cregit-Linux how code gets into the kernel

Release 4.12 include/net/xfrm.h

Directory: include/net
#ifndef _NET_XFRM_H

#define _NET_XFRM_H

#include <linux/compiler.h>
#include <linux/xfrm.h>
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/in6.h>
#include <linux/mutex.h>
#include <linux/audit.h>
#include <linux/slab.h>

#include <net/sock.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/flow.h>

#include <linux/interrupt.h>

#include <net/snmp.h>

#define XFRM_PROTO_ESP		50

#define XFRM_PROTO_AH		51

#define XFRM_PROTO_COMP		108

#define XFRM_PROTO_IPIP		4

#define XFRM_PROTO_IPV6		41



#define XFRM_ALIGN4(len)	(((len) + 3) & ~3)

#define XFRM_ALIGN8(len)	(((len) + 7) & ~7)

#define MODULE_ALIAS_XFRM_MODE(family, encap) \
	MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap))

#define MODULE_ALIAS_XFRM_TYPE(family, proto) \
	MODULE_ALIAS("xfrm-type-" __stringify(family) "-" __stringify(proto))


#define XFRM_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.xfrm_statistics, field)

#define XFRM_INC_STATS(net, field)	((void)(net))

/* Organization of SPD aka "XFRM rules"

   Basic objects:
   - policy rule, struct xfrm_policy (=SPD entry)
   - bundle of transformations, struct dst_entry == struct xfrm_dst (=SA bundle)
   - instance of a transformer, struct xfrm_state (=SA)
   - template to clone xfrm_state, struct xfrm_tmpl

   SPD is plain linear list of xfrm_policy rules, ordered by priority.
   (To be compatible with existing pfkeyv2 implementations,
   many rules with priority of 0x7fffffff are allowed to exist and
   such rules are ordered in an unpredictable way, thanks to bsd folks.)

   Lookup is plain linear search until the first match with selector.

   If "action" is "block", then we prohibit the flow, otherwise:
   if "xfrms_nr" is zero, the flow passes untransformed. Otherwise,
   policy entry has list of up to XFRM_MAX_DEPTH transformations,
   described by templates xfrm_tmpl. Each template is resolved
   to a complete xfrm_state (see below) and we pack bundle of transformations
   to a dst_entry returned to requestor.

   dst -. xfrm  .-> xfrm_state #1
    |---. child .-> dst -. xfrm .-> xfrm_state #2
                     |---. child .-> dst -. xfrm .-> xfrm_state #3
                                      |---. child .-> NULL

   Bundles are cached at xrfm_policy struct (field ->bundles).

   Resolution of xrfm_tmpl
   Template contains:
   1. ->mode            Mode: transport or tunnel
   2. ->id.proto        Protocol: AH/ESP/IPCOMP
   3. ->id.daddr        Remote tunnel endpoint, ignored for transport mode.
      Q: allow to resolve security gateway?
   4. ->id.spi          If not zero, static SPI.
   5. ->saddr           Local tunnel endpoint, ignored for transport mode.
   6. ->algos           List of allowed algos. Plain bitmask now.
      Q: ealgos, aalgos, calgos. What a mess...
   7. ->share           Sharing mode.
      Q: how to implement private sharing mode? To add struct sock* to
      flow id?

   Having this template we search through SAD searching for entries
   with appropriate mode/proto/algo, permitted by selector.
   If no appropriate entry found, it is requested from key manager.

   Q: How to find all the bundles referring to a physical path for
      PMTU discovery? Seems, dst should contain list of all parents...
      and enter to infinite locking hierarchy disaster.
      No! It is easier, we will not search for them, let them find us.
      We add genid to each dst plus pointer to genid of raw IP route,
      pmtu disc will update pmtu on raw IP route and increase its genid.
      dst_check() will see this for top level and trigger resyncing
      metrics. Plus, it will be made via sk->sk_dst_cache. Solved.

struct xfrm_state_walk {
struct list_head	all;
u8			state;
u8			dying;
u8			proto;
u32			seq;
struct xfrm_address_filter *filter;

struct xfrm_state_offload {
struct net_device	*dev;
unsigned long		offload_handle;
unsigned int		num_exthdrs;
u8			flags;

