android_kernel_samsung_msm8976/include/net/netfilter/nf_conntrack.h
Alan Stern e041c68341 [PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe.  There is no
protection against entries being added to or removed from a chain while the
chain is in use.  The issues were discussed in this thread:

    http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2

We noticed that notifier chains in the kernel fall into two basic usage
classes:

	"Blocking" chains are always called from a process context
	and the callout routines are allowed to sleep;

	"Atomic" chains can be called from an atomic context and
	the callout routines are not allowed to sleep.

We decided to codify this distinction and make it part of the API.  Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name).  New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain.  The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.

With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed.  For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections.  (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)

There are some limitations, which should not be too hard to live with.  For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem.  Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain.  (This did happen in a couple of places and the code
had to be changed to avoid it.)

Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization.  Instead we use RCU.  The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.

Here is the list of chains that we adjusted and their classifications.  None
of them use the raw API, so for the moment it is only a placeholder.

  ATOMIC CHAINS
  -------------
arch/i386/kernel/traps.c:		i386die_chain
arch/ia64/kernel/traps.c:		ia64die_chain
arch/powerpc/kernel/traps.c:		powerpc_die_chain
arch/sparc64/kernel/traps.c:		sparc64die_chain
arch/x86_64/kernel/traps.c:		die_chain
drivers/char/ipmi/ipmi_si_intf.c:	xaction_notifier_list
kernel/panic.c:				panic_notifier_list
kernel/profile.c:			task_free_notifier
net/bluetooth/hci_core.c:		hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c:	ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c:	ip_conntrack_expect_chain
net/ipv6/addrconf.c:			inet6addr_chain
net/netfilter/nf_conntrack_core.c:	nf_conntrack_chain
net/netfilter/nf_conntrack_core.c:	nf_conntrack_expect_chain
net/netlink/af_netlink.c:		netlink_chain

  BLOCKING CHAINS
  ---------------
arch/powerpc/platforms/pseries/reconfig.c:	pSeries_reconfig_chain
arch/s390/kernel/process.c:		idle_chain
arch/x86_64/kernel/process.c		idle_notifier
drivers/base/memory.c:			memory_chain
drivers/cpufreq/cpufreq.c		cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c		cpufreq_transition_notifier_list
drivers/macintosh/adb.c:		adb_client_list
drivers/macintosh/via-pmu.c		sleep_notifier_list
drivers/macintosh/via-pmu68k.c		sleep_notifier_list
drivers/macintosh/windfarm_core.c	wf_client_list
drivers/usb/core/notify.c		usb_notifier_list
drivers/video/fbmem.c			fb_notifier_list
kernel/cpu.c				cpu_chain
kernel/module.c				module_notify_list
kernel/profile.c			munmap_notifier
kernel/profile.c			task_exit_notifier
kernel/sys.c				reboot_notifier_list
net/core/dev.c				netdev_chain
net/decnet/dn_dev.c:			dnaddr_chain
net/ipv4/devinet.c:			inetaddr_chain

It's possible that some of these classifications are wrong.  If they are,
please let us know or submit a patch to fix them.  Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)

The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.

