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

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

35 files changed, 961 insertions, 830 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index f4f19e89af5e..76bff79d6fed 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -14,7 +14,7 @@ menuconfig IPV6
 	  <https://en.wikipedia.org/wiki/IPv6>.
 	  For specific information about IPv6 under Linux, see
 	  Documentation/networking/ipv6.rst and read the HOWTO at
-	  <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/>
+	  <https://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/>
 
 	  To compile this protocol support as a module, choose M here: the
 	  module will be called ipv6.
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 840bfdb3d7bd..8e761b8c47c6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -163,7 +163,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
 
 static void addrconf_type_change(struct net_device *dev,
 				 unsigned long event);
-static int addrconf_ifdown(struct net_device *dev, int how);
+static int addrconf_ifdown(struct net_device *dev, bool unregister);
 
 static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 						  int plen,
@@ -1983,6 +1983,45 @@ int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
 }
 EXPORT_SYMBOL(ipv6_chk_prefix);
 
+/**
+ * ipv6_dev_find - find the first device with a given source address.
+ * @net: the net namespace
+ * @addr: the source address
+ *
+ * The caller should be protected by RCU, or RTNL.
+ */
+struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr)
+{
+	unsigned int hash = inet6_addr_hash(net, addr);
+	struct inet6_ifaddr *ifp, *result = NULL;
+	struct net_device *dev = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
+		if (net_eq(dev_net(ifp->idev->dev), net) &&
+		    ipv6_addr_equal(&ifp->addr, addr)) {
+			result = ifp;
+			break;
+		}
+	}
+
+	if (!result) {
+		struct rt6_info *rt;
+
+		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
+		if (rt) {
+			dev = rt->dst.dev;
+			ip6_rt_put(rt);
+		}
+	} else {
+		dev = result->idev->dev;
+	}
+	rcu_read_unlock();
+
+	return dev;
+}
+EXPORT_SYMBOL(ipv6_dev_find);
+
 struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr,
 				     struct net_device *dev, int strict)
 {
@@ -3630,7 +3669,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		 * an L3 master device (e.g., VRF)
 		 */
 		if (info->upper_dev && netif_is_l3_master(info->upper_dev))
-			addrconf_ifdown(dev, 0);
+			addrconf_ifdown(dev, false);
 	}
 
 	return NOTIFY_OK;
@@ -3663,9 +3702,9 @@ static bool addr_is_local(const struct in6_addr *addr)
 		(IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
-static int addrconf_ifdown(struct net_device *dev, int how)
+static int addrconf_ifdown(struct net_device *dev, bool unregister)
 {
-	unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN;
+	unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN;
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
 	struct inet6_ifaddr *ifa, *tmp;
@@ -3684,7 +3723,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	 * Step 1: remove reference to ipv6 device from parent device.
 	 *	   Do not dev_put!
 	 */
-	if (how) {
+	if (unregister) {
 		idev->dead = 1;
 
 		/* protected by rtnl_lock */
@@ -3698,7 +3737,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	/* combine the user config with event to determine if permanent
 	 * addresses are to be removed from address hash table
 	 */
-	if (!how && !idev->cnf.disable_ipv6) {
+	if (!unregister && !idev->cnf.disable_ipv6) {
 		/* aggregate the system setting and interface setting */
 		int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down;
 
@@ -3736,7 +3775,7 @@ restart:
 	addrconf_del_rs_timer(idev);
 
 	/* Step 2: clear flags for stateless addrconf */
-	if (!how)
+	if (!unregister)
 		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
 
 	/* Step 3: clear tempaddr list */
@@ -3806,7 +3845,7 @@ restart:
 	write_unlock_bh(&idev->lock);
 
 	/* Step 5: Discard anycast and multicast list */
-	if (how) {
+	if (unregister) {
 		ipv6_ac_destroy_dev(idev);
 		ipv6_mc_destroy_dev(idev);
 	} else {
@@ -3816,7 +3855,7 @@ restart:
 	idev->tstamp = jiffies;
 
 	/* Last: Shot the device (if unregistered) */
-	if (how) {
+	if (unregister) {
 		addrconf_sysctl_unregister(idev);
 		neigh_parms_release(&nd_tbl, idev->nd_parms);
 		neigh_ifdown(&nd_tbl, dev);
@@ -4038,7 +4077,7 @@ static void addrconf_dad_work(struct work_struct *w)
 		in6_ifa_hold(ifp);
 		addrconf_dad_stop(ifp, 1);
 		if (disable_ipv6)
-			addrconf_ifdown(idev->dev, 0);
+			addrconf_ifdown(idev->dev, false);
 		goto out;
 	}
 
