Ocfs2 devel - Dec 2014 - [patch 04/15] ocfs2: avoid access invalid address when read o2dlm debug messages

From: jiangyiwen <jiangyiwen at huawei.com>
Subject: ocfs2: avoid access invalid address when read o2dlm debug messages

The following case will lead to a lockres is freed but is still in use.

cat /sys/kernel/debug/o2dlm/locking_state	dlm_thread
lockres_seq_start
    -> lock dlm->track_lock
    -> get resA
                                                resA->refs decrease to 0,
                                                call dlm_lockres_release,
                                                and wait for "cat"
unlock.
Although resA->refs is already set to 0,
increase resA->refs, and then unlock
                                                lock dlm->track_lock
                                                    -> list_del_init()
                                                    -> unlock
                                                    -> free resA

In such a race case, invalid address access may occurs.  So we should
delete list res->tracking before resA->refs decrease to 0.


Signed-off-by: jiangyiwen <jiangyiwen at huawei.com>
Cc: Joel Becker <jlbec at evilplan.org>
Cc: Mark Fasheh <mfasheh at suse.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
---

 fs/ocfs2/dlm/dlmmaster.c |   10 ----------
 fs/ocfs2/dlm/dlmthread.c |   10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

diff -puN
fs/ocfs2/dlm/dlmmaster.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
fs/ocfs2/dlm/dlmmaster.c
---
a/fs/ocfs2/dlm/dlmmaster.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
+++ a/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct k
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
diff -puN
fs/ocfs2/dlm/dlmthread.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
fs/ocfs2/dlm/dlmthread.c
---
a/fs/ocfs2/dlm/dlmthread.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
+++ a/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
_

On Mon, Dec 15, 2014 at 02:51:00PM -0800, Andrew Morton
wrote:
> In such a race case, invalid address access may occurs.  So we should
> delete list res->tracking before resA->refs decrease to 0.
> 
> diff -puN
fs/ocfs2/dlm/dlmmaster.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
fs/ocfs2/dlm/dlmmaster.c
> ---
a/fs/ocfs2/dlm/dlmmaster.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
> +++ a/fs/ocfs2/dlm/dlmmaster.c
> @@ -498,16 +498,6 @@ static void dlm_lockres_release(struct k
>  	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
>  	     res->lockname.name);
>  
> -	spin_lock(&dlm->track_lock);
> -	if (!list_empty(&res->tracking))
> -		list_del_init(&res->tracking);
> -	else {
> -		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
> -		     res->lockname.len, res->lockname.name);
> -		dlm_print_one_lock_resource(res);
> -	}
> -	spin_unlock(&dlm->track_lock);
> -
>  	atomic_dec(&dlm->res_cur_count);
>  
>  	if (!hlist_unhashed(&res->hash_node) ||
> diff -puN
fs/ocfs2/dlm/dlmthread.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
fs/ocfs2/dlm/dlmthread.c
> ---
a/fs/ocfs2/dlm/dlmthread.c~ocfs2-avoid-access-invalid-address-when-read-o2dlm-debug-messages
> +++ a/fs/ocfs2/dlm/dlmthread.c
> @@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm
>  
>  	__dlm_unhash_lockres(dlm, res);
>  
> +	spin_lock(&dlm->track_lock);
> +	if (!list_empty(&res->tracking))
> +		list_del_init(&res->tracking);
> +	else {
> +		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
> +				res->lockname.len, res->lockname.name);
> +		__dlm_print_one_lock_resource(res);
> +	}
> +	spin_unlock(&dlm->track_lock);
> +
>  	/* lockres is not in the hash now.  drop the flag and wake up
>  	 * any processes waiting in dlm_get_lock_resource. */
>  	if (!master) {
> _
How do we know that dlm_purge_lockres() is the last caller of
dlm_lockres_put()? Don't we now have a problem where if the last ref is
dropped by any other function than dlm_purge_lockres() the lockres is freed
while on the tracking list?
	--Mark

--
Mark Fasheh