#include <linux/slab.h>
#include <linux/list.h>
#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/idr.h>
+#include <linux/rculist.h>
+#include <linux/nsproxy.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
/*
* Our network namespace constructor/destructor lists
static struct list_head *first_device = &pernet_list;
static DEFINE_MUTEX(net_mutex);
-static DEFINE_MUTEX(net_list_mutex);
LIST_HEAD(net_namespace_list);
-
-static struct kmem_cache *net_cachep;
+EXPORT_SYMBOL_GPL(net_namespace_list);
struct net init_net;
-EXPORT_SYMBOL_GPL(init_net);
+EXPORT_SYMBOL(init_net);
+
+#define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */
-void net_lock(void)
+static int ops_init(const struct pernet_operations *ops, struct net *net)
{
- mutex_lock(&net_list_mutex);
+ int err;
+ if (ops->id && ops->size) {
+ void *data = kzalloc(ops->size, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ err = net_assign_generic(net, *ops->id, data);
+ if (err) {
+ kfree(data);
+ return err;
+ }
+ }
+ if (ops->init)
+ return ops->init(net);
+ return 0;
}
-void net_unlock(void)
+static void ops_free(const struct pernet_operations *ops, struct net *net)
{
- mutex_unlock(&net_list_mutex);
+ if (ops->id && ops->size) {
+ int id = *ops->id;
+ kfree(net_generic(net, id));
+ }
}
-#if 0
-static struct net *net_alloc(void)
+static void ops_exit_list(const struct pernet_operations *ops,
+ struct list_head *net_exit_list)
{
- return kmem_cache_alloc(net_cachep, GFP_KERNEL);
+ struct net *net;
+ if (ops->exit) {
+ list_for_each_entry(net, net_exit_list, exit_list)
+ ops->exit(net);
+ }
+ if (ops->exit_batch)
+ ops->exit_batch(net_exit_list);
+}
+
+static void ops_free_list(const struct pernet_operations *ops,
+ struct list_head *net_exit_list)
+{
+ struct net *net;
+ if (ops->size && ops->id) {
+ list_for_each_entry(net, net_exit_list, exit_list)
+ ops_free(ops, net);
+ }
}
+
+/*
+ * setup_net runs the initializers for the network namespace object.
+ */
+static __net_init int setup_net(struct net *net)
+{
+ /* Must be called with net_mutex held */
+ const struct pernet_operations *ops, *saved_ops;
+ int error = 0;
+ LIST_HEAD(net_exit_list);
+
+ atomic_set(&net->count, 1);
+
+#ifdef NETNS_REFCNT_DEBUG
+ atomic_set(&net->use_count, 0);
#endif
-static void net_free(struct net *net)
+ list_for_each_entry(ops, &pernet_list, list) {
+ error = ops_init(ops, net);
+ if (error < 0)
+ goto out_undo;
+ }
+out:
+ return error;
+
+out_undo:
+ /* Walk through the list backwards calling the exit functions
+ * for the pernet modules whose init functions did not fail.
