Merge branch 'master' into for-next

Sync with Linus' tree to be able to apply fixes on top of newer things
in tree (efi-stub).

Signed-off-by: Jiri Kosina <jkosina@suse.cz>

net/core/datagram.c

@@ -577,7 +577,7 @@ EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
 /**
  *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
  *	@skb: buffer to copy
- *	@from: io vector to copy to
+ *	@from: io vector to copy from
  *	@offset: offset in the io vector to start copying from
  *	@count: amount of vectors to copy to buffer from
  *

net/core/dev_addr_lists.c

@@ -752,7 +752,7 @@ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr)
 EXPORT_SYMBOL(dev_mc_del_global);
 
 /**
- *	dev_mc_sync - Synchronize device's unicast list to another device
+ *	dev_mc_sync - Synchronize device's multicast list to another device
  *	@to: destination device
  *	@from: source device
  *
@@ -780,7 +780,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
 EXPORT_SYMBOL(dev_mc_sync);
 
 /**
- *	dev_mc_sync_multiple - Synchronize device's unicast list to another
+ *	dev_mc_sync_multiple - Synchronize device's multicast list to another
  *	device, but allow for multiple calls to sync to multiple devices.
  *	@to: destination device
  *	@from: source device

net/core/drop_monitor.c

@@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = {
 	.hdrsize        = 0,
 	.name           = "NET_DM",
 	.version        = 2,
-	.maxattr        = NET_DM_CMD_MAX,
 };
 
 static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
@@ -106,6 +105,10 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	return skb;
 }
 
+static struct genl_multicast_group dropmon_mcgrps[] = {
+	{ .name = "events", },
+};
+
 static void send_dm_alert(struct work_struct *work)
 {
 	struct sk_buff *skb;
@@ -116,7 +119,8 @@ static void send_dm_alert(struct work_struct *work)
 	skb = reset_per_cpu_data(data);
 
 	if (skb)
-		genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+		genlmsg_multicast(&net_drop_monitor_family, skb, 0,
+				  0, GFP_KERNEL);
 }
 
 /*
@@ -333,7 +337,7 @@ out:
 	return NOTIFY_DONE;
 }
 
-static struct genl_ops dropmon_ops[] = {
+static const struct genl_ops dropmon_ops[] = {
 	{
 		.cmd = NET_DM_CMD_CONFIG,
 		.doit = net_dm_cmd_config,
@@ -364,13 +368,13 @@ static int __init init_net_drop_monitor(void)
 		return -ENOSPC;
 	}
 
-	rc = genl_register_family_with_ops(&net_drop_monitor_family,
-					   dropmon_ops,
-					   ARRAY_SIZE(dropmon_ops));
+	rc = genl_register_family_with_ops_groups(&net_drop_monitor_family,
+						  dropmon_ops, dropmon_mcgrps);
 	if (rc) {
 		pr_err("Could not create drop monitor netlink family\n");
 		return rc;
 	}
+	WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
 
 	rc = register_netdevice_notifier(&dropmon_net_notifier);
 	if (rc < 0) {

net/core/ethtool.c

@@ -81,6 +81,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
+	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
+	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
@@ -94,6 +96,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_LOOPBACK_BIT] =         "loopback",
 	[NETIF_F_RXFCS_BIT] =            "rx-fcs",
 	[NETIF_F_RXALL_BIT] =            "rx-all",
+	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)

net/core/fib_rules.c

@@ -460,7 +460,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		if (frh->action && (frh->action != rule->action))
 			continue;
 
-		if (frh->table && (frh_get_table(frh, tb) != rule->table))
+		if (frh_get_table(frh, tb) &&
+		    (frh_get_table(frh, tb) != rule->table))
 			continue;
 
 		if (tb[FRA_PRIORITY] &&

net/core/filter.c

@@ -644,7 +644,6 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
 	bpf_jit_free(fp);
-	kfree(fp);
 }
 EXPORT_SYMBOL(sk_filter_release_rcu);
 
@@ -683,7 +682,7 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
 	if (fprog->filter == NULL)
 		return -EINVAL;
 
-	fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL);
+	fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
 	memcpy(fp->insns, fprog->filter, fsize);
@@ -723,6 +722,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct sk_filter *fp, *old_fp;
 	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+	unsigned int sk_fsize = sk_filter_size(fprog->len);
 	int err;
 
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
@@ -732,11 +732,11 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (fprog->filter == NULL)
 		return -EINVAL;
 
-	fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL);
+	fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
 	if (copy_from_user(fp->insns, fprog->filter, fsize)) {
-		sock_kfree_s(sk, fp, fsize+sizeof(*fp));
+		sock_kfree_s(sk, fp, sk_fsize);
 		return -EFAULT;
 	}
 

net/core/flow_dissector.c

@@ -25,9 +25,35 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
 	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
 }
 
