OpenCloudOS-Kernel/include/net/net_namespace.h

389 lines
9.0 KiB
C
Raw Normal View History

/*
* Operations on the network namespace
*/
#ifndef __NET_NET_NAMESPACE_H
#define __NET_NET_NAMESPACE_H
#include <linux/atomic.h>
#include <linux/workqueue.h>
#include <linux/list.h>
#include <linux/sysctl.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/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
#include <net/netns/nftables.h>
#include <net/netns/xfrm.h>
#include <linux/ns_common.h>
struct user_namespace;
struct proc_dir_entry;
struct net_device;
struct sock;
struct ctl_table_header;
struct net_generic;
genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-10 17:51:34 +08:00
struct sock;
struct netns_ipvs;
#define NETDEV_HASHBITS 8
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
struct net {
atomic_t passive; /* To decided 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 */
struct user_namespace *user_ns; /* Owning user namespace */
struct ns_common ns;
struct proc_dir_entry *proc_net;
struct proc_dir_entry *proc_net_stat;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
#ifdef CONFIG_SYSCTL
struct ctl_table_set sysctls;
#endif
struct sock *rtnl; /* rtnetlink socket */
struct sock *genl_sock;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
struct list_head dev_base_head;
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
unsigned int dev_base_seq; /* protected by rtnl_mutex */
int ifindex;
net: Delay default_device_exit_batch until no devices are unregistering v2 There is currently serialization network namespaces exiting and network devices exiting as the final part of netdev_run_todo does not happen under the rtnl_lock. This is compounded by the fact that the only list of devices unregistering in netdev_run_todo is local to the netdev_run_todo. This lack of serialization in extreme cases results in network devices unregistering in netdev_run_todo after the loopback device of their network namespace has been freed (making dst_ifdown unsafe), and after the their network namespace has exited (making the NETDEV_UNREGISTER, and NETDEV_UNREGISTER_FINAL callbacks unsafe). Add the missing serialization by a per network namespace count of how many network devices are unregistering and having a wait queue that is woken up whenever the count is decreased. The count and wait queue allow default_device_exit_batch to wait until all of the unregistration activity for a network namespace has finished before proceeding to unregister the loopback device and then allowing the network namespace to exit. Only a single global wait queue is used because there is a single global lock, and there is a single waiter, per network namespace wait queues would be a waste of resources. The per network namespace count of unregistering devices gives a progress guarantee because the number of network devices unregistering in an exiting network namespace must ultimately drop to zero (assuming network device unregistration completes). The basic logic remains the same as in v1. This patch is now half comment and half rtnl_lock_unregistering an expanded version of wait_event performs no extra work in the common case where no network devices are unregistering when we get to default_device_exit_batch. Reported-by: Francesco Ruggeri <fruggeri@aristanetworks.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-24 12:19:49 +08:00
unsigned int dev_unreg_count;
/* 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;
struct netns_unix unx;
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 defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE)
struct netns_nftables nft;
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag nf_frag;
#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;
/* Note : following structs are cache line aligned */
#ifdef CONFIG_XFRM
struct netns_xfrm xfrm;
#endif
#if IS_ENABLED(CONFIG_IP_VS)
struct netns_ipvs *ipvs;
#endif
struct sock *diag_nlsk;
atomic_t fnhe_genid;
};
#include <linux/seq_file_net.h>
/* Init's network namespace */
extern struct net init_net;
#ifdef CONFIG_NET_NS
struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns,
struct net *old_net);
#else /* CONFIG_NET_NS */
#include <linux/sched.h>
#include <linux/nsproxy.h>
static inline struct net *copy_net_ns(unsigned long flags,
struct user_namespace *user_ns, struct net *old_net)
{
if (flags & CLONE_NEWNET)
return ERR_PTR(-EINVAL);
return old_net;
}
#endif /* CONFIG_NET_NS */
extern struct list_head net_namespace_list;
struct net *get_net_ns_by_pid(pid_t pid);
struct net *get_net_ns_by_fd(int 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
void __put_net(struct net *net);
static inline struct net *get_net(struct net *net)
{
atomic_inc(&net->count);
return net;
}
static inline struct net *maybe_get_net(struct net *net)
{
/* Used when we know struct net exists but we
* aren't guaranteed a previous reference count
* exists. If the reference count is zero this
* function fails and returns NULL.
