
 	if (hslot->count > 10)
 		return NULL;
 
-	rcu_read_lock();
-begin:
-	count = 0;
 	result = NULL;
-	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
-		if (__udp_is_mcast_sock(net, sk,
-					loc_port, loc_addr,
-					rmt_port, rmt_addr,
-					dif, hnum)) {
+	sk_for_each_rcu(sk, &hslot->head) {
+		if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr,
+					rmt_port, rmt_addr, dif, hnum)) {
+			if (result)
+				return NULL;
 			result = sk;
-			++count;
-		}
-	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot)
-		goto begin;
-
-	if (result) {
-		if (count != 1 ||
-		    unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(!__udp_is_mcast_sock(net, result,
-						       loc_port, loc_addr,
-						       rmt_port, rmt_addr,
-						       dif, hnum))) {
-			sock_put(result);
-			result = NULL;
 		}
 	}
-	rcu_read_unlock();
+
 	return result;
 }
 
@@ -2018,37 +1918,22 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 					    __be16 rmt_port, __be32 rmt_addr,
 					    int dif)
 {
-	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(loc_port);
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
 	unsigned int slot2 = hash2 & udp_table.mask;
 	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
 	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
 	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+	struct sock *sk;
 
-	rcu_read_lock();
-	result = NULL;
-	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
-		if (INET_MATCH(sk, net, acookie,
-			       rmt_addr, loc_addr, ports, dif))
-			result = sk;
+	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
+		if (INET_MATCH(sk, net, acookie, rmt_addr,
+			       loc_addr, ports, dif))
+			return sk;
 		/* Only check first socket in chain */
 		break;
 	}
-
-	if (result) {
-		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(!INET_MATCH(sk, net, acookie,
-					      rmt_addr, loc_addr,
-					      ports, dif))) {
-			sock_put(result);
-			result = NULL;
-		}
-	}
-	rcu_read_unlock();
-	return result;
+	return NULL;
 }
 
 void udp_v4_early_demux(struct sk_buff *skb)
@@ -2056,7 +1941,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
 	const struct udphdr *uh;
-	struct sock *sk;
+	struct sock *sk = NULL;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
 	int ours;
@@ -2088,11 +1973,9 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	} else {
-		return;
 	}
 
-	if (!sk)
+	if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2))
 		return;
 
 	skb->sk = sk;
@@ -2392,14 +2275,13 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 
 	for (state->bucket = start; state->bucket <= state->udp_table->mask;
 	     ++state->bucket) {
-		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
 
-		if (hlist_nulls_empty(&hslot->head))
+		if (hlist_empty(&hslot->head))
 			continue;
 
 		spin_lock_bh(&hslot->lock);
-		sk_nulls_for_each(sk, node, &hslot->head) {
+		sk_for_each(sk, &hslot->head) {
 			if (!net_eq(sock_net(sk), net))
 				continue;
 			if (sk->sk_family == state->family)
@@ -2418,7 +2300,7 @@ static struct sock *udp_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) || sk->sk_family != state->family));
 
 	if (!sk) {
@@ -2627,12 +2509,12 @@ void __init udp_table_init(struct udp_table *table, const char *name)
 
 	table->hash2 = table->hash + (table->mask + 1);
 	for (i = 0; i <= table->mask; i++) {
-		INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
+		INIT_HLIST_HEAD(&table->hash[i].head);
 		table->hash[i].count = 0;
 		spin_lock_init(&table->hash[i].lock);
 	}
 	for (i = 0; i <= table->mask; i++) {
-		INIT_HLIST_NULLS_HEAD(&table->hash2[i].head, i);
+		INIT_HLIST_HEAD(&table->hash2[i].head);
 		table->hash2[i].count = 0;
 		spin_lock_init(&table->hash2[i].lock);
 	}
author	Linus Torvalds <torvalds@linux-foundation.org>	2016-05-18 02:26:30 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2016-05-18 02:26:30 +0300
commit	a7fd20d1c476af4563e66865213474a2f9f473a4 (patch)
tree	fb1399e2f82842450245fb058a8fb23c52865f43 /net/ipv4/udp.c
parent	b80fed9595513384424cd141923c9161c4b5021b (diff)
parent	917fa5353da05e8a0045b8acacba8d50400d5b12 (diff)
download	linux-a7fd20d1c476af4563e66865213474a2f9f473a4.tar.xz