1 files changed, 324 insertions, 91 deletions

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 84e37b1ca9e1..cb664f6e3558 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Operations on the network namespace
  */
@@ -5,24 +6,43 @@
 #define __NET_NET_NAMESPACE_H
 
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <linux/sysctl.h>
+#include <linux/uidgid.h>
 
+#include <net/flow.h>
 #include <net/netns/core.h>
 #include <net/netns/mib.h>
 #include <net/netns/unix.h>
 #include <net/netns/packet.h>
 #include <net/netns/ipv4.h>
 #include <net/netns/ipv6.h>
+#include <net/netns/nexthop.h>
+#include <net/netns/ieee802154_6lowpan.h>
 #include <net/netns/sctp.h>
-#include <net/netns/dccp.h>
 #include <net/netns/netfilter.h>
-#include <net/netns/x_tables.h>
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netns/conntrack.h>
 #endif
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+#include <net/netns/flow_table.h>
+#endif
+#include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
+#include <net/netns/mpls.h>
+#include <net/netns/can.h>
+#include <net/netns/xdp.h>
+#include <net/netns/smc.h>
+#include <net/netns/bpf.h>
+#include <net/netns/mctp.h>
+#include <net/net_trackers.h>
+#include <linux/ns_common.h>
+#include <linux/idr.h>
+#include <linux/skbuff.h>
+#include <linux/notifier.h>
+#include <linux/xarray.h>
 
 struct user_namespace;
 struct proc_dir_entry;
@@ -30,35 +50,55 @@ struct net_device;
 struct sock;
 struct ctl_table_header;
 struct net_generic;
-struct sock;
+struct uevent_sock;
 struct netns_ipvs;
+struct bpf_prog;
 
 
 #define NETDEV_HASHBITS    8
 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
 
 struct net {
-	atomic_t		passive;	/* To decided when the network
+	/* First cache line can be often dirtied.
+	 * Do not place here read-mostly fields.
+	 */
+	refcount_t		passive;	/* To decide when the network
 						 * namespace should be freed.
 						 */
-	atomic_t		count;		/* To decided when the network
-						 *  namespace should be shut down.
-						 */
-#ifdef NETNS_REFCNT_DEBUG
-	atomic_t		use_count;	/* To track references we
-						 * destroy on demand
-						 */
-#endif
 	spinlock_t		rules_mod_lock;
 
-	struct list_head	list;		/* list of network namespaces */
-	struct list_head	cleanup_list;	/* namespaces on death row */
-	struct list_head	exit_list;	/* Use only net_mutex */
+	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
+	u32			ifindex;
 
-	struct user_namespace   *user_ns;	/* Owning user namespace */
+	spinlock_t		nsid_lock;
+	atomic_t		fnhe_genid;
+
+	struct list_head	list;		/* list of network namespaces */
+	struct list_head	exit_list;	/* To linked to call pernet exit
+						 * methods on dead net (
+						 * pernet_ops_rwsem read locked),
+						 * or to unregister pernet ops
+						 * (pernet_ops_rwsem write locked).
+						 */
+	struct llist_node	defer_free_list;
+	struct llist_node	cleanup_list;	/* namespaces on death row */
 
-	unsigned int		proc_inum;
+	struct list_head ptype_all;
+	struct list_head ptype_specific;
 
+#ifdef CONFIG_KEYS
+	struct key_tag		*key_domain;	/* Key domain of operation tag */
+#endif
+	struct user_namespace   *user_ns;	/* Owning user namespace */
+	struct ucounts		*ucounts;
+	struct idr		netns_ids;
+
+	struct ns_common	ns;
+	struct ref_tracker_dir  refcnt_tracker;
+	struct ref_tracker_dir  notrefcnt_tracker; /* tracker for objects not
+						    * refcounted against netns
+						    */
+	struct list_head 	dev_base_head;
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
 
@@ -69,67 +109,94 @@ struct net {
 	struct sock 		*rtnl;			/* rtnetlink socket */
 	struct sock		*genl_sock;
 