+/**
+ * skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: buffer to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ *
+ * The function will try to retrieve the ports at offset thoff + poff where poff
+ * is the protocol port offset returned from proto_ports_offset
+ */
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+{
+	int poff = proto_ports_offset(ip_proto);
+
+	if (poff >= 0) {
+		__be32 *ports, _ports;
+
+		ports = skb_header_pointer(skb, thoff + poff,
+					   sizeof(_ports), &_ports);
+		if (ports)
+			return *ports;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_flow_get_ports);
+
 bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
 {
-	int poff, nhoff = skb_network_offset(skb);
+	int nhoff = skb_network_offset(skb);
 	u8 ip_proto;
 	__be16 proto = skb->protocol;
 
@@ -40,15 +66,15 @@ again:
 		struct iphdr _iph;
 ip:
 		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-		if (!iph)
+		if (!iph || iph->ihl < 5)
 			return false;
+		nhoff += iph->ihl * 4;
 
+		ip_proto = iph->protocol;
 		if (ip_is_fragment(iph))
 			ip_proto = 0;
-		else
-			ip_proto = iph->protocol;
+
 		iph_to_flow_copy_addrs(flow, iph);
-		nhoff += iph->ihl * 4;
 		break;
 	}
 	case __constant_htons(ETH_P_IPV6): {
@@ -150,16 +176,7 @@ ipv6:
 	}
 
 	flow->ip_proto = ip_proto;
-	poff = proto_ports_offset(ip_proto);
-	if (poff >= 0) {
-		__be32 *ports, _ports;
-
-		nhoff += poff;
-		ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
-		if (ports)
-			flow->ports = *ports;
-	}
-
+	flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
 	flow->thoff = (u16) nhoff;
 
 	return true;
@@ -167,6 +184,22 @@ ipv6:
 EXPORT_SYMBOL(skb_flow_dissect);
 
 static u32 hashrnd __read_mostly;
+static __always_inline void __flow_hash_secret_init(void)
+{
+	net_get_random_once(&hashrnd, sizeof(hashrnd));
+}
+
+static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c)
+{
+	__flow_hash_secret_init();
+	return jhash_3words(a, b, c, hashrnd);
+}
+
+static __always_inline u32 __flow_hash_1word(u32 a)
+{
+	__flow_hash_secret_init();
+	return jhash_1word(a, hashrnd);
+}
 
 /*
  * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
@@ -193,9 +226,9 @@ void __skb_get_rxhash(struct sk_buff *skb)
 		swap(keys.port16[0], keys.port16[1]);
 	}
 
-	hash = jhash_3words((__force u32)keys.dst,
-			    (__force u32)keys.src,
-			    (__force u32)keys.ports, hashrnd);
+	hash = __flow_hash_3words((__force u32)keys.dst,
+				  (__force u32)keys.src,
+				  (__force u32)keys.ports);
 	if (!hash)
 		hash = 1;
 
@@ -231,7 +264,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 		hash = skb->sk->sk_hash;
 	else
 		hash = (__force u16) skb->protocol;
-	hash = jhash_1word(hash, hashrnd);
+	hash = __flow_hash_1word(hash);
 
 	return (u16) (((u64) hash * qcount) >> 32) + qoffset;
 }
@@ -323,7 +356,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 				else
 					hash = (__force u16) skb->protocol ^
 					    skb->rxhash;
-				hash = jhash_1word(hash, hashrnd);
+				hash = __flow_hash_1word(hash);
 				queue_index = map->queues[
 				    ((u64)hash * map->len) >> 32];
 			}
@@ -352,7 +385,7 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 
 		if (queue_index != new_index && sk &&
 		    rcu_access_pointer(sk->sk_dst_cache))
-			sk_tx_queue_set(sk, queue_index);
+			sk_tx_queue_set(sk, new_index);
 
 		queue_index = new_index;
 	}
@@ -378,11 +411,3 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 	skb_set_queue_mapping(skb, queue_index);
 	return netdev_get_tx_queue(dev, queue_index);
 }
-
-static int __init initialize_hashrnd(void)
-{
-	get_random_bytes(&hashrnd, sizeof(hashrnd));
-	return 0;
-}
-
-late_initcall_sync(initialize_hashrnd);

net/core/iovec.c

@@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		m->msg_name = address;
+		if (m->msg_name)
+			m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
 	}
@@ -100,7 +101,7 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
 EXPORT_SYMBOL(memcpy_toiovecend);
 
 /*
- *	Copy iovec from kernel. Returns -EFAULT on error.
+ *	Copy iovec to kernel. Returns -EFAULT on error.
  */
 