@@ -7187,9 +7226,9 @@ void addrconf_cleanup(void)
 	for_each_netdev(&init_net, dev) {
 		if (__in6_dev_get(dev) == NULL)
 			continue;
-		addrconf_ifdown(dev, 1);
+		addrconf_ifdown(dev, true);
 	}
-	addrconf_ifdown(init_net.loopback_dev, 2);
+	addrconf_ifdown(init_net.loopback_dev, true);
 
 	/*
 	 *	Check hash table.
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b304b882e031..0306509ab063 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -688,8 +688,6 @@ const struct proto_ops inet6_stream_ops = {
 	.peek_len	   = tcp_peek_len,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
@@ -717,8 +715,6 @@ const struct proto_ops inet6_dgram_ops = {
 	.set_peek_off	   = sk_set_peek_off,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet6_compat_ioctl,
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
 };
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 390bedde21a5..cc8ad7ddecda 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -19,6 +19,7 @@
 #include <linux/route.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/icmp.h>
 
 #include <net/ipv6.h>
 #include <net/ndisc.h>
@@ -284,6 +285,17 @@ int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only);
 
+static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb,
+				    struct sock_ee_data_rfc4884 *out)
+{
+	switch (icmp6_hdr(skb)->icmp6_type) {
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_DEST_UNREACH:
+		ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr),
+				      icmp6_hdr(skb)->icmp6_datagram_len * 8);
+	}
+}
+
 void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		     __be16 port, u32 info, u8 *payload)
 {
@@ -313,6 +325,10 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 	serr->port = port;
 
 	__skb_pull(skb, payload - skb->data);
+
+	if (inet6_sk(sk)->recverr_rfc4884)
+		ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+
 	skb_reset_transport_header(skb);
 
 	if (sock_queue_err_skb(sk, skb))
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 5a8bbcdcaf2b..374105e4394f 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -580,7 +580,7 @@ looped_back:
 	hdr->segments_left--;
 	i = n - hdr->segments_left;
 
-	buf = kzalloc(ipv6_rpl_srh_alloc_size(n + 1) * 2, GFP_ATOMIC);
+	buf = kcalloc(struct_size(hdr, segments.addr, n + 2), 2, GFP_ATOMIC);
 	if (unlikely(!buf)) {
 		kfree_skb(skb);
 		return -1;
@@ -1232,7 +1232,6 @@ static void ipv6_renew_option(int renewtype,
  * @opt: original options
  * @newtype: option type to replace in @opt
  * @newopt: new option of type @newtype to replace (user-mem)
- * @newoptlen: length of @newopt
  *
  * Returns a new set of options which is a copy of @opt with the
  * option type @newtype replaced with @newopt.
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index fafe556d21e0..8f9a83314de7 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -13,6 +13,7 @@
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
 #include <linux/export.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/fib_rules.h>
 #include <net/ipv6.h>
@@ -111,11 +112,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	} else {
 		struct rt6_info *rt;
 
-		rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags);
+		rt = pol_lookup_func(lookup,
+			     net, net->ipv6.fib6_local_tbl, fl6, skb, flags);
 		if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN)
 			return &rt->dst;
 		ip6_rt_put_flags(rt, flags);
-		rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
+		rt = pol_lookup_func(lookup,
+			     net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
 		if (rt->dst.error != -EAGAIN)
 			return &rt->dst;
 		ip6_rt_put_flags(rt, flags);
@@ -226,7 +229,8 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 		goto out;
 	}
 
-	rt = lookup(net, table, flp6, arg->lookup_data, flags);
+	rt = pol_lookup_func(lookup,
+			     net, table, flp6, arg->lookup_data, flags);
 	if (rt != net->ipv6.ip6_null_entry) {
 		err = fib6_rule_saddr(net, rule, flags, flp6,
 				      ip6_dst_idev(&rt->dst)->dev);
@@ -252,8 +256,9 @@ out:
 	return err;
 }
 
-static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
-			    int flags, struct fib_lookup_arg *arg)
+INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule,
+					     struct flowi *flp, int flags,
+					     struct fib_lookup_arg *arg)
 {
 	if (arg->lookup_ptr == fib6_table_lookup)
 		return fib6_rule_action_alt(rule, flp, flags, arg);
@@ -261,7 +266,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 	return __fib6_rule_action(rule, flp, flags, arg);
 }
 
