IB/mlx4: Synchronize cleanup of MCGs in MCG paravirtualization

A client re-register event invokes cleanup of all MCGs.  This is
required to protect against misbehaved guests leading to corruption of
join/leave database.  However, since cleaning up the MCGs is a heavy
operation, it is pushed to a work queue for further processing.
Client re-register is also propagated to ULPs (e.g IPoIB).

However, since the cleanup is performed in a workqueue, the ULP could
leave and re-join groups before the cleanup occurs.  In this case,
when the cleanup takes place, it prunes the (newly-joined) MCGs and
the ULP is left without actual MCGs while believing it joined them.

Fix this by setting the flushing flag before invoking the cleanup task
and clearing it after flushing is complete.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/infiniband/hw/mlx4/mcg.c

@@ -1075,10 +1075,6 @@ static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy
 	unsigned long end;
 	int count;
 
-	if (ctx->flushing)
-		return;
-
-	ctx->flushing = 1;
 	for (i = 0; i < MAX_VFS; ++i)
 		clean_vf_mcast(ctx, i);
 
@@ -1108,9 +1104,6 @@ static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy
 		force_clean_group(group);
 	}
 	mutex_unlock(&ctx->mcg_table_lock);
-
-	if (!destroy_wq)
-		ctx->flushing = 0;
 }
 
 struct clean_work {
@@ -1124,6 +1117,7 @@ static void mcg_clean_task(struct work_struct *work)
 	struct clean_work *cw = container_of(work, struct clean_work, work);
 
 	_mlx4_ib_mcg_port_cleanup(cw->ctx, cw->destroy_wq);
+	cw->ctx->flushing = 0;
 	kfree(cw);
 }
 
@@ -1131,13 +1125,20 @@ void mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy_wq)
 {
 	struct clean_work *work;
 
+	if (ctx->flushing)
+		return;
+
+	ctx->flushing = 1;
+
 	if (destroy_wq) {
 		_mlx4_ib_mcg_port_cleanup(ctx, destroy_wq);
+		ctx->flushing = 0;
 		return;
 	}
 
 	work = kmalloc(sizeof *work, GFP_KERNEL);
 	if (!work) {
+		ctx->flushing = 0;
 		mcg_warn("failed allocating work for cleanup\n");
 		return;
 	}