Re: [PATCH v2] pNFS: deadlock in pnfs_send_layoutreturn

[Trond Myklebust]

On Wed, 2026-04-22 at 10:46 +0000, Ben Roberts wrote:
> Hi Ben,
> 
> > The kzalloc failure is definitely a rarely-used/tested path, so its
> > possible
> > there's an issue there no one has seen yet, but from what I can see
> > it looks
> > like every call to pnfs_send_layoutreturn() first calls
> > pnfs_prepare_layoutreturn(), which already clears
> > NFS_LAYOUT_RETURN_REQUESTED. I don't see how you can end up with
> > another
> > proccess seeing the flag.
> 

I had first applied this patch, however when looking more closely, it
seems that it will also be defeated by the by the loop in
pnfs_clear_layoutreturn_info() that checks if there are any layouts
that need returning, and resets NFS_LAYOUT_RETURN_REQUESTED.

> Understood, thank you for the feedback here. I withdraw the patch
> request and
> will take this back to the drawing board. Likely removing the patch
> from local
> systems and looking to capture more useful diagnostics if/when the
> problem
> reoccurs. 
> 
> > There's at least one body of work in this area that your systems
> > don't yet have:
> > https://lore.kernel.org/linux-nfs/20240613050055.854323-1-trond.myklebust@xxxxxxxxxxxxxxx/
> 
> For what it's worth, I checked this patch set and the changes are
> almost
> completely present in the EL source. Patch 2 is only partially
> applied. 
> 
> Ben Roberts