Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Maor Gottlieb <maorg@nvidia.com>
To: Chuck Lever III <chuck.lever@oracle.com>,
	linux-rdma <linux-rdma@vger.kernel.org>
Subject: Re: f0ae4afe3d35 ("RDMA/mlx5: Fix releasing unallocated memory in dereg MR flow")
Date: Sun, 19 Dec 2021 11:51:02 +0200	[thread overview]
Message-ID: <3fa317ce-e0cf-cfce-c4f2-8940ba546b61@nvidia.com> (raw)
In-Reply-To: <EEBA2D1C-F29C-4237-901C-587B60CEE113@oracle.com>


On 12/18/2021 11:25 PM, Chuck Lever III wrote:
> NFS/RDMA with an NFS client using mlx5-based hardware triggers a
> system deadlock (no error messages) on the client. I bisected to
> f0ae4afe3d35 ("RDMA/mlx5: Fix releasing unallocated memory in
> dereg MR flow").
>
> --
> Chuck Lever

Hi Chuck,

I found some bug in the cited commit. Can you please test if the below 
patch fixes this deadlock ?

diff --git a/drivers/infiniband/hw/mlx5/mr.c 
b/drivers/infiniband/hw/mlx5/mr.c
index 157d862fb864..3cb4e34fe199 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1978,7 +1978,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct 
ib_udata *udata)
                         return rc;
         }

-   if (mr->umem) {
+ if (udata && mr->umem) {
                 bool is_odp = is_odp_mr(mr);

                 if (!is_odp)

>
>
>

  parent reply	other threads:[~2021-12-19  9:51 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-18 21:25 f0ae4afe3d35 ("RDMA/mlx5: Fix releasing unallocated memory in dereg MR flow") Chuck Lever III
2021-12-19  8:57 ` Leon Romanovsky
2021-12-19  9:51 ` Maor Gottlieb [this message]
2021-12-19 18:19   ` Chuck Lever III

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3fa317ce-e0cf-cfce-c4f2-8940ba546b61@nvidia.com \
    --to=maorg@nvidia.com \
    --cc=chuck.lever@oracle.com \
    --cc=linux-rdma@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox