linux-stable/net/netfilter/nf_conntrack_expect.c

744 lines
20 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* Expectation handling for nf_conntrack. */
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
* (c) 2005-2012 Patrick McHardy <kaber@trash.net>
*/
#include <linux/types.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/kernel.h>
#include <linux/siphash.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/netns/hash.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>
unsigned int nf_ct_expect_hsize __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);
struct hlist_head *nf_ct_expect_hash __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hash);
unsigned int nf_ct_expect_max __read_mostly;
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
static siphash_aligned_key_t nf_ct_expect_hashrnd;
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
u32 portid, int report)
{
struct nf_conn_help *master_help = nfct_help(exp->master);
struct net *net = nf_ct_exp_net(exp);
struct nf_conntrack_net *cnet;
WARN_ON(!master_help);
WARN_ON(timer_pending(&exp->timeout));
hlist_del_rcu(&exp->hnode);
cnet = nf_ct_pernet(net);
cnet->expect_count--;
hlist_del_rcu(&exp->lnode);
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
master_help->expecting[exp->class]--;
nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
nf_ct_expect_put(exp);
NF_CT_STAT_INC(net, expect_delete);
}
EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report);
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-16 21:43:17 +00:00
static void nf_ct_expectation_timed_out(struct timer_list *t)
{
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-16 21:43:17 +00:00
struct nf_conntrack_expect *exp = from_timer(exp, t, timeout);
spin_lock_bh(&nf_conntrack_expect_lock);
nf_ct_unlink_expect(exp);
spin_unlock_bh(&nf_conntrack_expect_lock);
nf_ct_expect_put(exp);
}
static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
struct {
union nf_inet_addr dst_addr;
u32 net_mix;
u16 dport;
u8 l3num;
u8 protonum;
} __aligned(SIPHASH_ALIGNMENT) combined;
u32 hash;
get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd));
memset(&combined, 0, sizeof(combined));
combined.dst_addr = tuple->dst.u3;
combined.net_mix = net_hash_mix(n);
combined.dport = (__force __u16)tuple->dst.u.all;
combined.l3num = tuple->src.l3num;
combined.protonum = tuple->dst.protonum;
hash = siphash(&combined, sizeof(combined), &nf_ct_expect_hashrnd);
return reciprocal_scale(hash, nf_ct_expect_hsize);
}
static bool
nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_expect *i,
const struct nf_conntrack_zone *zone,
const struct net *net)
{
return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
net_eq(net, nf_ct_net(i->master)) &&
nf_ct_zone_equal_any(i->master, zone);
}
bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
{
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(nf_ct_remove_expect);
struct nf_conntrack_expect *
__nf_ct_expect_find(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_net *cnet = nf_ct_pernet(net);
struct nf_conntrack_expect *i;
unsigned int h;
if (!cnet->expect_count)
return NULL;
h = nf_ct_expect_dst_hash(net, tuple);
hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) {
if (nf_ct_exp_equal(tuple, i, zone, net))
return i;
}
return NULL;
}
EXPORT_SYMBOL_GPL(__nf_ct_expect_find);
/* Just find a expectation corresponding to a tuple. */
struct nf_conntrack_expect *
nf_ct_expect_find_get(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i;
rcu_read_lock();
i = __nf_ct_expect_find(net, zone, tuple);
if (i && !refcount_inc_not_zero(&i->use))
i = NULL;
rcu_read_unlock();
return i;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_find_get);
/* If an expectation for this connection is found, it gets delete from
* global list then returned. */
struct nf_conntrack_expect *
nf_ct_find_expectation(struct net *net,
const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple, bool unlink)
{
struct nf_conntrack_net *cnet = nf_ct_pernet(net);
struct nf_conntrack_expect *i, *exp = NULL;
unsigned int h;
if (!cnet->expect_count)
return NULL;
h = nf_ct_expect_dst_hash(net, tuple);
hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
nf_ct_exp_equal(tuple, i, zone, net)) {
exp = i;
break;
}
}
if (!exp)
return NULL;
/* If master is not in hash table yet (ie. packet hasn't left
this machine yet), how can other end know about expected?
Hence these are not the droids you are looking for (if
master ct never got confirmed, we'd hold a reference to it
and weird things would happen to future packets). */
if (!nf_ct_is_confirmed(exp->master))
return NULL;
/* Avoid race with other CPUs, that for exp->master ct, is
* about to invoke ->destroy(), or nf_ct_delete() via timeout
* or early_drop().
