Merge branch 'master' into for-4.4-fixes

The following commit which went into mainline through networking tree

  3b13758f51de ("cgroups: Allow dynamically changing net_classid")

conflicts in net/core/netclassid_cgroup.c with the following pending
fix in cgroup/for-4.4-fixes.

  1f7dd3e5a6e4 ("cgroup: fix handling of multi-destination migration from subtree_control enabling")

The former separates out update_classid() from cgrp_attach() and
updates it to walk all fds of all tasks in the target css so that it
can be used from both migration and config change paths.  The latter
drops @css from cgrp_attach().

Resolve the conflict by making cgrp_attach() call update_classid()
with the css from the first task.  We can revive @tset walking in
cgrp_attach() but given that net_cls is v1 only where there always is
only one target css during migration, this is fine.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Nina Schiff <ninasc@fb.com>

11 files changed, 77 insertions, 50 deletions

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6baf36e11808..05e4cba14162 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2126,7 +2126,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 	ASSERT_RTNL();
 
 	in_dev = ip_mc_find_dev(net, imr);
-	if (!in_dev) {
+	if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) {
 		ret = -ENODEV;
 		goto out;
 	}
@@ -2147,7 +2147,8 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 		*imlp = iml->next_rcu;
 
-		ip_mc_dec_group(in_dev, group);
+		if (in_dev)
+			ip_mc_dec_group(in_dev, group);
 
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1feb15f23de8..46b9c887bede 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -563,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data)
 	int max_retries, thresh;
 	u8 defer_accept;
 
-	if (sk_listener->sk_state != TCP_LISTEN)
+	if (sk_state_load(sk_listener) != TCP_LISTEN)
 		goto drop;
 
 	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
@@ -749,7 +749,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 	 * It is OK, because this socket enters to hash table only
 	 * after validation is complete.
 	 */
-	sk->sk_state = TCP_LISTEN;
+	sk_state_store(sk, TCP_LISTEN);
 	if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
 		inet->inet_sport = htons(inet->inet_num);
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 92dd4b74d513..c3a38353f5dc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -350,7 +350,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -441,10 +441,6 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
 	return dev;
 
 failure:
-	/* allow the register to be completed before unregistering. */
-	rtnl_unlock();
-	rtnl_lock();
-
 	unregister_netdevice(dev);
 	return NULL;
 }
@@ -540,10 +536,6 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 	return dev;
 
 failure:
-	/* allow the register to be completed before unregistering. */
-	rtnl_unlock();
-	rtnl_lock();
-
 	unregister_netdevice(dev);
 	return NULL;
 }
@@ -1208,7 +1200,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1217,8 +1209,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
 	/* Shut down all active vif entries */
 
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-			vif_delete(mrt, i, 0, &list);
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+			continue;
+		vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1226,7 +1219,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
 	for (i = 0; i < MFC_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			list_del_rcu(&c->list);
 			mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1261,7 +1254,7 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 		}
 	}
 	rtnl_unlock();
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 657d2307f031..b3ca21b2ba9b 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -45,7 +45,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	struct net *net = nf_ct_net(ct);
 	const struct nf_conn *master = ct->master;
 	struct nf_conntrack_expect *other_exp;
-	struct nf_conntrack_tuple t;
+	struct nf_conntrack_tuple t = {};
 	const struct nf_ct_pptp_master *ct_pptp_info;
 	const struct nf_nat_pptp *nat_pptp_info;
 	struct nf_nat_range range;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8c0d0bdc2a7c..63e5be0abd86 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -406,10 +406,12 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			ip_select_ident(net, skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+		skb->transport_header += iphlen;
+		if (iph->protocol == IPPROTO_ICMP &&
+		    length >= iphlen + sizeof(struct icmphdr))
+			icmp_out_count(net, ((struct icmphdr *)
+				skb_transport_header(skb))->type);
 	}
-	if (iph->protocol == IPPROTO_ICMP)
-		icmp_out_count(net, ((struct icmphdr *)
-			skb_transport_header(skb))->type);
 
 	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
 		      net, sk, skb, NULL, rt->dst.dev,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0cfa7c0c1e80..c82cca18c90f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -451,11 +451,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
+	int state;
 
 	sock_rps_record_flow(sk);
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
-	if (sk->sk_state == TCP_LISTEN)
+
+	state = sk_state_load(sk);
+	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
 	/* Socket is not locked. We are protected from async events
@@ -492,14 +495,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
 	 * blocking on fresh not-connected or disconnected socket. --ANK
 	 */
-	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
+	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
 		mask |= POLLHUP;
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= POLLIN | POLLRDNORM | POLLRDHUP;
 
 	/* Connected or passive Fast Open socket? */
-	if (sk->sk_state != TCP_SYN_SENT &&
-	    (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+	if (state != TCP_SYN_SENT &&
+	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
 		if (tp->urg_seq == tp->copied_seq &&
@@ -507,9 +510,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		    tp->urg_data)
 			target++;
 
-		/* Potential race condition. If read of tp below will
-		 * escape above sk->sk_state, we can be illegally awaken
-		 * in SYN_* states. */
 		if (tp->rcv_nxt - tp->copied_seq >= target)
 			mask |= POLLIN | POLLRDNORM;
 