+ */
+ list_add(&net->exit_list, &net_exit_list);
+ saved_ops = ops;
+ list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+ ops_exit_list(ops, &net_exit_list);
+
+ ops = saved_ops;
+ list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+ ops_free_list(ops, &net_exit_list);
+
+ rcu_barrier();
+ goto out;
+}
+
+static struct net_generic *net_alloc_generic(void)
{
+ struct net_generic *ng;
+ size_t generic_size = sizeof(struct net_generic) +
+ INITIAL_NET_GEN_PTRS * sizeof(void *);
+
+ ng = kzalloc(generic_size, GFP_KERNEL);
+ if (ng)
+ ng->len = INITIAL_NET_GEN_PTRS;
+
+ return ng;
+}
+
+#ifdef CONFIG_NET_NS
+static struct kmem_cache *net_cachep;
+static struct workqueue_struct *netns_wq;
+
+static struct net *net_alloc(void)
+{
+ struct net *net = NULL;
+ struct net_generic *ng;
+
+ ng = net_alloc_generic();
+ if (!ng)
+ goto out;
+
+ net = kmem_cache_zalloc(net_cachep, GFP_KERNEL);
if (!net)
- return;
+ goto out_free;
+ rcu_assign_pointer(net->gen, ng);
+out:
+ return net;
+
+out_free:
+ kfree(ng);
+ goto out;
+}
+
+static void net_free(struct net *net)
+{
+#ifdef NETNS_REFCNT_DEBUG
if (unlikely(atomic_read(&net->use_count) != 0)) {
printk(KERN_EMERG "network namespace not free! Usage: %d\n",
atomic_read(&net->use_count));
return;
}
-
+#endif
+ kfree(net->gen);
kmem_cache_free(net_cachep, net);
}
-static void cleanup_net(struct work_struct *work)
+static struct net *net_create(void)
{
- struct pernet_operations *ops;
- struct list_head *ptr;
struct net *net;
+ int rv;
- net = container_of(work, struct net, work);
+ net = net_alloc();
+ if (!net)
+ return ERR_PTR(-ENOMEM);
+ mutex_lock(&net_mutex);
+ rv = setup_net(net);
+ if (rv == 0) {
+ rtnl_lock();
+ list_add_tail_rcu(&net->list, &net_namespace_list);
+ rtnl_unlock();
+ }
+ mutex_unlock(&net_mutex);
+ if (rv < 0) {
+ net_free(net);
+ return ERR_PTR(rv);
+ }
+ return net;
+}
+
+struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+{
+ if (!(flags & CLONE_NEWNET))
+ return get_net(old_net);
+ return net_create();
+}
+
+static DEFINE_SPINLOCK(cleanup_list_lock);
+static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */
+
+static void cleanup_net(struct work_struct *work)
+{
+ const struct pernet_operations *ops;
+ struct net *net, *tmp;
+ LIST_HEAD(net_kill_list);
+ LIST_HEAD(net_exit_list);
+
+ /* Atomically snapshot the list of namespaces to cleanup */
+ spin_lock_irq(&cleanup_list_lock);
+ list_replace_init(&cleanup_list, &net_kill_list);
+ spin_unlock_irq(&cleanup_list_lock);
mutex_lock(&net_mutex);
/* Don't let anyone else find us. */
- net_lock();
- list_del(&net->list);
- net_unlock();
+ rtnl_lock();
+ list_for_each_entry(net, &net_kill_list, cleanup_list) {
+ list_del_rcu(&net->list);
+ list_add_tail(&net->exit_list, &net_exit_list);
+ }
+ rtnl_unlock();
+
+ /*
+ * Another CPU might be rcu-iterating the list, wait for it.
+ * This needs to be before calling the exit() notifiers, so
+ * the rcu_barrier() below isn't sufficient alone.
+ */
+ synchronize_rcu();
/* Run all of the network namespace exit methods */
- list_for_each_prev(ptr, &pernet_list) {
- ops = list_entry(ptr, struct pernet_operations, list);
- if (ops->exit)
- ops->exit(net);
- }
+ list_for_each_entry_reverse(ops, &pernet_list, list)
+ ops_exit_list(ops, &net_exit_list);
+
+ /* Free the net generic variables */
+ list_for_each_entry_reverse(ops, &pernet_list, list)
+ ops_free_list(ops, &net_exit_list);
mutex_unlock(&net_mutex);
rcu_barrier();
/* Finally it is safe to free my network namespace structure */
- net_free(net);
+ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
+ list_del_init(&net->exit_list);
+ net_free(net);
+ }
}
-
+static DECLARE_WORK(net_cleanup_work, cleanup_net);
void __put_net(struct net *net)
{
/* Cleanup the network namespace in process context */
- INIT_WORK(&net->work, cleanup_net);
- schedule_work(&net->work);
+ unsigned long flags;
+
+ spin_lock_irqsave(&cleanup_list_lock, flags);
+ list_add(&net->cleanup_list, &cleanup_list);
+ spin_unlock_irqrestore(&cleanup_list_lock, flags);
+
+ queue_work(netns_wq, &net_cleanup_work);
}
EXPORT_SYMBOL_GPL(__put_net);
-/*
- * setup_net runs the initializers for the network namespace object.