*/
if (!atomic_inc_not_zero(&net->count))
net = NULL;
return net;
}
static inline void put_net(struct net *net)
{
if (atomic_dec_and_test(&net->count))
__put_net(net);
}
static inline
int net_eq(const struct net *net1, const struct net *net2)
{
return net1 == net2;
}
void net_drop_ns(void *);
#else
netns: Don't receive new packets in a dead network namespace. Alexey Dobriyan <adobriyan@gmail.com> writes: > Subject: ICMP sockets destruction vs ICMP packets oops > After icmp_sk_exit() nuked ICMP sockets, we get an interrupt. > icmp_reply() wants ICMP socket. > > Steps to reproduce: > > launch shell in new netns > move real NIC to netns > setup routing > ping -i 0 > exit from shell > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 > IP: [<ffffffff803fce17>] icmp_sk+0x17/0x30 > PGD 17f3cd067 PUD 17f3ce067 PMD 0 > Oops: 0000 [1] PREEMPT SMP DEBUG_PAGEALLOC > CPU 0 > Modules linked in: usblp usbcore > Pid: 0, comm: swapper Not tainted 2.6.26-rc6-netns-ct #4 > RIP: 0010:[<ffffffff803fce17>] [<ffffffff803fce17>] icmp_sk+0x17/0x30 > RSP: 0018:ffffffff8057fc30 EFLAGS: 00010286 > RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff81017c7db900 > RDX: 0000000000000034 RSI: ffff81017c7db900 RDI: ffff81017dc41800 > RBP: ffffffff8057fc40 R08: 0000000000000001 R09: 000000000000a815 > R10: 0000000000000000 R11: 0000000000000001 R12: ffffffff8057fd28 > R13: ffffffff8057fd00 R14: ffff81017c7db938 R15: ffff81017dc41800 > FS: 0000000000000000(0000) GS:ffffffff80525000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 000000017fcda000 CR4: 00000000000006e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Process swapper (pid: 0, threadinfo ffffffff8053a000, task ffffffff804fa4a0) > Stack: 0000000000000000 ffff81017c7db900 ffffffff8057fcf0 ffffffff803fcfe4 > ffffffff804faa38 0000000000000246 0000000000005a40 0000000000000246 > 000000000001ffff ffff81017dd68dc0 0000000000005a40 0000000055342436 > Call Trace: > <IRQ> [<ffffffff803fcfe4>] icmp_reply+0x44/0x1e0 > [<ffffffff803d3a0a>] ? ip_route_input+0x23a/0x1360 > [<ffffffff803fd645>] icmp_echo+0x65/0x70 > [<ffffffff803fd300>] icmp_rcv+0x180/0x1b0 > [<ffffffff803d6d84>] ip_local_deliver+0xf4/0x1f0 > [<ffffffff803d71bb>] ip_rcv+0x33b/0x650 > [<ffffffff803bb16a>] netif_receive_skb+0x27a/0x340 > [<ffffffff803be57d>] process_backlog+0x9d/0x100 > [<ffffffff803bdd4d>] net_rx_action+0x18d/0x250 > [<ffffffff80237be5>] __do_softirq+0x75/0x100 > [<ffffffff8020c97c>] call_softirq+0x1c/0x30 > [<ffffffff8020f085>] do_softirq+0x65/0xa0 > [<ffffffff80237af7>] irq_exit+0x97/0xa0 > [<ffffffff8020f198>] do_IRQ+0xa8/0x130 > [<ffffffff80212ee0>] ? mwait_idle+0x0/0x60 > [<ffffffff8020bc46>] ret_from_intr+0x0/0xf > <EOI> [<ffffffff80212f2c>] ? mwait_idle+0x4c/0x60 > [<ffffffff80212f23>] ? mwait_idle+0x43/0x60 > [<ffffffff8020a217>] ? cpu_idle+0x57/0xa0 > [<ffffffff8040f380>] ? rest_init+0x70/0x80 > Code: 10 5b 41 5c 41 5d 41 5e c9 c3 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 53 > 48 83 ec 08 48 8b 9f 78 01 00 00 e8 2b c7 f1 ff 89 c0 <48> 8b 04 c3 48 83 c4 08 > 5b c9 c3 66 66 66 66 66 2e 0f 1f 84 00 > RIP [<ffffffff803fce17>] icmp_sk+0x17/0x30 > RSP <ffffffff8057fc30> > CR2: 0000000000000000 > ---[ end trace ea161157b76b33e8 ]--- > Kernel panic - not syncing: Aiee, killing interrupt handler! Receiving packets while we are cleaning up a network namespace is a racy proposition. It is possible when the packet arrives that we have removed some but not all of the state we need to fully process it. We have the choice of either playing wack-a-mole with the cleanup routines or simply dropping packets when we don't have a network namespace to handle them. Since the check looks inexpensive in netif_receive_skb let's just drop the incoming packets. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-21 13:16:51 +08:00