-static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
+INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
+						struct fib_lookup_arg *arg)
 {
 	struct fib6_result *res = arg->result;
 	struct rt6_info *rt = res->rt6;
@@ -293,7 +299,8 @@ suppress_route:
 	return true;
 }
 
-static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
+					    struct flowi *fl, int flags)
 {
 	struct fib6_rule *r = (struct fib6_rule *) rule;
 	struct flowi6 *fl6 = &fl->u.ip6;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 9df8737ae0d3..a4e4912ad607 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -439,8 +439,8 @@ static int icmp6_iif(const struct sk_buff *skb)
 /*
  *	Send an ICMP message in response to a packet in error
  */
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-		       const struct in6_addr *force_saddr)
+void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+		const struct in6_addr *force_saddr)
 {
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -625,6 +625,7 @@ out:
 out_bh_enable:
 	local_bh_enable();
 }
+EXPORT_SYMBOL(icmp6_send);
 
 /* Slightly more convenient version of icmp6_send.
  */
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index fbe9d4295eac..2d3add9e6116 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -21,6 +21,8 @@
 #include <net/ip.h>
 #include <net/sock_reuseport.h>
 
+extern struct inet_hashinfo tcp_hashinfo;
+
 u32 inet6_ehashfn(const struct net *net,
 		  const struct in6_addr *laddr, const u16 lport,
 		  const struct in6_addr *faddr, const __be16 fport)
@@ -111,6 +113,23 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
+static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
+					    struct sk_buff *skb, int doff,
+					    const struct in6_addr *saddr,
+					    __be16 sport,
+					    const struct in6_addr *daddr,
+					    unsigned short hnum)
+{
+	struct sock *reuse_sk = NULL;
+	u32 phash;
+
+	if (sk->sk_reuseport) {
+		phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
+	}
+	return reuse_sk;
+}
+
 /* called with rcu_read_lock() */
 static struct sock *inet6_lhash2_lookup(struct net *net,
 		struct inet_listen_hashbucket *ilb2,
@@ -123,21 +142,17 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
-	u32 phash = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
 		score = compute_score(sk, net, hnum, daddr, dif, sdif,
 				      exact_dif);
 		if (score > hiscore) {
-			if (sk->sk_reuseport) {
-				phash = inet6_ehashfn(net, daddr, hnum,
-						      saddr, sport);
-				result = reuseport_select_sock(sk, phash,
-							       skb, doff);
-				if (result)
-					return result;
-			}
+			result = lookup_reuseport(net, sk, skb, doff,
+						  saddr, sport, daddr, hnum);
+			if (result)
+				return result;
+
 			result = sk;
 			hiscore = score;
 		}
@@ -146,6 +161,31 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	return result;
 }
 
+static inline struct sock *inet6_lookup_run_bpf(struct net *net,
+						struct inet_hashinfo *hashinfo,
+						struct sk_buff *skb, int doff,
+						const struct in6_addr *saddr,
+						const __be16 sport,
+						const struct in6_addr *daddr,
+						const u16 hnum)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	if (hashinfo != &tcp_hashinfo)
+		return NULL; /* only TCP is supported */
+
+	no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP,
+					    saddr, sport, daddr, hnum, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+
 struct sock *inet6_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
 		struct sk_buff *skb, int doff,
@@ -157,6 +197,14 @@ struct sock *inet6_lookup_listener(struct net *net,
 	struct sock *result = NULL;
 	unsigned int hash2;
 
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
+					      saddr, sport, daddr, hnum);
+		if (result)
+			goto done;
+	}
+
 	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 49ee89bbcba0..25a90f3f705c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -314,7 +314,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 {
 	struct rt6_info *rt;
 
-	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
+	rt = pol_lookup_func(lookup,
+			net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
 	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put_flags(rt, flags);
 		rt = net->ipv6.ip6_null_entry;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 73bb047e6037..aa673a6a7e43 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -371,7 +371,7 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo
 
 static struct ip6_flowlabel *
 fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
-	  char __user *optval, int optlen, int *err_p)
+	  sockptr_t optval, int optlen, int *err_p)
 {
 	struct ip6_flowlabel *fl = NULL;
 	int olen;
@@ -401,7 +401,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		memset(fl->opt, 0, sizeof(*fl->opt));
 		fl->opt->tot_len = sizeof(*fl->opt) + olen;
 		err = -EFAULT;
-		if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen))
+		if (copy_from_sockptr_offset(fl->opt + 1, optval,
+				CMSG_ALIGN(sizeof(*freq)), olen))
 			goto done;
 
 		msg.msg_controllen = olen;
@@ -533,187 +534,212 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
 	return -ENOENT;
 }
 
