Merge branch 'netns-defrag'

Eric W. Biederman says:

====================
net: Pass net into defragmentation

This is the next installment of my work to pass struct net through the
output path so the code does not need to guess how to figure out which
network namespace it is in, and ultimately routes can have output
devices in another network namespace.

In netfilter and af_packet we defragment packets in the output path,
and there is the usual amount of confusion about how to compute which
net we are processing the packets in.  This patchset clears that
confusion up by explicitly passing in struct net in ip_defrag,
ip_check_defrag, and nf_ct_frag6_gather.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 27 insertions, 26 deletions

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 47da43595ac2..86f6c6292c27 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -412,7 +412,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 
 	port = macvlan_port_get_rcu(skb->dev);
 	if (is_multicast_ether_addr(eth->h_dest)) {
-		skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
+		skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN);
 		if (!skb)
 			return RX_HANDLER_CONSUMED;
 		eth = eth_hdr(skb);
diff --git a/include/net/ip.h b/include/net/ip.h
index 3c904a28d5e5..1a98f1ca1638 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -506,11 +506,11 @@ static inline bool ip_defrag_user_in_between(u32 user,
 	return user >= lower_bond && user <= upper_bond;
 }
 
-int ip_defrag(struct sk_buff *skb, u32 user);
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #ifdef CONFIG_INET
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #else
-static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	return skb;
 }
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 27666d8a0bd0..fb7da5bb76cc 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -5,7 +5,7 @@ void nf_defrag_ipv6_enable(void);
 
 int nf_ct_frag6_init(void);
 void nf_ct_frag6_cleanup(void);
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
+struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user);
 void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9772b789adf3..5482745d5d68 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -654,11 +654,10 @@ out_fail:
 }
 
 /* Process an incoming IP datagram fragment. */
-int ip_defrag(struct sk_buff *skb, u32 user)
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
 	int vif = l3mdev_master_ifindex_rcu(dev);
-	struct net *net = dev_net(dev);
 	struct ipq *qp;
 
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
@@ -683,7 +682,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_defrag);
 
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
 	int netoff;
@@ -712,7 +711,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-			if (ip_defrag(skb, user))
+			if (ip_defrag(net, skb, user))
 				return NULL;
 			skb_clear_hash(skb);
 		}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 7cc9f7bb7fb7..b1209b63381f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -157,6 +157,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 	u8 protocol = ip_hdr(skb)->protocol;
 	struct sock *last = NULL;
 	struct net_device *dev = skb->dev;
+	struct net *net = dev_net(dev);
 
 	for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) {
 		struct sock *sk = ra->sk;
@@ -167,9 +168,9 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 		if (sk && inet_sk(sk)->inet_num == protocol &&
 		    (!sk->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == dev->ifindex) &&
-		    net_eq(sock_net(sk), dev_net(dev))) {
+		    net_eq(sock_net(sk), net)) {
 			if (ip_is_fragment(ip_hdr(skb))) {
-				if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN))
+				if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
 					return true;
 			}
 			if (last) {
@@ -246,14 +247,15 @@ int ip_local_deliver(struct sk_buff *skb)
 	/*
 	 *	Reassemble IP fragments.
 	 */
+	struct net *net = dev_net(skb->dev);
 
 	if (ip_is_fragment(ip_hdr(skb))) {
-		if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER))
+		if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
 			return 0;
 	}
 
 	return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
-		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+		       net, NULL, skb, skb->dev, NULL,
 		       ip_local_deliver_finish);
 }
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index b246346ee849..bf25f45b23d2 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,14 +22,15 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
+static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
+				   u_int32_t user)
 {
 	int err;
 
 	skb_orphan(skb);
 
 	local_bh_disable();
-	err = ip_defrag(skb, user);
+	err = ip_defrag(net, skb, user);
 	local_bh_enable();
 
 	if (!err) {
@@ -85,7 +86,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
 		enum ip_defrag_users user =
 			nf_ct_defrag_user(state->hook, skb);
 
-		if (nf_ct_ipv4_gather_frags(skb, user))
+		if (nf_ct_ipv4_gather_frags(state->net, skb, user))
 			return NF_STOLEN;
 	}
 	return NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 701cd2bae0a9..2fb86a99bf5f 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -563,12 +563,10 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
 	return 0;
 }
 
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
+struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct sk_buff *clone;
 	struct net_device *dev = skb->dev;
-	struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev)
-				       : dev_net(skb->dev);
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
 	struct ipv6hdr *hdr;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index a99baf63eccf..5173a89a238e 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -63,7 +63,8 @@ static unsigned int ipv6_defrag(void *priv,
 		return NF_ACCEPT;
 #endif
 
-	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb));
+	reasm = nf_ct_frag6_gather(state->net, skb,
+				   nf_ct6_defrag_user(state->hook, skb));
 	/* queued */
 	if (reasm == NULL)
 		return NF_STOLEN;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 37dd77a3d0fb..07a791ecdfba 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -694,7 +694,7 @@ static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs,
 	int err;
 
 	local_bh_disable();
-	err = ip_defrag(skb, user);
+	err = ip_defrag(ipvs->net, skb, user);
 	local_bh_enable();
 	if (!err)
 		ip_send_check(ip_hdr(skb));
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index eb759e3a88ca..ad614267cc2a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -304,7 +304,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 		int err;
 
 		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-		err = ip_defrag(skb, user);
+		err = ip_defrag(net, skb, user);
 		if (err)
 			return err;
 
@@ -315,7 +315,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 		struct sk_buff *reasm;
 
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
-		reasm = nf_ct_frag6_gather(skb, user);
+		reasm = nf_ct_frag6_gather(net, skb, user);
 		if (!reasm)
 			return -EINPROGRESS;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 396b3f1e7cc0..691660b9b7ef 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1439,17 +1439,17 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 {
 	struct packet_fanout *f = pt->af_packet_priv;
 	unsigned int num = READ_ONCE(f->num_members);
+	struct net *net = read_pnet(&f->net);
 	struct packet_sock *po;
 	unsigned int idx;
 
-	if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
-	    !num) {
+	if (!net_eq(dev_net(dev), net) || !num) {
 		kfree_skb(skb);
 		return 0;
 	}
 
 	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
-		skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
+		skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
 		if (!skb)
 			return 0;
 	}