/* Full description of state of transformer. */

struct xfrm_state {
possible_net_t		xs_net;
	union {
struct hlist_node	gclist;
struct hlist_node	bydst;
struct hlist_node	bysrc;
struct hlist_node	byspi;

atomic_t		refcnt;
spinlock_t		lock;

struct xfrm_id		id;
struct xfrm_selector	sel;
struct xfrm_mark	mark;
u32			tfcpad;

u32			genid;

	/* Key manager bits */
struct xfrm_state_walk	km;

	/* Parameters of this state. */
	struct {
u32		reqid;
u8		mode;
u8		replay_window;

u8		aalgo, ealgo, calgo;
u8		flags;
u16		family;
xfrm_address_t	saddr;
int		header_len;
int		trailer_len;
u32		extra_flags;
} props;

struct xfrm_lifetime_cfg lft;

	/* Data for transformer */
struct xfrm_algo_auth	*aalg;
struct xfrm_algo	*ealg;
struct xfrm_algo	*calg;
struct xfrm_algo_aead	*aead;
const char		*geniv;

	/* Data for encapsulator */
struct xfrm_encap_tmpl	*encap;

	/* Data for care-of address */
xfrm_address_t	*coaddr;

	/* IPComp needs an IPIP tunnel for handling uncompressed packets */
struct xfrm_state	*tunnel;

	/* If a tunnel, number of users + 1 */
atomic_t		tunnel_users;

	/* State for replay detection */
struct xfrm_replay_state replay;
struct xfrm_replay_state_esn *replay_esn;

	/* Replay detection state at the time we sent the last notification */
struct xfrm_replay_state preplay;
struct xfrm_replay_state_esn *preplay_esn;

	/* The functions for replay detection. */
const struct xfrm_replay *repl;

	/* internal flag that only holds state for delayed aevent at the
         * moment
u32			xflags;

	/* Replay detection notification settings */
u32			replay_maxage;
u32			replay_maxdiff;

	/* Replay detection notification timer */
struct timer_list	rtimer;

	/* Statistics */
struct xfrm_stats	stats;

struct xfrm_lifetime_cur curlft;
struct tasklet_hrtimer	mtimer;

struct xfrm_state_offload xso;

	/* used to fix curlft->add_time when changing date */
long		saved_tmo;

	/* Last used time */
unsigned long		lastused;

struct page_frag xfrag;

	/* Reference to data common to all the instances of this
         * transformer. */
const struct xfrm_type	*type;
struct xfrm_mode	*inner_mode;
struct xfrm_mode	*inner_mode_iaf;
struct xfrm_mode	*outer_mode;

const struct xfrm_type_offload	*type_offload;

	/* Security context */
struct xfrm_sec_ctx	*security;

	/* Private data of this transformer, format is opaque,
         * interpreted by xfrm_type methods. */
void			*data;

static inline struct net *xs_net(struct xfrm_state *x) { return read_pnet(&x->xs_net); }


