From mboxrd@z Thu Jan  1 00:00:00 1970
From: swise@opengridcomputing.com (Steve Wise)
Date: Tue, 20 Sep 2016 15:14:15 -0500
Subject: [PATCH] nvme-rdma: Fix early queue flags settings
In-Reply-To: <20160920200803.GA839@lst.de>
References: <1474397848-19013-1-git-send-email-sagi@grimberg.me>
 <20160920200803.GA839@lst.de>
Message-ID: <013901d2137b$8f329e10$ad97da30$@opengridcomputing.com>

> 
> On Tue, Sep 20, 2016@11:57:28AM -0700, Sagi Grimberg wrote:
> > When we reconnect we can't really clear the
> > queue flags (DELETING flag in specific) because
> > we might end up trigerring a use-after-free condition
> > if we fail to establish the rdma connection.
> 
> Can you add a comment explaining this to the assignment?  Looking
> at the patch it looks like black magic to be, and that's even
> after reading the above changelog..

Maybe this changelog?

    nvme-rdma: only clear queue flags after successful connect

    Otherwise, nvme_rdma_stop_and_clear_queue() will incorrectly
    try to stop/free rdma qps/cm_ids that are already freed.