| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20080905115506.GA26179@gondor.apana.org.au>
Date: Fri, 5 Sep 2008 21:55:07 +1000
From: Herbert Xu <herbert@...dor.apana.org.au>
To: David Miller <davem@...emloft.net>
Cc: timo.teras@....fi, netdev@...r.kernel.org
Subject: Re: xfrm_state locking regression...
On Tue, Sep 02, 2008 at 11:47:23PM -0700, David Miller wrote:
>
> Get creative, use a key of some sort to continue the walk, that's what
> other netlink'ish subsystems use.
OK let's see if this is creative enough :)
The next step after this patch is to kill x->all altogether and
go back to the old walking method (plus the saved state).
ipsec: Use RCU-like construct for saved state within a walk
Now that we save states within a walk we need synchronisation
so that the list the saved state is on doesn't disappear from
under us.
As it stands this is done by keeping the state on the list which
is bad because it gets in the way of the management of the state
life-cycle.
An alternative is to make our own pseudo-RCU system where we use
counters to indicate which state can't be freed immediately as
it may be referenced by an ongoing walk when that resumes.
Signed-off-by: Herbert Xu <herbert@...dor.apana.org.au>
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2933d74..4bb9499 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -120,9 +120,11 @@ extern struct mutex xfrm_cfg_mutex;
/* Full description of state of transformer. */
struct xfrm_state
{
- /* Note: bydst is re-used during gc */
struct list_head all;
- struct hlist_node bydst;
+ union {
+ struct list_head gclist;
+ struct hlist_node bydst;
+ };
struct hlist_node bysrc;
struct hlist_node byspi;
@@ -1286,16 +1288,9 @@ static inline void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
walk->count = 0;
}
-static inline void xfrm_state_walk_done(struct xfrm_state_walk *walk)
-{
- if (walk->state != NULL) {
- xfrm_state_put(walk->state);
- walk->state = NULL;
- }
-}
-
extern int xfrm_state_walk(struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*), void *);
+extern void xfrm_state_walk_done(struct xfrm_state_walk *walk);
extern struct xfrm_state *xfrm_state_alloc(void);
extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
struct flowi *fl, struct xfrm_tmpl *tmpl,
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 7bd62f6..ec9d1e5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -59,6 +59,11 @@ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static unsigned int xfrm_state_num;
static unsigned int xfrm_state_genid;
+/* Counter indicating ongoing walk, protected by xfrm_state_lock. */
+static unsigned long xfrm_state_walk_ongoing;
+/* Counter indicating walk completion, protected by xfrm_cfg_mutex. */
+static unsigned long xfrm_state_walk_completed;
+
static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
@@ -191,7 +196,7 @@ static DEFINE_RWLOCK(xfrm_state_afinfo_lock);
static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO];
static struct work_struct xfrm_state_gc_work;
-static HLIST_HEAD(xfrm_state_gc_list);
+static LIST_HEAD(xfrm_state_gc_list);
static DEFINE_SPINLOCK(xfrm_state_gc_lock);
int __xfrm_state_delete(struct xfrm_state *x);
@@ -403,17 +408,23 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x)
static void xfrm_state_gc_task(struct work_struct *data)
{
- struct xfrm_state *x;
- struct hlist_node *entry, *tmp;
- struct hlist_head gc_list;
+ struct xfrm_state *x, *tmp;
+ static LIST_HEAD(gc_list);
+ unsigned long completed;
spin_lock_bh(&xfrm_state_gc_lock);
- gc_list.first = xfrm_state_gc_list.first;
- INIT_HLIST_HEAD(&xfrm_state_gc_list);
+ list_splice_tail_init(&xfrm_state_gc_list, &gc_list);
spin_unlock_bh(&xfrm_state_gc_lock);
- hlist_for_each_entry_safe(x, entry, tmp, &gc_list, bydst)
+ mutex_lock(&xfrm_cfg_mutex);
+ completed = xfrm_state_walk_completed;
+ mutex_unlock(&xfrm_cfg_mutex);
+
+ list_for_each_entry_safe(x, tmp, &gc_list, gclist) {
+ if ((long)(x->lastused - completed) > 0)
+ break;
xfrm_state_gc_destroy(x);
+ }
wake_up(&km_waitq);
}
@@ -540,12 +551,8 @@ void __xfrm_state_destroy(struct xfrm_state *x)
{
WARN_ON(x->km.state != XFRM_STATE_DEAD);
- spin_lock_bh(&xfrm_state_lock);
- list_del(&x->all);
- spin_unlock_bh(&xfrm_state_lock);
-
spin_lock_bh(&xfrm_state_gc_lock);
- hlist_add_head(&x->bydst, &xfrm_state_gc_list);
+ list_add_tail(&x->gclist, &xfrm_state_gc_list);
spin_unlock_bh(&xfrm_state_gc_lock);
schedule_work(&xfrm_state_gc_work);
}
@@ -558,6 +565,8 @@ int __xfrm_state_delete(struct xfrm_state *x)
if (x->km.state != XFRM_STATE_DEAD) {
x->km.state = XFRM_STATE_DEAD;
spin_lock(&xfrm_state_lock);
+ x->lastused = xfrm_state_walk_ongoing;
+ list_del_rcu(&x->all);
hlist_del(&x->bydst);
hlist_del(&x->bysrc);
if (x->id.spi)
@@ -1572,6 +1581,7 @@ int xfrm_state_walk(struct xfrm_state_walk *walk,
if (err) {
xfrm_state_hold(last);
walk->state = last;
+ xfrm_state_walk_ongoing++;
goto out;
}
}
@@ -1586,12 +1596,26 @@ int xfrm_state_walk(struct xfrm_state_walk *walk,
err = func(last, 0, data);
out:
spin_unlock_bh(&xfrm_state_lock);
- if (old != NULL)
+ if (old != NULL) {
xfrm_state_put(old);
+ xfrm_state_walk_completed++;
+ schedule_work(&xfrm_state_gc_work);
+ }
return err;
}
EXPORT_SYMBOL(xfrm_state_walk);
+void xfrm_state_walk_done(struct xfrm_state_walk *walk)
+{
+ if (walk->state != NULL) {
+ xfrm_state_put(walk->state);
+ walk->state = NULL;
+ xfrm_state_walk_completed++;
+ schedule_work(&xfrm_state_gc_work);
+ }
+}
+EXPORT_SYMBOL(xfrm_state_walk_done);
+
void xfrm_replay_notify(struct xfrm_state *x, int event)
{
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@...dor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists