[PATCH] IB/hfi1: Close PSM sdma_progress sleep window

[Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx>]

commit da9de5f8527f4b9efc82f967d29a583318c034c7 upstream.

The call to sdma_progress() is called outside the wait lock.

In this case, there is a race condition where sdma_progress() can return
false and the sdma_engine can idle.  If that happens, there will be no
more sdma interrupts to cause the wakeup and the user_sdma xmit will hang.

Fix by moving the lock to enclose the sdma_progress() call.

Also, delete busycount. The need for this was removed by:
commit bcad29137a97 ("IB/hfi1: Serve the most starved iowait entry first")

Ported to linux-4.9.y.

Cc: <stable@xxxxxxxxxxxxxxx>
Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Reviewed-by: Gary Leshner <Gary.S.Leshner@xxxxxxxxx>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
---
 drivers/infiniband/hw/hfi1/user_sdma.c |   13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 4c11116..098296a 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -260,7 +260,6 @@ struct user_sdma_txreq {
 	struct list_head list;
 	struct user_sdma_request *req;
 	u16 flags;
-	unsigned busycount;
 	u64 seqnum;
 };
 
@@ -323,25 +322,22 @@ static int defer_packet_queue(
 	struct hfi1_user_sdma_pkt_q *pq =
 		container_of(wait, struct hfi1_user_sdma_pkt_q, busy);
 	struct hfi1_ibdev *dev = &pq->dd->verbs_dev;
-	struct user_sdma_txreq *tx =
-		container_of(txreq, struct user_sdma_txreq, txreq);
 
-	if (sdma_progress(sde, seq, txreq)) {
-		if (tx->busycount++ < MAX_DEFER_RETRY_COUNT)
-			goto eagain;
-	}
+	write_seqlock(&dev->iowait_lock);
+	if (sdma_progress(sde, seq, txreq))
+		goto eagain;
 	/*
 	 * We are assuming that if the list is enqueued somewhere, it
 	 * is to the dmawait list since that is the only place where
 	 * it is supposed to be enqueued.
 	 */
 	xchg(&pq->state, SDMA_PKT_Q_DEFERRED);
-	write_seqlock(&dev->iowait_lock);
 	if (list_empty(&pq->busy.list))
 		list_add_tail(&pq->busy.list, &sde->dmawait);
 	write_sequnlock(&dev->iowait_lock);
 	return -EBUSY;
 eagain:
+	write_sequnlock(&dev->iowait_lock);
 	return -EAGAIN;
 }
 
@@ -925,7 +921,6 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 
 		tx->flags = 0;
 		tx->req = req;
-		tx->busycount = 0;
 		INIT_LIST_HEAD(&tx->list);
 
 		if (req->seqnum == req->info.npkts - 1)