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,

net/core/neighbour.c

@@ -867,7 +867,7 @@ static void neigh_invalidate(struct neighbour *neigh)
 static void neigh_probe(struct neighbour *neigh)
 	__releases(neigh->lock)
 {
-	struct sk_buff *skb = skb_peek(&neigh->arp_queue);
+	struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue);
 	/* keep skb alive even if arp_queue overflows */
 	if (skb)
 		skb = skb_copy(skb, GFP_ATOMIC);

net/core/net-sysfs.c

@@ -1196,6 +1196,13 @@ static void remove_queue_kobjects(struct net_device *net)
 #endif
 }
 
+static bool net_current_may_mount(void)
+{
+	struct net *net = current->nsproxy->net_ns;
+
+	return ns_capable(net->user_ns, CAP_SYS_ADMIN);
+}
+
 static void *net_grab_current_ns(void)
 {
 	struct net *ns = current->nsproxy->net_ns;
@@ -1218,6 +1225,7 @@ static const void *net_netlink_ns(struct sock *sk)
 
 struct kobj_ns_type_operations net_ns_type_operations = {
 	.type = KOBJ_NS_TYPE_NET,
+	.current_may_mount = net_current_may_mount,
 	.grab_current_ns = net_grab_current_ns,
 	.netlink_ns = net_netlink_ns,
 	.initial_ns = net_initial_ns,
@@ -1255,7 +1263,7 @@ static void netdev_release(struct device *d)
 	BUG_ON(dev->reg_state != NETREG_RELEASED);
 
 	kfree(dev->ifalias);
-	kfree((char *)dev - dev->padded);
+	netdev_freemem(dev);
 }
 
 static const void *net_namespace(struct device *d)
@@ -1336,17 +1344,19 @@ int netdev_register_kobject(struct net_device *net)
 	return error;
 }
 
-int netdev_class_create_file(struct class_attribute *class_attr)
+int netdev_class_create_file_ns(struct class_attribute *class_attr,
+				const void *ns)
 {
-	return class_create_file(&net_class, class_attr);
+	return class_create_file_ns(&net_class, class_attr, ns);
 }
-EXPORT_SYMBOL(netdev_class_create_file);
+EXPORT_SYMBOL(netdev_class_create_file_ns);
 
-void netdev_class_remove_file(struct class_attribute *class_attr)
+void netdev_class_remove_file_ns(struct class_attribute *class_attr,
+				 const void *ns)
 {
-	class_remove_file(&net_class, class_attr);
+	class_remove_file_ns(&net_class, class_attr, ns);
 }
-EXPORT_SYMBOL(netdev_class_remove_file);
+EXPORT_SYMBOL(netdev_class_remove_file_ns);
 
 int netdev_kobject_init(void)
 {

net/core/net_namespace.c

@@ -651,7 +651,7 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 	struct net *net = ns;
 
 	if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
-	    !nsown_capable(CAP_SYS_ADMIN))
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
 	put_net(nsproxy->net_ns);

net/core/netpoll.c

@@ -550,7 +550,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 		return;
 
 	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto == ETH_P_IP) {
+	if (proto == ETH_P_ARP) {
 		struct arphdr *arp;
 		unsigned char *arp_ptr;
 		/* No arp on this interface */
@@ -636,8 +636,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 
 			netpoll_send_skb(np, send_skb);
 
-			/* If there are several rx_hooks for the same address,
-			   we're fine by sending a single reply */
+			/* If there are several rx_skb_hooks for the same
+			 * address we're fine by sending a single reply
+			 */
 			break;
 		}
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -719,8 +720,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 
 			netpoll_send_skb(np, send_skb);
 
-			/* If there are several rx_hooks for the same address,
-			   we're fine by sending a single reply */
+			/* If there are several rx_skb_hooks for the same
+			 * address, we're fine by sending a single reply
+			 */
 			break;
 		}
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -756,11 +758,12 @@ static bool pkt_is_ns(struct sk_buff *skb)
 
 int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 {
-	int proto, len, ulen;
-	int hits = 0;
+	int proto, len, ulen, data_len;
+	int hits = 0, offset;
 	const struct iphdr *iph;
 	struct udphdr *uh;
 	struct netpoll *np, *tmp;
+	uint16_t source;
 
 	if (list_empty(&npinfo->rx_np))
 		goto out;
@@ -820,7 +823,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 
 		len -= iph->ihl*4;
 		uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
+		offset = (unsigned char *)(uh + 1) - skb->data;
 		ulen = ntohs(uh->len);
+		data_len = skb->len - offset;
+		source = ntohs(uh->source);
 
 		if (ulen != len)
 			goto out;
@@ -834,9 +840,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 			if (np->local_port && np->local_port != ntohs(uh->dest))
 				continue;
 