*
* The refcount_inc_not_zero() check tells: If that fails, we
* know that the ct is being destroyed. If it succeeds, we
* can be sure the ct cannot disappear underneath.
*/
if (unlikely(nf_ct_is_dying(exp->master) ||
!refcount_inc_not_zero(&exp->master->ct_general.use)))
return NULL;
if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) {
refcount_inc(&exp->use);
return exp;
} else if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
return exp;
}
/* Undo exp->master refcnt increase, if del_timer() failed */
nf_ct_put(exp->master);
return NULL;
}
/* delete all expectations for this conntrack */
void nf_ct_remove_expectations(struct nf_conn *ct)
{
struct nf_conn_help *help = nfct_help(ct);
struct nf_conntrack_expect *exp;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *next;
/* Optimization: most connection never expect any others. */
if (!help)
return;
spin_lock_bh(&nf_conntrack_expect_lock);
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
nf_ct_remove_expect(exp);
}
spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);
/* Would two expected things clash? */
static inline int expect_clash(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
/* Part covered by intersection of masks must be unequal,
otherwise they clash */
struct nf_conntrack_tuple_mask intersect_mask;
int count;
intersect_mask.src.u.all = a->mask.src.u.all & b->mask.src.u.all;
for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
intersect_mask.src.u3.all[count] =
a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
}
return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
netfilter: nf_conntrack: add direction support for zones This work adds a direction parameter to netfilter zones, so identity separation can be performed only in original/reply or both directions (default). This basically opens up the possibility of doing NAT with conflicting IP address/port tuples from multiple, isolated tenants on a host (e.g. from a netns) without requiring each tenant to NAT twice resp. to use its own dedicated IP address to SNAT to, meaning overlapping tuples can be made unique with the zone identifier in original direction, where the NAT engine will then allocate a unique tuple in the commonly shared default zone for the reply direction. In some restricted, local DNAT cases, also port redirection could be used for making the reply traffic unique w/o requiring SNAT. The consensus we've reached and discussed at NFWS and since the initial implementation [1] was to directly integrate the direction meta data into the existing zones infrastructure, as opposed to the ct->mark approach we proposed initially. As we pass the nf_conntrack_zone object directly around, we don't have to touch all call-sites, but only those, that contain equality checks of zones. Thus, based on the current direction (original or reply), we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID. CT expectations are direction-agnostic entities when expectations are being compared among themselves, so we can only use the identifier in this case. Note that zone identifiers can not be included into the hash mix anymore as they don't contain a "stable" value that would be equal for both directions at all times, f.e. if only zone->id would unconditionally be xor'ed into the table slot hash, then replies won't find the corresponding conntracking entry anymore. If no particular direction is specified when configuring zones, the behaviour is exactly as we expect currently (both directions). Support has been added for the CT netlink interface as well as the x_tables raw CT target, which both already offer existing interfaces to user space for the configuration of zones. Below a minimal, simplified collision example (script in [2]) with netperf sessions: +--- tenant-1 ---+ mark := 1 | netperf |--+ +----------------+ | CT zone := mark [ORIGINAL] [ip,sport] := X +--------------+ +--- gateway ---+ | mark routing |--| SNAT |-- ... + +--------------+ +---------------+ | +--- tenant-2 ---+ | ~~~|~~~ | netperf |--+ +-----------+ | +----------------+ mark := 2 | netserver |------ ... + [ip,sport] := X +-----------+ [ip,port] := Y On the gateway netns, example: iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark conntrack dump from gateway netns: netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2 Taking this further, test script in [2] creates 200 tenants and runs original-tuple colliding netperf sessions each. A conntrack -L dump in the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED state as expected. I also did run various other tests with some permutations of the script, to mention some: SNAT in random/random-fully/persistent mode, no zones (no overlaps), static zones (original, reply, both directions), etc. [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/ [2] https://paste.fedoraproject.org/242835/65657871/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2015-08-14 14:03:39 +00:00
nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
return nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
netfilter: nf_conntrack: add direction support for zones This work adds a direction parameter to netfilter zones, so identity separation can be performed only in original/reply or both directions (default). This basically opens up the possibility of doing NAT with conflicting IP address/port tuples from multiple, isolated tenants on a host (e.g. from a netns) without requiring each tenant to NAT twice resp. to use its own dedicated IP address to SNAT to, meaning overlapping tuples can be made unique with the zone identifier in original direction, where the NAT engine will then allocate a unique tuple in the commonly shared default zone for the reply direction. In some restricted, local DNAT cases, also port redirection could be used for making the reply traffic unique w/o requiring SNAT. The consensus we've reached and discussed at NFWS and since the initial implementation [1] was to directly integrate the direction meta data into the existing zones infrastructure, as opposed to the ct->mark approach we proposed initially. As we pass the nf_conntrack_zone object directly around, we don't have to touch all call-sites, but only those, that contain equality checks of zones. Thus, based on the current direction (original or reply), we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID. CT expectations are direction-agnostic entities when expectations are being compared among themselves, so we can only use the identifier in this case. Note that zone identifiers can not be included into the hash mix anymore as they don't contain a "stable" value that would be equal for both directions at all times, f.e. if only zone->id would unconditionally be xor'ed into the table slot hash, then replies won't find the corresponding conntracking entry anymore. If no particular direction is specified when configuring zones, the behaviour is exactly as we expect currently (both directions). Support has been added for the CT netlink interface as well as the x_tables raw CT target, which both already offer existing interfaces to user space for the configuration of zones. Below a minimal, simplified collision example (script in [2]) with netperf sessions: +--- tenant-1 ---+ mark := 1 | netperf |--+ +----------------+ | CT zone := mark [ORIGINAL] [ip,sport] := X +--------------+ +--- gateway ---+ | mark routing |--| SNAT |-- ... + +--------------+ +---------------+ | +--- tenant-2 ---+ | ~~~|~~~ | netperf |--+ +-----------+ | +----------------+ mark := 2 | netserver |------ ... + [ip,sport] := X +-----------+ [ip,port] := Y On the gateway netns, example: iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark conntrack dump from gateway netns: netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2 Taking this further, test script in [2] creates 200 tenants and runs original-tuple colliding netperf sessions each. A conntrack -L dump in the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED state as expected. I also did run various other tests with some permutations of the script, to mention some: SNAT in random/random-fully/persistent mode, no zones (no overlaps), static zones (original, reply, both directions), etc. [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/ [2] https://paste.fedoraproject.org/242835/65657871/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2015-08-14 14:03:39 +00:00
nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
static bool master_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b,
unsigned int flags)
{
if (flags & NF_CT_EXP_F_SKIP_MASTER)
return true;
return a->master == b->master;
}
/* Generally a bad idea to call this: could have matched already. */
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
{
spin_lock_bh(&nf_conntrack_expect_lock);
nf_ct_remove_expect(exp);
spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
/* We don't increase the master conntrack refcount for non-fulfilled
* conntracks. During the conntrack destruction, the expectations are
* always killed before the conntrack itself */
struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
{
struct nf_conntrack_expect *new;
new = kmem_cache_alloc(nf_ct_expect_cachep, GFP_ATOMIC);