-	struct list_head 	dev_base_head;
+	struct uevent_sock	*uevent_sock;		/* uevent socket */
+
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
-	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
-	int			ifindex;
+	struct xarray		dev_by_index;
+	struct raw_notifier_head	netdev_chain;
+
+	/* Note that @hash_mix can be read millions times per second,
+	 * it is critical that it is on a read_mostly cache line.
+	 */
+	u32			hash_mix;
+
+	struct net_device       *loopback_dev;          /* The loopback */
 
 	/* core fib_rules */
 	struct list_head	rules_ops;
 
-
-	struct net_device       *loopback_dev;          /* The loopback */
 	struct netns_core	core;
 	struct netns_mib	mib;
 	struct netns_packet	packet;
+#if IS_ENABLED(CONFIG_UNIX)
 	struct netns_unix	unx;
+#endif
+	struct netns_nexthop	nexthop;
 	struct netns_ipv4	ipv4;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct netns_ipv6	ipv6;
 #endif
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	struct netns_ieee802154_lowpan	ieee802154_lowpan;
+#endif
 #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE)
 	struct netns_sctp	sctp;
 #endif
-#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
-	struct netns_dccp	dccp;
-#endif
 #ifdef CONFIG_NETFILTER
 	struct netns_nf		nf;
-	struct netns_xt		xt;
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct netns_ct		ct;
 #endif
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-	struct netns_nf_frag	nf_frag;
+#if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE)
+	struct netns_nftables	nft;
+#endif
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	struct netns_ft ft;
 #endif
-	struct sock		*nfnl;
-	struct sock		*nfnl_stash;
 #endif
 #ifdef CONFIG_WEXT_CORE
 	struct sk_buff_head	wext_nlevents;
 #endif
 	struct net_generic __rcu	*gen;
 
+	/* Used to store attached BPF programs */
+	struct netns_bpf	bpf;
+
 	/* Note : following structs are cache line aligned */
 #ifdef CONFIG_XFRM
 	struct netns_xfrm	xfrm;
 #endif
+
+	u64			net_cookie; /* written once */
+
 #if IS_ENABLED(CONFIG_IP_VS)
 	struct netns_ipvs	*ipvs;
 #endif
+#if IS_ENABLED(CONFIG_MPLS)
+	struct netns_mpls	mpls;
+#endif
+#if IS_ENABLED(CONFIG_CAN)
+	struct netns_can	can;
+#endif
+#ifdef CONFIG_XDP_SOCKETS
+	struct netns_xdp	xdp;
+#endif
+#if IS_ENABLED(CONFIG_MCTP)
+	struct netns_mctp	mctp;
+#endif
+#if IS_ENABLED(CONFIG_CRYPTO_USER)
+	struct sock		*crypto_nlsk;
+#endif
 	struct sock		*diag_nlsk;
-	atomic_t		rt_genid;
-	atomic_t		fnhe_genid;
-};
-
-/*
- * ifindex generation is per-net namespace, and loopback is
- * always the 1st device in ns (see net_dev_init), thus any
- * loopback device should get ifindex 1
- */
-
-#define LOOPBACK_IFINDEX	1
+#if IS_ENABLED(CONFIG_SMC)
+	struct netns_smc	smc;
+#endif
+#ifdef CONFIG_DEBUG_NET_SMALL_RTNL
+	/* Move to a better place when the config guard is removed. */
+	struct mutex		rtnl_mutex;
+#endif
+} __randomize_layout;
 
 #include <linux/seq_file_net.h>
 
@@ -137,33 +204,73 @@ struct net {
 extern struct net init_net;
 
 #ifdef CONFIG_NET_NS
-extern struct net *copy_net_ns(unsigned long flags,
-	struct user_namespace *user_ns, struct net *old_net);
+struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns,
+			struct net *old_net);
+
+void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
+
+void net_ns_barrier(void);
+
+struct ns_common *get_net_ns(struct ns_common *ns);
+struct net *get_net_ns_by_fd(int fd);
+extern struct task_struct *cleanup_net_task;
 
