[PATCH for-rc v1] RDMA/rxe: Avoid CQ polling hang triggered by CQ resize

[Daisuke Matsuda <dskmtsd@xxxxxxxxx>]

When running the test_resize_cq testcase from rdma-core, polling a
completion queue from userspace may occasionally hang and eventually fail
with a timeout:
=====
ERROR: test_resize_cq (tests.test_cq.CQTest.test_resize_cq)
Test resize CQ, start with specific value and then increase and decrease
----------------------------------------------------------------------
Traceback (most recent call last):
    File "/root/deb/rdma-core/tests/test_cq.py", line 135, in test_resize_cq
      u.poll_cq(self.client.cq)
    File "/root/deb/rdma-core/tests/utils.py", line 687, in poll_cq
      wcs = _poll_cq(cq, count, data)
            ^^^^^^^^^^^^^^^^^^^^^^^^^
    File "/root/deb/rdma-core/tests/utils.py", line 669, in _poll_cq
      raise PyverbsError(f'Got timeout on polling ({count} CQEs remaining)')
pyverbs.pyverbs_error.PyverbsError: Got timeout on polling (1 CQEs
remaining)
=====

The issue is caused when rxe_cq_post() fails to post a CQE due to the queue
being temporarily full, and the CQE is effectively lost. To mitigate this,
add a bounded busy-wait with fallback rescheduling so that CQE does not get
lost.

Signed-off-by: Daisuke Matsuda <dskmtsd@xxxxxxxxx>
---
 drivers/infiniband/sw/rxe/rxe_cq.c | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index fffd144d509e..7b0fba63204e 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -84,14 +84,36 @@ int rxe_cq_resize_queue(struct rxe_cq *cq, int cqe,
 /* caller holds reference to cq */
 int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 {
+	unsigned long flags;
+	u32 spin_cnt = 3000;
 	struct ib_event ev;
-	int full;
 	void *addr;
-	unsigned long flags;
+	int full;
 
 	spin_lock_irqsave(&cq->cq_lock, flags);
 
 	full = queue_full(cq->queue, QUEUE_TYPE_TO_CLIENT);
+	if (likely(!full))
+		goto post_queue;
+
+	/* constant backoff until queue is ready */
+	while (spin_cnt--) {
+		full = queue_full(cq->queue, QUEUE_TYPE_TO_CLIENT);
+		if (!full)
+			goto post_queue;
+
+		cpu_relax();
+	}
+
+	/* try giving up cpu and retry */
+	if (full) {
+		spin_unlock_irqrestore(&cq->cq_lock, flags);
+		cond_resched();
+		spin_lock_irqsave(&cq->cq_lock, flags);
+
+		full = queue_full(cq->queue, QUEUE_TYPE_TO_CLIENT);
+	}
+
 	if (unlikely(full)) {
 		rxe_err_cq(cq, "queue full\n");
 		spin_unlock_irqrestore(&cq->cq_lock, flags);
@@ -105,6 +127,7 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 		return -EBUSY;
 	}
 
+ post_queue:
 	addr = queue_producer_addr(cq->queue, QUEUE_TYPE_TO_CLIENT);
 	memcpy(addr, cqe, sizeof(*cqe));
 
-- 
2.43.0