static inline struct net *get_net(struct net *net)
{
return net;
}
static inline void put_net(struct net *net)
{
}
static inline struct net *maybe_get_net(struct net *net)
{
return net;
}
static inline
int net_eq(const struct net *net1, const struct net *net2)
{
return 1;
}
#define net_drop_ns NULL
#endif
#ifdef NETNS_REFCNT_DEBUG
static inline struct net *hold_net(struct net *net)
{
if (net)
atomic_inc(&net->use_count);
return net;
}
static inline void release_net(struct net *net)
{
if (net)
atomic_dec(&net->use_count);
}
#else
static inline struct net *hold_net(struct net *net)
{
return net;
}
static inline void release_net(struct net *net)
{
}
#endif
#ifdef CONFIG_NET_NS
static inline void write_pnet(struct net **pnet, struct net *net)
{
*pnet = net;
}
static inline struct net *read_pnet(struct net * const *pnet)
{
return *pnet;
}
#else
#define write_pnet(pnet, net) do { (void)(net);} while (0)
#define read_pnet(pnet) (&init_net)
#endif
#define for_each_net(VAR) \
list_for_each_entry(VAR, &net_namespace_list, list)
#define for_each_net_rcu(VAR) \
list_for_each_entry_rcu(VAR, &net_namespace_list, list)
#ifdef CONFIG_NET_NS
#define __net_init
#define __net_exit
#define __net_initdata
#define __net_initconst
#else
#define __net_init __init
#define __net_exit __exit_refok
#define __net_initdata __initdata
#define __net_initconst __initconst
#endif
struct pernet_operations {
struct list_head list;
int (*init)(struct net *net);
void (*exit)(struct net *net);
void (*exit_batch)(struct list_head *net_exit_list);
int *id;
size_t size;
};
/*
* Use these carefully. If you implement a network device and it
* needs per network namespace operations use device pernet operations,
* otherwise use pernet subsys operations.
*
* Network interfaces need to be removed from a dying netns _before_
* subsys notifiers can be called, as most of the network code cleanup
* (which is done from subsys notifiers) runs with the assumption that
* dev_remove_pack has been called so no new packets will arrive during
* and after the cleanup functions have been called. dev_remove_pack
* is not per namespace so instead the guarantee of no more packets
* arriving in a network namespace is provided by ensuring that all
* network devices and all sockets have left the network namespace
* before the cleanup methods are called.
*
* For the longest time the ipv4 icmp code was registered as a pernet
* device which caused kernel oops, and panics during network
* namespace cleanup. So please don't get this wrong.
*/
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;
#ifdef CONFIG_SYSCTL
int net_sysctl_init(void);
struct ctl_table_header *register_net_sysctl(struct net *net, const char *path,
struct ctl_table *table);
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)
{
return NULL;
}
static inline void unregister_net_sysctl_table(struct ctl_table_header *header)
{
}
#endif
static inline int rt_genid_ipv4(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
static inline void rt_genid_bump_ipv4(struct net *net)
{
atomic_inc(&net->ipv4.rt_genid);
}
extern void (*__fib6_flush_trees)(struct net *net);
static inline void rt_genid_bump_ipv6(struct net *net)
{
if (__fib6_flush_trees)
__fib6_flush_trees(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(struct net *net)
{
return atomic_read(&net->fnhe_genid);
}
static inline void fnhe_genid_bump(struct net *net)
{
atomic_inc(&net->fnhe_genid);
}
#endif /* __NET_NET_NAMESPACE_H */