Merge branch 'net-first-round-to-use-dev_net_rcu'

Eric Dumazet says:

====================
net: first round to use dev_net_rcu()

dev_net(dev) should either be protected by RTNL or RCU.

There is no LOCKDEP support yet for this helper.

Adding it would trigger too many splats.

Instead, add dev_net_rcu() for rcu_read_lock() contexts
and start to use it to fix bugs and clearly document the
safety requirements.

v4: https://lore.kernel.org/CANn89i+AozhFhZNK0Y4e_EqXV1=[e-mail]
v3: https://lore.kernel.org/[e-mail]/
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/linux/netdevice.h

···
 }
 
 static inline
+struct net *dev_net_rcu(const struct net_device *dev)
+{
+	return read_pnet_rcu(&dev->nd_net);
+}
+
+static inline
 void dev_net_set(struct net_device *dev, struct net *net)
 {
 	write_pnet(&dev->nd_net, net);

include/net/ip.h

···
 						    bool forwarding)
 {
 	const struct rtable *rt = dst_rtable(dst);
-	struct net *net = dev_net(dst->dev);
-	unsigned int mtu;
+	unsigned int mtu, res;
+	struct net *net;
 
+	rcu_read_lock();
+
+	net = dev_net_rcu(dst->dev);
 	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding) {
···
 out:
 	mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+	res = mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+
+	rcu_read_unlock();
+
+	return res;
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,

include/net/net_namespace.h

···
 #endif
 }
 
-static inline struct net *read_pnet_rcu(possible_net_t *pnet)
+static inline struct net *read_pnet_rcu(const possible_net_t *pnet)
 {
 #ifdef CONFIG_NET_NS
 	return rcu_dereference(pnet->net);

include/net/route.h

···
 static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 {
 	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
-	struct net *net = dev_net(dst->dev);
 
-	if (hoplimit == 0)
+	if (hoplimit == 0) {
+		const struct net *net;
+
+		rcu_read_lock();
+		net = dev_net_rcu(dst->dev);
 		hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
+		rcu_read_unlock();
+	}
 	return hoplimit;
 }
 

net/core/flow_dissector.c

···
 					      FLOW_DISSECTOR_KEY_BASIC,
 					      target_container);
 
+	rcu_read_lock();
+
 	if (skb) {
 		if (!net) {
 			if (skb->dev)
-				net = dev_net(skb->dev);
+				net = dev_net_rcu(skb->dev);
 			else if (skb->sk)
 				net = sock_net(skb->sk);
 		}
···
 		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
 		struct bpf_prog_array *run_array;
 
-		rcu_read_lock();
 		run_array = rcu_dereference(init_net.bpf.run_array[type]);
 		if (!run_array)
 			run_array = rcu_dereference(net->bpf.run_array[type]);
···
 			prog = READ_ONCE(run_array->items[0].prog);
 			result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
 						  hlen, flags);
-			if (result == BPF_FLOW_DISSECTOR_CONTINUE)
-				goto dissect_continue;
-			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
-						 target_container);
-			rcu_read_unlock();
-			return result == BPF_OK;
+			if (result != BPF_FLOW_DISSECTOR_CONTINUE) {
+				__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
+							 target_container);
+				rcu_read_unlock();
+				return result == BPF_OK;
+			}
 		}
-dissect_continue:
-		rcu_read_unlock();
 	}
+
+	rcu_read_unlock();
 
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_ETH_ADDRS)) {

net/ipv4/devinet.c

···
 	__be32 addr = 0;
 	unsigned char localnet_scope = RT_SCOPE_HOST;
 	struct in_device *in_dev;
-	struct net *net = dev_net(dev);
+	struct net *net;
 	int master_idx;
 
 	rcu_read_lock();
+	net = dev_net_rcu(dev);
 	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev)
 		goto no_in_dev;

net/ipv4/icmp.c

···
 
 static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 {
-	struct ipcm_cookie ipc;
 	struct rtable *rt = skb_rtable(skb);
-	struct net *net = dev_net(rt->dst.dev);
+	struct net *net = dev_net_rcu(rt->dst.dev);
 	bool apply_ratelimit = false;
+	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct sock *sk;
 	struct inet_sock *inet;
···
 	struct sock *sk;
 
 	if (!rt)
-		goto out;
+		return;
+
+	rcu_read_lock();
 
 	if (rt->dst.dev)
-		net = dev_net(rt->dst.dev);
+		net = dev_net_rcu(rt->dst.dev);
 	else if (skb_in->dev)
-		net = dev_net(skb_in->dev);
+		net = dev_net_rcu(skb_in->dev);
 	else
 		goto out;
 
