OpenCloudOS-Kernel/net/xfrm/xfrm_state.c

2330 lines
56 KiB
C
Raw Normal View History

/*
* xfrm_state.c
*
* Changes:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* IPv6 support
* YOSHIFUJI Hideaki @USAGI
* Split up af-specific functions
* Derek Atkins <derek@ihtfp.com>
* Add UDP Encapsulation
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
*
*/
#include <linux/workqueue.h>
#include <net/xfrm.h>
#include <linux/pfkeyv2.h>
#include <linux/ipsec.h>
#include <linux/module.h>
#include <linux/cache.h>
#include <linux/audit.h>
#include <asm/uaccess.h>
#include <linux/ktime.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include "xfrm_hash.h"
#define xfrm_state_deref_prot(table, net) \
rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
/* Each xfrm_state may be linked to two tables:
1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
2. Hash table by (daddr,family,reqid) to find what SAs exist for given
destination/tunnel endpoint. (output)
*/
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
{
return atomic_inc_not_zero(&x->refcnt);
}
static inline unsigned int xfrm_dst_hash(struct net *net,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
u32 reqid,
unsigned short family)
{
return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
}
static inline unsigned int xfrm_src_hash(struct net *net,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
unsigned short family)
{
return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
}
static inline unsigned int
xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
__be32 spi, u8 proto, unsigned short family)
{
return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
}
static void xfrm_hash_transfer(struct hlist_head *list,
struct hlist_head *ndsttable,
struct hlist_head *nsrctable,
struct hlist_head *nspitable,
unsigned int nhashmask)
{
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 09:06:00 +08:00
struct hlist_node *tmp;
struct xfrm_state *x;
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 09:06:00 +08:00
hlist_for_each_entry_safe(x, tmp, list, bydst) {
unsigned int h;
h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr,
x->props.reqid, x->props.family,
nhashmask);
hlist_add_head_rcu(&x->bydst, ndsttable + h);
h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
x->props.family,
nhashmask);
hlist_add_head_rcu(&x->bysrc, nsrctable + h);
if (x->id.spi) {
h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
x->id.proto, x->props.family,
nhashmask);
hlist_add_head_rcu(&x->byspi, nspitable + h);
}
}
}
static unsigned long xfrm_hash_new_size(unsigned int state_hmask)
{
return ((state_hmask + 1) << 1) * sizeof(struct hlist_head);
}
static void xfrm_hash_resize(struct work_struct *work)
{
struct net *net = container_of(work, struct net, xfrm.state_hash_work);
struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi;
unsigned long nsize, osize;
unsigned int nhashmask, ohashmask;
int i;
nsize = xfrm_hash_new_size(net->xfrm.state_hmask);
ndst = xfrm_hash_alloc(nsize);
if (!ndst)
return;
nsrc = xfrm_hash_alloc(nsize);
if (!nsrc) {
xfrm_hash_free(ndst, nsize);
return;
}
nspi = xfrm_hash_alloc(nsize);
if (!nspi) {
xfrm_hash_free(ndst, nsize);
xfrm_hash_free(nsrc, nsize);
return;
}
spin_lock_bh(&net->xfrm.xfrm_state_lock);
write_seqcount_begin(&xfrm_state_hash_generation);
nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
for (i = net->xfrm.state_hmask; i >= 0; i--)
xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask);
osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net);
ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net);
ohashmask = net->xfrm.state_hmask;
rcu_assign_pointer(net->xfrm.state_bydst, ndst);
rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
rcu_assign_pointer(net->xfrm.state_byspi, nspi);
net->xfrm.state_hmask = nhashmask;
write_seqcount_end(&xfrm_state_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
osize = (ohashmask + 1) * sizeof(struct hlist_head);
synchronize_rcu();
xfrm_hash_free(odst, osize);
xfrm_hash_free(osrc, osize);
xfrm_hash_free(ospi, osize);
}
static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
static DEFINE_SPINLOCK(xfrm_state_gc_lock);
int __xfrm_state_delete(struct xfrm_state *x);
int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
bool km_is_alive(const struct km_event *c);
void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
static DEFINE_SPINLOCK(xfrm_type_lock);
int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
{
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
const struct xfrm_type **typemap;
int err = 0;
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
typemap = afinfo->type_map;
spin_lock_bh(&xfrm_type_lock);
if (likely(typemap[type->proto] == NULL))
typemap[type->proto] = type;
else
err = -EEXIST;
spin_unlock_bh(&xfrm_type_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_register_type);
int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
{
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
const struct xfrm_type **typemap;
int err = 0;
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
typemap = afinfo->type_map;
spin_lock_bh(&xfrm_type_lock);
if (unlikely(typemap[type->proto] != type))
err = -ENOENT;
else
typemap[type->proto] = NULL;
spin_unlock_bh(&xfrm_type_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_unregister_type);
static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
{
struct xfrm_state_afinfo *afinfo;
const struct xfrm_type **typemap;
const struct xfrm_type *type;
int modload_attempted = 0;
retry:
afinfo = xfrm_state_get_afinfo(family);
if (unlikely(afinfo == NULL))
return NULL;
typemap = afinfo->type_map;
type = typemap[proto];
if (unlikely(type && !try_module_get(type->owner)))
type = NULL;
if (!type && !modload_attempted) {
xfrm_state_put_afinfo(afinfo);
request_module("xfrm-type-%d-%d", family, proto);
modload_attempted = 1;
goto retry;
}
xfrm_state_put_afinfo(afinfo);
return type;
}
static void xfrm_put_type(const struct xfrm_type *type)
{
module_put(type->owner);
}
static DEFINE_SPINLOCK(xfrm_mode_lock);
int xfrm_register_mode(struct xfrm_mode *mode, int family)
{
struct xfrm_state_afinfo *afinfo;
struct xfrm_mode **modemap;
int err;
if (unlikely(mode->encap >= XFRM_MODE_MAX))
return -EINVAL;
afinfo = xfrm_state_get_afinfo(family);
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
err = -EEXIST;
modemap = afinfo->mode_map;
spin_lock_bh(&xfrm_mode_lock);
if (modemap[mode->encap])
goto out;
err = -ENOENT;
if (!try_module_get(afinfo->owner))
goto out;
mode->afinfo = afinfo;
modemap[mode->encap] = mode;
err = 0;
out:
spin_unlock_bh(&xfrm_mode_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_register_mode);
int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
{
struct xfrm_state_afinfo *afinfo;
struct xfrm_mode **modemap;
int err;
if (unlikely(mode->encap >= XFRM_MODE_MAX))
return -EINVAL;
afinfo = xfrm_state_get_afinfo(family);
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
err = -ENOENT;
modemap = afinfo->mode_map;
spin_lock_bh(&xfrm_mode_lock);
if (likely(modemap[mode->encap] == mode)) {
modemap[mode->encap] = NULL;
module_put(mode->afinfo->owner);
err = 0;
}
spin_unlock_bh(&xfrm_mode_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_unregister_mode);
static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
{
struct xfrm_state_afinfo *afinfo;
struct xfrm_mode *mode;
int modload_attempted = 0;
if (unlikely(encap >= XFRM_MODE_MAX))
return NULL;
retry:
afinfo = xfrm_state_get_afinfo(family);
if (unlikely(afinfo == NULL))
return NULL;
mode = afinfo->mode_map[encap];
if (unlikely(mode && !try_module_get(mode->owner)))
mode = NULL;
if (!mode && !modload_attempted) {
xfrm_state_put_afinfo(afinfo);
request_module("xfrm-mode-%d-%d", family, encap);
modload_attempted = 1;
goto retry;
}
xfrm_state_put_afinfo(afinfo);
return mode;
}
static void xfrm_put_mode(struct xfrm_mode *mode)
{
module_put(mode->owner);
}
static void xfrm_state_gc_destroy(struct xfrm_state *x)
{
tasklet_hrtimer_cancel(&x->mtimer);
del_timer_sync(&x->rtimer);
kfree(x->aalg);
kfree(x->ealg);
kfree(x->calg);
kfree(x->encap);
kfree(x->coaddr);
kfree(x->replay_esn);
kfree(x->preplay_esn);
if (x->inner_mode)
xfrm_put_mode(x->inner_mode);
if (x->inner_mode_iaf)
xfrm_put_mode(x->inner_mode_iaf);
if (x->outer_mode)
xfrm_put_mode(x->outer_mode);
if (x->type) {
x->type->destructor(x);
xfrm_put_type(x->type);
}
[LSM-IPSec]: Security association restriction. This patch series implements per packet access control via the extension of the Linux Security Modules (LSM) interface by hooks in the XFRM and pfkey subsystems that leverage IPSec security associations to label packets. Extensions to the SELinux LSM are included that leverage the patch for this purpose. This patch implements the changes necessary to the XFRM subsystem, pfkey interface, ipv4/ipv6, and xfrm_user interface to restrict a socket to use only authorized security associations (or no security association) to send/receive network packets. Patch purpose: The patch is designed to enable access control per packets based on the strongly authenticated IPSec security association. Such access controls augment the existing ones based on network interface and IP address. The former are very coarse-grained, and the latter can be spoofed. By using IPSec, the system can control access to remote hosts based on cryptographic keys generated using the IPSec mechanism. This enables access control on a per-machine basis or per-application if the remote machine is running the same mechanism and trusted to enforce the access control policy. Patch design approach: The overall approach is that policy (xfrm_policy) entries set by user-level programs (e.g., setkey for ipsec-tools) are extended with a security context that is used at policy selection time in the XFRM subsystem to restrict the sockets that can send/receive packets via security associations (xfrm_states) that are built from those policies. A presentation available at www.selinux-symposium.org/2005/presentations/session2/2-3-jaeger.pdf from the