- */
-static int setup_net(struct net *net)
+#else
+struct net *copy_net_ns(unsigned long flags, struct net *old_net)
{
- /* Must be called with net_mutex held */
- struct pernet_operations *ops;
- struct list_head *ptr;
- int error;
+ if (flags & CLONE_NEWNET)
+ return ERR_PTR(-EINVAL);
+ return old_net;
+}
+#endif
- memset(net, 0, sizeof(struct net));
- atomic_set(&net->count, 1);
- atomic_set(&net->use_count, 0);
+struct net *get_net_ns_by_pid(pid_t pid)
+{
+ struct task_struct *tsk;
+ struct net *net;
- error = 0;
- list_for_each(ptr, &pernet_list) {
- ops = list_entry(ptr, struct pernet_operations, list);
- if (ops->init) {
- error = ops->init(net);
- if (error < 0)
- goto out_undo;
- }
- }
-out:
- return error;
-out_undo:
- /* Walk through the list backwards calling the exit functions
- * for the pernet modules whose init functions did not fail.
- */
- for (ptr = ptr->prev; ptr != &pernet_list; ptr = ptr->prev) {
- ops = list_entry(ptr, struct pernet_operations, list);
- if (ops->exit)
- ops->exit(net);
+ /* Lookup the network namespace */
+ net = ERR_PTR(-ESRCH);
+ rcu_read_lock();
+ tsk = find_task_by_vpid(pid);
+ if (tsk) {
+ struct nsproxy *nsproxy;
+ nsproxy = task_nsproxy(tsk);
+ if (nsproxy)
+ net = get_net(nsproxy->net_ns);
}
- goto out;
+ rcu_read_unlock();
+ return net;
}
+EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
static int __init net_ns_init(void)
{
- int err;
+ struct net_generic *ng;
- printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net));
+#ifdef CONFIG_NET_NS
net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
SMP_CACHE_BYTES,
SLAB_PANIC, NULL);
+
+ /* Create workqueue for cleanup */
+ netns_wq = create_singlethread_workqueue("netns");
+ if (!netns_wq)
+ panic("Could not create netns workq");
+#endif
+
+ ng = net_alloc_generic();
+ if (!ng)
+ panic("Could not allocate generic netns");
+
+ rcu_assign_pointer(init_net.gen, ng);
+
mutex_lock(&net_mutex);
- err = setup_net(&init_net);
+ if (setup_net(&init_net))
+ panic("Could not setup the initial network namespace");
- net_lock();
- list_add_tail(&init_net.list, &net_namespace_list);
- net_unlock();
+ rtnl_lock();
+ list_add_tail_rcu(&init_net.list, &net_namespace_list);
+ rtnl_unlock();
mutex_unlock(&net_mutex);
- if (err)
- panic("Could not setup the initial network namespace");
return 0;
}
pure_initcall(net_ns_init);
-static int register_pernet_operations(struct list_head *list,
- struct pernet_operations *ops)
+#ifdef CONFIG_NET_NS
+static int __register_pernet_operations(struct list_head *list,
+ struct pernet_operations *ops)
{
- struct net *net, *undo_net;
+ struct net *net;
int error;
+ LIST_HEAD(net_exit_list);
- error = 0;
list_add_tail(&ops->list, list);
- for_each_net(net) {
- if (ops->init) {
- error = ops->init(net);
+ if (ops->init || (ops->id && ops->size)) {
+ for_each_net(net) {
+ error = ops_init(ops, net);
if (error)
goto out_undo;
+ list_add_tail(&net->exit_list, &net_exit_list);
}
}
-out:
- return error;
+ return 0;
out_undo:
/* If I have an error cleanup all namespaces I initialized */
list_del(&ops->list);
- for_each_net(undo_net) {
- if (undo_net == net)
- goto undone;
- if (ops->exit)
- ops->exit(undo_net);
- }
-undone:
- goto out;
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
+ return error;
}
-static void unregister_pernet_operations(struct pernet_operations *ops)