-			np->rx_hook(np, ntohs(uh->source),
-				       (char *)(uh+1),
-				       ulen - sizeof(struct udphdr));
+			np->rx_skb_hook(np, source, skb, offset, data_len);
 			hits++;
 		}
 	} else {
@@ -859,7 +863,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 			goto out;
 		uh = udp_hdr(skb);
+		offset = (unsigned char *)(uh + 1) - skb->data;
 		ulen = ntohs(uh->len);
+		data_len = skb->len - offset;
+		source = ntohs(uh->source);
 		if (ulen != skb->len)
 			goto out;
 		if (udp6_csum_init(skb, uh, IPPROTO_UDP))
@@ -872,9 +879,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 			if (np->local_port && np->local_port != ntohs(uh->dest))
 				continue;
 
-			np->rx_hook(np, ntohs(uh->source),
-				       (char *)(uh+1),
-				       ulen - sizeof(struct udphdr));
+			np->rx_skb_hook(np, source, skb, offset, data_len);
 			hits++;
 		}
 #endif
@@ -1062,7 +1067,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	npinfo->netpoll = np;
 
-	if (np->rx_hook) {
+	if (np->rx_skb_hook) {
 		spin_lock_irqsave(&npinfo->rx_lock, flags);
 		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
 		list_add_tail(&np->rx, &npinfo->rx_np);
@@ -1284,15 +1289,14 @@ EXPORT_SYMBOL_GPL(__netpoll_free_async);
 
 void netpoll_cleanup(struct netpoll *np)
 {
-	if (!np->dev)
-		return;
-
 	rtnl_lock();
+	if (!np->dev)
+		goto out;
 	__netpoll_cleanup(np);
-	rtnl_unlock();
-
 	dev_put(np->dev);
 	np->dev = NULL;
+out:
+	rtnl_unlock();
 }
 EXPORT_SYMBOL(netpoll_cleanup);
 

net/core/netprio_cgroup.c

@@ -222,11 +222,10 @@ static void net_prio_attach(struct cgroup_subsys_state *css,
 			    struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
-	void *v;
+	void *v = (void *)(unsigned long)css->cgroup->id;
 
 	cgroup_taskset_for_each(p, css, tset) {
 		task_lock(p);
-		v = (void *)(unsigned long)task_netprioidx(p);
 		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
 	}

net/core/pktgen.c

@@ -2527,6 +2527,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
 		if (x) {
 			int ret;
 			__u8 *eth;
+			struct iphdr *iph;
+
 			nhead = x->props.header_len - skb_headroom(skb);
 			if (nhead > 0) {
 				ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
@@ -2548,6 +2550,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
 			eth = (__u8 *) skb_push(skb, ETH_HLEN);
 			memcpy(eth, pkt_dev->hh, 12);
 			*(u16 *) &eth[12] = protocol;
+
+			/* Update IPv4 header len as well as checksum value */
+			iph = ip_hdr(skb);
+			iph->tot_len = htons(skb->len - ETH_HLEN);
+			ip_send_check(iph);
 		}
 	}
 	return 1;

net/core/rtnetlink.c

@@ -1647,9 +1647,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 	}
 
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
 
-	__dev_notify_flags(dev, old_flags);
+	__dev_notify_flags(dev, old_flags, ~0U);
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
@@ -1985,14 +1984,15 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 	size_t if_info_size;
 
-	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL);
+	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags);
 	if (skb == NULL)
 		goto errout;
 
@@ -2003,7 +2003,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
 	return;
 errout:
 	if (err < 0)
@@ -2717,7 +2717,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_JOIN:
 		break;
 	default:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	}
 	return NOTIFY_DONE;

net/core/scm.c

@@ -56,9 +56,9 @@ static __inline__ int scm_check_creds(struct ucred *creds)
 	if ((creds->pid == task_tgid_vnr(current) ||
 	     ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) &&
 	    ((uid_eq(uid, cred->uid)   || uid_eq(uid, cred->euid) ||
-	      uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) &&
+	      uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) &&
 	    ((gid_eq(gid, cred->gid)   || gid_eq(gid, cred->egid) ||
-	      gid_eq(gid, cred->sgid)) || nsown_capable(CAP_SETGID))) {
+	      gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) {
 	       return 0;
 	}
 	return -EPERM;

net/core/secure_seq.c

@@ -7,15 +7,20 @@
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
 #include <linux/string.h>
+#include <linux/net.h>
 
 #include <net/secure_seq.h>
 
-static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
-void net_secret_init(void)
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static __always_inline void net_secret_init(void)
 {
-	get_random_bytes(net_secret, sizeof(net_secret));
+	net_get_random_once(net_secret, sizeof(net_secret));
 }
+#endif
 