SELinux symposium describes the overall approach. Patch implementation details: On output, the policy retrieved (via xfrm_policy_lookup or xfrm_sk_policy_lookup) must be authorized for the security context of the socket and the same security context is required for resultant security association (retrieved or negotiated via racoon in ipsec-tools). This is enforced in xfrm_state_find. On input, the policy retrieved must also be authorized for the socket (at __xfrm_policy_check), and the security context of the policy must also match the security association being used. The patch has virtually no impact on packets that do not use IPSec. The existing Netfilter (outgoing) and LSM rcv_skb hooks are used as before. Also, if IPSec is used without security contexts, the impact is minimal. The LSM must allow such policies to be selected for the combination of socket and remote machine, but subsequent IPSec processing proceeds as in the original case. Testing: The pfkey interface is tested using the ipsec-tools. ipsec-tools have been modified (a separate ipsec-tools patch is available for version 0.5) that supports assignment of xfrm_policy entries and security associations with security contexts via setkey and the negotiation using the security contexts via racoon. The xfrm_user interface is tested via ad hoc programs that set security contexts. These programs are also available from me, and contain programs for setting, getting, and deleting policy for testing this interface. Testing of sa functions was done by tracing kernel behavior. Signed-off-by: Trent Jaeger <tjaeger@cse.psu.edu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-12-14 15:12:27 +08:00
security_xfrm_state_free(x);
kfree(x);
}
static void xfrm_state_gc_task(struct work_struct *work)
{
struct net *net = container_of(work, struct net, xfrm.state_gc_work);
struct xfrm_state *x;
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 09:06:00 +08:00
struct hlist_node *tmp;
struct hlist_head gc_list;
spin_lock_bh(&xfrm_state_gc_lock);
hlist_move_list(&net->xfrm.state_gc_list, &gc_list);
spin_unlock_bh(&xfrm_state_gc_lock);
synchronize_rcu();
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 09:06:00 +08:00
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
xfrm_state_gc_destroy(x);
}
static inline unsigned long make_jiffies(long secs)
{
if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
return MAX_SCHEDULE_TIMEOUT-1;
else
return secs*HZ;
}
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
{
struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
unsigned long now = get_seconds();
long next = LONG_MAX;
int warn = 0;
int err = 0;
spin_lock(&x->lock);
if (x->km.state == XFRM_STATE_DEAD)
goto out;
if (x->km.state == XFRM_STATE_EXPIRED)
goto expired;
if (x->lft.hard_add_expires_seconds) {
long tmo = x->lft.hard_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
if (x->xflags & XFRM_SOFT_EXPIRE) {
/* enter hard expire without soft expire first?!
* setting a new date could trigger this.
* workarbound: fix x->curflt.add_time by below:
*/
x->curlft.add_time = now - x->saved_tmo - 1;
tmo = x->lft.hard_add_expires_seconds - x->saved_tmo;
} else
goto expired;
}
if (tmo < next)
next = tmo;
}
if (x->lft.hard_use_expires_seconds) {
long tmo = x->lft.hard_use_expires_seconds +
(x->curlft.use_time ? : now) - now;
if (tmo <= 0)
goto expired;
if (tmo < next)
next = tmo;
}
if (x->km.dying)
goto resched;
if (x->lft.soft_add_expires_seconds) {
long tmo = x->lft.soft_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
warn = 1;
x->xflags &= ~XFRM_SOFT_EXPIRE;
} else if (tmo < next) {
next = tmo;
x->xflags |= XFRM_SOFT_EXPIRE;
x->saved_tmo = tmo;
}
}
if (x->lft.soft_use_expires_seconds) {
long tmo = x->lft.soft_use_expires_seconds +
(x->curlft.use_time ? : now) - now;
if (tmo <= 0)
warn = 1;
else if (tmo < next)
next = tmo;
}
x->km.dying = warn;
if (warn)
km_state_expired(x, 0, 0);
resched:
if (next != LONG_MAX) {
tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
}
goto out;
expired:
if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
x->km.state = XFRM_STATE_EXPIRED;
err = __xfrm_state_delete(x);
if (!err)
km_state_expired(x, 1, 0);
xfrm_audit_state_delete(x, err ? 0 : 1, true);
out:
spin_unlock(&x->lock);
return HRTIMER_NORESTART;
}
static void xfrm_replay_timer_handler(unsigned long data);
struct xfrm_state *xfrm_state_alloc(struct net *net)
{
struct xfrm_state *x;
x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC);
if (x) {
write_pnet(&x->xs_net, net);
atomic_set(&x->refcnt, 1);
atomic_set(&x->tunnel_users, 0);
INIT_LIST_HEAD(&x->km.all);
INIT_HLIST_NODE(&x->bydst);
INIT_HLIST_NODE(&x->bysrc);
INIT_HLIST_NODE(&x->byspi);
tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
setup_timer(&x->rtimer, xfrm_replay_timer_handler,
(unsigned long)x);
x->curlft.add_time = get_seconds();
x->lft.soft_byte_limit = XFRM_INF;
x->lft.soft_packet_limit = XFRM_INF;
x->lft.hard_byte_limit = XFRM_INF;
x->lft.hard_packet_limit = XFRM_INF;
x->replay_maxage = 0;
x->replay_maxdiff = 0;
x->inner_mode = NULL;
x->inner_mode_iaf = NULL;
spin_lock_init(&x->lock);
}
return x;
}
EXPORT_SYMBOL(xfrm_state_alloc);
void __xfrm_state_destroy(struct xfrm_state *x)
{
struct net *net = xs_net(x);
WARN_ON(x->km.state != XFRM_STATE_DEAD);
spin_lock_bh(&xfrm_state_gc_lock);
hlist_add_head(&x->gclist, &net->xfrm.state_gc_list);
spin_unlock_bh(&xfrm_state_gc_lock);
schedule_work(&net->xfrm.state_gc_work);
}
EXPORT_SYMBOL(__xfrm_state_destroy);
int __xfrm_state_delete(struct xfrm_state *x)
{
struct net *net = xs_net(x);
int err = -ESRCH;
if (x->km.state != XFRM_STATE_DEAD) {
x->km.state = XFRM_STATE_DEAD;
spin_lock(&net->xfrm.xfrm_state_lock);
list_del(&x->km.all);
hlist_del_rcu(&x->bydst);
hlist_del_rcu(&x->bysrc);
if (x->id.spi)
hlist_del_rcu(&x->byspi);
net->xfrm.state_num--;
spin_unlock(&net->xfrm.xfrm_state_lock);
/* All xfrm_state objects are created by xfrm_state_alloc.
* The xfrm_state_alloc call gives a reference, and that
* is what we are dropping here.
*/
xfrm_state_put(x);
err = 0;
}
return err;
}
EXPORT_SYMBOL(__xfrm_state_delete);
int xfrm_state_delete(struct xfrm_state *x)
{
int err;
spin_lock_bh(&x->lock);
err = __xfrm_state_delete(x);
spin_unlock_bh(&x->lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_delete);
#ifdef CONFIG_SECURITY_NETWORK_XFRM
static inline int
xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
{
int i, err = 0;
for (i = 0; i <= net->xfrm.state_hmask; i++) {
struct xfrm_state *x;
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
if (xfrm_id_proto_match(x->id.proto, proto) &&
(err = security_xfrm_state_delete(x)) != 0) {
xfrm_audit_state_delete(x, 0, task_valid);
return err;
}
}
}
return err;
}
#else
static inline int
xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
{
return 0;
}
#endif
int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
{
int i, err = 0, cnt = 0;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_flush_secctx_check(net, proto, task_valid);
if (err)
goto out;
err = -ESRCH;
for (i = 0; i <= net->xfrm.state_hmask; i++) {
struct xfrm_state *x;
restart:
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
if (!xfrm_state_kern(x) &&
xfrm_id_proto_match(x->id.proto, proto)) {
xfrm_state_hold(x);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
task_valid);
xfrm_state_put(x);
if (!err)
cnt++;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
goto restart;
}
}
}
if (cnt)
err = 0;
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_flush);
void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
{
spin_lock_bh(&net->xfrm.xfrm_state_lock);
si->sadcnt = net->xfrm.state_num;
si->sadhcnt = net->xfrm.state_hmask;
si->sadhmcnt = xfrm_state_hashmax;
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_sad_getinfo);
static int
xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
const struct xfrm_tmpl *tmpl,
const xfrm_address_t *daddr, const xfrm_address_t *saddr,
unsigned short family)
{
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
return -1;
afinfo->init_tempsel(&x->sel, fl);
if (family != tmpl->encap_family) {
xfrm_state_put_afinfo(afinfo);
afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
if (!afinfo)
return -1;
}
afinfo->init_temprop(x, tmpl, daddr, saddr);
xfrm_state_put_afinfo(afinfo);
return 0;
}
static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
const xfrm_address_t *daddr,
__be32 spi, u8 proto,
unsigned short family)
{
unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
struct xfrm_state *x;
hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
if (x->props.family != family ||
x->id.spi != spi ||
x->id.proto != proto ||
!xfrm_addr_equal(&x->id.daddr, daddr, family))
continue;
if ((mark & x->mark.m) != x->mark.v)
continue;
if (!xfrm_state_hold_rcu(x))
continue;
return x;
}
return NULL;
}
static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
struct xfrm_state *x;
hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
if (x->props.family != family ||
x->id.proto != proto ||
!xfrm_addr_equal(&x->id.daddr, daddr, family) ||
!xfrm_addr_equal(&x->props.saddr, saddr, family))
continue;
if ((mark & x->mark.m) != x->mark.v)
continue;
if (!xfrm_state_hold_rcu(x))
continue;
return x;
}
return NULL;
}
static inline struct xfrm_state *
__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
{
struct net *net = xs_net(x);
u32 mark = x->mark.v & x->mark.m;
if (use_spi)
return __xfrm_state_lookup(net, mark, &x->id.daddr,
x->id.spi, x->id.proto, family);
else
return __xfrm_state_lookup_byaddr(net, mark,
&x->id.daddr,
&x->props.saddr,
x->id.proto, family);
}
static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
{
if (have_hash_collision &&
(net->xfrm.state_hmask + 1) < xfrm_state_hashmax &&
net->xfrm.state_num > net->xfrm.state_hmask)
schedule_work(&net->xfrm.state_hash_work);
}
static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
const struct flowi *fl, unsigned short family,
struct xfrm_state **best, int *acq_in_progress,
int *error)
{
/* Resolution logic:
* 1. There is a valid state with matching selector. Done.
