Changes in 4.9.169 x86/power: Fix some ordering bugs in __restore_processor_context() x86/power/64: Use struct desc_ptr for the IDT in struct saved_context x86/power/32: Move SYSENTER MSR restoration to fix_processor_context() x86/power: Make restore_processor_context() sane powerpc/tm: Limit TM code inside PPC_TRANSACTIONAL_MEM kbuild: clang: choose GCC_TOOLCHAIN_DIR not on LD x86: vdso: Use $LD instead of $CC to link x86/vdso: Drop implicit common-page-size linker flag lib/string.c: implement a basic bcmp powerpc: Fix invalid use of register expressions powerpc/64s: Add barrier_nospec powerpc/64s: Add support for ori barrier_nospec patching powerpc: Avoid code patching freed init sections powerpc/64s: Patch barrier_nospec in modules powerpc/64s: Enable barrier_nospec based on firmware settings powerpc: Use barrier_nospec in copy_from_user() powerpc/64: Use barrier_nospec in syscall entry powerpc/64s: Enhance the information in cpu_show_spectre_v1() powerpc64s: Show ori31 availability in spectre_v1 sysfs file not v2 powerpc/64: Disable the speculation barrier from the command line powerpc/64: Make stf barrier PPC_BOOK3S_64 specific. powerpc/64: Add CONFIG_PPC_BARRIER_NOSPEC powerpc/64: Call setup_barrier_nospec() from setup_arch() powerpc/64: Make meltdown reporting Book3S 64 specific powerpc/fsl: Add barrier_nospec implementation for NXP PowerPC Book3E powerpc/fsl: Sanitize the syscall table for NXP PowerPC 32 bit platforms powerpc/asm: Add a patch_site macro & helpers for patching instructions powerpc/64s: Add new security feature flags for count cache flush powerpc/64s: Add support for software count cache flush powerpc/pseries: Query hypervisor for count cache flush settings powerpc/powernv: Query firmware for count cache flush settings powerpc/fsl: Add infrastructure to fixup branch predictor flush powerpc/fsl: Add macro to flush the branch predictor powerpc/fsl: Fix spectre_v2 mitigations reporting powerpc/fsl: Emulate SPRN_BUCSR register powerpc/fsl: Add nospectre_v2 command line argument powerpc/fsl: Flush the branch predictor at each kernel entry (64bit) powerpc/fsl: Flush the branch predictor at each kernel entry (32 bit) powerpc/fsl: Flush branch predictor when entering KVM powerpc/fsl: Enable runtime patching if nospectre_v2 boot arg is used powerpc/fsl: Update Spectre v2 reporting powerpc/fsl: Fixed warning: orphan section `__btb_flush_fixup' powerpc/fsl: Fix the flush of branch predictor. powerpc/security: Fix spectre_v2 reporting arm64: kaslr: Reserve size of ARM64_MEMSTART_ALIGN in linear region tty: mark Siemens R3964 line discipline as BROKEN tty: ldisc: add sysctl to prevent autoloading of ldiscs ipv6: Fix dangling pointer when ipv6 fragment ipv6: sit: reset ip header pointer in ipip6_rcv kcm: switch order of device registration to fix a crash net: rds: force to destroy connection if t_sock is NULL in rds_tcp_kill_sock(). openvswitch: fix flow actions reallocation qmi_wwan: add Olicard 600 sctp: initialize _pad of sockaddr_in before copying to user memory tcp: Ensure DCTCP reacts to losses vrf: check accept_source_route on the original netdevice bnxt_en: Reset device on RX buffer errors. bnxt_en: Improve RX consumer index validity check. net/mlx5e: Add a lock on tir list netns: provide pure entropy for net_hash_mix() net: ethtool: not call vzalloc for zero sized memory request ip6_tunnel: Match to ARPHRD_TUNNEL6 for dev type ALSA: seq: Fix OOB-reads from strlcpy parisc: Detect QEMU earlier in boot process include/linux/bitrev.h: fix constant bitrev ASoC: fsl_esai: fix channel swap issue when stream starts Btrfs: do not allow trimming when a fs is mounted with the nologreplay option block: do not leak memory in bio_copy_user_iov() genirq: Respect IRQCHIP_SKIP_SET_WAKE in irq_chip_set_wake_parent() virtio: Honour 'may_reduce_num' in vring_create_virtqueue ARM: dts: at91: Fix typo in ISC_D0 on PC9 arm64: futex: Fix FUTEX_WAKE_OP atomic ops with non-zero result value parisc: Use cr16 interval timers unconditionally on qemu xen: Prevent buffer overflow in privcmd ioctl sched/fair: Do not re-read ->h_load_next during hierarchical load calculation xtensa: fix return_address PCI: Add function 1 DMA alias quirk for Marvell 9170 SATA controller Linux 4.9.169 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
397 lines
9.4 KiB
C
397 lines
9.4 KiB
C
/*
|
|
* 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 <net/netns/mpls.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 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.
|
|
*/
|
|
spinlock_t rules_mod_lock;
|
|
|
|
u32 hash_mix;
|
|
atomic64_t cookie_gen;
|
|
|
|
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 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 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 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;
|
|
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;
|
|
|
|
/* 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
|
|
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 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)
|
|
{
|
|
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;
|
|
}
|
|
|
|
static inline int check_net(const struct net *net)
|
|
{
|
|
return atomic_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
|
|
}
|
|
|
|
#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;
|
|
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 */
|