diff mbox

[3/8] RDMAVT: Fix synchronization around percpu_ref

Message ID 20180314194515.1661824-3-tj@kernel.org (mailing list archive)
State Accepted
Delegated to: Jason Gunthorpe
Headers show

Commit Message

Tejun Heo March 14, 2018, 7:45 p.m. UTC 
rvt_mregion uses percpu_ref for reference counting and RCU to protect
accesses from lkey_table.  When a rvt_mregion needs to be freed, it
first gets unregistered from lkey_table and then rvt_check_refs() is
called to wait for in-flight usages before the rvt_mregion is freed.

rvt_check_refs() seems to have a couple issues.

* It has a fast exit path which tests percpu_ref_is_zero().  However,
  a percpu_ref reading zero doesn't mean that the object can be
  released.  In fact, the ->release() callback might not even have
  started executing yet.  Proceeding with freeing can lead to
  use-after-free.

* lkey_table is RCU protected but there is no RCU grace period in the
  free path.  percpu_ref uses RCU internally but it's sched-RCU whose
  grace periods are different from regular RCU.  Also, it generally
  isn't a good idea to depend on internal behaviors like this.

To address the above issues, this patch removes the fast exit and adds
an explicit synchronize_rcu().

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: linux-rdma@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/infiniband/sw/rdmavt/mr.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

Comments

Jason Gunthorpe March 15, 2018, 10:24 p.m. UTC | #1 
On Wed, Mar 14, 2018 at 12:45:10PM -0700, Tejun Heo wrote:
> rvt_mregion uses percpu_ref for reference counting and RCU to protect
> accesses from lkey_table.  When a rvt_mregion needs to be freed, it
> first gets unregistered from lkey_table and then rvt_check_refs() is
> called to wait for in-flight usages before the rvt_mregion is freed.
> 
> rvt_check_refs() seems to have a couple issues.
> 
> * It has a fast exit path which tests percpu_ref_is_zero().  However,
>   a percpu_ref reading zero doesn't mean that the object can be
>   released.  In fact, the ->release() callback might not even have
>   started executing yet.  Proceeding with freeing can lead to
>   use-after-free.
> 
> * lkey_table is RCU protected but there is no RCU grace period in the
>   free path.  percpu_ref uses RCU internally but it's sched-RCU whose
>   grace periods are different from regular RCU.  Also, it generally
>   isn't a good idea to depend on internal behaviors like this.
> 
> To address the above issues, this patch removes the fast exit and adds
> an explicit synchronize_rcu().
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
> Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
> Cc: linux-rdma@vger.kernel.org
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
>  drivers/infiniband/sw/rdmavt/mr.c | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)

Applied to rdma for-next

Thanks,
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 1b2e536..cc429b5 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -489,11 +489,13 @@  static int rvt_check_refs(struct rvt_mregion *mr, const char *t)
 	unsigned long timeout;
 	struct rvt_dev_info *rdi = ib_to_rvt(mr->pd->device);
 
-	if (percpu_ref_is_zero(&mr->refcount))
-		return 0;
-	/* avoid dma mr */
-	if (mr->lkey)
+	if (mr->lkey) {
+		/* avoid dma mr */
 		rvt_dereg_clean_qps(mr);
+		/* @mr was indexed on rcu protected @lkey_table */
+		synchronize_rcu();
+	}
+
 	timeout = wait_for_completion_timeout(&mr->comp, 5 * HZ);
 	if (!timeout) {
 		rvt_pr_err(rdi,