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
-static inline struct net *copy_net_ns(unsigned long flags,
+static inline struct net *copy_net_ns(u64 flags,
 	struct user_namespace *user_ns, struct net *old_net)
 {
 	if (flags & CLONE_NEWNET)
 		return ERR_PTR(-EINVAL);
 	return old_net;
 }
+
+static inline void net_ns_get_ownership(const struct net *net,
+					kuid_t *uid, kgid_t *gid)
+{
+	*uid = GLOBAL_ROOT_UID;
+	*gid = GLOBAL_ROOT_GID;
+}
+
+static inline void net_ns_barrier(void) {}
+
+static inline struct ns_common *get_net_ns(struct ns_common *ns)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct net *get_net_ns_by_fd(int fd)
+{
+	return ERR_PTR(-EINVAL);
+}
 #endif /* CONFIG_NET_NS */
 
 
 extern struct list_head net_namespace_list;
 
-extern struct net *get_net_ns_by_pid(pid_t pid);
-extern struct net *get_net_ns_by_fd(int pid);
+struct net *get_net_ns_by_pid(pid_t pid);
+
+#ifdef CONFIG_SYSCTL
+void ipx_register_sysctl(void);
+void ipx_unregister_sysctl(void);
+#else
+#define ipx_register_sysctl()
+#define ipx_unregister_sysctl()
+#endif
 
 #ifdef CONFIG_NET_NS
-extern void __put_net(struct net *net);
+void __put_net(struct net *net);
+
+static inline struct net *to_net_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct net, ns);
+}
 
+/* Try using get_net_track() instead */
 static inline struct net *get_net(struct net *net)
 {
-	atomic_inc(&net->count);
+	ns_ref_inc(net);
 	return net;
 }
 
@@ -174,14 +281,15 @@ static inline struct net *maybe_get_net(struct net *net)
 	 * exists.  If the reference count is zero this
 	 * function fails and returns NULL.
 	 */
-	if (!atomic_inc_not_zero(&net->count))
+	if (!ns_ref_get(net))
 		net = NULL;
 	return net;
 }
 
+/* Try using put_net_track() instead */
 static inline void put_net(struct net *net)
 {
-	if (atomic_dec_and_test(&net->count))
+	if (ns_ref_put(net))
 		__put_net(net);
 }
 
@@ -191,7 +299,13 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return net1 == net2;
 }
 
-extern void net_drop_ns(void *);
+static inline int check_net(const struct net *net)
+{
+	return ns_ref_read(net) != 0;
+}
+
+void net_drop_ns(void *);
+void net_passive_dec(struct net *net);
 
 #else
 
@@ -215,56 +329,108 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return 1;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return 1;
+}
+
 #define net_drop_ns NULL
+
+static inline void net_passive_dec(struct net *net)
+{
+	refcount_dec(&net->passive);
+}
 #endif
 
+static inline void net_passive_inc(struct net *net)
+{
+	refcount_inc(&net->passive);
+}
 
-#ifdef NETNS_REFCNT_DEBUG
-static inline struct net *hold_net(struct net *net)
+/* Returns true if the netns initialization is completed successfully */
+static inline bool net_initialized(const struct net *net)
 {
-	if (net)
-		atomic_inc(&net->use_count);
-	return net;
+	return READ_ONCE(net->list.next);
 }
 
