Re: [PATCH v2] pNFS: deadlock in pnfs_send_layoutreturn

[Benjamin Coddington]

Hi Ben,

Did you reproduce and diagnose this problem on a recent upstream kernel
version?  If not, you probably want to report the issue to your Red Hat
support channel directly instead of sending fixes upstream because the
maintainers will want to see patches and fixes against the upstream code.
The code in 5.14.0-611.9.1.el9 may have different behaviors.

Ben

On 8 Apr 2026, at 8:25, Ben Roberts wrote:

> On a HPC cluster running 5.14.0-611.9.1.el9.x86_64, regular deadlocks were
> seen within pnfs_send_layoutreturn leading to userspace processes stuck in
> uninterruptible sleep, ultimately requiring reboots to clear. This was
> occurring frequently, sometimes multiple times per day on specific hosts
> with heavy load.  Claude code was tasked with hunting down any potential
> deadlocks within pnfs_send_layoutreturn, and identified the following
> condition. This patch has been running in production on top of the EL9
> kernel for over three months without any reoccurrence of the deadlock.
>
> The pnfs_send_layoutreturn() function can deadlock when memory
> allocation fails. The issue occurs in the error path where
> pnfs_put_layout_hdr() is called, which may trigger
> pnfs_layoutreturn_before_put_layout_hdr(), potentially causing
> a recursive call back to pnfs_send_layoutreturn().
>
> Call chain that triggers the deadlock:
> 1. pnfs_send_layoutreturn() - kzalloc() fails
> 2. Error path calls pnfs_put_layout_hdr(lo)
> 3. pnfs_put_layout_hdr() calls pnfs_layoutreturn_before_put_layout_hdr()
> 4. If NFS_LAYOUT_RETURN_REQUESTED is still set, attempts another
>    layoutreturn, creating recursion/deadlock
>
> The fix ensures that NFS_LAYOUT_RETURN_REQUESTED is cleared in the
> allocation failure path before calling pnfs_put_layout_hdr(). This
> prevents pnfs_layoutreturn_before_put_layout_hdr() from attempting
> another layout return, breaking the recursion cycle.
>
> v2 fixes a syntax error introduced while composing the original mail.
>
> Signed-off-by: Ben Roberts <ben.roberts@xxxxxxxxxxxxxx>
> Assisted-by: Claude:claude-sonnet-4-5
> ---
>  fs/nfs/pnfs.c | 1 +
>  1 file changed, 1 insertion(+)
>
> diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
> index bc13d1e69449..47bda53b2b3a 100644
> --- a/fs/nfs/pnfs.c
> +++ b/fs/nfs/pnfs.c
> @@ -1361,6 +1361,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo,
>  	if (unlikely(lrp == NULL)) {
>  		status = -ENOMEM;
>  		spin_lock(&ino->i_lock);
> +		pnfs_clear_layoutreturn_info(lo);
>  		pnfs_clear_layoutreturn_waitbit(lo);
>  		spin_unlock(&ino->i_lock);
>  		put_cred(cred);
> --
> 2.43.0
>
> For details of how GSA uses your personal information, please see our Privacy Notice here: https://www.gsacapital.com/privacy-notice
>
> This email and any files transmitted with it contain confidential and proprietary information and is solely for the use of the intended recipient.
> If you are not the intended recipient please return the email to the sender and delete it from your computer and you must not use, disclose, distribute, copy, print or rely on this email or its contents.
> This communication is for informational purposes only.
> It is not intended as an offer or solicitation for the purchase or sale of any financial instrument or as an official confirmation of any transaction.
> Any comments or statements made herein do not necessarily reflect those of GSA Capital.
> GSA Capital Partners LLP is authorised and regulated by the Financial Conduct Authority and is registered in England and Wales at Stratton House, 5 Stratton Street, London W1J 8LA, number OC309261.
> GSA Capital Services Limited is registered in England and Wales at the same address, number 5320529.