if (!new)
return NULL;
new->master = me;
refcount_set(&new->use, 1);
return new;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);
void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
u_int8_t family,
const union nf_inet_addr *saddr,
const union nf_inet_addr *daddr,
u_int8_t proto, const __be16 *src, const __be16 *dst)
{
int len;
if (family == AF_INET)
len = 4;
else
len = 16;
exp->flags = 0;
exp->class = class;
exp->expectfn = NULL;
exp->helper = NULL;
exp->tuple.src.l3num = family;
exp->tuple.dst.protonum = proto;
if (saddr) {
memcpy(&exp->tuple.src.u3, saddr, len);
if (sizeof(exp->tuple.src.u3) > len)
/* address needs to be cleared for nf_ct_tuple_equal */
memset((void *)&exp->tuple.src.u3 + len, 0x00,
sizeof(exp->tuple.src.u3) - len);
memset(&exp->mask.src.u3, 0xFF, len);
if (sizeof(exp->mask.src.u3) > len)
memset((void *)&exp->mask.src.u3 + len, 0x00,
sizeof(exp->mask.src.u3) - len);
} else {
memset(&exp->tuple.src.u3, 0x00, sizeof(exp->tuple.src.u3));
memset(&exp->mask.src.u3, 0x00, sizeof(exp->mask.src.u3));
}
if (src) {
exp->tuple.src.u.all = *src;
exp->mask.src.u.all = htons(0xFFFF);
} else {
exp->tuple.src.u.all = 0;
exp->mask.src.u.all = 0;
}
memcpy(&exp->tuple.dst.u3, daddr, len);
if (sizeof(exp->tuple.dst.u3) > len)
/* address needs to be cleared for nf_ct_tuple_equal */
memset((void *)&exp->tuple.dst.u3 + len, 0x00,
sizeof(exp->tuple.dst.u3) - len);
exp->tuple.dst.u.all = *dst;
#if IS_ENABLED(CONFIG_NF_NAT)
memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
#endif
}
EXPORT_SYMBOL_GPL(nf_ct_expect_init);
static void nf_ct_expect_free_rcu(struct rcu_head *head)
{
struct nf_conntrack_expect *exp;
exp = container_of(head, struct nf_conntrack_expect, rcu);
kmem_cache_free(nf_ct_expect_cachep, exp);
}
void nf_ct_expect_put(struct nf_conntrack_expect *exp)
{
if (refcount_dec_and_test(&exp->use))
call_rcu(&exp->rcu, nf_ct_expect_free_rcu);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_put);
static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
{
struct nf_conntrack_net *cnet;
struct nf_conn_help *master_help = nfct_help(exp->master);
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(exp);
unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
/* two references : one for hash insert, one for the timer */
refcount_add(2, &exp->use);
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-16 21:43:17 +00:00
timer_setup(&exp->timeout, nf_ct_expectation_timed_out, 0);
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
helper = rcu_dereference_protected(master_help->helper,
lockdep_is_held(&nf_conntrack_expect_lock));
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
if (helper) {
exp->timeout.expires = jiffies +
helper->expect_policy[exp->class].timeout * HZ;
}
add_timer(&exp->timeout);
hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
master_help->expecting[exp->class]++;
hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
cnet = nf_ct_pernet(net);
cnet->expect_count++;
NF_CT_STAT_INC(net, expect_create);
}
/* Race with expectations being used means we could have none to find; OK. */
static void evict_oldest_expect(struct nf_conn *master,
struct nf_conntrack_expect *new)
{
struct nf_conn_help *master_help = nfct_help(master);
struct nf_conntrack_expect *exp, *last = NULL;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry(exp, &master_help->expectations, lnode) {
if (exp->class == new->class)
last = exp;
}
if (last)
nf_ct_remove_expect(last);
}
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
unsigned int flags)
{
const struct nf_conntrack_expect_policy *p;
struct nf_conntrack_expect *i;
struct nf_conntrack_net *cnet;
struct nf_conn *master = expect->master;
struct nf_conn_help *master_help = nfct_help(master);
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(expect);
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *next;
unsigned int h;
int ret = 0;
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
if (!master_help) {
ret = -ESHUTDOWN;
goto out;
}
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
if (master_matches(i, expect, flags) &&
expect_matches(i, expect)) {
if (i->class != expect->class ||
i->master != expect->master)
return -EALREADY;
if (nf_ct_remove_expect(i))
