IB/ehca: Fix sync between completion handler and destroy cq

This patch fixes two issues reported by Roland Dreier and Christoph Hellwig:

- Mismatched sync/locking between completion handler and destroy cq We
  introduced a counter nr_events per cq to track number of irq events
  seen. This counter is incremented when an event queue entry is seen
  and decremented after completion handler has been called regardless
  if scaling code is active or not. Note that nr_callbacks tracks
  number of events assigned to a cpu and both counters can potentially
  diverge.

  The sync between running completion handler and destroy cq is done
  by using the global spin lock ehca_cq_idr_lock.

- Replace yield by wait_event on the counter above to become zero.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h
index 40404c9..82ded44 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -52,6 +52,8 @@ struct ehca_mw;
 struct ehca_pd;
 struct ehca_av;
 
+#include <linux/wait.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
 
@@ -153,7 +155,9 @@ struct ehca_cq {
 	spinlock_t cb_lock;
 	struct hlist_head qp_hashtab[QP_HASHTAB_LEN];
 	struct list_head entry;
-	u32 nr_callbacks;
+	u32 nr_callbacks; /* #events assigned to cpu by scaling code */
+	u32 nr_events;    /* #events seen */
+	wait_queue_head_t wait_completion;
 	spinlock_t task_lock;
 	u32 ownpid;
 	/* mmap counter for resources mapped into user space */