* 2. Valid state with inappropriate selector. Skip.
*
* Entering area of "sysdeps".
*
* 3. If state is not valid, selector is temporary, it selects
* only session which triggered previous resolution. Key
* manager will do something to install a state with proper
* selector.
*/
if (x->km.state == XFRM_STATE_VALID) {
if ((x->sel.family &&
!xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
!security_xfrm_state_pol_flow_match(x, pol, fl))
return;
if (!*best ||
(*best)->km.dying > x->km.dying ||
((*best)->km.dying == x->km.dying &&
(*best)->curlft.add_time < x->curlft.add_time))
*best = x;
} else if (x->km.state == XFRM_STATE_ACQ) {
*acq_in_progress = 1;
} else if (x->km.state == XFRM_STATE_ERROR ||
x->km.state == XFRM_STATE_EXPIRED) {
if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
security_xfrm_state_pol_flow_match(x, pol, fl))
*error = -ESRCH;
}
}
struct xfrm_state *
xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
const struct flowi *fl, struct xfrm_tmpl *tmpl,
struct xfrm_policy *pol, int *err,
unsigned short family)
{
static xfrm_address_t saddr_wildcard = { };
struct net *net = xp_net(pol);
unsigned int h, h_wildcard;
struct xfrm_state *x, *x0, *to_put;
int acquire_in_progress = 0;
int error = 0;
struct xfrm_state *best = NULL;
u32 mark = pol->mark.v & pol->mark.m;
unsigned short encap_family = tmpl->encap_family;
unsigned int sequence;
struct km_event c;
to_put = NULL;
sequence = read_seqcount_begin(&xfrm_state_hash_generation);
rcu_read_lock();
h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, encap_family,
&best, &acquire_in_progress, &error);
}
if (best || acquire_in_progress)
goto found;
h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, encap_family,
&best, &acquire_in_progress, &error);
}
found:
x = best;
if (!x && !error && !acquire_in_progress) {
if (tmpl->id.spi &&
(x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi,
tmpl->id.proto, encap_family)) != NULL) {
to_put = x0;
error = -EEXIST;
goto out;
}
c.net = net;
/* If the KMs have no listeners (yet...), avoid allocating an SA
* for each and every packet - garbage collection might not
* handle the flood.
*/
if (!km_is_alive(&c)) {
error = -ESRCH;
goto out;
}
x = xfrm_state_alloc(net);
if (x == NULL) {
error = -ENOMEM;
goto out;
}
/* Initialize temporary state matching only
* to current session. */
xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
memcpy(&x->mark, &pol->mark, sizeof(x->mark));
error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
if (error) {
x->km.state = XFRM_STATE_DEAD;
to_put = x;
x = NULL;
goto out;
}
if (km_query(x, tmpl, pol) == 0) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x->km.state = XFRM_STATE_ACQ;
list_add(&x->km.all, &net->xfrm.state_all);
hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
h = xfrm_src_hash(net, daddr, saddr, encap_family);
hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
if (x->id.spi) {
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
}
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
} else {
x->km.state = XFRM_STATE_DEAD;
to_put = x;
x = NULL;
error = -ESRCH;
}
}
out:
if (x) {
if (!xfrm_state_hold_rcu(x)) {
*err = -EAGAIN;
x = NULL;
}
} else {
*err = acquire_in_progress ? -EAGAIN : error;
}
rcu_read_unlock();
if (to_put)
xfrm_state_put(to_put);
if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
*err = -EAGAIN;
if (x) {
xfrm_state_put(x);
x = NULL;
}
}
return x;
}
struct xfrm_state *
xfrm_stateonly_find(struct net *net, u32 mark,
xfrm_address_t *daddr, xfrm_address_t *saddr,
unsigned short family, u8 mode, u8 proto, u32 reqid)
{
unsigned int h;
struct xfrm_state *rx = NULL, *x = NULL;
{pktgen, xfrm} Correct xfrm_state_lock usage in xfrm_stateonly_find Acquiring xfrm_state_lock in process context is expected to turn BH off, as this lock is also used in BH context, namely xfrm state timer handler. Otherwise it surprises LOCKDEP with below messages. [ 81.422781] pktgen: Packet Generator for packet performance testing. Version: 2.74 [ 81.725194] [ 81.725211] ========================================================= [ 81.725212] [ INFO: possible irq lock inversion dependency detected ] [ 81.725215] 3.13.0-rc2+ #92 Not tainted [ 81.725216] --------------------------------------------------------- [ 81.725218] kpktgend_0/2780 just changed the state of lock: [ 81.725220] (xfrm_state_lock){+.+...}, at: [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725231] but this lock was taken by another, SOFTIRQ-safe lock in the past: [ 81.725232] (&(&x->lock)->rlock){+.-...} [ 81.725232] [ 81.725232] and interrupts could create inverse lock ordering between them. [ 81.725232] [ 81.725235] [ 81.725235] other info that might help us debug this: [ 81.725237] Possible interrupt unsafe locking scenario: [ 81.725237] [ 81.725238] CPU0 CPU1 [ 81.725240] ---- ---- [ 81.725241] lock(xfrm_state_lock); [ 81.725243] local_irq_disable(); [ 81.725244] lock(&(&x->lock)->rlock); [ 81.725246] lock(xfrm_state_lock); [ 81.725248] <Interrupt> [ 81.725249] lock(&(&x->lock)->rlock); [ 81.725251] [ 81.725251] *** DEADLOCK *** [ 81.725251] [ 81.725254] no locks held by kpktgend_0/2780. [ 81.725255] [ 81.725255] the shortest dependencies between 2nd lock and 1st lock: [ 81.725269] -> (&(&x->lock)->rlock){+.-...} ops: 8 { [ 81.725274] HARDIRQ-ON-W at: [ 81.725276] [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70 [ 81.725282] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725284] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725289] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725292] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725300] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725303] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725305] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725308] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725313] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725316] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725329] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725333] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725338] IN-SOFTIRQ-W at: [ 81.725340] [<ffffffff8109a61d>] __lock_acquire+0x62d/0x1d70 [ 81.725342] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725344] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725347] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725349] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725352] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725355] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725358] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725360] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725363] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725365] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725368] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725370] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725373] INITIAL USE at: [ 81.725375] [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70 [ 81.725385] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725388] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725390] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725394] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725398] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725401] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725404] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725407] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725409] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725412] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725415] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725417] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725420] } [ 81.725421] ... key at: [<ffffffff8295b9c8>] __key.46349+0x0/0x8 [ 81.725445] ... acquired at: [ 81.725446] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725449] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725452] [<ffffffff816dc057>] __xfrm_state_delete+0x37/0x140 [ 81.725454] [<ffffffff816dc18c>] xfrm_state_delete+0x2c/0x50 [ 81.725456] [<ffffffff816dc277>] xfrm_state_flush+0xc7/0x1b0 [ 81.725458] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725465] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725468] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725471] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725476] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725479] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725482] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725484] [ 81.725486] -> (xfrm_state_lock){+.+...