netfilter: nf_ct_expect: fix possible access to uninitialized timer In __nf_ct_expect_check, the function refresh_timer returns 1 if a matching expectation is found and its timer is successfully refreshed. This results in nf_ct_expect_related returning 0. Note that at this point: - the passed expectation is not inserted in the expectation table and its timer was not initialized, since we have refreshed one matching/existing expectation. - nf_ct_expect_alloc uses kmem_cache_alloc, so the expectation timer is in some undefined state just after the allocation, until it is appropriately initialized. This can be a problem for the SIP helper during the expectation addition: ... if (nf_ct_expect_related(rtp_exp) == 0) { if (nf_ct_expect_related(rtcp_exp) != 0) nf_ct_unexpect_related(rtp_exp); ... Note that nf_ct_expect_related(rtp_exp) may return 0 for the timer refresh case that is detailed above. Then, if nf_ct_unexpect_related(rtcp_exp) returns != 0, nf_ct_unexpect_related(rtp_exp) is called, which does: spin_lock_bh(&nf_conntrack_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_lock); Note that del_timer always returns false if the timer has been initialized. However, the timer was not initialized since setup_timer was not called, therefore, the expectation timer remains in some undefined state. If I'm not missing anything, this may lead to the removal an unexistent expectation. To fix this, the optimization that allows refreshing an expectation is removed. Now nf_conntrack_expect_related looks more consistent to me since it always add the expectation in case that it returns success. Thanks to Patrick McHardy for participating in the discussion of this patch. I think this may be the source of the problem described by: http://marc.info/?l=netfilter-devel&m=134073514719421&w=2 Reported-by: Rafal Fitt <rafalf@aplusc.com.pl> Acked-by: Patrick McHardy <kaber@trash.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2012-08-16 00:25:24 +00:00
break;
} else if (expect_clash(i, expect)) {
ret = -EBUSY;
goto out;
}
}
/* Will be over limit? */
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
helper = rcu_dereference_protected(master_help->helper,
lockdep_is_held(&nf_conntrack_expect_lock));
netfilter: rework user-space expectation helper support This partially reworks bc01befdcf3e40979eb518085a075cbf0aacede0 which added userspace expectation support. This patch removes the nf_ct_userspace_expect_list since now we force to use the new iptables CT target feature to add the helper extension for conntracks that have attached expectations from userspace. A new version of the proof-of-concept code to implement userspace helpers from userspace is available at: http://people.netfilter.org/pablo/userspace-conntrack-helpers/nf-ftp-helper-POC.tar.bz2 This patch also modifies the CT target to allow to set the conntrack's userspace helper status flags. This flag is used to tell the conntrack system to explicitly allocate the helper extension. This helper extension is useful to link the userspace expectations with the master conntrack that is being tracked from one userspace helper. This feature fixes a problem in the current approach of the userspace helper support. Basically, if the master conntrack that has got a userspace expectation vanishes, the expectations point to one invalid memory address. Thus, triggering an oops in the expectation deletion event path. I decided not to add a new revision of the CT target because I only needed to add a new flag for it. I'll document in this issue in the iptables manpage. I have also changed the return value from EINVAL to EOPNOTSUPP if one flag not supported is specified. Thus, in the future adding new features that only require a new flag can be added without a new revision. There is no official code using this in userspace (apart from the proof-of-concept) that uses this infrastructure but there will be some by beginning 2012. Reported-by: Sam Roberts <vieuxtech@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2011-12-18 00:55:54 +00:00
if (helper) {
p = &helper->expect_policy[expect->class];
if (p->max_expected &&
master_help->expecting[expect->class] >= p->max_expected) {
evict_oldest_expect(master, expect);
if (master_help->expecting[expect->class]
>= p->max_expected) {
ret = -EMFILE;
goto out;
}
}
}
cnet = nf_ct_pernet(net);
if (cnet->expect_count >= nf_ct_expect_max) {
net_warn_ratelimited("nf_conntrack: expectation table full\n");
ret = -EMFILE;
}
out:
return ret;
}
int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
u32 portid, int report, unsigned int flags)
{
int ret;
spin_lock_bh(&nf_conntrack_expect_lock);