-static inline void release_net(struct net *net)
+static inline void __netns_tracker_alloc(struct net *net,
+					 netns_tracker *tracker,
+					 bool refcounted,
+					 gfp_t gfp)
 {
-	if (net)
-		atomic_dec(&net->use_count);
+#ifdef CONFIG_NET_NS_REFCNT_TRACKER
+	ref_tracker_alloc(refcounted ? &net->refcnt_tracker :
+				       &net->notrefcnt_tracker,
+			  tracker, gfp);
+#endif
 }
-#else
-static inline struct net *hold_net(struct net *net)
+
+static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker,
+				       gfp_t gfp)
 {
+	__netns_tracker_alloc(net, tracker, true, gfp);
+}
+
+static inline void __netns_tracker_free(struct net *net,
+					netns_tracker *tracker,
+					bool refcounted)
+{
+#ifdef CONFIG_NET_NS_REFCNT_TRACKER
+       ref_tracker_free(refcounted ? &net->refcnt_tracker :
+				     &net->notrefcnt_tracker, tracker);
+#endif
+}
+
+static inline struct net *get_net_track(struct net *net,
+					netns_tracker *tracker, gfp_t gfp)
+{
+	get_net(net);
+	netns_tracker_alloc(net, tracker, gfp);
 	return net;
 }
 
-static inline void release_net(struct net *net)
+static inline void put_net_track(struct net *net, netns_tracker *tracker)
 {
+	__netns_tracker_free(net, tracker, true);
+	put_net(net);
 }
-#endif
 
+typedef struct {
 #ifdef CONFIG_NET_NS
+	struct net __rcu *net;
+#endif
+} possible_net_t;
 
-static inline void write_pnet(struct net **pnet, struct net *net)
+static inline void write_pnet(possible_net_t *pnet, struct net *net)
 {
-	*pnet = net;
+#ifdef CONFIG_NET_NS
+	rcu_assign_pointer(pnet->net, net);
+#endif
 }
 
-static inline struct net *read_pnet(struct net * const *pnet)
+static inline struct net *read_pnet(const possible_net_t *pnet)
 {
-	return *pnet;
+#ifdef CONFIG_NET_NS
+	return rcu_dereference_protected(pnet->net, true);
+#else
+	return &init_net;
+#endif
 }
 
+static inline struct net *read_pnet_rcu(const possible_net_t *pnet)
+{
+#ifdef CONFIG_NET_NS
+	return rcu_dereference(pnet->net);
 #else
-
-#define write_pnet(pnet, net)	do { (void)(net);} while (0)
-#define read_pnet(pnet)		(&init_net)
-
+	return &init_net;
 #endif
+}
 
+/* Protected by net_rwsem */
 #define for_each_net(VAR)				\
 	list_for_each_entry(VAR, &net_namespace_list, list)
-
+#define for_each_net_continue_reverse(VAR)		\
+	list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list)
 #define for_each_net_rcu(VAR)				\
 	list_for_each_entry_rcu(VAR, &net_namespace_list, list)
 
@@ -275,18 +441,49 @@ static inline struct net *read_pnet(struct net * const *pnet)
 #define __net_initconst
 #else
 #define __net_init	__init
-#define __net_exit	__exit_refok
+#define __net_exit	__ref
 #define __net_initdata	__initdata
 #define __net_initconst	__initconst
 #endif
 
+int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp);
+int peernet2id(const struct net *net, struct net *peer);
+bool peernet_has_id(const struct net *net, struct net *peer);
+struct net *get_net_ns_by_id(const struct net *net, int id);
+
 struct pernet_operations {
 	struct list_head list;
+	/*
+	 * Below methods are called without any exclusive locks.
+	 * More than one net may be constructed and destructed
+	 * in parallel on several cpus. Every pernet_operations
+	 * have to keep in mind all other pernet_operations and
+	 * to introduce a locking, if they share common resources.
+	 *
+	 * The only time they are called with exclusive lock is
+	 * from register_pernet_subsys(), unregister_pernet_subsys()
+	 * register_pernet_device() and unregister_pernet_device().
+	 *
+	 * Exit methods using blocking RCU primitives, such as
+	 * synchronize_rcu(), should be implemented via exit_batch.
+	 * Then, destruction of a group of net requires single
+	 * synchronize_rcu() related to these pernet_operations,
+	 * instead of separate synchronize_rcu() for every net.
+	 * Please, avoid synchronize_rcu() at all, where it's possible.
+	 *
+	 * Note that a combination of pre_exit() and exit() can
+	 * be used, since a synchronize_rcu() is guaranteed between
+	 * the calls.
+	 */
 	int (*init)(struct net *net);
+	void (*pre_exit)(struct net *net);
 	void (*exit)(struct net *net);
 	void (*exit_batch)(struct list_head *net_exit_list);
-	int *id;
-	size_t size;
+	/* Following method is called with RTNL held. */
+	void (*exit_rtnl)(struct net *net,
+			  struct list_head *dev_kill_list);
+	unsigned int * const id;
+	const size_t size;
 };
 
