3.16.62-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
commit bc52e9ca74b9a395897bb640c6671b2cbf716032 upstream.
__flush_qp() has a race condition where during the flush operation,
the qp lock is released allowing another thread to possibly post a WR,
which corrupts the queue state, possibly causing crashes. The lock was
released to preserve the cq/qp locking hierarchy of cq first, then qp.
However releasing the qp lock is not necessary; both RQ and SQ CQ locks
can be acquired first, followed by the qp lock, and then the RQ and SQ
flushing can be done w/o unlocking.
Signed-off-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Doug Ledford <dledford@xxxxxxxxxx>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
drivers/infiniband/hw/cxgb4/qp.c | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1071,31 +1071,34 @@ static void __flush_qp(struct c4iw_qp *q
PDBG("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp);
- /* locking hierarchy: cq lock first, then qp lock. */
+ /* locking hierarchy: cqs lock first, then qp lock. */
spin_lock_irqsave(&rchp->lock, flag);
+ if (schp != rchp)
+ spin_lock(&schp->lock);
spin_lock(&qhp->lock);
if (qhp->wq.flushed) {
spin_unlock(&qhp->lock);
+ if (schp != rchp)
+ spin_unlock(&schp->lock);
spin_unlock_irqrestore(&rchp->lock, flag);
return;
}
qhp->wq.flushed = 1;
+ t4_set_wq_in_error(&qhp->wq);
c4iw_flush_hw_cq(rchp, qhp);
c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
rq_flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
- spin_unlock(&qhp->lock);
- spin_unlock_irqrestore(&rchp->lock, flag);
- /* locking hierarchy: cq lock first, then qp lock. */
- spin_lock_irqsave(&schp->lock, flag);
- spin_lock(&qhp->lock);
if (schp != rchp)
c4iw_flush_hw_cq(schp, qhp);
sq_flushed = c4iw_flush_sq(qhp);
+
spin_unlock(&qhp->lock);
- spin_unlock_irqrestore(&schp->lock, flag);
+ if (schp != rchp)
+ spin_unlock(&schp->lock);
+ spin_unlock_irqrestore(&rchp->lock, flag);
if (schp == rchp) {
if (t4_clear_cq_armed(&rchp->cq) &&
@@ -1129,8 +1132,8 @@ static void flush_qp(struct c4iw_qp *qhp
rchp = to_c4iw_cq(qhp->ibqp.recv_cq);
schp = to_c4iw_cq(qhp->ibqp.send_cq);
- t4_set_wq_in_error(&qhp->wq);
if (qhp->ibqp.uobject) {
+ t4_set_wq_in_error(&qhp->wq);
t4_set_cq_in_error(&rchp->cq);
spin_lock_irqsave(&rchp->comp_handler_lock, flag);
(*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context);
