Re: [PATCH V3 18/21] famfs_fuse: Add holder_operations for dax notify_failure()

[Jonathan Cameron <jonathan.cameron@huawei.com>]

On Wed,  7 Jan 2026 09:33:27 -0600
John Groves <John@Groves.net> wrote:

> Memory errors are at least somewhat more likely on disaggregated memory
> than on-board memory. This commit registers to be notified by fsdev_dax
> in the event that a memory failure is detected.
> 
> When a file access resolves to a daxdev with memory errors, it will fail
> with an appropriate error.
> 
> If a daxdev failed fs_dax_get(), we set dd->dax_err. If a daxdev called
> our notify_failure(), set dd->error. When any of the above happens, set
> (file)->error and stop allowing access.
> 
> In general, the recovery from memory errors is to unmount the file
> system and re-initialize the memory, but there may be usable degraded
> modes of operation - particularly in the future when famfs supports
> file systems backed by more than one daxdev. In those cases,
> accessing data that is on a working daxdev can still work.
> 
> For now, return errors for any file that has encountered a memory or dax
> error.
> 
> Signed-off-by: John Groves <john@groves.net>
> ---
>  fs/fuse/famfs.c       | 115 +++++++++++++++++++++++++++++++++++++++---
>  fs/fuse/famfs_kfmap.h |   3 +-
>  2 files changed, 109 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
> index c02b14789c6e..4eb87c5c628e 100644
> --- a/fs/fuse/famfs.c
> +++ b/fs/fuse/famfs.c

> @@ -254,6 +288,38 @@ famfs_update_daxdev_table(
>  	return 0;
>  }
>  
> +static void
> +famfs_set_daxdev_err(
> +	struct fuse_conn *fc,
> +	struct dax_device *dax_devp)
> +{
> +	int i;
> +
> +	/* Gotta search the list by dax_devp;
> +	 * read lock because we're not adding or removing daxdev entries
> +	 */
> +	down_read(&fc->famfs_devlist_sem);

Use a guard()

> +	for (i = 0; i < fc->dax_devlist->nslots; i++) {
> +		if (fc->dax_devlist->devlist[i].valid) {
> +			struct famfs_daxdev *dd = &fc->dax_devlist->devlist[i];
> +
> +			if (dd->devp != dax_devp)
> +				continue;
> +
> +			dd->error = true;
> +			up_read(&fc->famfs_devlist_sem);
> +
> +			pr_err("%s: memory error on daxdev %s (%d)\n",
> +			       __func__, dd->name, i);
> +			goto done;
> +		}
> +	}
> +	up_read(&fc->famfs_devlist_sem);
> +	pr_err("%s: memory err on unrecognized daxdev\n", __func__);
> +
> +done:

If this isn't getting more interesting, just return above.

> +}
> +
>  /***************************************************************************/
>  
>  void
> @@ -611,6 +677,26 @@ famfs_file_init_dax(
>  
>  static ssize_t famfs_file_bad(struct inode *inode);
>  
> +static int famfs_dax_err(struct famfs_daxdev *dd)

I'd introduce this earlier in the series to reduce need
to refactor below.

> +{
> +	if (!dd->valid) {
> +		pr_err("%s: daxdev=%s invalid\n",
> +		       __func__, dd->name);
> +		return -EIO;
> +	}
> +	if (dd->dax_err) {
> +		pr_err("%s: daxdev=%s dax_err\n",
> +		       __func__, dd->name);
> +		return -EIO;
> +	}
> +	if (dd->error) {
> +		pr_err("%s: daxdev=%s memory error\n",
> +		       __func__, dd->name);
> +		return -EHWPOISON;
> +	}
> +	return 0;
> +}

...

> @@ -966,7 +1064,8 @@ famfs_file_bad(struct inode *inode)
>  		return -EIO;
>  	}
>  	if (meta->error) {
> -		pr_debug("%s: previously detected metadata errors\n", __func__);
> +		pr_debug("%s: previously detected metadata errors\n",
> +			 __func__);

Spurious change.

>  		return -EIO;
>  	}