 /*
@@ -308,23 +505,24 @@ struct pernet_operations {
  * device which caused kernel oops, and panics during network
  * namespace cleanup.   So please don't get this wrong.
  */
-extern int register_pernet_subsys(struct pernet_operations *);
-extern void unregister_pernet_subsys(struct pernet_operations *);
-extern int register_pernet_device(struct pernet_operations *);
-extern void unregister_pernet_device(struct pernet_operations *);
+int register_pernet_subsys(struct pernet_operations *);
+void unregister_pernet_subsys(struct pernet_operations *);
+int register_pernet_device(struct pernet_operations *);
+void unregister_pernet_device(struct pernet_operations *);
 
 struct ctl_table;
-struct ctl_table_header;
 
+#define register_net_sysctl(net, path, table)	\
+	register_net_sysctl_sz(net, path, table, ARRAY_SIZE(table))
 #ifdef CONFIG_SYSCTL
-extern int net_sysctl_init(void);
-extern struct ctl_table_header *register_net_sysctl(struct net *net,
-	const char *path, struct ctl_table *table);
-extern void unregister_net_sysctl_table(struct ctl_table_header *header);
+int net_sysctl_init(void);
+struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path,
+					     struct ctl_table *table, size_t table_size);
+void unregister_net_sysctl_table(struct ctl_table_header *header);
 #else
 static inline int net_sysctl_init(void) { return 0; }
-static inline struct ctl_table_header *register_net_sysctl(struct net *net,
-	const char *path, struct ctl_table *table)
+static inline struct ctl_table_header *register_net_sysctl_sz(struct net *net,
+	const char *path, struct ctl_table *table, size_t table_size)
 {
 	return NULL;
 }
@@ -333,17 +531,46 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header)
 }
 #endif
 
-static inline int rt_genid(struct net *net)
+static inline int rt_genid_ipv4(const struct net *net)
+{
+	return atomic_read(&net->ipv4.rt_genid);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(const struct net *net)
+{
+	return atomic_read(&net->ipv6.fib6_sernum);
+}
+#endif
+
+static inline void rt_genid_bump_ipv4(struct net *net)
 {
-	return atomic_read(&net->rt_genid);
+	atomic_inc(&net->ipv4.rt_genid);
 }
 
-static inline void rt_genid_bump(struct net *net)
+extern void (*__fib6_flush_trees)(struct net *net);
+static inline void rt_genid_bump_ipv6(struct net *net)
 {
-	atomic_inc(&net->rt_genid);
+	if (__fib6_flush_trees)
+		__fib6_flush_trees(net);
 }
 
-static inline int fnhe_genid(struct net *net)
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+static inline struct netns_ieee802154_lowpan *
+net_ieee802154_lowpan(struct net *net)
+{
+	return &net->ieee802154_lowpan;
+}
+#endif
+
+/* For callers who don't really care about whether it's IPv4 or IPv6 */
+static inline void rt_genid_bump_all(struct net *net)
+{
+	rt_genid_bump_ipv4(net);
+	rt_genid_bump_ipv6(net);
+}
+
+static inline int fnhe_genid(const struct net *net)
 {
 	return atomic_read(&net->fnhe_genid);
 }
@@ -353,4 +580,10 @@ static inline void fnhe_genid_bump(struct net *net)
 	atomic_inc(&net->fnhe_genid);
 }
 
+#ifdef CONFIG_NET
+void net_ns_init(void);
+#else
+static inline void net_ns_init(void) {}
+#endif
+
 #endif /* __NET_NET_NAMESPACE_H */