Wengang Wang
2010-Jun-16 06:52 UTC
[Ocfs2-devel] [PATCH] ocfs2/dlm: remove potential deadlock
When we need to take both dlm_domain_lock and dlm->spinlock, we should take
them in order of:
dlm_domain_lock then dlm->spinlock.
There is pathes disobey this order. That is calling dlm_lockres_put with
dlm->
spinlock held. dlm_lockres_put() finally calls dlm_put() which take
dlm_domain_lock.
The fix is moving the locking on dlm_domain_lock to dlm_ctxt_release() from
dlm_put(). dlm_ctxt_release() is only called on the release of the last
reference. Any path should not be holding dlm->spinlock when dropping the
"last"
reference.
Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com>
---
fs/ocfs2/dlm/dlmdomain.c | 12 ++++--------
1 files changed, 4 insertions(+), 8 deletions(-)
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index ab82add..754baf2 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -321,28 +321,24 @@ static void dlm_ctxt_release(struct kref *kref)
dlm = container_of(kref, struct dlm_ctxt, dlm_refs);
+ if (spin_is_locked(&dlm->spinlock))
+ BUG();
BUG_ON(dlm->num_joins);
BUG_ON(dlm->dlm_state == DLM_CTXT_JOINED);
+ spin_lock(&dlm_domain_lock);
/* we may still be in the list if we hit an error during join. */
list_del_init(&dlm->list);
-
spin_unlock(&dlm_domain_lock);
- mlog(0, "freeing memory from domain %s\n", dlm->name);
-
wake_up(&dlm_domain_events);
-
+ mlog(0, "freeing memory from domain %s\n", dlm->name);
dlm_free_ctxt_mem(dlm);
-
- spin_lock(&dlm_domain_lock);
}
void dlm_put(struct dlm_ctxt *dlm)
{
- spin_lock(&dlm_domain_lock);
kref_put(&dlm->dlm_refs, dlm_ctxt_release);
- spin_unlock(&dlm_domain_lock);
}
static void __dlm_get(struct dlm_ctxt *dlm)
--
1.6.6.1
Wengang Wang
2010-Jun-21 05:31 UTC
[Ocfs2-devel] [PATCH] ocfs2/dlm: remove potential deadlock
Why atomic operations on dlm_refs need spinlock's protect?
/* NOTE: Next three are protected by dlm_domain_lock */
struct kref dlm_refs;
enum dlm_ctxt_state dlm_state;
unsigned int num_joins;
regards,
wengang.
On 10-06-16 14:52, Wengang Wang wrote:> When we need to take both dlm_domain_lock and dlm->spinlock, we should
take
> them in order of:
> dlm_domain_lock then dlm->spinlock.
>
> There is pathes disobey this order. That is calling dlm_lockres_put with
dlm->
> spinlock held. dlm_lockres_put() finally calls dlm_put() which take
> dlm_domain_lock.
>
> The fix is moving the locking on dlm_domain_lock to dlm_ctxt_release() from
> dlm_put(). dlm_ctxt_release() is only called on the release of the last
> reference. Any path should not be holding dlm->spinlock when dropping
the "last"
> reference.
>
> Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com>
> ---
> fs/ocfs2/dlm/dlmdomain.c | 12 ++++--------
> 1 files changed, 4 insertions(+), 8 deletions(-)
>
> diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
> index ab82add..754baf2 100644
> --- a/fs/ocfs2/dlm/dlmdomain.c
> +++ b/fs/ocfs2/dlm/dlmdomain.c
> @@ -321,28 +321,24 @@ static void dlm_ctxt_release(struct kref *kref)
>
> dlm = container_of(kref, struct dlm_ctxt, dlm_refs);
>
> + if (spin_is_locked(&dlm->spinlock))
> + BUG();
> BUG_ON(dlm->num_joins);
> BUG_ON(dlm->dlm_state == DLM_CTXT_JOINED);
>
> + spin_lock(&dlm_domain_lock);
> /* we may still be in the list if we hit an error during join. */
> list_del_init(&dlm->list);
> -
> spin_unlock(&dlm_domain_lock);
>
> - mlog(0, "freeing memory from domain %s\n", dlm->name);
> -
> wake_up(&dlm_domain_events);
> -
> + mlog(0, "freeing memory from domain %s\n", dlm->name);
> dlm_free_ctxt_mem(dlm);
> -
> - spin_lock(&dlm_domain_lock);
> }
>
> void dlm_put(struct dlm_ctxt *dlm)
> {
> - spin_lock(&dlm_domain_lock);
> kref_put(&dlm->dlm_refs, dlm_ctxt_release);
> - spin_unlock(&dlm_domain_lock);
> }
>
> static void __dlm_get(struct dlm_ctxt *dlm)
> --
> 1.6.6.1
>
>
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel at oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-devel
Wengang Wang
2010-Jun-21 13:20 UTC
[Ocfs2-devel] [PATCH] ocfs2/dlm: remove potential deadlock
This patch is not good, please ignore it. I will post a revised one. regards, wengang. On 10-06-16 14:52, Wengang Wang wrote:> When we need to take both dlm_domain_lock and dlm->spinlock, we should take > them in order of: > dlm_domain_lock then dlm->spinlock. > > There is pathes disobey this order. That is calling dlm_lockres_put with dlm-> > spinlock held. dlm_lockres_put() finally calls dlm_put() which take > dlm_domain_lock. > > The fix is moving the locking on dlm_domain_lock to dlm_ctxt_release() from > dlm_put(). dlm_ctxt_release() is only called on the release of the last > reference. Any path should not be holding dlm->spinlock when dropping the "last" > reference. > > Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> > --- > fs/ocfs2/dlm/dlmdomain.c | 12 ++++-------- > 1 files changed, 4 insertions(+), 8 deletions(-) > > diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c > index ab82add..754baf2 100644 > --- a/fs/ocfs2/dlm/dlmdomain.c > +++ b/fs/ocfs2/dlm/dlmdomain.c > @@ -321,28 +321,24 @@ static void dlm_ctxt_release(struct kref *kref) > > dlm = container_of(kref, struct dlm_ctxt, dlm_refs); > > + if (spin_is_locked(&dlm->spinlock)) > + BUG(); > BUG_ON(dlm->num_joins); > BUG_ON(dlm->dlm_state == DLM_CTXT_JOINED); > > + spin_lock(&dlm_domain_lock); > /* we may still be in the list if we hit an error during join. */ > list_del_init(&dlm->list); > - > spin_unlock(&dlm_domain_lock); > > - mlog(0, "freeing memory from domain %s\n", dlm->name); > - > wake_up(&dlm_domain_events); > - > + mlog(0, "freeing memory from domain %s\n", dlm->name); > dlm_free_ctxt_mem(dlm); > - > - spin_lock(&dlm_domain_lock); > } > > void dlm_put(struct dlm_ctxt *dlm) > { > - spin_lock(&dlm_domain_lock); > kref_put(&dlm->dlm_refs, dlm_ctxt_release); > - spin_unlock(&dlm_domain_lock); > } > > static void __dlm_get(struct dlm_ctxt *dlm) > -- > 1.6.6.1 > > > _______________________________________________ > Ocfs2-devel mailing list > Ocfs2-devel at oss.oracle.com > http://oss.oracle.com/mailman/listinfo/ocfs2-devel