pagemap,pmem: introduce ->memory_failure()

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.

Link: https://lkml.kernel.org/r/20220603053738.1218681-4-ruansy.fnst@fujitsu.com
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Williams <dan.j.wiliams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

drivers/nvdimm/pmem.c

@@ -453,6 +453,21 @@ 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)
 {
@@ -514,6 +529,7 @@ 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);
@@ -527,6 +543,7 @@ 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;

include/linux/memremap.h

@@ -87,6 +87,18 @@ 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)

mm/memory-failure.c

@@ -1748,6 +1748,20 @@ 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;
+	}
+
 	rc = mf_generic_kill_procs(pfn, flags, pgmap);
 out:
 	/* drop pgmap ref acquired in caller */