-int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
+#define socklist_dereference(__sflp) \
+	rcu_dereference_protected(__sflp, lockdep_is_held(&ip6_sk_fl_lock))
+
+static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq)
 {
-	int err;
-	struct net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct in6_flowlabel_req freq;
-	struct ipv6_fl_socklist *sfl1 = NULL;
-	struct ipv6_fl_socklist *sfl;
 	struct ipv6_fl_socklist __rcu **sflp;
-	struct ip6_flowlabel *fl, *fl1 = NULL;
+	struct ipv6_fl_socklist *sfl;
 
+	if (freq->flr_flags & IPV6_FL_F_REFLECT) {
+		if (sk->sk_protocol != IPPROTO_TCP)
+			return -ENOPROTOOPT;
+		if (!np->repflow)
+			return -ESRCH;
+		np->flow_label = 0;
+		np->repflow = 0;
+		return 0;
+	}
 
-	if (optlen < sizeof(freq))
-		return -EINVAL;
+	spin_lock_bh(&ip6_sk_fl_lock);
+	for (sflp = &np->ipv6_fl_list;
+	     (sfl = socklist_dereference(*sflp)) != NULL;
+	     sflp = &sfl->next) {
+		if (sfl->fl->label == freq->flr_label)
+			goto found;
+	}
+	spin_unlock_bh(&ip6_sk_fl_lock);
+	return -ESRCH;
+found:
+	if (freq->flr_label == (np->flow_label & IPV6_FLOWLABEL_MASK))
+		np->flow_label &= ~IPV6_FLOWLABEL_MASK;
+	*sflp = sfl->next;
+	spin_unlock_bh(&ip6_sk_fl_lock);
+	fl_release(sfl->fl);
+	kfree_rcu(sfl, rcu);
+	return 0;
+}
 
-	if (copy_from_user(&freq, optval, sizeof(freq)))
-		return -EFAULT;
+static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net *net = sock_net(sk);
+	struct ipv6_fl_socklist *sfl;
+	int err;
 
-	switch (freq.flr_action) {
-	case IPV6_FL_A_PUT:
-		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
-			if (sk->sk_protocol != IPPROTO_TCP)
-				return -ENOPROTOOPT;
-			if (!np->repflow)
-				return -ESRCH;
-			np->flow_label = 0;
-			np->repflow = 0;
-			return 0;
-		}
-		spin_lock_bh(&ip6_sk_fl_lock);
-		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference_protected(*sflp,
-						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
-		     sflp = &sfl->next) {
-			if (sfl->fl->label == freq.flr_label) {
-				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
-					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = sfl->next;
-				spin_unlock_bh(&ip6_sk_fl_lock);
-				fl_release(sfl->fl);
-				kfree_rcu(sfl, rcu);
-				return 0;
-			}
+	rcu_read_lock_bh();
+	for_each_sk_fl_rcu(np, sfl) {
+		if (sfl->fl->label == freq->flr_label) {
+			err = fl6_renew(sfl->fl, freq->flr_linger,
+					freq->flr_expires);
+			rcu_read_unlock_bh();
+			return err;
 		}
-		spin_unlock_bh(&ip6_sk_fl_lock);
-		return -ESRCH;
+	}
+	rcu_read_unlock_bh();
 
-	case IPV6_FL_A_RENEW:
-		rcu_read_lock_bh();
-		for_each_sk_fl_rcu(np, sfl) {
-			if (sfl->fl->label == freq.flr_label) {
-				err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires);
-				rcu_read_unlock_bh();
-				return err;
-			}
-		}
-		rcu_read_unlock_bh();
+	if (freq->flr_share == IPV6_FL_S_NONE &&
+	    ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		struct ip6_flowlabel *fl = fl_lookup(net, freq->flr_label);
 
-		if (freq.flr_share == IPV6_FL_S_NONE &&
-		    ns_capable(net->user_ns, CAP_NET_ADMIN)) {
-			fl = fl_lookup(net, freq.flr_label);
-			if (fl) {
-				err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
-				fl_release(fl);
-				return err;
-			}
+		if (fl) {
+			err = fl6_renew(fl, freq->flr_linger,
+					freq->flr_expires);
+			fl_release(fl);
+			return err;
 		}
-		return -ESRCH;
-
-	case IPV6_FL_A_GET:
-		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
-			struct net *net = sock_net(sk);
-			if (net->ipv6.sysctl.flowlabel_consistency) {
-				net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
-				return -EPERM;
-			}
+	}
+	return -ESRCH;
+}
 
-			if (sk->sk_protocol != IPPROTO_TCP)
-				return -ENOPROTOOPT;
+static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq,
+		sockptr_t optval, int optlen)
+{
+	struct ipv6_fl_socklist *sfl, *sfl1 = NULL;
+	struct ip6_flowlabel *fl, *fl1 = NULL;
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net *net = sock_net(sk);
+	int err;
 
-			np->repflow = 1;
-			return 0;
+	if (freq->flr_flags & IPV6_FL_F_REFLECT) {
+		if (net->ipv6.sysctl.flowlabel_consistency) {
+			net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
+			return -EPERM;
 		}
 
-		if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
-			return -EINVAL;
+		if (sk->sk_protocol != IPPROTO_TCP)
+			return -ENOPROTOOPT;
+		np->repflow = 1;
+		return 0;
+	}
 
-		if (net->ipv6.sysctl.flowlabel_state_ranges &&
-		    (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
-			return -ERANGE;
+	if (freq->flr_label & ~IPV6_FLOWLABEL_MASK)
+		return -EINVAL;
+	if (net->ipv6.sysctl.flowlabel_state_ranges &&
+	    (freq->flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
+		return -ERANGE;
 
-		fl = fl_create(net, sk, &freq, optval, optlen, &err);
-		if (!fl)
-			return err;
-		sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
+	fl = fl_create(net, sk, freq, optval, optlen, &err);
+	if (!fl)
+		return err;
 
-		if (freq.flr_label) {
-			err = -EEXIST;
-			rcu_read_lock_bh();
-			for_each_sk_fl_rcu(np, sfl) {
-				if (sfl->fl->label == freq.flr_label) {
-					if (freq.flr_flags&IPV6_FL_F_EXCL) {
-						rcu_read_unlock_bh();
-						goto done;
-					}
-					fl1 = sfl->fl;
-					if (!atomic_inc_not_zero(&fl1->users))
-						fl1 = NULL;
-					break;
+	sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
+
+	if (freq->flr_label) {
+		err = -EEXIST;
+		rcu_read_lock_bh();
+		for_each_sk_fl_rcu(np, sfl) {
+			if (sfl->fl->label == freq->flr_label) {
+				if (freq->flr_flags & IPV6_FL_F_EXCL) {
+					rcu_read_unlock_bh();
+					goto done;
 				}
+				fl1 = sfl->fl;
+				if (!atomic_inc_not_zero(&fl1->users))
+					fl1 = NULL;
+				break;
 			}
-			rcu_read_unlock_bh();
+		}
+		rcu_read_unlock_bh();
 
-			if (!fl1)
-				fl1 = fl_lookup(net, freq.flr_label);
-			if (fl1) {
+		if (!fl1)
+			fl1 = fl_lookup(net, freq->flr_label);
+		if (fl1) {
 recheck:
-				err = -EEXIST;
-				if (freq.flr_flags&IPV6_FL_F_EXCL)
-					goto release;
-				err = -EPERM;
-				if (fl1->share == IPV6_FL_S_EXCL ||
-				    fl1->share != fl->share ||
-				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid != fl->owner.pid)) ||
-				    ((fl1->share == IPV6_FL_S_USER) &&
-				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
-					goto release;
-
-				err = -ENOMEM;
-				if (!sfl1)
-					goto release;
-				if (fl->linger > fl1->linger)
-					fl1->linger = fl->linger;
-				if ((long)(fl->expires - fl1->expires) > 0)
-					fl1->expires = fl->expires;
-				fl_link(np, sfl1, fl1);
-				fl_free(fl);
-				return 0;
+			err = -EEXIST;
+			if (freq->flr_flags&IPV6_FL_F_EXCL)
+				goto release;
+			err = -EPERM;
+			if (fl1->share == IPV6_FL_S_EXCL ||
+			    fl1->share != fl->share ||
+			    ((fl1->share == IPV6_FL_S_PROCESS) &&
+			     (fl1->owner.pid != fl->owner.pid)) ||
+			    ((fl1->share == IPV6_FL_S_USER) &&
+			     !uid_eq(fl1->owner.uid, fl->owner.uid)))
+				goto release;
+