} ops: 11 { [ 81.725490] HARDIRQ-ON-W at: [ 81.725493] [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70 [ 81.725504] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725507] [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70 [ 81.725510] [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0 [ 81.725513] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725516] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725519] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725522] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725525] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725527] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725530] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725533] SOFTIRQ-ON-W at: [ 81.725534] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725537] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725539] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725541] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725544] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725547] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725550] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725555] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725565] INITIAL USE at: [ 81.725567] [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70 [ 81.725569] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725572] [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70 [ 81.725574] [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0 [ 81.725576] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725580] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725583] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725586] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725589] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725594] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725597] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725599] } [ 81.725600] ... key at: [<ffffffff81cadef8>] xfrm_state_lock+0x18/0x50 [ 81.725606] ... acquired at: [ 81.725607] [<ffffffff810995c0>] check_usage_backwards+0x110/0x150 [ 81.725609] [<ffffffff81099e96>] mark_lock+0x196/0x2f0 [ 81.725611] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725614] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725616] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725627] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725629] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725632] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725635] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725637] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725640] [ 81.725641] [ 81.725641] stack backtrace: [ 81.725645] CPU: 0 PID: 2780 Comm: kpktgend_0 Not tainted 3.13.0-rc2+ #92 [ 81.725647] Hardware name: innotek GmbH VirtualBox, BIOS VirtualBox 12/01/2006 [ 81.725649] ffffffff82537b80 ffff880018199988 ffffffff8176af37 0000000000000007 [ 81.725652] ffff8800181999f0 ffff8800181999d8 ffffffff81099358 ffffffff82537b80 [ 81.725655] ffffffff81a32def ffff8800181999f4 0000000000000000 ffff880002cbeaa8 [ 81.725659] Call Trace: [ 81.725664] [<ffffffff8176af37>] dump_stack+0x46/0x58 [ 81.725667] [<ffffffff81099358>] print_irq_inversion_bug.part.42+0x1e8/0x1f0 [ 81.725670] [<ffffffff810995c0>] check_usage_backwards+0x110/0x150 [ 81.725672] [<ffffffff81099e96>] mark_lock+0x196/0x2f0 [ 81.725675] [<ffffffff810994b0>] ? check_usage_forwards+0x150/0x150 [ 81.725685] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725691] [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90 [ 81.725694] [<ffffffff81089b38>] ? sched_clock_cpu+0xa8/0x120 [ 81.725697] [<ffffffff8109a31a>] ? __lock_acquire+0x32a/0x1d70 [ 81.725699] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725702] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725704] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725707] [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90 [ 81.725710] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725712] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725715] [<ffffffff810971ec>] ? lock_release_holdtime.part.26+0x1c/0x1a0 [ 81.725717] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725721] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725724] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725727] [<ffffffffa008ba71>] ? pktgen_thread_worker+0xb11/0x1880 [pktgen] [ 81.725729] [<ffffffff8109cf9d>] ? trace_hardirqs_on+0xd/0x10 [ 81.725733] [<ffffffff81775410>] ? _raw_spin_unlock_irq+0x30/0x40 [ 81.725745] [<ffffffff8151faa0>] ? e1000_clean+0x9d0/0x9d0 [ 81.725751] [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60 [ 81.725753] [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60 [ 81.725757] [<ffffffffa008af60>] ? mod_cur_headers+0x7f0/0x7f0 [pktgen] [ 81.725759] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725762] [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170 [ 81.725765] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725768] [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170 Signed-off-by: Fan Du <fan.du@windriver.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-01-03 11:18:29 +08:00
spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
(mark & x->mark.m) == x->mark.v &&
!(x->props.flags & XFRM_STATE_WILDRECV) &&
xfrm_state_addr_check(x, daddr, saddr, family) &&
mode == x->props.mode &&
proto == x->id.proto &&
x->km.state == XFRM_STATE_VALID) {
rx = x;
break;
}
}
if (rx)
xfrm_state_hold(rx);
{pktgen, xfrm} Correct xfrm_state_lock usage in xfrm_stateonly_find Acquiring xfrm_state_lock in process context is expected to turn BH off, as this lock is also used in BH context, namely xfrm state timer handler. Otherwise it surprises LOCKDEP with below messages. [ 81.422781] pktgen: Packet Generator for packet performance testing. Version: 2.74 [ 81.725194] [ 81.725211] ========================================================= [ 81.725212] [ INFO: possible irq lock inversion dependency detected ] [ 81.725215] 3.13.0-rc2+ #92 Not tainted [ 81.725216] --------------------------------------------------------- [ 81.725218] kpktgend_0/2780 just changed the state of lock: [ 81.725220] (xfrm_state_lock){+.+...}, at: [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725231] but this lock was taken by another, SOFTIRQ-safe lock in the past: [ 81.725232] (&(&x->lock)->rlock){+.-...} [ 81.725232] [ 81.725232] and interrupts could create inverse lock ordering between them. [ 81.725232] [ 81.725235] [ 81.725235] other info that might help us debug this: [ 81.725237] Possible interrupt unsafe locking scenario: [ 81.725237] [ 81.725238] CPU0 CPU1 [ 81.725240] ---- ---- [ 81.725241] lock(xfrm_state_lock); [ 81.725243] local_irq_disable(); [ 81.725244] lock(&(&x->lock)->rlock); [ 81.725246] lock(xfrm_state_lock); [ 81.725248] <Interrupt> [ 81.725249] lock(&(&x->lock)->rlock); [ 81.725251] [ 81.725251] *** DEADLOCK *** [ 81.725251] [ 81.725254] no locks held by kpktgend_0/2780. [ 81.725255] [ 81.725255] the shortest dependencies between 2nd lock and 1st lock: [ 81.725269] -> (&(&x->lock)->rlock){+.-...} ops: 8 { [ 81.725274] HARDIRQ-ON-W at: [ 81.725276] [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70 [ 81.725282] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725284] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725289] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725292] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725300] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725303] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725305] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725308] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725313] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725316] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725329] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725333] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725338] IN-SOFTIRQ-W at: [ 81.725340] [<ffffffff8109a61d>] __lock_acquire+0x62d/0x1d70 [ 81.725342] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725344] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725347] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725349] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725352] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725355] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725358] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725360] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725363] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725365] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725368] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725370] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725373] INITIAL USE at: [ 81.725375] [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70 [ 81.725385] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725388] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725390] [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290 [ 81.725394] [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725398] [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0 [ 81.725401] [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0 [ 81.725404] [<ffffffff8105a026>] irq_exit+0x96/0xc0 [ 81.725407] [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725409] [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80 [ 81.725412] [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30 [ 81.725415] [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0 [ 81.725417] [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0 [ 81.725420] } [ 81.725421] ... key at: [<ffffffff8295b9c8>] __key.46349+0x0/0x8 [ 81.725445] ... acquired at: [ 81.725446] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725449] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725452] [<ffffffff816dc057>] __xfrm_state_delete+0x37/0x140 [ 81.725454] [<ffffffff816dc18c>] xfrm_state_delete+0x2c/0x50 [ 81.725456] [<ffffffff816dc277>] xfrm_state_flush+0xc7/0x1b0 [ 81.725458] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725465] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725468] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725471] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725476] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725479] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725482] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725484] [ 81.725486] -> (xfrm_state_lock){+.+...