 #ifdef CONFIG_INET
 static u32 seq_scale(u32 seq)
@@ -42,6 +47,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32)daddr[i];
@@ -63,6 +69,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32) daddr[i];
@@ -82,6 +89,7 @@ __u32 secure_ip_id(__be32 daddr)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force __u32) daddr;
 	hash[1] = net_secret[13];
 	hash[2] = net_secret[14];
@@ -96,6 +104,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4])
 {
 	__u32 hash[4];
 
+	net_secret_init();
 	memcpy(hash, daddr, 16);
 	md5_transform(hash, net_secret);
 
@@ -107,6 +116,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -121,6 +131,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = (__force u32)dport ^ net_secret[14];
@@ -140,6 +151,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u64 seq;
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -164,6 +176,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 	u64 seq;
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + daddr[i];

net/core/skbuff.c

@@ -476,6 +476,18 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 }
 EXPORT_SYMBOL(skb_add_rx_frag);
 
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
+			  unsigned int truesize)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+	skb_frag_size_add(frag, size);
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += truesize;
+}
+EXPORT_SYMBOL(skb_coalesce_rx_frag);
+
 static void skb_drop_list(struct sk_buff **listp)
 {
 	kfree_skb_list(*listp);
@@ -580,9 +592,6 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 #endif
@@ -903,6 +912,9 @@ EXPORT_SYMBOL(skb_clone);
 
 static void skb_headers_offset_update(struct sk_buff *skb, int off)
 {
+	/* Only adjust this if it actually is csum_start rather than csum */
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		skb->csum_start += off;
 	/* {transport,network,mac}_header and tail are relative to skb->head */
 	skb->transport_header += off;
 	skb->network_header   += off;
@@ -1036,8 +1048,8 @@ EXPORT_SYMBOL(__pskb_copy);
  *	@ntail: room to add at tail
  *	@gfp_mask: allocation priority
  *
- *	Expands (or creates identical copy, if &nhead and &ntail are zero)
- *	header of skb. &sk_buff itself is not changed. &sk_buff MUST have
+ *	Expands (or creates identical copy, if @nhead and @ntail are zero)
+ *	header of @skb. &sk_buff itself is not changed. &sk_buff MUST have
  *	reference count of 1. Returns zero in the case of success or error,
  *	if expansion failed. In the last case, &sk_buff is not changed.
  *
@@ -1109,9 +1121,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 #endif
 	skb->tail	      += off;
 	skb_headers_offset_update(skb, nhead);
-	/* Only adjust this if it actually is csum_start rather than csum */
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		skb->csum_start += nhead;
 	skb->cloned   = 0;
 	skb->hdr_len  = 0;
 	skb->nohdr    = 0;
@@ -1176,7 +1185,6 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 					NUMA_NO_NODE);
 	int oldheadroom = skb_headroom(skb);
 	int head_copy_len, head_copy_off;
-	int off;
 
 	if (!n)
 		return NULL;
@@ -1200,11 +1208,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 
 	copy_skb_header(n, skb);
 
-	off                  = newheadroom - oldheadroom;
-	if (n->ip_summed == CHECKSUM_PARTIAL)
-		n->csum_start += off;
-
-	skb_headers_offset_update(n, off);
+	skb_headers_offset_update(n, newheadroom - oldheadroom);
 
 	return n;
 }
@@ -1256,6 +1260,29 @@ free_skb:
 }
 EXPORT_SYMBOL(skb_pad);
 
+/**
+ *	pskb_put - add data to the tail of a potentially fragmented buffer
+ *	@skb: start of the buffer to use
+ *	@tail: tail fragment of the buffer to use
+ *	@len: amount of data to add
+ *
+ *	This function extends the used data area of the potentially
+ *	fragmented buffer. @tail must be the last fragment of @skb -- or
+ *	@skb itself. If this would exceed the total buffer size the kernel
+ *	will panic. A pointer to the first byte of the extra data is
+ *	returned.
+ */
+
+unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
+{
+	if (tail != skb) {
+		skb->data_len += len;
+		skb->len += len;
+	}
+	return skb_put(tail, len);
+}
+EXPORT_SYMBOL_GPL(pskb_put);
+
 /**
  *	skb_put - add data to a buffer
  *	@skb: buffer to use
@@ -1933,9 +1960,8 @@ fault:
 EXPORT_SYMBOL(skb_store_bits);
 