+static void __unregister_pernet_operations(struct pernet_operations *ops)
{
struct net *net;
+ LIST_HEAD(net_exit_list);
list_del(&ops->list);
for_each_net(net)
- if (ops->exit)
- ops->exit(net);
+ list_add_tail(&net->exit_list, &net_exit_list);
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
+}
+
+#else
+
+static int __register_pernet_operations(struct list_head *list,
+ struct pernet_operations *ops)
+{
+ int err = 0;
+ err = ops_init(ops, &init_net);
+ if (err)
+ ops_free(ops, &init_net);
+ return err;
+
+}
+
+static void __unregister_pernet_operations(struct pernet_operations *ops)
+{
+ LIST_HEAD(net_exit_list);
+ list_add(&init_net.exit_list, &net_exit_list);
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
+}
+
+#endif /* CONFIG_NET_NS */
+
+static DEFINE_IDA(net_generic_ids);
+
+static int register_pernet_operations(struct list_head *list,
+ struct pernet_operations *ops)
+{
+ int error;
+
+ if (ops->id) {
+again:
+ error = ida_get_new_above(&net_generic_ids, 1, ops->id);
+ if (error < 0) {
+ if (error == -EAGAIN) {
+ ida_pre_get(&net_generic_ids, GFP_KERNEL);
+ goto again;
+ }
+ return error;
+ }
+ }
+ error = __register_pernet_operations(list, ops);
+ if (error) {
+ rcu_barrier();
+ if (ops->id)
+ ida_remove(&net_generic_ids, *ops->id);
+ }
+
+ return error;
+}
+
+static void unregister_pernet_operations(struct pernet_operations *ops)
+{
+
+ __unregister_pernet_operations(ops);
+ rcu_barrier();
+ if (ops->id)
+ ida_remove(&net_generic_ids, *ops->id);
}
/**
* @ops: pernet operations structure to manipulate
*
* Remove the pernet operations structure from the list to be
- * used when network namespaces are created or destoryed. In
+ * used when network namespaces are created or destroyed. In
* addition run the exit method for all existing network
* namespaces.
*/
* @ops: pernet operations structure to manipulate
*
* Remove the pernet operations structure from the list to be
- * used when network namespaces are created or destoryed. In
+ * used when network namespaces are created or destroyed. In
* addition run the exit method for all existing network
* namespaces.
*/
mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_device);
+
+static void net_generic_release(struct rcu_head *rcu)
+{
+ struct net_generic *ng;
+
+ ng = container_of(rcu, struct net_generic, rcu);
+ kfree(ng);
+}
+
+int net_assign_generic(struct net *net, int id, void *data)
+{
+ struct net_generic *ng, *old_ng;
+
+ BUG_ON(!mutex_is_locked(&net_mutex));
+ BUG_ON(id == 0);
+
+ ng = old_ng = net->gen;
+ if (old_ng->len >= id)
+ goto assign;
+
+ ng = kzalloc(sizeof(struct net_generic) +
+ id * sizeof(void *), GFP_KERNEL);
+ if (ng == NULL)
+ return -ENOMEM;
+
+ /*
+ * Some synchronisation notes:
+ *
+ * The net_generic explores the net->gen array inside rcu
+ * read section. Besides once set the net->gen->ptr[x]
+ * pointer never changes (see rules in netns/generic.h).
+ *
+ * That said, we simply duplicate this array and schedule
+ * the old copy for kfree after a grace period.
+ */
+
+ ng->len = id;
+ memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
+
+ rcu_assign_pointer(net->gen, ng);
+ call_rcu(&old_ng->rcu, net_generic_release);
+assign:
+ ng->ptr[id - 1] = data;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(net_assign_generic);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff