[PATCH v3 5/6] mm: Fix memory_failure() handling of dax-namespace metadata

From: Dan Williams <dan.j.williams@intel.com>
To: linux-mm@kvack.org
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@redhat.com>,
	vishal.l.verma@intel.com, linux-nvdimm@lists.01.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v3 5/6] mm: Fix memory_failure() handling of dax-namespace metadata
Date: Tue, 12 Jan 2021 23:35:44 -0800	[thread overview]
Message-ID: <161052334425.1805594.17861842381807251887.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <161052331545.1805594.2356512831689786960.stgit@dwillia2-desk3.amr.corp.intel.com>

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 looking up by get_user_pages().
I.e. metadata pfns are never user mapped.

Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reported-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/memremap.h |    6 ++++++
 mm/memory-failure.c      |    6 ++++++
 mm/memremap.c            |   15 +++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 79c49e7f5c30..f5b464daeeca 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -137,6 +137,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
 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);
@@ -165,6 +166,11 @@ static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	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;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 78b173c7190c..541569cb4a99 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1308,6 +1308,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		 */
 		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
diff --git a/mm/memremap.c b/mm/memremap.c
index 16b2fb482da1..2455bac89506 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -80,6 +80,21 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
 	return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
+bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
+{
+	int i;
+
+	for (i = 0; i < pgmap->nr_range; i++) {
+		struct range *range = &pgmap->ranges[i];
+
+		if (pfn >= PHYS_PFN(range->start) &&
+		    pfn <= PHYS_PFN(range->end))
+			return pfn >= pfn_first(pgmap, i);
+	}
+
+	return false;
+}
+
 static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
 {
 	const struct range *range = &pgmap->ranges[range_id];