···
 	icmp_xmit_unlock(sk);
 out_bh_enable:
 	local_bh_enable();
-out:;
+out:
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(__icmp_send);
 
···
 	 * avoid additional coding at protocol handlers.
 	 */
 	if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) {
-		__ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
+		__ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS);
 		return;
 	}
 
···
 	struct net *net;
 	u32 info = 0;
 
-	net = dev_net(skb_dst(skb)->dev);
+	net = dev_net_rcu(skb_dst(skb)->dev);
 
 	/*
 	 *	Incomplete header ?
···
 static enum skb_drop_reason icmp_redirect(struct sk_buff *skb)
 {
 	if (skb->len < sizeof(struct iphdr)) {
-		__ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
+		__ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS);
 		return SKB_DROP_REASON_PKT_TOO_SMALL;
 	}
 
···
 	struct icmp_bxm icmp_param;
 	struct net *net;
 
-	net = dev_net(skb_dst(skb)->dev);
+	net = dev_net_rcu(skb_dst(skb)->dev);
 	/* should there be an ICMP stat for ignored echos? */
 	if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
 		return SKB_NOT_DROPPED_YET;
···
 
 bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
 {
+	struct net *net = dev_net_rcu(skb->dev);
 	struct icmp_ext_hdr *ext_hdr, _ext_hdr;
 	struct icmp_ext_echo_iio *iio, _iio;
-	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *in6_dev;
 	struct in_device *in_dev;
 	struct net_device *dev;
···
 	return SKB_NOT_DROPPED_YET;
 
 out_err:
-	__ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
+	__ICMP_INC_STATS(dev_net_rcu(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
 	return SKB_DROP_REASON_PKT_TOO_SMALL;
 }
 
···
 {
 	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct rtable *rt = skb_rtable(skb);
-	struct net *net = dev_net(rt->dst.dev);
+	struct net *net = dev_net_rcu(rt->dst.dev);
 	struct icmphdr *icmph;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
···
 	struct iphdr *iph = (struct iphdr *)skb->data;
 	int offset = iph->ihl<<2;
 	struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
+	struct net *net = dev_net_rcu(skb->dev);
 	int type = icmp_hdr(skb)->type;
 	int code = icmp_hdr(skb)->code;
-	struct net *net = dev_net(skb->dev);
 
 	/*
 	 * Use ping_err to handle all icmp errors except those

net/ipv4/route.c

···
 
 static inline bool rt_is_expired(const struct rtable *rth)
 {
-	return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
+	bool res;
+
+	rcu_read_lock();
+	res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev));
+	rcu_read_unlock();
+
+	return res;
 }
 
 void rt_cache_flush(struct net *net)
···
 static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
-	struct net *net = dev_net(dst->dev);
 	struct fib_result res;
 	bool lock = false;
+	struct net *net;
 	u32 old_mtu;
 
 	if (ip_mtu_locked(dst))
···
 	if (old_mtu < mtu)
 		return;
 
+	rcu_read_lock();
+	net = dev_net_rcu(dst->dev);
 	if (mtu < net->ipv4.ip_rt_min_pmtu) {
 		lock = true;
 		mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
···
 
 	if (rt->rt_pmtu == mtu && !lock &&
 	    time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2))
-		return;
+		goto out;
 
-	rcu_read_lock();
 	if (fib_lookup(net, fl4, &res, 0) == 0) {
 		struct fib_nh_common *nhc;
 
···
 				update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 						      jiffies + net->ipv4.ip_rt_mtu_expires);
 			}
-			rcu_read_unlock();
-			return;
+			goto out;
 		}
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 		nhc = FIB_RES_NHC(res);
 		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + net->ipv4.ip_rt_mtu_expires);
 	}
+out:
 	rcu_read_unlock();
 }
 
