mm: consider zone which is not fully populated to have holes

__pageblock_pfn_to_page has two users currently, set_zone_contiguous
which checks whether the given zone contains holes and
pageblock_pfn_to_page which then carefully returns a first valid page
from the given pfn range for the given zone.  This doesn't handle zones
which are not fully populated though.  Memory pageblocks can be offlined
or might not have been onlined yet.  In such a case the zone should be
considered to have holes otherwise pfn walkers can touch and play with
offline pages.

Current callers of pageblock_pfn_to_page in compaction seem to work
properly right now because they only isolate PageBuddy
(isolate_freepages_block) or PageLRU resp.  __PageMovable
(isolate_migratepages_block) which will be always false for these pages.
It would be safer to skip these pages altogether, though.

In order to do this patch adds a new memory section state
(SECTION_IS_ONLINE) which is set in memory_present (during boot time) or
in online_pages_range during the memory hotplug.  Similarly
offline_mem_sections clears the bit and it is called when the memory
range is offlined.

pfn_to_online_page helper is then added which check the mem section and
only returns a page if it is onlined already.

Use the new helper in __pageblock_pfn_to_page and skip the whole page
block in such a case.

[mhocko@suse.com: check valid section number in pfn_to_online_page (Vlastimil),
 mark sections online after all struct pages are initialized in
 online_pages_range (Vlastimil)]
  Link: http://lkml.kernel.org/r/20170518164210.GD18333@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170515085827.16474-8-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Daniel Kiper <daniel.kiper@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Reza Arbab <arbab@linux.vnet.ibm.com>
Cc: Tobias Regnery <tobias.regnery@gmail.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 52 insertions, 2 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index caa58338d121..b2ebe9ad7f6c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -929,12 +929,16 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	unsigned long i;
 	unsigned long onlined_pages = *(unsigned long *)arg;
 	struct page *page;
+
 	if (PageReserved(pfn_to_page(start_pfn)))
 		for (i = 0; i < nr_pages; i++) {
 			page = pfn_to_page(start_pfn + i);
 			(*online_page_callback)(page);
 			onlined_pages++;
 		}
+
+	online_mem_sections(start_pfn, start_pfn + nr_pages);
+
 	*(unsigned long *)arg = onlined_pages;
 	return 0;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 73f854344735..387f20db217c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1365,7 +1365,9 @@ struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
 	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
 		return NULL;
 
-	start_page = pfn_to_page(start_pfn);
+	start_page = pfn_to_online_page(start_pfn);
+	if (!start_page)
+		return NULL;
 
 	if (page_zone(start_page) != zone)
 		return NULL;
@@ -7656,6 +7658,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			break;
 	if (pfn == end_pfn)
 		return;
+	offline_mem_sections(pfn, end_pfn);
 	zone = page_zone(pfn_to_page(pfn));
 	spin_lock_irqsave(&zone->lock, flags);
 	pfn = start_pfn;
diff --git a/mm/sparse.c b/mm/sparse.c
index 5032c9a619de..9d7fd666015e 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -222,7 +222,8 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 
 		ms = __nr_to_section(section);
 		if (!ms->section_mem_map) {
-			ms->section_mem_map = sparse_encode_early_nid(nid);
+			ms->section_mem_map = sparse_encode_early_nid(nid) |
+							SECTION_IS_ONLINE;
 			section_mark_present(ms);
 		}
 	}
@@ -622,6 +623,48 @@ void __init sparse_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+
+/* Mark all memory sections within the pfn range as online */
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(start_pfn);
+		struct mem_section *ms;
+
+		/* onlining code should never touch invalid ranges */
+		if (WARN_ON(!valid_section_nr(section_nr)))
+			continue;
+
+		ms = __nr_to_section(section_nr);
+		ms->section_mem_map |= SECTION_IS_ONLINE;
+	}
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/* Mark all memory sections within the pfn range as online */
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(start_pfn);
+		struct mem_section *ms;
+
+		/*
+		 * TODO this needs some double checking. Offlining code makes
+		 * sure to check pfn_valid but those checks might be just bogus
+		 */
+		if (WARN_ON(!valid_section_nr(section_nr)))
+			continue;
+
+		ms = __nr_to_section(section_nr);
+		ms->section_mem_map &= ~SECTION_IS_ONLINE;
+	}
+}
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {