mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
237f83dfbe
Pull networking updates from David Miller: "Some highlights from this development cycle: 1) Big refactoring of ipv6 route and neigh handling to support nexthop objects configurable as units from userspace. From David Ahern. 2) Convert explored_states in BPF verifier into a hash table, significantly decreased state held for programs with bpf2bpf calls, from Alexei Starovoitov. 3) Implement bpf_send_signal() helper, from Yonghong Song. 4) Various classifier enhancements to mvpp2 driver, from Maxime Chevallier. 5) Add aRFS support to hns3 driver, from Jian Shen. 6) Fix use after free in inet frags by allocating fqdirs dynamically and reworking how rhashtable dismantle occurs, from Eric Dumazet. 7) Add act_ctinfo packet classifier action, from Kevin Darbyshire-Bryant. 8) Add TFO key backup infrastructure, from Jason Baron. 9) Remove several old and unused ISDN drivers, from Arnd Bergmann. 10) Add devlink notifications for flash update status to mlxsw driver, from Jiri Pirko. 11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski. 12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes. 13) Various enhancements to ipv6 flow label handling, from Eric Dumazet and Willem de Bruijn. 14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van der Merwe, and others. 15) Various improvements to axienet driver including converting it to phylink, from Robert Hancock. 16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean. 17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana Radulescu. 18) Add devlink health reporting to mlx5, from Moshe Shemesh. 19) Convert stmmac over to phylink, from Jose Abreu. 20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from Shalom Toledo. 21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera. 22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel. 23) Track spill/fill of constants in BPF verifier, from Alexei Starovoitov. 24) Support bounded loops in BPF, from Alexei Starovoitov. 25) Various page_pool API fixes and improvements, from Jesper Dangaard Brouer. 26) Just like ipv4, support ref-countless ipv6 route handling. From Wei Wang. 27) Support VLAN offloading in aquantia driver, from Igor Russkikh. 28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy. 29) Add flower GRE encap/decap support to nfp driver, from Pieter Jansen van Vuuren. 30) Protect against stack overflow when using act_mirred, from John Hurley. 31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen. 32) Use page_pool API in netsec driver, Ilias Apalodimas. 33) Add Google gve network driver, from Catherine Sullivan. 34) More indirect call avoidance, from Paolo Abeni. 35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan. 36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek. 37) Add MPLS manipulation actions to TC, from John Hurley. 38) Add sending a packet to connection tracking from TC actions, and then allow flower classifier matching on conntrack state. From Paul Blakey. 39) Netfilter hw offload support, from Pablo Neira Ayuso" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits) net/mlx5e: Return in default case statement in tx_post_resync_params mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync(). net: dsa: add support for BRIDGE_MROUTER attribute pkt_sched: Include const.h net: netsec: remove static declaration for netsec_set_tx_de() net: netsec: remove superfluous if statement netfilter: nf_tables: add hardware offload support net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload net: flow_offload: add flow_block_cb_is_busy() and use it net: sched: remove tcf block API drivers: net: use flow block API net: sched: use flow block API net: flow_offload: add flow_block_cb_{priv, incref, decref}() net: flow_offload: add list handling functions net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free() net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND net: flow_offload: add flow_block_cb_setup_simple() net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC ...