Alexey Dobriyan23100.00%1100.00%

/* xflags - make enum if more show up */ #define XFRM_TIME_DEFER 1 #define XFRM_SOFT_EXPIRE 2 enum { XFRM_STATE_VOID, XFRM_STATE_ACQ, XFRM_STATE_VALID, XFRM_STATE_ERROR, XFRM_STATE_EXPIRED, XFRM_STATE_DEAD }; /* callback structure passed from either netlink or pfkey */ struct km_event { union { u32 hard; u32 proto; u32 byid; u32 aevent; u32 type; } data; u32 seq; u32 portid; u32 event; struct net *net; }; struct xfrm_replay { void (*advance)(struct xfrm_state *x, __be32 net_seq); int (*check)(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); int (*recheck)(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void (*notify)(struct xfrm_state *x, int event); int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); }; struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; struct dst_entry *(*dst_lookup)(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr); int (*get_saddr)(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); int (*get_tos)(const struct flowi *fl); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { unsigned int family; unsigned int proto; __be16 eth_proto; struct module *owner; const struct xfrm_type *type_map[IPPROTO_MAX]; const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); void (*init_tempsel)(struct xfrm_selector *sel, const struct flowi *fl); void (*init_temprop)(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*output_finish)(struct sock *sk, struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); int (*extract_output)(struct xfrm_state *x, struct sk_buff *skb); int (*transport_finish)(struct sk_buff *skb, int async); void (*local_error)(struct sk_buff *skb, u32 mtu); }; int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family); struct xfrm_input_afinfo { unsigned int family; int (*callback)(struct sk_buff *skb, u8 protocol, int err); }; int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { char *description; struct module *owner; u8 proto; u8 flags; #define XFRM_TYPE_NON_FRAGMENT 1 #define XFRM_TYPE_REPLAY_PROT 2 #define XFRM_TYPE_LOCAL_COADDR 4 #define XFRM_TYPE_REMOTE_COADDR 8 int (*init_state)(struct xfrm_state *x); void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); /* Estimate maximal size of result of transformation of a dgram */ u32 (*get_mtu)(struct xfrm_state *, int size); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { char *description; struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); int (*input_tail)(struct xfrm_state *x, struct sk_buff *skb); int (*xmit)(struct xfrm_state *, struct sk_buff *pskb, netdev_features_t features); }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); struct xfrm_mode { /* * Remove encapsulation header. * * The IP header will be moved over the top of the encapsulation * header. * * On entry, the transport header shall point to where the IP header * should be and the network header shall be set to where the IP * header currently is. skb->data shall point to the start of the * payload. */ int (*input2)(struct xfrm_state *x, struct sk_buff *skb); /* * This is the actual input entry point. * * For transport mode and equivalent this would be identical to * input2 (which does not need to be set). While tunnel mode * and equivalent would set this to the tunnel encapsulation function * xfrm4_prepare_input that would in turn call input2. */ int (*input)(struct xfrm_state *x, struct sk_buff *skb); /* * Add encapsulation header. * * On exit, the transport header will be set to the start of the * encapsulation header to be filled in by x->type->output and * the mac header will be set to the nextheader (protocol for * IPv4) field of the extension header directly preceding the * encapsulation header, or in its absence, that of the top IP * header. The value of the network header will always point * to the top IP header while skb->data will point to the payload. */ int (*output2)(struct xfrm_state *x,struct sk_buff *skb); /* * This is the actual output entry point. * * For transport mode and equivalent this would be identical to * output2 (which does not need to be set). While tunnel mode * and equivalent would set this to a tunnel encapsulation function * (xfrm4_prepare_output or xfrm6_prepare_output) that would in turn * call output2. */ int (*output)(struct xfrm_state *x, struct sk_buff *skb); /* * Adjust pointers into the packet and do GSO segmentation. */ struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features); /* * Adjust pointers into the packet when IPsec is done at layer2. */ void (*xmit)(struct xfrm_state *x, struct sk_buff *skb); struct xfrm_state_afinfo *afinfo; struct module *owner; unsigned int encap; int flags; }; /* Flags for xfrm_mode. */ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; int xfrm_register_mode(struct xfrm_mode *mode, int family); int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
static inline int xfrm_af2proto(unsigned int family) { switch(family) { case AF_INET: return IPPROTO_IPIP; case AF_INET6: return IPPROTO_IPV6; default: return 0; } }


Kazunori Miyazawa33100.00%1100.00%

static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { if ((ipproto == IPPROTO_IPIP && x-> == AF_INET) || (ipproto == IPPROTO_IPV6 && x-> == AF_INET6)) return x->inner_mode; else return x->inner_mode_iaf; }


Kazunori Miyazawa58100.00%1100.00%

struct xfrm_tmpl { /* id in template is interpreted as: * daddr - destination of tunnel, may be zero for transport mode. * spi - zero to acquire spi. Not zero if spi is static, then * daddr must be fixed too. * proto - AH/ESP/IPCOMP */ struct xfrm_id id; /* Source address of tunnel. Ignored, if it is not a tunnel. */ xfrm_address_t saddr; unsigned short encap_family; u32 reqid; /* Mode: transport, tunnel etc. */ u8 mode; /* Sharing mode: unique, this session only, this user only etc. */ u8 share; /* May skip this transfomration if no SA is found */ u8 optional; /* Skip aalgos/ealgos/calgos checks. */ u8 allalgs; /* Bit mask of algos allowed for acquisition */ u32 aalgos; u32 ealgos; u32 calgos; }; #define XFRM_MAX_DEPTH 6 #define XFRM_MAX_OFFLOAD_DEPTH 1 struct xfrm_policy_walk_entry { struct list_head all; u8 dead; }; struct xfrm_policy_walk { struct xfrm_policy_walk_entry walk; u8 type; u32 seq; }; struct xfrm_policy_queue { struct sk_buff_head hold_queue; struct timer_list hold_timer; unsigned long timeout; }; struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; /* This lock only affects elements except for entry. */ rwlock_t lock; atomic_t refcnt; struct timer_list timer; struct flow_cache_object flo; atomic_t genid; u32 priority; u32 index; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; struct xfrm_policy_walk_entry walk; struct xfrm_policy_queue polq; u8 type; u8 action; u8 flags; u8 xfrm_nr; u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; struct rcu_head rcu; };
static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); }


