On Fri, Sep 24, 2021 at 09:09:55PM +0800, Shiyang Ruan wrote:
> When memory-failure occurs, we call this function which is implemented
> by each kind of devices.  For the fsdax case, pmem device driver
> implements it.  Pmem device driver will find out the filesystem in which
> the corrupted page located in.
> 
> With dax_holder notify support, we are able to notify the memory failure
> from pmem driver to upper layers.  If there is something not support in
> the notify routine, memory_failure will fall back to the generic hanlder.
> 
> Signed-off-by: Shiyang Ruan <ruansy.f...@fujitsu.com>
> ---
>  drivers/nvdimm/pmem.c    | 11 +++++++++++
>  include/linux/memremap.h |  9 +++++++++
>  mm/memory-failure.c      | 14 ++++++++++++++
>  3 files changed, 34 insertions(+)
> 
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 72de88ff0d30..0dfafad8fcc5 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -362,9 +362,20 @@ static void pmem_release_disk(void *__pmem)
>       del_gendisk(pmem->disk);
>  }
>  
> +static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
> +             unsigned long pfn, size_t size, int flags)
> +{
> +     struct pmem_device *pmem =
> +                     container_of(pgmap, struct pmem_device, pgmap);
> +     loff_t offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset;
> +
> +     return dax_holder_notify_failure(pmem->dax_dev, offset, size, flags);
> +}
> +
>  static const struct dev_pagemap_ops fsdax_pagemap_ops = {
>       .kill                   = pmem_pagemap_kill,
>       .cleanup                = pmem_pagemap_cleanup,
> +     .memory_failure         = pmem_pagemap_memory_failure,
>  };
>  
>  static int pmem_attach_disk(struct device *dev,
> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
> index c0e9d35889e8..36d47bacd46d 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -87,6 +87,15 @@ struct dev_pagemap_ops {
>        * the page back to a CPU accessible page.
>        */
>       vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf);
> +
> +     /*
> +      * Handle the memory failure happens on a range of pfns.  Notify the
> +      * processes who are using these pfns, and try to recover the data on
> +      * them if necessary.  The flag is finally passed to the recover
> +      * function through the whole notify routine.
> +      */
> +     int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
> +                           size_t size, int flags);
>  };
>  
>  #define PGMAP_ALTMAP_VALID   (1 << 0)
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 8ff9b52823c0..85eab206b68f 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1605,6 +1605,20 @@ static int memory_failure_dev_pagemap(unsigned long 
> pfn, int flags,
>       if (!pgmap_pfn_valid(pgmap, pfn))
>               goto out;
>  
> +     /*
> +      * Call driver's implementation to handle the memory failure, otherwise
> +      * fall back to generic handler.
> +      */
> +     if (pgmap->ops->memory_failure) {
> +             rc = pgmap->ops->memory_failure(pgmap, pfn, PAGE_SIZE, flags);
> +             /*
> +              * Fall back to generic handler too if operation is not
> +              * supported inside the driver/device/filesystem.
> +              */
> +             if (rc != EOPNOTSUPP)

-EOPNOTSUPP?  (negative errno)

--D

> +                     goto out;
> +     }
> +
>       rc = mf_generic_kill_procs(pfn, flags, pgmap);
>  out:
>       /* drop pgmap ref acquired in caller */
> -- 
> 2.33.0
> 
> 
> 

Reply via email to