netfilter: nf_conntrack_sip: fix expectation clash When conntracks change during a dialog, SDP messages may be sent from different conntracks to establish expects with identical tuples. In this case expects conflict may be detected for the 2nd SDP message and end up with a process failure. The fixing here is to reuse an existing expect who has the same tuple for a different conntrack if any. Here are two scenarios for the case. 1) SERVER CPE | INVITE SDP | 5060 |<----------------------|5060 | 100 Trying | 5060 |---------------------->|5060 | 183 SDP | 5060 |---------------------->|5060 ===> Conntrack 1 | PRACK | 50601 |<----------------------|5060 | 200 OK (PRACK) | 50601 |---------------------->|5060 | 200 OK (INVITE) | 5060 |---------------------->|5060 | ACK | 50601 |<----------------------|5060 | | |<--- RTP stream ------>| | | | INVITE SDP (t38) | 50601 |---------------------->|5060 ===> Conntrack 2 With a certain configuration in the CPE, SIP messages "183 with SDP" and "re-INVITE with SDP t38" will go through the sip helper to create expects for RTP and RTCP. It is okay to create RTP and RTCP expects for "183", whose master connection source port is 5060, and destination port is 5060. In the "183" message, port in Contact header changes to 50601 (from the original 5060). So the following requests e.g. PRACK and ACK are sent to port 50601. It is a different conntrack (let call Conntrack 2) from the original INVITE (let call Conntrack 1) due to the port difference. In this example, after the call is established, there is RTP stream but no RTCP stream for Conntrack 1, so the RTP expect created upon "183" is cleared, and RTCP expect created for Conntrack 1 retains. When "re-INVITE with SDP t38" arrives to create RTP&RTCP expects, current ALG implementation will call nf_ct_expect_related() for RTP and RTCP. The expects tuples are identical to those for Conntrack 1. RTP expect for Conntrack 2 succeeds in creation as the one for Conntrack 1 has been removed. RTCP expect for Conntrack 2 fails in creation because it has idential tuples and 'conflict' with the one retained for Conntrack 1. And then result in a failure in processing of the re-INVITE. 2) SERVER A CPE | REGISTER | 5060 |<------------------| 5060 ==> CT1 | 200 | 5060 |------------------>| 5060 | | | INVITE SDP(1) | 5060 |<------------------| 5060 | 300(multi choice) | 5060 |------------------>| 5060 SERVER B | ACK | 5060 |<------------------| 5060 | INVITE SDP(2) | 5060 |-------------------->| 5060 ==> CT2 | 100 | 5060 |<--------------------| 5060 | 200(contact changes)| 5060 |<--------------------| 5060 | ACK | 5060 |-------------------->| 50601 ==> CT3 | | |<--- RTP stream ---->| | | | BYE | 5060 |<--------------------| 50601 | 200 | 5060 |-------------------->| 50601 | INVITE SDP(3) | 5060 |<------------------| 5060 ==> CT1 CPE sends an INVITE request(1) to Server A, and creates a RTP&RTCP expect pair for this Conntrack 1 (CT1). Server A responds 300 to redirect to Server B. The RTP&RTCP expect pairs created on CT1 are removed upon 300 response. CPE sends the INVITE request(2) to Server B, and creates an expect pair for the new conntrack (due to destination address difference), let call CT2. Server B changes the port to 50601 in 200 OK response, and the following requests ACK and BYE from CPE are sent to 50601. The call is established. There is RTP stream and no RTCP stream. So RTP expect is removed and RTCP expect for CT2 retains. As BYE request is sent from port 50601, it is another conntrack, let call CT3, different from CT2 due to the port difference. So the BYE request will not remove the RTCP expect for CT2. Then another outgoing call is made, with the same RTP port being used (not definitely but possibly). CPE firstly sends the INVITE request(3) to Server A, and tries to create a RTP&RTCP expect pairs for this CT1. In current ALG implementation, the RTCP expect for CT1 fails in creation because it 'conflicts' with the residual one for CT2. As a result the INVITE request fails to send. Signed-off-by: xiao ruizhu <katrina.xiaorz@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-07-04 03:31:13 +00:00
ret = __nf_ct_expect_check(expect, flags);
if (ret < 0)
goto out;
nf_ct_expect_insert(expect);
spin_unlock_bh(&nf_conntrack_expect_lock);
nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
return 0;
out:
spin_unlock_bh(&nf_conntrack_expect_lock);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data),
void *data)
{
struct nf_conntrack_expect *exp;
const struct hlist_node *next;
unsigned int i;
spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
&nf_ct_expect_hash[i],
hnode) {
if (iter(exp, data) && del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
}
}
}
spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_iterate_destroy);
void nf_ct_expect_iterate_net(struct net *net,
bool (*iter)(struct nf_conntrack_expect *e, void *data),
void *data,
u32 portid, int report)
{