} ops: 11 { [ 81.725490] HARDIRQ-ON-W at: [ 81.725493] [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70 [ 81.725504] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725507] [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70 [ 81.725510] [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0 [ 81.725513] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725516] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725519] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725522] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725525] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725527] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725530] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725533] SOFTIRQ-ON-W at: [ 81.725534] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725537] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725539] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725541] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725544] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725547] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725550] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725555] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725565] INITIAL USE at: [ 81.725567] [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70 [ 81.725569] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725572] [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70 [ 81.725574] [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0 [ 81.725576] [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key] [ 81.725580] [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725583] [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725586] [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0 [ 81.725589] [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130 [ 81.725594] [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10 [ 81.725597] [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b [ 81.725599] } [ 81.725600] ... key at: [<ffffffff81cadef8>] xfrm_state_lock+0x18/0x50 [ 81.725606] ... acquired at: [ 81.725607] [<ffffffff810995c0>] check_usage_backwards+0x110/0x150 [ 81.725609] [<ffffffff81099e96>] mark_lock+0x196/0x2f0 [ 81.725611] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725614] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725616] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725627] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725629] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725632] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725635] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725637] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725640] [ 81.725641] [ 81.725641] stack backtrace: [ 81.725645] CPU: 0 PID: 2780 Comm: kpktgend_0 Not tainted 3.13.0-rc2+ #92 [ 81.725647] Hardware name: innotek GmbH VirtualBox, BIOS VirtualBox 12/01/2006 [ 81.725649] ffffffff82537b80 ffff880018199988 ffffffff8176af37 0000000000000007 [ 81.725652] ffff8800181999f0 ffff8800181999d8 ffffffff81099358 ffffffff82537b80 [ 81.725655] ffffffff81a32def ffff8800181999f4 0000000000000000 ffff880002cbeaa8 [ 81.725659] Call Trace: [ 81.725664] [<ffffffff8176af37>] dump_stack+0x46/0x58 [ 81.725667] [<ffffffff81099358>] print_irq_inversion_bug.part.42+0x1e8/0x1f0 [ 81.725670] [<ffffffff810995c0>] check_usage_backwards+0x110/0x150 [ 81.725672] [<ffffffff81099e96>] mark_lock+0x196/0x2f0 [ 81.725675] [<ffffffff810994b0>] ? check_usage_forwards+0x150/0x150 [ 81.725685] [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70 [ 81.725691] [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90 [ 81.725694] [<ffffffff81089b38>] ? sched_clock_cpu+0xa8/0x120 [ 81.725697] [<ffffffff8109a31a>] ? __lock_acquire+0x32a/0x1d70 [ 81.725699] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725702] [<ffffffff8109c3c7>] lock_acquire+0x97/0x130 [ 81.725704] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725707] [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90 [ 81.725710] [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70 [ 81.725712] [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725715] [<ffffffff810971ec>] ? lock_release_holdtime.part.26+0x1c/0x1a0 [ 81.725717] [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0 [ 81.725721] [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725724] [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725727] [<ffffffffa008ba71>] ? pktgen_thread_worker+0xb11/0x1880 [pktgen] [ 81.725729] [<ffffffff8109cf9d>] ? trace_hardirqs_on+0xd/0x10 [ 81.725733] [<ffffffff81775410>] ? _raw_spin_unlock_irq+0x30/0x40 [ 81.725745] [<ffffffff8151faa0>] ? e1000_clean+0x9d0/0x9d0 [ 81.725751] [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60 [ 81.725753] [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60 [ 81.725757] [<ffffffffa008af60>] ? mod_cur_headers+0x7f0/0x7f0 [pktgen] [ 81.725759] [<ffffffff81078f84>] kthread+0xe4/0x100 [ 81.725762] [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170 [ 81.725765] [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0 [ 81.725768] [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170 Signed-off-by: Fan Du <fan.du@windriver.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2014-01-03 11:18:29 +08:00
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return rx;
}
EXPORT_SYMBOL(xfrm_stateonly_find);
struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
unsigned short family)
{
struct xfrm_state *x;
struct xfrm_state_walk *w;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
list_for_each_entry(w, &net->xfrm.state_all, all) {
x = container_of(w, struct xfrm_state, km);
if (x->props.family != family ||
x->id.spi != spi)
continue;
xfrm_state_hold(x);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return NULL;
}
EXPORT_SYMBOL(xfrm_state_lookup_byspi);
static void __xfrm_state_insert(struct xfrm_state *x)
{
struct net *net = xs_net(x);
unsigned int h;
list_add(&x->km.all, &net->xfrm.state_all);
h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
x->props.reqid, x->props.family);
hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
if (x->id.spi) {
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
x->props.family);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
}
tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
if (x->replay_maxage)
mod_timer(&x->rtimer, jiffies + x->replay_maxage);
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
}
/* net->xfrm.xfrm_state_lock is held */
static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
{
struct net *net = xs_net(xnew);
unsigned short family = xnew->props.family;
u32 reqid = xnew->props.reqid;
struct xfrm_state *x;
unsigned int h;
u32 mark = xnew->mark.v & xnew->mark.m;
h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
(mark & x->mark.m) == x->mark.v &&
xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
x->genid++;
}
}
void xfrm_state_insert(struct xfrm_state *x)
{
struct net *net = xs_net(x);
spin_lock_bh(&net->xfrm.xfrm_state_lock);
__xfrm_state_bump_genids(x);
__xfrm_state_insert(x);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_insert);
/* net->xfrm.xfrm_state_lock is held */
static struct xfrm_state *__find_acq_core(struct net *net,
const struct xfrm_mark *m,
unsigned short family, u8 mode,
u32 reqid, u8 proto,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
int create)
{
unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
struct xfrm_state *x;
u32 mark = m->v & m->m;
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.reqid != reqid ||
x->props.mode != mode ||
x->props.family != family ||
x->km.state != XFRM_STATE_ACQ ||
x->id.spi != 0 ||
x->id.proto != proto ||
(mark & x->mark.m) != x->mark.v ||
!xfrm_addr_equal(&x->id.daddr, daddr, family) ||
!xfrm_addr_equal(&x->props.saddr, saddr, family))
continue;
xfrm_state_hold(x);
return x;
}
if (!create)
return NULL;
x = xfrm_state_alloc(net);
if (likely(x)) {
switch (family) {
case AF_INET:
x->sel.daddr.a4 = daddr->a4;
x->sel.saddr.a4 = saddr->a4;
x->sel.prefixlen_d = 32;
x->sel.prefixlen_s = 32;
x->props.saddr.a4 = saddr->a4;
x->id.daddr.a4 = daddr->a4;
break;
case AF_INET6:
x->sel.daddr.in6 = daddr->in6;
x->sel.saddr.in6 = saddr->in6;
x->sel.prefixlen_d = 128;
x->sel.prefixlen_s = 128;
x->props.saddr.in6 = saddr->in6;
x->id.daddr.in6 = daddr->in6;
break;
}
x->km.state = XFRM_STATE_ACQ;
x->id.proto = proto;
x->props.family = family;
x->props.mode = mode;
x->props.reqid = reqid;
x->mark.v = m->v;
x->mark.m = m->m;
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
xfrm_state_hold(x);
tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
list_add(&x->km.all, &net->xfrm.state_all);
hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
h = xfrm_src_hash(net, daddr, saddr, family);
hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
}
return x;
}
static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
int xfrm_state_add(struct xfrm_state *x)
{
struct net *net = xs_net(x);
struct xfrm_state *x1, *to_put;
int family;
int err;
u32 mark = x->mark.v & x->mark.m;
int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
family = x->props.family;
to_put = NULL;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, family);
if (x1) {
to_put = x1;
x1 = NULL;
err = -EEXIST;
goto out;
}
if (use_spi && x->km.seq) {
x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq);
if (x1 && ((x1->id.proto != x->id.proto) ||
!xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) {
to_put = x1;
x1 = NULL;
}
}
if (use_spi && !x1)
x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
x->props.reqid, x->id.proto,
&x->id.daddr, &x->props.saddr, 0);
__xfrm_state_bump_genids(x);
__xfrm_state_insert(x);
err = 0;
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (x1) {
xfrm_state_delete(x1);
xfrm_state_put(x1);
}
if (to_put)
xfrm_state_put(to_put);
return err;
}
EXPORT_SYMBOL(xfrm_state_add);
#ifdef CONFIG_XFRM_MIGRATE
static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig)
{
struct net *net = xs_net(orig);
struct xfrm_state *x = xfrm_state_alloc(net);
if (!x)
goto out;
memcpy(&x->id, &orig->id, sizeof(x->id));
memcpy(&x->sel, &orig->sel, sizeof(x->sel));
memcpy(&x->lft, &orig->lft, sizeof(x->lft));
x->props.mode = orig->props.mode;
x->props.replay_window = orig->props.replay_window;
x->props.reqid = orig->props.reqid;
x->props.family = orig->props.family;
x->props.saddr = orig->props.saddr;
if (orig->aalg) {
x->aalg = xfrm_algo_auth_clone(orig->aalg);
if (!x->aalg)
goto error;
}
x->props.aalgo = orig->props.aalgo;
if (orig->aead) {
x->aead = xfrm_algo_aead_clone(orig->aead);
if (!x->aead)
goto error;
}
if (orig->ealg) {
x->ealg = xfrm_algo_clone(orig->ealg);
if (!x->ealg)
goto error;
}
x->props.ealgo = orig->props.ealgo;
if (orig->calg) {
x->calg = xfrm_algo_clone(orig->calg);
if (!x->calg)
goto error;
}
x->props.calgo = orig->props.calgo;
if (orig->encap) {
x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL);
if (!x->encap)
goto error;
}
if (orig->coaddr) {
x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
GFP_KERNEL);
if (!x->coaddr)
goto error;
}
if (orig->replay_esn) {
if (xfrm_replay_clone(x, orig))
goto error;
}
memcpy(&x->mark, &orig->mark, sizeof(x->mark));
if (xfrm_init_state(x) < 0)
goto error;
x->props.flags = orig->props.flags;
x->props.extra_flags = orig->props.extra_flags;
x->tfcpad = orig->tfcpad;
x->replay_maxdiff = orig->replay_maxdiff;
x->replay_maxage = orig->replay_maxage;
x->curlft.add_time = orig->curlft.add_time;
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
return x;
error:
xfrm_state_put(x);
out:
return NULL;
}
struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
{
unsigned int h;
struct xfrm_state *x = NULL;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (m->reqid) {
h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
m->reqid, m->old_family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
if (m->reqid && x->props.reqid != m->reqid)
continue;
if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
m->old_family) ||
!xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
m->old_family))
continue;
xfrm_state_hold(x);
break;
}
} else {
h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
m->old_family);
hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
m->old_family) ||
!xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
m->old_family))
continue;
xfrm_state_hold(x);
break;
}
}
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_migrate_state_find);
struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m)
{
struct xfrm_state *xc;
xc = xfrm_state_clone(x);
if (!xc)
return NULL;
memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
/* add state */
if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
/* a care is needed when the destination address of the
state is to be updated as it is a part of triplet */
xfrm_state_insert(xc);
} else {
if (xfrm_state_add(xc) < 0)
goto error;
}
return xc;
error:
xfrm_state_put(xc);
return NULL;
}
EXPORT_SYMBOL(xfrm_state_migrate);
#endif
int xfrm_state_update(struct xfrm_state *x)
{
struct xfrm_state *x1, *to_put;
int err;
int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
struct net *net = xs_net(x);
to_put = NULL;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, x->props.family);
err = -ESRCH;
if (!x1)
goto out;
if (xfrm_state_kern(x1)) {
to_put = x1;
err = -EEXIST;
goto out;
}
if (x1->km.state == XFRM_STATE_ACQ) {
__xfrm_state_insert(x);
x = NULL;
}
err = 0;
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (to_put)
xfrm_state_put(to_put);
if (err)
return err;
if (!x) {
xfrm_state_delete(x1);
xfrm_state_put(x1);
return 0;
}
err = -EINVAL;
spin_lock_bh(&x1->lock);
if (likely(x1->km.state == XFRM_STATE_VALID)) {
if (x->encap && x1->encap)
memcpy(x1->encap, x->encap, sizeof(*x1->encap));
if (x->coaddr && x1->coaddr) {
memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr));
}
if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel)))
memcpy(&x1->sel, &x->sel, sizeof(x1->sel));
memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
x1->km.dying = 0;
tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
if (x1->curlft.use_time)
xfrm_state_check_expire(x1);
err = 0;
x->km.state = XFRM_STATE_DEAD;
__xfrm_state_put(x);
}
spin_unlock_bh(&x1->lock);
xfrm_state_put(x1);
return err;
}
EXPORT_SYMBOL(xfrm_state_update);
int xfrm_state_check_expire(struct xfrm_state *x)
{
if (!x->curlft.use_time)
x->curlft.use_time = get_seconds();
if (x->curlft.bytes >= x->lft.hard_byte_limit ||
x->curlft.packets >= x->lft.hard_packet_limit) {
x->km.state = XFRM_STATE_EXPIRED;
tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
return -EINVAL;
}
if (!x->km.dying &&
(x->curlft.bytes >= x->lft.soft_byte_limit ||
x->curlft.packets >= x->lft.soft_packet_limit)) {
x->km.dying = 1;
km_state_expired(x, 0, 0);
}
return 0;
}
EXPORT_SYMBOL(xfrm_state_check_expire);
struct xfrm_state *
xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
u8 proto, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup);
struct xfrm_state *
xfrm_state_lookup_byaddr(struct net *net, u32 mark,
const xfrm_address_t *daddr, const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
struct xfrm_state *
xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
u8 proto, const xfrm_address_t *daddr,
const xfrm_address_t *saddr, int create, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_find_acq);
#ifdef CONFIG_XFRM_SUB_POLICY
int
xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
unsigned short family, struct net *net)
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
return -EAFNOSUPPORT;
spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
if (afinfo->tmpl_sort)
err = afinfo->tmpl_sort(dst, src, n);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_tmpl_sort);
int
xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
unsigned short family)
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
struct net *net = xs_net(*src);
if (!afinfo)
return -EAFNOSUPPORT;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (afinfo->state_sort)
err = afinfo->state_sort(dst, src, n);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_state_sort);
#endif
/* Silly enough, but I'm lazy to build resolution list */
static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
{
int i;
for (i = 0; i <= net->xfrm.state_hmask; i++) {
struct xfrm_state *x;
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 09:06:00 +08:00
hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
if (x->km.seq == seq &&
(mark & x->mark.m) == x->mark.v &&
x->km.state == XFRM_STATE_ACQ) {
xfrm_state_hold(x);
return x;
}
}
}
return NULL;
}
struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_find_acq_byseq(net, mark, seq);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_find_acq_byseq);
u32 xfrm_get_acqseq(void)
{
u32 res;
static atomic_t acqseq;
do {
res = atomic_inc_return(&acqseq);
} while (!res);
return res;
}
EXPORT_SYMBOL(xfrm_get_acqseq);
int verify_spi_info(u8 proto, u32 min, u32 max)
{
switch (proto) {
case IPPROTO_AH:
case IPPROTO_ESP:
break;
case IPPROTO_COMP:
/* IPCOMP spi is 16-bits. */
if (max >= 0x10000)
return -EINVAL;
break;
default:
return -EINVAL;
}
if (min > max)
return -EINVAL;
return 0;
}
EXPORT_SYMBOL(verify_spi_info);
int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
{
struct net *net = xs_net(x);
unsigned int h;
struct xfrm_state *x0;
int err = -ENOENT;
__be32 minspi = htonl(low);
__be32 maxspi = htonl(high);
u32 mark = x->mark.v & x->mark.m;
spin_lock_bh(&x->lock);
if (x->km.state == XFRM_STATE_DEAD)
goto unlock;
err = 0;
if (x->id.spi)
goto unlock;
err = -ENOENT;
if (minspi == maxspi) {
x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family);
if (x0) {
xfrm_state_put(x0);
goto unlock;
}
x->id.spi = minspi;
} else {
u32 spi = 0;
for (h = 0; h < high-low+1; h++) {
spi = low + prandom_u32()%(high-low+1);
x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
if (x0 == NULL) {
x->id.spi = htonl(spi);
break;
}
xfrm_state_put(x0);
}
}
if (x->id.spi) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = 0;
}
unlock:
spin_unlock_bh(&x->lock);
return err;
}
EXPORT_SYMBOL(xfrm_alloc_spi);
static bool __xfrm_state_filter_match(struct xfrm_state *x,
struct xfrm_address_filter *filter)
{
if (filter) {
if ((filter->family == AF_INET ||
filter->family == AF_INET6) &&
x->props.family != filter->family)
return false;
return addr_match(&x->props.saddr, &filter->saddr,
filter->splen) &&
addr_match(&x->id.daddr, &filter->daddr,
filter->dplen);
}
return true;
}
int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*),
void *data)
{
struct xfrm_state *state;
struct xfrm_state_walk *x;
int err = 0;
if (walk->seq != 0 && list_empty(&walk->all))
return 0;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (list_empty(&walk->all))
x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
else
x = list_first_entry(&walk->all, struct xfrm_state_walk, all);
list_for_each_entry_from(x, &net->xfrm.state_all, all) {
if (x->state == XFRM_STATE_DEAD)
continue;
state = container_of(x, struct xfrm_state, km);
if (!xfrm_id_proto_match(state->id.proto, walk->proto))
continue;
if (!__xfrm_state_filter_match(state, walk->filter))
continue;
err = func(state, walk->seq, data);
if (err) {
list_move_tail(&walk->all, &x->all);
goto out;
}
walk->seq++;
}
if (walk->seq == 0) {
err = -ENOENT;
goto out;
}
list_del_init(&walk->all);
