On 2022/4/19 12:50, 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.fnst@xxxxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
> ---
> drivers/nvdimm/pmem.c | 17 +++++++++++++++++
> include/linux/memremap.h | 12 ++++++++++++
> mm/memory-failure.c | 14 ++++++++++++++
> 3 files changed, 43 insertions(+)
>
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 58d95242a836..bd502957cfdf 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -366,6 +366,21 @@ static void pmem_release_disk(void *__pmem)
> blk_cleanup_disk(pmem->disk);
> }
>
> +static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
> + unsigned long pfn, unsigned long nr_pages, int mf_flags)
> +{
> + struct pmem_device *pmem =
> + container_of(pgmap, struct pmem_device, pgmap);
> + u64 offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset;
> + u64 len = nr_pages << PAGE_SHIFT;
> +
> + return dax_holder_notify_failure(pmem->dax_dev, offset, len, mf_flags);
> +}
> +
> +static const struct dev_pagemap_ops fsdax_pagemap_ops = {
> + .memory_failure = pmem_pagemap_memory_failure,
> +};
> +
> static int pmem_attach_disk(struct device *dev,
> struct nd_namespace_common *ndns)
> {
> @@ -427,6 +442,7 @@ static int pmem_attach_disk(struct device *dev,
> pmem->pfn_flags = PFN_DEV;
> if (is_nd_pfn(dev)) {
> pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
> + pmem->pgmap.ops = &fsdax_pagemap_ops;
> addr = devm_memremap_pages(dev, &pmem->pgmap);
> pfn_sb = nd_pfn->pfn_sb;
> pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
> @@ -440,6 +456,7 @@ static int pmem_attach_disk(struct device *dev,
> pmem->pgmap.range.end = res->end;
> pmem->pgmap.nr_range = 1;
> pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
> + pmem->pgmap.ops = &fsdax_pagemap_ops;
> addr = devm_memremap_pages(dev, &pmem->pgmap);
> pmem->pfn_flags |= PFN_MAP;
> bb_range = pmem->pgmap.range;
> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
> index ad6062d736cd..bcfb6bf4ce5a 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -79,6 +79,18 @@ 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 mf_flags is finally passed to the recover
> + * function through the whole notify routine.
> + *
> + * When this is not implemented, or it returns -EOPNOTSUPP, the caller
> + * will fall back to a common handler called mf_generic_kill_procs().
> + */
> + int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
> + unsigned long nr_pages, int mf_flags);
> };
>
> #define PGMAP_ALTMAP_VALID (1 << 0)
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 7c8c047bfdc8..a40e79e634a4 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1741,6 +1741,20 @@ 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, 1, flags);
> + /*
> + * Fall back to generic handler too if operation is not
> + * supported inside the driver/device/filesystem.
> + */
> + if (rc != -EOPNOTSUPP)
> + goto out;
> + }
> +
Thanks for your patch. There are two questions:
1.Is dax_lock_page + dax_unlock_page pair needed here?
2.hwpoison_filter and SetPageHWPoison will be handled by the callback or they're just ignored deliberately?
Thanks!
> rc = mf_generic_kill_procs(pfn, flags, pgmap);
> out:
> /* drop pgmap ref acquired in caller */
>