 /* Checksum skb data. */
-
-__wsum skb_checksum(const struct sk_buff *skb, int offset,
-			  int len, __wsum csum)
+__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
+		      __wsum csum, const struct skb_checksum_ops *ops)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -1946,7 +1972,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		csum = csum_partial(skb->data + offset, copy, csum);
+		csum = ops->update(skb->data + offset, copy, csum);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -1967,10 +1993,10 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 			if (copy > len)
 				copy = len;
 			vaddr = kmap_atomic(skb_frag_page(frag));
-			csum2 = csum_partial(vaddr + frag->page_offset +
-					     offset - start, copy, 0);
+			csum2 = ops->update(vaddr + frag->page_offset +
+					    offset - start, copy, 0);
 			kunmap_atomic(vaddr);
-			csum = csum_block_add(csum, csum2, pos);
+			csum = ops->combine(csum, csum2, pos, copy);
 			if (!(len -= copy))
 				return csum;
 			offset += copy;
@@ -1989,9 +2015,9 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 			__wsum csum2;
 			if (copy > len)
 				copy = len;
-			csum2 = skb_checksum(frag_iter, offset - start,
-					     copy, 0);
-			csum = csum_block_add(csum, csum2, pos);
+			csum2 = __skb_checksum(frag_iter, offset - start,
+					       copy, 0, ops);
+			csum = ops->combine(csum, csum2, pos, copy);
 			if ((len -= copy) == 0)
 				return csum;
 			offset += copy;
@@ -2003,6 +2029,18 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 
 	return csum;
 }
+EXPORT_SYMBOL(__skb_checksum);
+
+__wsum skb_checksum(const struct sk_buff *skb, int offset,
+		    int len, __wsum csum)
+{
+	const struct skb_checksum_ops ops = {
+		.update  = csum_partial_ext,
+		.combine = csum_block_add_ext,
+	};
+
+	return __skb_checksum(skb, offset, len, csum, &ops);
+}
 EXPORT_SYMBOL(skb_checksum);
 
 /* Both of above in one bottle. */
@@ -2522,14 +2560,14 @@ EXPORT_SYMBOL(skb_prepare_seq_read);
  * @data: destination pointer for data to be returned
  * @st: state variable
  *
- * Reads a block of skb data at &consumed relative to the
+ * Reads a block of skb data at @consumed relative to the
  * lower offset specified to skb_prepare_seq_read(). Assigns
- * the head of the data block to &data and returns the length
+ * the head of the data block to @data and returns the length
  * of the block or 0 if the end of the skb data or the upper
  * offset has been reached.
  *
  * The caller is not required to consume all of the data
- * returned, i.e. &consumed is typically set to the number
+ * returned, i.e. @consumed is typically set to the number
  * of bytes already consumed and the next call to
  * skb_seq_read() will return the remaining part of the block.
  *
@@ -2758,6 +2796,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
 	struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
+	skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
 	unsigned int mss = skb_shinfo(skb)->gso_size;
 	unsigned int doffset = skb->data - skb_mac_header(skb);
 	unsigned int offset = doffset;
@@ -2797,16 +2836,38 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		if (hsize > len || !sg)
 			hsize = len;
 
-		if (!hsize && i >= nfrags) {
-			BUG_ON(fskb->len != len);
+		if (!hsize && i >= nfrags && skb_headlen(fskb) &&
+		    (skb_headlen(fskb) == len || sg)) {
+			BUG_ON(skb_headlen(fskb) > len);
+
+			i = 0;
+			nfrags = skb_shinfo(fskb)->nr_frags;
+			skb_frag = skb_shinfo(fskb)->frags;
+			pos += skb_headlen(fskb);
+
+			while (pos < offset + len) {
+				BUG_ON(i >= nfrags);
+
+				size = skb_frag_size(skb_frag);
+				if (pos + size > offset + len)
+					break;
+
+				i++;
+				pos += size;
+				skb_frag++;
+			}
 
-			pos += len;
 			nskb = skb_clone(fskb, GFP_ATOMIC);
 			fskb = fskb->next;
 
 			if (unlikely(!nskb))
 				goto err;
 
+			if (unlikely(pskb_trim(nskb, len))) {
+				kfree_skb(nskb);
+				goto err;
+			}
+
 			hsize = skb_end_offset(nskb);
 			if (skb_cow_head(nskb, doffset + headroom)) {
 				kfree_skb(nskb);
@@ -2837,20 +2898,13 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		__copy_skb_header(nskb, skb);
 		nskb->mac_len = skb->mac_len;
 
-		/* nskb and skb might have different headroom */
-		if (nskb->ip_summed == CHECKSUM_PARTIAL)
-			nskb->csum_start += skb_headroom(nskb) - headroom;
-
-		skb_reset_mac_header(nskb);
-		skb_set_network_header(nskb, skb->mac_len);
-		nskb->transport_header = (nskb->network_header +
-					  skb_network_header_len(skb));
+		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
 
 		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
 						 doffset + tnl_hlen);
 