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_walk);
void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
struct xfrm_address_filter *filter)
{
INIT_LIST_HEAD(&walk->all);
walk->proto = proto;
walk->state = XFRM_STATE_DEAD;
walk->seq = 0;
walk->filter = filter;
}
EXPORT_SYMBOL(xfrm_state_walk_init);
void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
{
kfree(walk->filter);
if (list_empty(&walk->all))
return;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
list_del(&walk->all);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_walk_done);
static void xfrm_replay_timer_handler(unsigned long data)
{
struct xfrm_state *x = (struct xfrm_state *)data;
spin_lock(&x->lock);
if (x->km.state == XFRM_STATE_VALID) {
if (xfrm_aevent_is_on(xs_net(x)))
x->repl->notify(x, XFRM_REPLAY_TIMEOUT);
else
x->xflags |= XFRM_TIME_DEFER;
}
spin_unlock(&x->lock);
}
static LIST_HEAD(xfrm_km_list);
void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
{
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list)
if (km->notify_policy)
km->notify_policy(xp, dir, c);
rcu_read_unlock();
}
void km_state_notify(struct xfrm_state *x, const struct km_event *c)
{
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list)
if (km->notify)
km->notify(x, c);
rcu_read_unlock();
}
EXPORT_SYMBOL(km_policy_notify);
EXPORT_SYMBOL(km_state_notify);
void km_state_expired(struct xfrm_state *x, int hard, u32 portid)
{
struct km_event c;
c.data.hard = hard;
c.portid = portid;
c.event = XFRM_MSG_EXPIRE;
km_state_notify(x, &c);
}
EXPORT_SYMBOL(km_state_expired);
/*
* We send to all registered managers regardless of failure
* We are happy with one success
*/
int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
{
int err = -EINVAL, acqret;
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
acqret = km->acquire(x, t, pol);
if (!acqret)
err = acqret;
}
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(km_query);
int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
{
int err = -EINVAL;
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
if (km->new_mapping)
err = km->new_mapping(x, ipaddr, sport);
if (!err)
break;
}
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(km_new_mapping);
void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
{
struct km_event c;
c.data.hard = hard;
c.portid = portid;
c.event = XFRM_MSG_POLEXPIRE;
km_policy_notify(pol, dir, &c);
}
EXPORT_SYMBOL(km_policy_expired);
#ifdef CONFIG_XFRM_MIGRATE
int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
const struct xfrm_migrate *m, int num_migrate,
const struct xfrm_kmaddress *k)
{
int err = -EINVAL;
int ret;
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
if (km->migrate) {
ret = km->migrate(sel, dir, type, m, num_migrate, k);
if (!ret)
err = ret;
}
}
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(km_migrate);
#endif
int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr)
{
int err = -EINVAL;
int ret;
struct xfrm_mgr *km;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
if (km->report) {
ret = km->report(net, proto, sel, addr);
if (!ret)
err = ret;
}
}
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(km_report);
bool km_is_alive(const struct km_event *c)
{
struct xfrm_mgr *km;
bool is_alive = false;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
if (km->is_alive && km->is_alive(c)) {
is_alive = true;
break;
}
}
rcu_read_unlock();
return is_alive;
}
EXPORT_SYMBOL(km_is_alive);
int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
{
int err;
u8 *data;
struct xfrm_mgr *km;
struct xfrm_policy *pol = NULL;
if (optlen <= 0 || optlen > PAGE_SIZE)
return -EMSGSIZE;
data = kmalloc(optlen, GFP_KERNEL);
if (!data)
return -ENOMEM;
err = -EFAULT;
if (copy_from_user(data, optval, optlen))
goto out;
err = -EINVAL;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
pol = km->compile_policy(sk, optname, data,
optlen, &err);
if (err >= 0)
break;
}
rcu_read_unlock();
if (err >= 0) {
xfrm_sk_policy_insert(sk, err, pol);
xfrm_pol_put(pol);
err = 0;
}
out:
kfree(data);
return err;
}
EXPORT_SYMBOL(xfrm_user_policy);
static DEFINE_SPINLOCK(xfrm_km_lock);
int xfrm_register_km(struct xfrm_mgr *km)
{
spin_lock_bh(&xfrm_km_lock);
list_add_tail_rcu(&km->list, &xfrm_km_list);
spin_unlock_bh(&xfrm_km_lock);
return 0;
}
EXPORT_SYMBOL(xfrm_register_km);
int xfrm_unregister_km(struct xfrm_mgr *km)
{
spin_lock_bh(&xfrm_km_lock);
list_del_rcu(&km->list);
spin_unlock_bh(&xfrm_km_lock);
synchronize_rcu();
return 0;
}
EXPORT_SYMBOL(xfrm_unregister_km);
int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo)
{
int err = 0;
if (unlikely(afinfo == NULL))
return -EINVAL;
if (unlikely(afinfo->family >= NPROTO))
return -EAFNOSUPPORT;
spin_lock_bh(&xfrm_state_afinfo_lock);
if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL))
err = -EEXIST;
else
rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo);
spin_unlock_bh(&xfrm_state_afinfo_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_register_afinfo);
int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
{
int err = 0;
if (unlikely(afinfo == NULL))
return -EINVAL;
if (unlikely(afinfo->family >= NPROTO))
return -EAFNOSUPPORT;
spin_lock_bh(&xfrm_state_afinfo_lock);
if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) {
if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo))
err = -EINVAL;
else
RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL);
}
spin_unlock_bh(&xfrm_state_afinfo_lock);
synchronize_rcu();
return err;
}
EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
{
struct xfrm_state_afinfo *afinfo;
if (unlikely(family >= NPROTO))
return NULL;
rcu_read_lock();
afinfo = rcu_dereference(xfrm_state_afinfo[family]);
if (unlikely(!afinfo))
rcu_read_unlock();
return afinfo;
}
void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
{
rcu_read_unlock();
}
/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
void xfrm_state_delete_tunnel(struct xfrm_state *x)
{
if (x->tunnel) {
struct xfrm_state *t = x->tunnel;
if (atomic_read(&t->tunnel_users) == 2)
xfrm_state_delete(t);
atomic_dec(&t->tunnel_users);
xfrm_state_put(t);
x->tunnel = NULL;
}
}
EXPORT_SYMBOL(xfrm_state_delete_tunnel);
int xfrm_state_mtu(struct xfrm_state *x, int mtu)
{
int res;
spin_lock_bh(&x->lock);
if (x->km.state == XFRM_STATE_VALID &&
x->type && x->type->get_mtu)
res = x->type->get_mtu(x, mtu);
else
res = mtu - x->props.header_len;
spin_unlock_bh(&x->lock);
return res;
}
xfrm: Fix initialize repl field of struct xfrm_state Commit 'xfrm: Move IPsec replay detection functions to a separate file' (9fdc4883d92d20842c5acea77a4a21bb1574b495) introduce repl field to struct xfrm_state, and only initialize it under SA's netlink create path, the other path, such as pf_key, ipcomp/ipcomp6 etc, the repl field remaining uninitialize. So if the SA is created by pf_key, any input packet with SA's encryption algorithm will cause panic. int xfrm_input() { ... x->repl->advance(x, seq); ... } This patch fixed it by introduce new function __xfrm_init_state(). Pid: 0, comm: swapper Not tainted 2.6.38-next+ #14 Bochs Bochs EIP: 0060:[<c078e5d5>] EFLAGS: 00010206 CPU: 0 EIP is at xfrm_input+0x31c/0x4cc EAX: dd839c00 EBX: 00000084 ECX: 00000000 EDX: 01000000 ESI: dd839c00 EDI: de3a0780 EBP: dec1de88 ESP: dec1de64 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process swapper (pid: 0, ti=dec1c000 task=c09c0f20 task.ti=c0992000) Stack: 00000000 00000000 00000002 c0ba27c0 00100000 01000000 de3a0798 c0ba27c0 00000033 dec1de98 c0786848 00000000 de3a0780 dec1dea4 c0786868 00000000 dec1debc c074ee56 e1da6b8c de3a0780 c074ed44 de3a07a8 dec1decc c074ef32 Call Trace: [<c0786848>] xfrm4_rcv_encap+0x22/0x27 [<c0786868>] xfrm4_rcv+0x1b/0x1d [<c074ee56>] ip_local_deliver_finish+0x112/0x1b1 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074ef77>] ip_local_deliver+0x3e/0x44 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ec03>] ip_rcv_finish+0x30a/0x332 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074f188>] ip_rcv+0x20b/0x247 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c072797d>] __netif_receive_skb+0x373/0x399 [<c0727bc1>] netif_receive_skb+0x4b/0x51 [<e0817e2a>] cp_rx_poll+0x210/0x2c4 [8139cp] [<c072818f>] net_rx_action+0x9a/0x17d [<c0445b5c>] __do_softirq+0xa1/0x149 [<c0445abb>] ? __do_softirq+0x0/0x149 Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-22 09:08:28 +08:00
int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
{
struct xfrm_state_afinfo *afinfo;
struct xfrm_mode *inner_mode;
int family = x->props.family;
int err;
err = -EAFNOSUPPORT;
afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
goto error;
err = 0;
if (afinfo->init_flags)
err = afinfo->init_flags(x);
xfrm_state_put_afinfo(afinfo);
if (err)
goto error;
err = -EPROTONOSUPPORT;
if (x->sel.family != AF_UNSPEC) {
inner_mode = xfrm_get_mode(x->props.mode, x->sel.family);
if (inner_mode == NULL)
goto error;
if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) &&
family != x->sel.family) {
xfrm_put_mode(inner_mode);
goto error;
}
x->inner_mode = inner_mode;
} else {
struct xfrm_mode *inner_mode_iaf;
int iafamily = AF_INET;
inner_mode = xfrm_get_mode(x->props.mode, x->props.family);
if (inner_mode == NULL)
goto error;
if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) {
xfrm_put_mode(inner_mode);
goto error;
}
x->inner_mode = inner_mode;
if (x->props.family == AF_INET)
iafamily = AF_INET6;
inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily);
if (inner_mode_iaf) {
if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)
x->inner_mode_iaf = inner_mode_iaf;
else
xfrm_put_mode(inner_mode_iaf);
}
}
x->type = xfrm_get_type(x->id.proto, family);
if (x->type == NULL)