struct nf_conntrack_expect *exp;
const struct hlist_node *next;
unsigned int i;
spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
&nf_ct_expect_hash[i],
hnode) {
if (!net_eq(nf_ct_exp_net(exp), net))
continue;
if (iter(exp, data) && del_timer(&exp->timeout)) {
nf_ct_unlink_expect_report(exp, portid, report);
nf_ct_expect_put(exp);
}
}
}
spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_iterate_net);
#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct ct_expect_iter_state {
struct seq_net_private p;
unsigned int bucket;
};
static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
{
struct ct_expect_iter_state *st = seq->private;
struct hlist_node *n;
for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
n = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
if (n)
return n;
}
return NULL;
}
static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
struct hlist_node *head)
{
struct ct_expect_iter_state *st = seq->private;
head = rcu_dereference(hlist_next_rcu(head));
while (head == NULL) {
if (++st->bucket >= nf_ct_expect_hsize)
return NULL;
head = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
}
return head;
}
static struct hlist_node *ct_expect_get_idx(struct seq_file *seq, loff_t pos)
{
struct hlist_node *head = ct_expect_get_first(seq);
if (head)
while (pos && (head = ct_expect_get_next(seq, head)))
pos--;
return pos ? NULL : head;
}
static void *exp_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
rcu_read_lock();
return ct_expect_get_idx(seq, *pos);
}
static void *exp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
(*pos)++;
return ct_expect_get_next(seq, v);
}
static void exp_seq_stop(struct seq_file *seq, void *v)
__releases(RCU)
{
rcu_read_unlock();
}
static int exp_seq_show(struct seq_file *s, void *v)
{
struct nf_conntrack_expect *expect;
struct nf_conntrack_helper *helper;
struct hlist_node *n = v;
char *delim = "";
expect = hlist_entry(n, struct nf_conntrack_expect, hnode);
if (expect->timeout.function)
seq_printf(s, "%ld ", timer_pending(&expect->timeout)
? (long)(expect->timeout.expires - jiffies)/HZ : 0);
else
seq_puts(s, "- ");
seq_printf(s, "l3proto = %u proto=%u ",
expect->tuple.src.l3num,
expect->tuple.dst.protonum);
print_tuple(s, &expect->tuple,
nf_ct_l4proto_find(expect->tuple.dst.protonum));
if (expect->flags & NF_CT_EXPECT_PERMANENT) {
seq_puts(s, "PERMANENT");
delim = ",";
}
if (expect->flags & NF_CT_EXPECT_INACTIVE) {
seq_printf(s, "%sINACTIVE", delim);
delim = ",";
}
if (expect->flags & NF_CT_EXPECT_USERSPACE)
seq_printf(s, "%sUSERSPACE", delim);
helper = rcu_dereference(nfct_help(expect->master)->helper);
if (helper) {
seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name);
if (helper->expect_policy[expect->class].name[0])
seq_printf(s, "/%s",
helper->expect_policy[expect->class].name);
}
seq_putc(s, '\n');
return 0;
}
static const struct seq_operations exp_seq_ops = {
.start = exp_seq_start,
.next = exp_seq_next,
.stop = exp_seq_stop,
.show = exp_seq_show
};
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
static int exp_proc_init(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct proc_dir_entry *proc;
kuid_t root_uid;
kgid_t root_gid;
proc = proc_create_net("nf_conntrack_expect", 0440, net->proc_net,
&exp_seq_ops, sizeof(struct ct_expect_iter_state));
if (!proc)
return -ENOMEM;
root_uid = make_kuid(net->user_ns, 0);
root_gid = make_kgid(net->user_ns, 0);
if (uid_valid(root_uid) && gid_valid(root_gid))
proc_set_user(proc, root_uid, root_gid);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
return 0;
}
static void exp_proc_remove(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
remove_proc_entry("nf_conntrack_expect", net->proc_net);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
}
module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);
int nf_conntrack_expect_pernet_init(struct net *net)
{
return exp_proc_init(net);
}
void nf_conntrack_expect_pernet_fini(struct net *net)
{
exp_proc_remove(net);
}
int nf_conntrack_expect_init(void)
{
if (!nf_ct_expect_hsize) {
nf_ct_expect_hsize = nf_conntrack_htable_size / 256;
if (!nf_ct_expect_hsize)
nf_ct_expect_hsize = 1;
}
nf_ct_expect_max = nf_ct_expect_hsize * 4;
nf_ct_expect_cachep = KMEM_CACHE(nf_conntrack_expect, 0);
if (!nf_ct_expect_cachep)
return -ENOMEM;
nf_ct_expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
if (!nf_ct_expect_hash) {
kmem_cache_destroy(nf_ct_expect_cachep);
return -ENOMEM;
}
return 0;
}
void nf_conntrack_expect_fini(void)
{
rcu_barrier(); /* Wait for call_rcu() before destroy */
kmem_cache_destroy(nf_ct_expect_cachep);
kvfree(nf_ct_expect_hash);
}