-		if (fskb != skb_shinfo(skb)->frag_list)
+		if (nskb->len == len + doffset)
 			goto perform_csum_check;
 
 		if (!sg) {
@@ -2868,8 +2922,28 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 
 		skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
 
-		while (pos < offset + len && i < nfrags) {
-			*frag = skb_shinfo(skb)->frags[i];
+		while (pos < offset + len) {
+			if (i >= nfrags) {
+				BUG_ON(skb_headlen(fskb));
+
+				i = 0;
+				nfrags = skb_shinfo(fskb)->nr_frags;
+				skb_frag = skb_shinfo(fskb)->frags;
+
+				BUG_ON(!nfrags);
+
+				fskb = fskb->next;
+			}
+
+			if (unlikely(skb_shinfo(nskb)->nr_frags >=
+				     MAX_SKB_FRAGS)) {
+				net_warn_ratelimited(
+					"skb_segment: too many frags: %u %u\n",
+					pos, mss);
+				goto err;
+			}
+
+			*frag = *skb_frag;
 			__skb_frag_ref(frag);
 			size = skb_frag_size(frag);
 
@@ -2882,6 +2956,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 
 			if (pos + size <= offset + len) {
 				i++;
+				skb_frag++;
 				pos += size;
 			} else {
 				skb_frag_size_sub(frag, pos + size - (offset + len));
@@ -2891,25 +2966,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 			frag++;
 		}
 
-		if (pos < offset + len) {
-			struct sk_buff *fskb2 = fskb;
-
-			BUG_ON(pos + fskb->len != offset + len);
-
-			pos += fskb->len;
-			fskb = fskb->next;
-
-			if (fskb2->next) {
-				fskb2 = skb_clone(fskb2, GFP_ATOMIC);
-				if (!fskb2)
-					goto err;
-			} else
-				skb_get(fskb2);
-
-			SKB_FRAG_ASSERT(nskb);
-			skb_shinfo(nskb)->frag_list = fskb2;
-		}
-
 skip_fraglist:
 		nskb->data_len = len - hsize;
 		nskb->len += nskb->data_len;
@@ -2936,32 +2992,30 @@ EXPORT_SYMBOL_GPL(skb_segment);
 
 int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
-	struct sk_buff *p = *head;
-	struct sk_buff *nskb;
-	struct skb_shared_info *skbinfo = skb_shinfo(skb);
-	struct skb_shared_info *pinfo = skb_shinfo(p);
-	unsigned int headroom;
-	unsigned int len = skb_gro_len(skb);
+	struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
 	unsigned int offset = skb_gro_offset(skb);
 	unsigned int headlen = skb_headlen(skb);
+	struct sk_buff *nskb, *lp, *p = *head;
+	unsigned int len = skb_gro_len(skb);
 	unsigned int delta_truesize;
+	unsigned int headroom;
 
-	if (p->len + len >= 65536)
+	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
 
-	if (pinfo->frag_list)
-		goto merge;
-	else if (headlen <= offset) {
+	lp = NAPI_GRO_CB(p)->last ?: p;
+	pinfo = skb_shinfo(lp);
+
+	if (headlen <= offset) {
 		skb_frag_t *frag;
 		skb_frag_t *frag2;
 		int i = skbinfo->nr_frags;
 		int nr_frags = pinfo->nr_frags + i;
 
-		offset -= headlen;
-
 		if (nr_frags > MAX_SKB_FRAGS)
-			return -E2BIG;
+			goto merge;
 
+		offset -= headlen;
 		pinfo->nr_frags = nr_frags;
 		skbinfo->nr_frags = 0;
 
@@ -2992,7 +3046,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		unsigned int first_offset;
 
 		if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)
-			return -E2BIG;
+			goto merge;
 
 		first_offset = skb->data -
 			       (unsigned char *)page_address(page) +
@@ -3010,7 +3064,10 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
 		NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
 		goto done;
-	} else if (skb_gro_len(p) != pinfo->gso_size)
+	}
+	if (pinfo->frag_list)
+		goto merge;
+	if (skb_gro_len(p) != pinfo->gso_size)
 		return -E2BIG;
 
 	headroom = skb_headroom(p);
@@ -3062,16 +3119,24 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	NAPI_GRO_CB(p)->last->next = skb;
+	if (!NAPI_GRO_CB(p)->last)
+		skb_shinfo(p)->frag_list = skb;
+	else
+		NAPI_GRO_CB(p)->last->next = skb;
 	NAPI_GRO_CB(p)->last = skb;
 	skb_header_release(skb);
+	lp = p;
 
 done:
 	NAPI_GRO_CB(p)->count++;
 	p->data_len += len;
 	p->truesize += delta_truesize;
 	p->len += len;
-
+	if (lp != p) {
+		lp->data_len += len;
+		lp->truesize += delta_truesize;
+		lp->len += len;
+	}
 	NAPI_GRO_CB(skb)->same_flow = 1;
 	return 0;
 }
@@ -3519,6 +3584,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
+	skb->local_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
 	secpath_reset(skb);

net/core/sock.c

@@ -475,12 +475,6 @@ discard_and_relse:
 }
 EXPORT_SYMBOL(sk_receive_skb);
 