goto error;
err = x->type->init_state(x);
if (err)
goto error;
x->outer_mode = xfrm_get_mode(x->props.mode, family);
if (x->outer_mode == NULL) {
err = -EPROTONOSUPPORT;
goto error;
}
xfrm: Fix initialize repl field of struct xfrm_state Commit 'xfrm: Move IPsec replay detection functions to a separate file' (9fdc4883d92d20842c5acea77a4a21bb1574b495) introduce repl field to struct xfrm_state, and only initialize it under SA's netlink create path, the other path, such as pf_key, ipcomp/ipcomp6 etc, the repl field remaining uninitialize. So if the SA is created by pf_key, any input packet with SA's encryption algorithm will cause panic. int xfrm_input() { ... x->repl->advance(x, seq); ... } This patch fixed it by introduce new function __xfrm_init_state(). Pid: 0, comm: swapper Not tainted 2.6.38-next+ #14 Bochs Bochs EIP: 0060:[<c078e5d5>] EFLAGS: 00010206 CPU: 0 EIP is at xfrm_input+0x31c/0x4cc EAX: dd839c00 EBX: 00000084 ECX: 00000000 EDX: 01000000 ESI: dd839c00 EDI: de3a0780 EBP: dec1de88 ESP: dec1de64 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process swapper (pid: 0, ti=dec1c000 task=c09c0f20 task.ti=c0992000) Stack: 00000000 00000000 00000002 c0ba27c0 00100000 01000000 de3a0798 c0ba27c0 00000033 dec1de98 c0786848 00000000 de3a0780 dec1dea4 c0786868 00000000 dec1debc c074ee56 e1da6b8c de3a0780 c074ed44 de3a07a8 dec1decc c074ef32 Call Trace: [<c0786848>] xfrm4_rcv_encap+0x22/0x27 [<c0786868>] xfrm4_rcv+0x1b/0x1d [<c074ee56>] ip_local_deliver_finish+0x112/0x1b1 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074ef77>] ip_local_deliver+0x3e/0x44 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ec03>] ip_rcv_finish+0x30a/0x332 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074f188>] ip_rcv+0x20b/0x247 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c072797d>] __netif_receive_skb+0x373/0x399 [<c0727bc1>] netif_receive_skb+0x4b/0x51 [<e0817e2a>] cp_rx_poll+0x210/0x2c4 [8139cp] [<c072818f>] net_rx_action+0x9a/0x17d [<c0445b5c>] __do_softirq+0xa1/0x149 [<c0445abb>] ? __do_softirq+0x0/0x149 Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-22 09:08:28 +08:00
if (init_replay) {
err = xfrm_init_replay(x);
if (err)
goto error;
}
x->km.state = XFRM_STATE_VALID;
error:
return err;
}
xfrm: Fix initialize repl field of struct xfrm_state Commit 'xfrm: Move IPsec replay detection functions to a separate file' (9fdc4883d92d20842c5acea77a4a21bb1574b495) introduce repl field to struct xfrm_state, and only initialize it under SA's netlink create path, the other path, such as pf_key, ipcomp/ipcomp6 etc, the repl field remaining uninitialize. So if the SA is created by pf_key, any input packet with SA's encryption algorithm will cause panic. int xfrm_input() { ... x->repl->advance(x, seq); ... } This patch fixed it by introduce new function __xfrm_init_state(). Pid: 0, comm: swapper Not tainted 2.6.38-next+ #14 Bochs Bochs EIP: 0060:[<c078e5d5>] EFLAGS: 00010206 CPU: 0 EIP is at xfrm_input+0x31c/0x4cc EAX: dd839c00 EBX: 00000084 ECX: 00000000 EDX: 01000000 ESI: dd839c00 EDI: de3a0780 EBP: dec1de88 ESP: dec1de64 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process swapper (pid: 0, ti=dec1c000 task=c09c0f20 task.ti=c0992000) Stack: 00000000 00000000 00000002 c0ba27c0 00100000 01000000 de3a0798 c0ba27c0 00000033 dec1de98 c0786848 00000000 de3a0780 dec1dea4 c0786868 00000000 dec1debc c074ee56 e1da6b8c de3a0780 c074ed44 de3a07a8 dec1decc c074ef32 Call Trace: [<c0786848>] xfrm4_rcv_encap+0x22/0x27 [<c0786868>] xfrm4_rcv+0x1b/0x1d [<c074ee56>] ip_local_deliver_finish+0x112/0x1b1 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074ef77>] ip_local_deliver+0x3e/0x44 [<c074ed44>] ? ip_local_deliver_finish+0x0/0x1b1 [<c074ec03>] ip_rcv_finish+0x30a/0x332 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c074ef32>] NF_HOOK.clone.1+0x3d/0x44 [<c074f188>] ip_rcv+0x20b/0x247 [<c074e8f9>] ? ip_rcv_finish+0x0/0x332 [<c072797d>] __netif_receive_skb+0x373/0x399 [<c0727bc1>] netif_receive_skb+0x4b/0x51 [<e0817e2a>] cp_rx_poll+0x210/0x2c4 [8139cp] [<c072818f>] net_rx_action+0x9a/0x17d [<c0445b5c>] __do_softirq+0xa1/0x149 [<c0445abb>] ? __do_softirq+0x0/0x149 Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-22 09:08:28 +08:00
EXPORT_SYMBOL(__xfrm_init_state);
int xfrm_init_state(struct xfrm_state *x)
{
return __xfrm_init_state(x, true);
}
EXPORT_SYMBOL(xfrm_init_state);
int __net_init xfrm_state_init(struct net *net)
{
unsigned int sz;
INIT_LIST_HEAD(&net->xfrm.state_all);
sz = sizeof(struct hlist_head) * 8;
net->xfrm.state_bydst = xfrm_hash_alloc(sz);
if (!net->xfrm.state_bydst)
goto out_bydst;
net->xfrm.state_bysrc = xfrm_hash_alloc(sz);
if (!net->xfrm.state_bysrc)
goto out_bysrc;
net->xfrm.state_byspi = xfrm_hash_alloc(sz);
if (!net->xfrm.state_byspi)
goto out_byspi;
net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1);
net->xfrm.state_num = 0;
INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
spin_lock_init(&net->xfrm.xfrm_state_lock);
return 0;
out_byspi:
xfrm_hash_free(net->xfrm.state_bysrc, sz);
out_bysrc:
xfrm_hash_free(net->xfrm.state_bydst, sz);
out_bydst:
return -ENOMEM;
}
void xfrm_state_fini(struct net *net)
{
unsigned int sz;
flush_work(&net->xfrm.state_hash_work);
xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
flush_work(&net->xfrm.state_gc_work);
WARN_ON(!list_empty(&net->xfrm.state_all));
sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
WARN_ON(!hlist_empty(net->xfrm.state_byspi));
xfrm_hash_free(net->xfrm.state_byspi, sz);
WARN_ON(!hlist_empty(net->xfrm.state_bysrc));
xfrm_hash_free(net->xfrm.state_bysrc, sz);
WARN_ON(!hlist_empty(net->xfrm.state_bydst));
xfrm_hash_free(net->xfrm.state_bydst, sz);
}
#ifdef CONFIG_AUDITSYSCALL
static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
struct audit_buffer *audit_buf)
{
struct xfrm_sec_ctx *ctx = x->security;
u32 spi = ntohl(x->id.spi);
if (ctx)
audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
switch (x->props.family) {
case AF_INET:
audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
&x->props.saddr.a4, &x->id.daddr.a4);
break;
case AF_INET6:
audit_log_format(audit_buf, " src=%pI6 dst=%pI6",
x->props.saddr.a6, x->id.daddr.a6);
break;
}
audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi);
}
static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
struct audit_buffer *audit_buf)
{
const struct iphdr *iph4;
const struct ipv6hdr *iph6;
switch (family) {
case AF_INET:
iph4 = ip_hdr(skb);
audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
&iph4->saddr, &iph4->daddr);
break;
case AF_INET6:
iph6 = ipv6_hdr(skb);
audit_log_format(audit_buf,
" src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
&iph6->saddr, &iph6->daddr,
iph6->flow_lbl[0] & 0x0f,
iph6->flow_lbl[1],
iph6->flow_lbl[2]);
break;
}
}
void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid)
{
struct audit_buffer *audit_buf;
audit_buf = xfrm_audit_start("SAD-add");
if (audit_buf == NULL)
return;
xfrm_audit_helper_usrinfo(task_valid, audit_buf);
xfrm_audit_helper_sainfo(x, audit_buf);
audit_log_format(audit_buf, " res=%u", result);
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid)
{
struct audit_buffer *audit_buf;
audit_buf = xfrm_audit_start("SAD-delete");
if (audit_buf == NULL)
return;
xfrm_audit_helper_usrinfo(task_valid, audit_buf);
xfrm_audit_helper_sainfo(x, audit_buf);
audit_log_format(audit_buf, " res=%u", result);
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_delete);
void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
struct sk_buff *skb)
{
struct audit_buffer *audit_buf;
u32 spi;
audit_buf = xfrm_audit_start("SA-replay-overflow");
if (audit_buf == NULL)
return;
xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
/* don't record the sequence number because it's inherent in this kind
* of audit message */
spi = ntohl(x->id.spi);
audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi);
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow);
void xfrm_audit_state_replay(struct xfrm_state *x,
struct sk_buff *skb, __be32 net_seq)
{
struct audit_buffer *audit_buf;
u32 spi;
audit_buf = xfrm_audit_start("SA-replayed-pkt");
if (audit_buf == NULL)
return;
xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
spi = ntohl(x->id.spi);
audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
spi, spi, ntohl(net_seq));
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_replay);
void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family)
{
struct audit_buffer *audit_buf;
audit_buf = xfrm_audit_start("SA-notfound");
if (audit_buf == NULL)
return;
xfrm_audit_helper_pktinfo(skb, family, audit_buf);
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple);
void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family,
__be32 net_spi, __be32 net_seq)
{
struct audit_buffer *audit_buf;
u32 spi;
audit_buf = xfrm_audit_start("SA-notfound");
if (audit_buf == NULL)
return;
xfrm_audit_helper_pktinfo(skb, family, audit_buf);
spi = ntohl(net_spi);
audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
spi, spi, ntohl(net_seq));
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound);
void xfrm_audit_state_icvfail(struct xfrm_state *x,
struct sk_buff *skb, u8 proto)
{
struct audit_buffer *audit_buf;
__be32 net_spi;
__be32 net_seq;
audit_buf = xfrm_audit_start("SA-icv-failure");
if (audit_buf == NULL)
return;
xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf);
if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) {
u32 spi = ntohl(net_spi);
audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u",
spi, spi, ntohl(net_seq));
}
audit_log_end(audit_buf);
}
EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail);
#endif /* CONFIG_AUDITSYSCALL */