Alexey Dobriyan2395.83%150.00%
David S. Miller14.17%150.00%

struct xfrm_kmaddress { xfrm_address_t local; xfrm_address_t remote; u32 reserved; u16 family; }; struct xfrm_migrate { xfrm_address_t old_daddr; xfrm_address_t old_saddr; xfrm_address_t new_daddr; xfrm_address_t new_saddr; u8 proto; u8 mode; u16 reserved; u32 reqid; u16 old_family; u16 new_family; }; #define XFRM_KM_TIMEOUT 30 /* what happened */ #define XFRM_REPLAY_UPDATE XFRM_AE_CR #define XFRM_REPLAY_TIMEOUT XFRM_AE_CE /* default aevent timeout in units of 100ms */ #define XFRM_AE_ETIME 10 /* Async Event timer multiplier */ #define XFRM_AE_ETH_M 10 /* default seq threshold size */ #define XFRM_AE_SEQT_SIZE 2 struct xfrm_mgr { struct list_head list; int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); int (*migrate)(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k); bool (*is_alive)(const struct km_event *c); }; int xfrm_register_km(struct xfrm_mgr *km); int xfrm_unregister_km(struct xfrm_mgr *km); struct xfrm_tunnel_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; } header; union { struct ip_tunnel *ip4; struct ip6_tnl *ip6; } tunnel; }; #define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0])) /* * This structure is used for the duration where packets are being * transformed by IPsec. As soon as the packet leaves IPsec the * area beyond the generic IP part may be overwritten. */ struct xfrm_skb_cb { struct xfrm_tunnel_skb_cb header; /* Sequence number for replay protection. */ union { struct { __u32 low; __u32 hi; } output; struct { __be32 low; __be32 hi; } input; } seq; }; #define XFRM_SKB_CB(__skb) ((struct xfrm_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the afinfo prepare_input/prepare_output functions * to transmit header information to the mode input/output functions. */ struct xfrm_mode_skb_cb { struct xfrm_tunnel_skb_cb header; /* Copied from header for IPv4, always set to zero and DF for IPv6. */ __be16 id; __be16 frag_off; /* IP header length (excluding options or extension headers). */ u8 ihl; /* TOS for IPv4, class for IPv6. */ u8 tos; /* TTL for IPv4, hop limitfor IPv6. */ u8 ttl; /* Protocol for IPv4, NH for IPv6. */ u8 protocol; /* Option length for IPv4, zero for IPv6. */ u8 optlen; /* Used by IPv6 only, zero for IPv4. */ u8 flow_lbl[3]; }; #define XFRM_MODE_SKB_CB(__skb) ((struct xfrm_mode_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the input processing to locate the SPI and * related information. */ struct xfrm_spi_skb_cb { struct xfrm_tunnel_skb_cb header; unsigned int daddroff; unsigned int family; __be32 seq; }; #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0])) #ifdef CONFIG_AUDITSYSCALL
static inline struct audit_buffer *xfrm_audit_start(const char *op) { struct audit_buffer *audit_buf = NULL; if (audit_enabled == 0) return NULL; audit_buf = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_MAC_IPSEC_EVENT); if (audit_buf == NULL) return NULL; audit_log_format(audit_buf, "op=%s", op); return audit_buf; }


Joy Latten4265.62%150.00%
Paul Moore2234.38%150.00%

static inline void xfrm_audit_helper_usrinfo(bool task_valid, struct audit_buffer *audit_buf) { const unsigned int auid = from_kuid(&init_user_ns, task_valid ? audit_get_loginuid(current) : INVALID_UID); const unsigned int ses = task_valid ? audit_get_sessionid(current) : (unsigned int) -1; audit_log_format(audit_buf, " auid=%u ses=%u"