[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 08:44:50 -08:00

399 lines
11 KiB
C

/*
* Connection state tracking for netfilter. This is separated from,
* but required by, the (future) NAT layer; it can also be used by an iptables
* extension.
*
* 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
* - generalize L3 protocol dependent part.
*
* Derived from include/linux/netfiter_ipv4/ip_conntrack.h
*/
#ifndef _NF_CONNTRACK_H
#define _NF_CONNTRACK_H
#include <linux/netfilter/nf_conntrack_common.h>
#ifdef __KERNEL__
#include <linux/config.h>
#include <linux/bitops.h>
#include <linux/compiler.h>
#include <asm/atomic.h>
#include <linux/netfilter/nf_conntrack_tcp.h>
#include <linux/netfilter/nf_conntrack_sctp.h>
#include <net/netfilter/ipv4/nf_conntrack_icmp.h>
#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
#include <net/netfilter/nf_conntrack_tuple.h>
/* per conntrack: protocol private data */
union nf_conntrack_proto {
/* insert conntrack proto private data here */
struct ip_ct_sctp sctp;
struct ip_ct_tcp tcp;
struct ip_ct_icmp icmp;
struct nf_ct_icmpv6 icmpv6;
};
union nf_conntrack_expect_proto {
/* insert expect proto private data here */
};
/* Add protocol helper include file here */
#include <linux/netfilter/nf_conntrack_ftp.h>
/* per conntrack: application helper private data */
union nf_conntrack_help {
/* insert conntrack helper private data (master) here */
struct ip_ct_ftp_master ct_ftp_info;
};
#include <linux/types.h>
#include <linux/skbuff.h>
#ifdef CONFIG_NETFILTER_DEBUG
#define NF_CT_ASSERT(x) \
do { \
if (!(x)) \
/* Wooah! I'm tripping my conntrack in a frenzy of \
netplay... */ \
printk("NF_CT_ASSERT: %s:%i(%s)\n", \
__FILE__, __LINE__, __FUNCTION__); \
} while(0)
#else
#define NF_CT_ASSERT(x)
#endif
struct nf_conntrack_helper;
/* nf_conn feature for connections that have a helper */
struct nf_conn_help {
/* Helper. if any */
struct nf_conntrack_helper *helper;
union nf_conntrack_help help;
/* Current number of expected connections */
unsigned int expecting;
};
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
struct nf_conn
{
/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
plus 1 for any connection(s) we are `master' for */
struct nf_conntrack ct_general;
/* XXX should I move this to the tail ? - Y.K */
/* These are my tuples; original and reply */
struct nf_conntrack_tuple_hash tuplehash[IP_CT_DIR_MAX];
/* Have we seen traffic both ways yet? (bitset) */
unsigned long status;
/* If we were expected by an expectation, this will be it */
struct nf_conn *master;
/* Timer function; drops refcnt when it goes off. */
struct timer_list timeout;
#ifdef CONFIG_NF_CT_ACCT
/* Accounting Information (same cache line as other written members) */
struct ip_conntrack_counter counters[IP_CT_DIR_MAX];
#endif
/* Unique ID that identifies this conntrack*/
unsigned int id;
/* features - nat, helper, ... used by allocating system */
u_int32_t features;
#if defined(CONFIG_NF_CONNTRACK_MARK)
u_int32_t mark;
#endif
/* Storage reserved for other modules: */
union nf_conntrack_proto proto;
/* features dynamically at the end: helper, nat (both optional) */
char data[0];
};
struct nf_conntrack_expect
{
/* Internal linked list (global expectation list) */
struct list_head list;
/* We expect this tuple, with the following mask */
struct nf_conntrack_tuple tuple, mask;
/* Function to call after setup and insertion */
void (*expectfn)(struct nf_conn *new,
struct nf_conntrack_expect *this);
/* The conntrack of the master connection */
struct nf_conn *master;
/* Timer function; deletes the expectation. */
struct timer_list timeout;
/* Usage count. */
atomic_t use;
/* Unique ID */
unsigned int id;
/* Flags */
unsigned int flags;
#ifdef CONFIG_NF_NAT_NEEDED
/* This is the original per-proto part, used to map the
* expected connection the way the recipient expects. */
union nf_conntrack_manip_proto saved_proto;
/* Direction relative to the master connection. */
enum ip_conntrack_dir dir;
#endif
};
#define NF_CT_EXPECT_PERMANENT 0x1
static inline struct nf_conn *
nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash)
{
return container_of(hash, struct nf_conn,
tuplehash[hash->tuple.dst.dir]);
}
/* get master conntrack via master expectation */
#define master_ct(conntr) (conntr->master)
/* Alter reply tuple (maybe alter helper). */
extern void
nf_conntrack_alter_reply(struct nf_conn *conntrack,
const struct nf_conntrack_tuple *newreply);
/* Is this tuple taken? (ignoring any belonging to the given
conntrack). */
extern int
nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
const struct nf_conn *ignored_conntrack);
/* Return conntrack_info and tuple hash for given skb. */
static inline struct nf_conn *
nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)
{
*ctinfo = skb->nfctinfo;
return (struct nf_conn *)skb->nfct;
}
/* decrement reference count on a conntrack */
static inline void nf_ct_put(struct nf_conn *ct)
{
NF_CT_ASSERT(ct);
nf_conntrack_put(&ct->ct_general);
}
/* Protocol module loading */
extern int nf_ct_l3proto_try_module_get(unsigned short l3proto);
extern void nf_ct_l3proto_module_put(unsigned short l3proto);
extern struct nf_conntrack_tuple_hash *
__nf_conntrack_find(const struct nf_conntrack_tuple *tuple,
const struct nf_conn *ignored_conntrack);
extern void nf_conntrack_hash_insert(struct nf_conn *ct);
extern struct nf_conntrack_expect *
__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
extern struct nf_conntrack_expect *
nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
extern void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
extern void nf_ct_remove_expectations(struct nf_conn *ct);
extern void nf_conntrack_flush(void);
extern struct nf_conntrack_helper *
nf_ct_helper_find_get( const struct nf_conntrack_tuple *tuple);
extern void nf_ct_helper_put(struct nf_conntrack_helper *helper);
extern struct nf_conntrack_helper *
__nf_conntrack_helper_find_byname(const char *name);
extern int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
const struct nf_conntrack_tuple *orig);
extern void __nf_ct_refresh_acct(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct sk_buff *skb,
unsigned long extra_jiffies,
int do_acct);
/* Refresh conntrack for this many jiffies and do accounting */
static inline void nf_ct_refresh_acct(struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct sk_buff *skb,
unsigned long extra_jiffies)
{
__nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, 1);
}
/* Refresh conntrack for this many jiffies */
static inline void nf_ct_refresh(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned long extra_jiffies)
{
__nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, 0);
}
/* These are for NAT. Icky. */
/* Update TCP window tracking data when NAT mangles the packet */
extern void nf_conntrack_tcp_update(struct sk_buff *skb,
unsigned int dataoff,
struct nf_conn *conntrack,
int dir);
/* Call me when a conntrack is destroyed. */
extern void (*nf_conntrack_destroyed)(struct nf_conn *conntrack);
/* Fake conntrack entry for untracked connections */
extern struct nf_conn nf_conntrack_untracked;
extern int nf_ct_no_defrag;
/* Iterate over all conntracks: if iter returns true, it's deleted. */
extern void
nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data);
extern void nf_conntrack_free(struct nf_conn *ct);
extern struct nf_conn *
nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
const struct nf_conntrack_tuple *repl);
/* It's confirmed if it is, or has been in the hash table. */
static inline int nf_ct_is_confirmed(struct nf_conn *ct)
{
return test_bit(IPS_CONFIRMED_BIT, &ct->status);
}
static inline int nf_ct_is_dying(struct nf_conn *ct)
{
return test_bit(IPS_DYING_BIT, &ct->status);
}
extern unsigned int nf_conntrack_htable_size;
#define NF_CT_STAT_INC(count) (__get_cpu_var(nf_conntrack_stat).count++)
#ifdef CONFIG_NF_CONNTRACK_EVENTS
#include <linux/notifier.h>
#include <linux/interrupt.h>
struct nf_conntrack_ecache {
struct nf_conn *ct;
unsigned int events;
};
DECLARE_PER_CPU(struct nf_conntrack_ecache, nf_conntrack_ecache);
#define CONNTRACK_ECACHE(x) (__get_cpu_var(nf_conntrack_ecache).x)
extern struct atomic_notifier_head nf_conntrack_chain;
extern struct atomic_notifier_head nf_conntrack_expect_chain;
static inline int nf_conntrack_register_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_register(&nf_conntrack_chain, nb);
}
static inline int nf_conntrack_unregister_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_unregister(&nf_conntrack_chain, nb);
}
static inline int
nf_conntrack_expect_register_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_register(&nf_conntrack_expect_chain, nb);
}
static inline int
nf_conntrack_expect_unregister_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_unregister(&nf_conntrack_expect_chain,
nb);
}
extern void nf_ct_deliver_cached_events(const struct nf_conn *ct);
extern void __nf_ct_event_cache_init(struct nf_conn *ct);
static inline void
nf_conntrack_event_cache(enum ip_conntrack_events event,
const struct sk_buff *skb)
{
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
struct nf_conntrack_ecache *ecache;
local_bh_disable();
ecache = &__get_cpu_var(nf_conntrack_ecache);
if (ct != ecache->ct)
__nf_ct_event_cache_init(ct);
ecache->events |= event;
local_bh_enable();
}
static inline void nf_conntrack_event(enum ip_conntrack_events event,
struct nf_conn *ct)
{
if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
atomic_notifier_call_chain(&nf_conntrack_chain, event, ct);
}
static inline void
nf_conntrack_expect_event(enum ip_conntrack_expect_events event,
struct nf_conntrack_expect *exp)
{
atomic_notifier_call_chain(&nf_conntrack_expect_chain, event, exp);
}
#else /* CONFIG_NF_CONNTRACK_EVENTS */
static inline void nf_conntrack_event_cache(enum ip_conntrack_events event,
const struct sk_buff *skb) {}
static inline void nf_conntrack_event(enum ip_conntrack_events event,
struct nf_conn *ct) {}
static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) {}
static inline void
nf_conntrack_expect_event(enum ip_conntrack_expect_events event,
struct nf_conntrack_expect *exp) {}
#endif /* CONFIG_NF_CONNTRACK_EVENTS */
/* no helper, no nat */
#define NF_CT_F_BASIC 0
/* for helper */
#define NF_CT_F_HELP 1
/* for nat. */
#define NF_CT_F_NAT 2
#define NF_CT_F_NUM 4
extern int
nf_conntrack_register_cache(u_int32_t features, const char *name, size_t size);
extern void
nf_conntrack_unregister_cache(u_int32_t features);
/* valid combinations:
* basic: nf_conn, nf_conn .. nf_conn_help
* nat: nf_conn .. nf_conn_nat, nf_conn .. nf_conn_nat, nf_conn help
*/
static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
{
unsigned int offset = sizeof(struct nf_conn);
if (!(ct->features & NF_CT_F_HELP))
return NULL;
return (struct nf_conn_help *) ((void *)ct + offset);
}
#endif /* __KERNEL__ */
#endif /* _NF_CONNTRACK_H */