···
 
 static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 {
-	struct net *net = dev_net(dst->dev);
 	unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
-	unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
-				    net->ipv4.ip_rt_min_advmss);
+	unsigned int advmss;
+	struct net *net;
+
+	rcu_read_lock();
+	net = dev_net_rcu(dst->dev);
+	advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
+				   net->ipv4.ip_rt_min_advmss);
+	rcu_read_unlock();
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);
 }

net/ipv6/icmp.c

···
 {
 	/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
 	struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 
 	if (type == ICMPV6_PKT_TOOBIG)
 		ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
···
 
 	if (!skb->dev)
 		return;
-	net = dev_net(skb->dev);
+
+	rcu_read_lock();
+
+	net = dev_net_rcu(skb->dev);
 	mark = IP6_REPLY_MARK(net, skb->mark);
 	/*
 	 *	Make sure we respect the rules
···
 		    !(type == ICMPV6_PARAMPROB &&
 		      code == ICMPV6_UNK_OPTION &&
 		      (opt_unrec(skb, info))))
-			return;
+			goto out;
 
 		saddr = NULL;
 	}
···
 	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
 		net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
 				    &hdr->saddr, &hdr->daddr);
-		return;
+		goto out;
 	}
 
 	/*
···
 	if (is_ineligible(skb)) {
 		net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
 				    &hdr->saddr, &hdr->daddr);
-		return;
+		goto out;
 	}
 
 	/* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */
···
 	np = inet6_sk(sk);
 
 	if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit))
-		goto out;
+		goto out_unlock;
 
 	tmp_hdr.icmp6_type = type;
 	tmp_hdr.icmp6_code = code;
···
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
 	if (IS_ERR(dst))
-		goto out;
+		goto out_unlock;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
···
 		goto out_dst_release;
 	}
 
-	rcu_read_lock();
 	idev = __in6_dev_get(skb->dev);
 
 	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
···
 		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
 					   len + sizeof(struct icmp6hdr));
 	}
-	rcu_read_unlock();
+
 out_dst_release:
 	dst_release(dst);
-out:
+out_unlock:
 	icmpv6_xmit_unlock(sk);
 out_bh_enable:
 	local_bh_enable();
+out:
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(icmp6_send);
 
···
 	skb_pull(skb2, nhs);
 	skb_reset_network_header(skb2);
 
-	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
-			skb, 0);
+	rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr,
+			NULL, 0, skb, 0);
 
 	if (rt && rt->dst.dev)
 		skb2->dev = rt->dst.dev;
···
 
 static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	struct sock *sk;
 	struct inet6_dev *idev;
 	struct ipv6_pinfo *np;
···
 				   u8 code, __be32 info)
 {
 	struct inet6_skb_parm *opt = IP6CB(skb);
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	const struct inet6_protocol *ipprot;
 	enum skb_drop_reason reason;
 	int inner_offset;
···
 static int icmpv6_rcv(struct sk_buff *skb)
 {
 	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	struct net_device *dev = icmp6_dev(skb);
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	const struct in6_addr *saddr, *daddr;
···
 		skb_set_network_header(skb, nh);
 	}
 
-	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INMSGS);
+	__ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS);
 
 	saddr = &ipv6_hdr(skb)->saddr;
 	daddr = &ipv6_hdr(skb)->daddr;
···
 
 	type = hdr->icmp6_type;
 
-	ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type);
+	ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type);
 
 	switch (type) {
 	case ICMPV6_ECHO_REQUEST:
···
 
 csum_error:
 	reason = SKB_DROP_REASON_ICMP_CSUM;
-	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
+	__ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS);
 discard_it:
-	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
+	__ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS);
 drop_no_count:
 	kfree_skb_reason(skb, reason);
 	return 0;

net/ipv6/ip6_input.c

···
 static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	skb_clear_delivery_time(skb);
-	rcu_read_lock();
 	ip6_protocol_deliver_rcu(net, skb, 0, false);
-	rcu_read_unlock();
 
 	return 0;
 }
···
 
 int ip6_input(struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
-		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
-		       ip6_input_finish);
+	int res;
+
+	rcu_read_lock();
+	res = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
+		      dev_net_rcu(skb->dev), NULL, skb, skb->dev, NULL,
+		      ip6_input_finish);
+	rcu_read_unlock();
+
+	return res;
 }
 EXPORT_SYMBOL_GPL(ip6_input);
 

net/ipv6/route.c

···
 {
 	struct net_device *dev = dst->dev;
 	unsigned int mtu = dst_mtu(dst);
-	struct net *net = dev_net(dev);
+	struct net *net;
 
 	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
 
+	rcu_read_lock();
+
+	net = dev_net_rcu(dev);
 	if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
 		mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
+
+	rcu_read_unlock();
 
 	/*
 	 * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and