@@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 			if (sk_stream_is_writeable(sk)) {
 				mask |= POLLOUT | POLLWRNORM;
 			} else {  /* send SIGIO later */
-				set_bit(SOCK_ASYNC_NOSPACE,
-					&sk->sk_socket->flags);
+				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 
 				/* Race breaker. If space is freed after
@@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			goto out_err;
 	}
 
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 	copied = 0;
@@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	}
 
 	/* This should be in poll */
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
@@ -1934,7 +1933,7 @@ void tcp_set_state(struct sock *sk, int state)
 	/* Change state AFTER socket is unhashed to avoid closed
 	 * socket sitting in hash tables.
 	 */
-	sk->sk_state = state;
+	sk_state_store(sk, state);
 
 #ifdef STATE_TRACE
 	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
@@ -2644,7 +2643,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	if (sk->sk_type != SOCK_STREAM)
 		return;
 
-	info->tcpi_state = sk->sk_state;
+	info->tcpi_state = sk_state_load(sk);
+
 	info->tcpi_ca_state = icsk->icsk_ca_state;
 	info->tcpi_retransmits = icsk->icsk_retransmits;
 	info->tcpi_probes = icsk->icsk_probes_out;
@@ -2672,7 +2672,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_snd_mss = tp->mss_cache;
 	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (info->tcpi_state == TCP_LISTEN) {
 		info->tcpi_unacked = sk->sk_ack_backlog;
 		info->tcpi_sacked = sk->sk_max_ack_backlog;
 	} else {
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 479f34946177..b31604086edd 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -21,7 +21,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 {
 	struct tcp_info *info = _info;
 
-	if (sk->sk_state == TCP_LISTEN) {
+	if (sk_state_load(sk) == TCP_LISTEN) {
 		r->idiag_rqueue = sk->sk_ack_backlog;
 		r->idiag_wqueue = sk->sk_max_ack_backlog;
 	} else if (sk->sk_type == SOCK_STREAM) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fdd88c3803a6..2d656eef7f8e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4481,19 +4481,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_buff *skb;
+	int err = -ENOMEM;
+	int data_len = 0;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size, sk->sk_allocation);
+	if (size > PAGE_SIZE) {
+		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+		data_len = npages << PAGE_SHIFT;
+		size = data_len + (size & ~PAGE_MASK);
+	}
+	skb = alloc_skb_with_frags(size - data_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER,
+				   &err, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	skb_put(skb, size - data_len);
+	skb->data_len = data_len;
+	skb->len = size;
+
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_from_msg(skb_put(skb, size), msg, size))
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (err)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4509,7 +4524,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
 	kfree_skb(skb);
 err:
-	return -ENOMEM;
+	return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5667,6 +5683,7 @@ discard:
 		}
 
 		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 950e28c0cdf2..db003438aaf5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -921,7 +921,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	}
 
 	md5sig = rcu_dereference_protected(tp->md5sig_info,
-					   sock_owned_by_user(sk));
+					   sock_owned_by_user(sk) ||
+					   lockdep_is_held(&sk->sk_lock.slock));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
@@ -2158,6 +2159,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	__u16 destp = ntohs(inet->inet_dport);
 	__u16 srcp = ntohs(inet->inet_sport);
 	int rx_queue;
+	int state;
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
@@ -2175,17 +2177,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		timer_expires = jiffies;
 	}
 
-	if (sk->sk_state == TCP_LISTEN)
+	state = sk_state_load(sk);
+	if (state == TCP_LISTEN)
 		rx_queue = sk->sk_ack_backlog;
 	else
-		/*
-		 * because we dont lock socket, we might find a transient negative value
+		/* Because we don't lock the socket,
+		 * we might find a transient negative value.
 		 */
 		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
-		i, src, srcp, dest, destp, sk->sk_state,
+		i, src, srcp, dest, destp, state,
 		tp->write_seq - tp->snd_una,
 		rx_queue,
 		timer_active,
@@ -2199,8 +2202,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		jiffies_to_clock_t(icsk->icsk_ack.ato),
 		(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
 		tp->snd_cwnd,
-		sk->sk_state == TCP_LISTEN ?
-		    (fastopenq ? fastopenq->max_qlen : 0) :
+		state == TCP_LISTEN ?
+		    fastopenq->max_qlen :
 		    (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh));
 }
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c9c716a483e4..193ba1fa8a9a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -168,7 +168,7 @@ static int tcp_write_timeout(struct sock *sk)
 			dst_negative_advice(sk);
 			if (tp->syn_fastopen || tp->syn_data)
 				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
-			if (tp->syn_data)
+			if (tp->syn_data && icsk->icsk_retransmits == 1)
 				NET_INC_STATS_BH(sock_net(sk),
 						 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		}
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
 		syn_set = true;
 	} else {
 		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+			/* Some middle-boxes may black-hole Fast Open _after_
+			 * the handshake. Therefore we conservatively disable
+			 * Fast Open on this path on recurring timeouts with
+			 * few or zero bytes acked after Fast Open.
+			 */
+			if (tp->syn_data_acked &&
+			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+				if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+					NET_INC_STATS_BH(sock_net(sk),
+							 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+			}
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24ec14f9825c..0c7b0e61b917 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -100,7 +100,6 @@
 #include <linux/slab.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
-#include <linux/netdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>