-void sk_reset_txq(struct sock *sk)
-{
-	sk_tx_queue_clear(sk);
-}
-EXPORT_SYMBOL(sk_reset_txq);
-
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
 {
 	struct dst_entry *dst = __sk_dst_get(sk);
@@ -888,7 +882,7 @@ set_rcvbuf:
 
 	case SO_PEEK_OFF:
 		if (sock->ops->set_peek_off)
-			sock->ops->set_peek_off(sk, val);
+			ret = sock->ops->set_peek_off(sk, val);
 		else
 			ret = -EOPNOTSUPP;
 		break;
@@ -914,6 +908,13 @@ set_rcvbuf:
 		}
 		break;
 #endif
+
+	case SO_MAX_PACING_RATE:
+		sk->sk_max_pacing_rate = val;
+		sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+					 sk->sk_max_pacing_rate);
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1177,6 +1178,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 #endif
 
+	case SO_MAX_PACING_RATE:
+		v.val = sk->sk_max_pacing_rate;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1836,7 +1841,17 @@ EXPORT_SYMBOL(sock_alloc_send_skb);
 /* On 32bit arches, an skb frag is limited to 2^15 */
 #define SKB_FRAG_PAGE_ORDER	get_order(32768)
 
-bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+/**
+ * skb_page_frag_refill - check that a page_frag contains enough room
+ * @sz: minimum size of the fragment we want to get
+ * @pfrag: pointer to page_frag
+ * @prio: priority for memory allocation
+ *
+ * Note: While this allocator tries to use high order pages, there is
+ * no guarantee that allocations succeed. Therefore, @sz MUST be
+ * less or equal than PAGE_SIZE.
+ */
+bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
 {
 	int order;
 
@@ -1845,16 +1860,16 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 			pfrag->offset = 0;
 			return true;
 		}
-		if (pfrag->offset < pfrag->size)
+		if (pfrag->offset + sz <= pfrag->size)
 			return true;
 		put_page(pfrag->page);
 	}
 
 	/* We restrict high order allocations to users that can afford to wait */
-	order = (sk->sk_allocation & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
+	order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
 
 	do {
-		gfp_t gfp = sk->sk_allocation;
+		gfp_t gfp = prio;
 
 		if (order)
 			gfp |= __GFP_COMP | __GFP_NOWARN;
@@ -1866,6 +1881,15 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 		}
 	} while (--order >= 0);
 
+	return false;
+}
+EXPORT_SYMBOL(skb_page_frag_refill);
+
+bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+{
+	if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
+		return true;
+
 	sk_enter_memory_pressure(sk);
 	sk_stream_moderate_sndbuf(sk);
 	return false;
@@ -2319,6 +2343,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_ll_usec		=	sysctl_net_busy_read;
 #endif
 
+	sk->sk_max_pacing_rate = ~0U;
+	sk->sk_pacing_rate = ~0U;
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)

net/core/utils.c

@@ -338,3 +338,52 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 				  csum_unfold(*sum)));
 }
 EXPORT_SYMBOL(inet_proto_csum_replace16);
+
+struct __net_random_once_work {
+	struct work_struct work;
+	struct static_key *key;
+};
+
+static void __net_random_once_deferred(struct work_struct *w)
+{
+	struct __net_random_once_work *work =
+		container_of(w, struct __net_random_once_work, work);
+	if (!static_key_enabled(work->key))
+		static_key_slow_inc(work->key);
+	kfree(work);
+}
+
+static void __net_random_once_disable_jump(struct static_key *key)
+{
+	struct __net_random_once_work *w;
+
+	w = kmalloc(sizeof(*w), GFP_ATOMIC);
+	if (!w)
+		return;
+
+	INIT_WORK(&w->work, __net_random_once_deferred);
+	w->key = key;
+	schedule_work(&w->work);
+}
+
+bool __net_get_random_once(void *buf, int nbytes, bool *done,
+			   struct static_key *done_key)
+{
+	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock, flags);
+	if (*done) {
+		spin_unlock_irqrestore(&lock, flags);
+		return false;
+	}
+
+	get_random_bytes(buf, nbytes);
+	*done = true;
+	spin_unlock_irqrestore(&lock, flags);
+
+	__net_random_once_disable_jump(done_key);
+
+	return true;
+}
+EXPORT_SYMBOL(__net_get_random_once);