Merge branch 'sched/urgent' into sched/core, to pick up fixes before merging new patches

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 115 insertions, 54 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 11c4ca13ec3b..5c5db6636704 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -257,6 +257,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index cc8f3e506cde..473447593060 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1155,6 +1155,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info;
 	struct in_device *in_dev;
 	struct net *net = dev_net(dev);
 	unsigned int flags;
@@ -1193,6 +1194,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	case NETDEV_CHANGEMTU:
 		rt_cache_flush(net);
 		break;
+	case NETDEV_CHANGEUPPER:
+		info = ptr;
+		/* flush all routes if dev is linked to or unlinked from
+		 * an L3 master device (e.g., VRF)
+		 */
+		if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+			fib_disable_ip(dev, NETDEV_DOWN, true);
+		break;
 	}
 	return NOTIFY_DONE;
 }
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index e0fcbbbcfe54..bd903fe0f750 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -24,6 +24,7 @@ struct fou {
 	u16 type;
 	struct udp_offload udp_offloads;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 #define FOU_F_REMCSUM_NOPARTIAL BIT(0)
@@ -417,7 +418,7 @@ static void fou_release(struct fou *fou)
 	list_del(&fou->list);
 	udp_tunnel_sock_release(sock);
 
-	kfree(fou);
+	kfree_rcu(fou, rcu);
 }
 
 static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
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/ipip.c b/net/ipv4/ipip.c
index f34c31defafe..a09fb0dec725 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -253,9 +253,6 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	p.i_key = p.o_key = 0;
 	p.i_flags = p.o_flags = 0;
-	if (p.iph.ttl)
-		p.iph.frag_off |= htons(IP_DF);
-
 	err = ip_tunnel_ioctl(dev, &p, cmd);
 	if (err)
 		return err;
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/Kconfig b/net/ipv4/netfilter/Kconfig
index a35584176535..c187c60e3e0c 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -60,6 +60,7 @@ config NFT_REJECT_IPV4
 
 config NFT_DUP_IPV4
 	tristate "IPv4 nf_tables packet duplication support"
+	depends on !NF_CONNTRACK || NF_CONNTRACK
 	select NF_DUP_IPV4
 	help
 	  This module enables IPv4 packet duplication support for nf_tables.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c1728771cf89..c82cca18c90f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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);
 
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 ba09016d1bfd..d8841a2f1569 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)
@@ -1492,7 +1493,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	if (likely(sk->sk_rx_dst))
 		skb_dst_drop(skb);
 	else
-		skb_dst_force(skb);
+		skb_dst_force_safe(skb);
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
@@ -1720,8 +1721,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
-		dst_hold(dst);
+	if (dst && dst_hold_safe(dst)) {
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cb7ca569052c..9bfc39ff2285 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3150,7 +3150,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0, copied;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3188,17 +3188,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	copied = copy_from_iter(skb_put(syn_data, space), space,
-				&fo->data->msg_iter);
-	if (unlikely(!copied)) {
-		kfree_skb(syn_data);
-		goto fallback;
-	}
-	if (copied != space) {
-		skb_trim(syn_data, copied);
-		space = copied;
+	if (space) {
+		int copied = copy_from_iter(skb_put(syn_data, space), space,
+					    &fo->data->msg_iter);
+		if (unlikely(!copied)) {
+			kfree_skb(syn_data);
+			goto fallback;
+		}
+		if (copied != space) {
+			skb_trim(syn_data, copied);
+			space = copied;
+		}
 	}
-
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)
 		fo->data = NULL;
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>
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 1e0c3c835a63..7b0edb37a115 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -259,7 +259,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
@@ -273,7 +273,7 @@ static struct dst_ops xfrm4_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.dst_ops =		&xfrm4_dst_ops,
+	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
@@ -295,7 +295,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -323,7 +323,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -335,12 +335,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+	       sizeof(xfrm4_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm4_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+	xfrm4_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
 
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
 };
-#endif
 
 static void __init xfrm4_policy_init(void)
 {
@@ -349,13 +381,9 @@ static void __init xfrm4_policy_init(void)
 
 void __init xfrm4_init(void)
 {
-	dst_entries_init(&xfrm4_dst_ops);
-
 	xfrm4_state_init();
 	xfrm4_policy_init();
 	xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
-#endif
 }