net: Use generic ns_common::count

Switch over network namespaces to use the newly introduced common lifetime
counter.
Network namespaces have an additional counter named "passive". This counter
does not guarantee that the network namespace is not already de-initialized
and so isn't concerned with the actual lifetime of the network namespace;
only the "count" counter is. So the latter is moved into struct ns_common.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
[christian.brauner@ubuntu.com: rewrite commit]
Link: https://lore.kernel.org/r/159644977635.604812.1319877322927063560.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2ee5901..cb4b33d 100644 (file)
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -60,9 +60,6 @@ struct net {
        refcount_t              passive;        /* To decide when the network
                                                 * namespace should be freed.
                                                 */
-       refcount_t              count;          /* To decided when the network
-                                                *  namespace should be shut down.
-                                                */
        spinlock_t              rules_mod_lock;
 
        unsigned int            dev_unreg_count;
@@ -245,7 +242,7 @@ void __put_net(struct net *net);
 
 static inline struct net *get_net(struct net *net)
 {
-       refcount_inc(&net->count);
+       refcount_inc(&net->ns.count);
        return net;
 }
 
@@ -256,14 +253,14 @@ static inline struct net *maybe_get_net(struct net *net)
         * exists.  If the reference count is zero this
         * function fails and returns NULL.
         */
-       if (!refcount_inc_not_zero(&net->count))
+       if (!refcount_inc_not_zero(&net->ns.count))
                net = NULL;
        return net;
 }
 
 static inline void put_net(struct net *net)
 {
-       if (refcount_dec_and_test(&net->count))
+       if (refcount_dec_and_test(&net->ns.count))
                __put_net(net);
 }
 
@@ -275,7 +272,7 @@ int net_eq(const struct net *net1, const struct net *net2)
 
 static inline int check_net(const struct net *net)
 {
-       return refcount_read(&net->count) != 0;
+       return refcount_read(&net->ns.count) != 0;
 }
 
 void net_drop_ns(void *);

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index efec66f..8d4128d 100644 (file)
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1027,7 +1027,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
        while (--i >= new_num) {
                struct kobject *kobj = &dev->_rx[i].kobj;
 
-               if (!refcount_read(&dev_net(dev)->count))
+               if (!refcount_read(&dev_net(dev)->ns.count))
                        kobj->uevent_suppress = 1;
                if (dev->sysfs_rx_queue_group)
                        sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1605,7 +1605,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
        while (--i >= new_num) {
                struct netdev_queue *queue = dev->_tx + i;
 
-               if (!refcount_read(&dev_net(dev)->count))
+               if (!refcount_read(&dev_net(dev)->ns.count))
                        queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
                sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1852,7 +1852,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
        struct device *dev = &ndev->dev;
 
-       if (!refcount_read(&dev_net(ndev)->count))
+       if (!refcount_read(&dev_net(ndev)->ns.count))
                dev_set_uevent_suppress(dev, 1);
 
        kobject_get(&dev->kobj);

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index dcd61ac..5f658cb 100644 (file)
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -44,7 +44,7 @@ static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
 #endif
 
 struct net init_net = {
-       .count          = REFCOUNT_INIT(1),
+       .ns.count       = REFCOUNT_INIT(1),
        .dev_base_head  = LIST_HEAD_INIT(init_net.dev_base_head),
 #ifdef CONFIG_KEYS
        .key_domain     = &init_net_key_domain,
@@ -248,7 +248,7 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 {
        int id;
 
-       if (refcount_read(&net->count) == 0)
+       if (refcount_read(&net->ns.count) == 0)
                return NETNSA_NSID_NOT_ASSIGNED;
 
        spin_lock(&net->nsid_lock);
@@ -328,7 +328,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
        int error = 0;
        LIST_HEAD(net_exit_list);
 
-       refcount_set(&net->count, 1);
+       refcount_set(&net->ns.count, 1);
        refcount_set(&net->passive, 1);
        get_random_bytes(&net->hash_mix, sizeof(u32));
        net->dev_base_seq = 1;

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index c411c87..437afe3 100644 (file)
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -272,14 +272,14 @@ restart:
                                continue;
                        tw = inet_twsk(sk);
                        if ((tw->tw_family != family) ||
-                               refcount_read(&twsk_net(tw)->count))
+                               refcount_read(&twsk_net(tw)->ns.count))
                                continue;
 
                        if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
                                continue;
 
                        if (unlikely((tw->tw_family != family) ||
-                                    refcount_read(&twsk_net(tw)->count))) {
+                                    refcount_read(&twsk_net(tw)->ns.count))) {
                                inet_twsk_put(tw);
                                goto restart;
                        }

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 279db88..39710c4 100644 (file)
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -887,7 +887,7 @@ static void tcp_metrics_flush_all(struct net *net)
                pp = &hb->chain;
                for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
                        match = net ? net_eq(tm_net(tm), net) :
-                               !refcount_read(&tm_net(tm)->count);
+                               !refcount_read(&tm_net(tm)->ns.count);
                        if (match) {
                                *pp = tm->tcpm_next;
                                kfree_rcu(tm, rcu_head);