461 lines
12 KiB
C
461 lines
12 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Operations on the network namespace
|
|
*/
|
|
#ifndef __NET_NET_NAMESPACE_H
|
|
#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
|
|
#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 <linux/ns_common.h>
|
|
#include <linux/idr.h>
|
|
#include <linux/skbuff.h>
|
|
|
|
struct user_namespace;
|
|
struct proc_dir_entry;
|
|
struct net_device;
|
|
struct sock;
|
|
struct ctl_table_header;
|
|
struct net_generic;
|
|
struct uevent_sock;
|
|
struct netns_ipvs;
|
|
struct bpf_prog;
|
|
|
|
|
|
#define NETDEV_HASHBITS 8
|
|
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
|
|
|
|
struct net {
|
|
refcount_t passive; /* To decided 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;
|
|
|
|
u32 hash_mix;
|
|
atomic64_t cookie_gen;
|
|
|
|
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 cleanup_list; /* namespaces on death row */
|
|
|
|
#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;
|
|
spinlock_t nsid_lock;
|
|
struct idr netns_ids;
|
|
|
|
struct ns_common ns;
|
|
|
|
struct proc_dir_entry *proc_net;
|
|
struct proc_dir_entry *proc_net_stat;
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
struct ctl_table_set sysctls;
|
|
#endif
|
|
|
|
struct sock *rtnl; /* rtnetlink socket */
|
|
struct sock *genl_sock;
|
|
|
|
struct uevent_sock *uevent_sock; /* uevent socket */
|
|
|
|
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;
|
|
unsigned int dev_unreg_count;
|
|
|
|
/* core fib_rules */
|
|
struct list_head rules_ops;
|
|
|
|
struct list_head fib_notifier_ops; /* Populated by
|
|
* register_pernet_subsys()
|
|
*/
|
|
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_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 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;
|
|
struct ctl_table_header *nf_frag_frags_hdr;
|
|
#endif
|
|
struct sock *nfnl;
|
|
struct sock *nfnl_stash;
|
|
#if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT)
|
|
struct list_head nfnl_acct_list;
|
|
#endif
|
|
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
|
|
struct list_head nfct_timeout_list;
|
|
#endif
|
|
#endif
|
|
#ifdef CONFIG_WEXT_CORE
|
|
struct sk_buff_head wext_nlevents;
|
|
#endif
|
|
struct net_generic __rcu *gen;
|
|
|
|
struct bpf_prog __rcu *flow_dissector_prog;
|
|
|
|
/* 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
|
|
#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
|
|
struct sock *diag_nlsk;
|
|
atomic_t fnhe_genid;
|
|
} __randomize_layout;
|
|
|
|
#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);
|
|
|
|
void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
|
|
|
|
void net_ns_barrier(void);
|
|
#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;
|
|
}
|
|
|
|
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) {}
|
|
#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 fd);
|
|
|
|
#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)
|
|
{
|
|
refcount_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 (!refcount_inc_not_zero(&net->count))
|
|
net = NULL;
|
|
return net;
|
|
}
|
|
|
|
static inline void put_net(struct net *net)
|
|
{
|
|
if (refcount_dec_and_test(&net->count))
|
|
__put_net(net);
|
|
}
|
|
|
|
static inline
|
|
int net_eq(const struct net *net1, const struct net *net2)
|
|
{
|
|
return net1 == net2;
|
|
}
|
|
|
|
static inline int check_net(const struct net *net)
|
|
{
|
|
return refcount_read(&net->count) != 0;
|
|
}
|
|
|
|
void net_drop_ns(void *);
|
|
|
|
#else
|
|
|
|
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;
|
|
}
|
|
|
|
static inline int check_net(const struct net *net)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
#define net_drop_ns NULL
|
|
#endif
|
|
|
|
|
|
typedef struct {
|
|
#ifdef CONFIG_NET_NS
|
|
struct net *net;
|
|
#endif
|
|
} possible_net_t;
|
|
|
|
static inline void write_pnet(possible_net_t *pnet, struct net *net)
|
|
{
|
|
#ifdef CONFIG_NET_NS
|
|
pnet->net = net;
|
|
#endif
|
|
}
|
|
|
|
static inline struct net *read_pnet(const possible_net_t *pnet)
|
|
{
|
|
#ifdef CONFIG_NET_NS
|
|
return pnet->net;
|
|
#else
|
|
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_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 __ref
|
|
#define __net_initdata __initdata
|
|
#define __net_initconst __initconst
|
|
#endif
|
|
|
|
int peernet2id_alloc(struct net *net, struct net *peer);
|
|
int peernet2id(struct net *net, struct net *peer);
|
|
bool peernet_has_id(struct net *net, struct net *peer);
|
|
struct net *get_net_ns_by_id(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);
|
|
unsigned 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 */
|