From 34dc45be4563f344d59ba0428416d0d265aa4f4d Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 25 Feb 2021 17:17:08 -0800
Subject: [PATCH] mm: fix memory_failure() handling of dax-namespace metadata
Git-commit: 34dc45be4563f344d59ba0428416d0d265aa4f4d
Patch-mainline: v5.12-rc1
References: bsc#1185335

Given 'struct dev_pagemap' spans both data pages and metadata pages be
careful to consult the altmap if present to delineate metadata.  In fact
the pfn_first() helper already identifies the first valid data pfn, so
export that helper for other code paths via pgmap_pfn_valid().

Other usage of get_dev_pagemap() are not a concern because those are
operating on known data pfns having been looked up by get_user_pages().
I.e.  metadata pfns are never user mapped.

Link: https://lkml.kernel.org/r/161058501758.1840162.4239831989762604527.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 6100e34b2526 ("mm, memory_failure: Teach memory_failure() about dev_pagemap pages")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Jan Kara <jack@suse.cz>

---
 include/linux/memremap.h |    6 ++++++
 kernel/memremap.c        |    9 +++++++++
 mm/memory-failure.c      |    6 ++++++
 3 files changed, 21 insertions(+)

--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -135,6 +135,7 @@ void *devm_memremap_pages(struct device
 void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap);
+bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
@@ -162,6 +163,11 @@ static inline struct dev_pagemap *get_de
 	return NULL;
 }
 
+static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
+{
+	return false;
+}
+
 static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
 	return 0;
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -269,6 +269,15 @@ static unsigned long pfn_first(struct de
 	return pfn;
 }
 
+bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
+{
+	const struct resource *res = &pgmap->res;
+
+	if (pfn >= PHYS_PFN(res->start) && pfn <= PHYS_PFN(res->end))
+		return pfn >= pfn_first(pgmap);
+	return false;
+}
+
 static unsigned long pfn_end(struct dev_pagemap *pgmap)
 {
 	const struct resource *res = &pgmap->res;
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1177,6 +1177,12 @@ static int memory_failure_dev_pagemap(un
 		 */
 		put_page(page);
 
+	/* device metadata space is not recoverable */
+	if (!pgmap_pfn_valid(pgmap, pfn)) {
+		rc = -ENXIO;
+		goto out;
+	}
+
 	/*
 	 * Prevent the inode from being freed while we are interrogating
 	 * the address_space, typically this would be handled by