From bcc9b67a5b65ec2e1ec5371226a729ec1b380860 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Thu, 7 Feb 2013 20:47:51 +0000 Subject: [PATCH] IB/qib: Fix QP locate/remove race remove_qp() can execute concurrently with a qib_lookup_qpn() on another CPU, which in of itself, is ok, given the RCU locking. The issue is that remove_qp() NULLs out the qp->next field so that a qib_lookup_qpn() might fail to find a qp if it occurs after the one that is being deleted. This is a momentary issue and subsequent qib_lookup_qpn() calls would find the qp's since the search restarts from the bucket head. At scale, the issue might causes dropped packets and unnecessary retransmissions. The fix just deletes the qp->next NULL assignment to prevent the remove_qp() from hiding qp's from qib_lookup_qpn(). Reviewed-by: Dean Luick Signed-off-by: Mike Marciniszyn Signed-off-by: Roland Dreier --- drivers/infiniband/hw/qib/qib_qp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 35275099cafd..a6a2cc2ba260 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -268,8 +268,9 @@ static void remove_qp(struct qib_ibdev *dev, struct qib_qp *qp) qpp = &q->next) if (q == qp) { atomic_dec(&qp->refcount); - *qpp = qp->next; - rcu_assign_pointer(qp->next, NULL); + rcu_assign_pointer(*qpp, + rcu_dereference_protected(qp->next, + lockdep_is_held(&dev->qpt_lock))); break; } } -- 2.39.5