Commit 2d070eab authored by Michal Hocko's avatar Michal Hocko Committed by Linus Torvalds
Browse files

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: default avatarMichal Hocko <mhocko@suse.com>
Acked-by: default avatarVlastimil 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 8b0662f2

include/linux/memory_hotplug.h

+22 −0
Original line number Original line Diff line number Diff line
@@ -14,6 +14,20 @@ struct memory_block; 
struct resource;

struct resource;





#ifdef CONFIG_MEMORY_HOTPLUG

#ifdef CONFIG_MEMORY_HOTPLUG

/*

 * Return page for the valid pfn only if the page is online. All pfn

 * walkers which rely on the fully initialized page->flags and others

 * should use this rather than pfn_valid && pfn_to_page

 */

#define pfn_to_online_page(pfn)				\

({							\

	struct page *___page = NULL;			\

	unsigned long ___nr = pfn_to_section_nr(pfn);	\

							\

	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\

		___page = pfn_to_page(pfn);		\

	___page;					\

})





/*

/*

 * Types for free bootmem stored in page->lru.next. These have to be in

 * Types for free bootmem stored in page->lru.next. These have to be in
@@ -203,6 +217,14 @@ extern void set_zone_contiguous(struct zone *zone); 
extern void clear_zone_contiguous(struct zone *zone);

extern void clear_zone_contiguous(struct zone *zone);





#else /* ! CONFIG_MEMORY_HOTPLUG */

#else /* ! CONFIG_MEMORY_HOTPLUG */

#define pfn_to_online_page(pfn)			\

({						\

	struct page *___page = NULL;		\

	if (pfn_valid(pfn))			\

		___page = pfn_to_page(pfn);	\

	___page;				\

 })



/*

/*

 * Stub functions for when hotplug is off

 * Stub functions for when hotplug is off

 */

 */

include/linux/mmzone.h

+29 −6
Original line number Original line Diff line number Diff line
@@ -1144,9 +1144,10 @@ extern unsigned long usemap_size(void); 
 */

 */

#define	SECTION_MARKED_PRESENT	(1UL<<0)

#define	SECTION_MARKED_PRESENT	(1UL<<0)

#define SECTION_HAS_MEM_MAP	(1UL<<1)

#define SECTION_HAS_MEM_MAP	(1UL<<1)

#define SECTION_MAP_LAST_BIT	(1UL<<2)

#define SECTION_IS_ONLINE	(1UL<<2)

#define SECTION_MAP_LAST_BIT	(1UL<<3)

#define SECTION_MAP_MASK	(~(SECTION_MAP_LAST_BIT-1))

#define SECTION_MAP_MASK	(~(SECTION_MAP_LAST_BIT-1))

#define SECTION_NID_SHIFT	2

#define SECTION_NID_SHIFT	3





static inline struct page *__section_mem_map_addr(struct mem_section *section)

static inline struct page *__section_mem_map_addr(struct mem_section *section)

{

{
@@ -1175,6 +1176,23 @@ static inline int valid_section_nr(unsigned long nr) 
	return valid_section(__nr_to_section(nr));

	return valid_section(__nr_to_section(nr));

}

}





static inline int online_section(struct mem_section *section)

{

	return (section && (section->section_mem_map & SECTION_IS_ONLINE));

}



static inline int online_section_nr(unsigned long nr)

{

	return online_section(__nr_to_section(nr));

}



#ifdef CONFIG_MEMORY_HOTPLUG

void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);

#ifdef CONFIG_MEMORY_HOTREMOVE

void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);

#endif

#endif



static inline struct mem_section *__pfn_to_section(unsigned long pfn)

static inline struct mem_section *__pfn_to_section(unsigned long pfn)

{

{

	return __nr_to_section(pfn_to_section_nr(pfn));

	return __nr_to_section(pfn_to_section_nr(pfn));
@@ -1253,10 +1271,15 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); 
#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL

#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL

/*

/*

 * pfn_valid() is meant to be able to tell if a given PFN has valid memmap

 * pfn_valid() is meant to be able to tell if a given PFN has valid memmap

 * associated with it or not. In FLATMEM, it is expected that holes always

 * associated with it or not. This means that a struct page exists for this

 * have valid memmap as long as there is valid PFNs either side of the hole.

 * pfn. The caller cannot assume the page is fully initialized in general.

 * In SPARSEMEM, it is assumed that a valid section has a memmap for the

 * Hotplugable pages might not have been onlined yet. pfn_to_online_page()

 * entire section.

 * will ensure the struct page is fully online and initialized. Special pages

 * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly.

 *

 * In FLATMEM, it is expected that holes always have valid memmap as long as

 * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed

 * that a valid section has a memmap for the entire section.

 *

 *

 * However, an ARM, and maybe other embedded architectures in the future

 * However, an ARM, and maybe other embedded architectures in the future

 * free memmap backing holes to save memory on the assumption the memmap is

 * free memmap backing holes to save memory on the assumption the memmap is

mm/memory_hotplug.c

+4 −0
Original line number Original line Diff line number Diff line
@@ -929,12 +929,16 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, 
	unsigned long i;

	unsigned long i;

	unsigned long onlined_pages = *(unsigned long *)arg;

	unsigned long onlined_pages = *(unsigned long *)arg;

	struct page *page;

	struct page *page;



	if (PageReserved(pfn_to_page(start_pfn)))

	if (PageReserved(pfn_to_page(start_pfn)))

		for (i = 0; i < nr_pages; i++) {

		for (i = 0; i < nr_pages; i++) {

			page = pfn_to_page(start_pfn + i);

			page = pfn_to_page(start_pfn + i);

			(*online_page_callback)(page);

			(*online_page_callback)(page);

			onlined_pages++;

			onlined_pages++;

		}

		}



	online_mem_sections(start_pfn, start_pfn + nr_pages);



	*(unsigned long *)arg = onlined_pages;

	*(unsigned long *)arg = onlined_pages;

	return 0;

	return 0;

}

}

mm/page_alloc.c

+4 −1
Original line number Original line Diff line number Diff line
@@ -1365,7 +1365,9 @@ struct page *__pageblock_pfn_to_page(unsigned long start_pfn, 
	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))

	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))

		return NULL;

		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)

	if (page_zone(start_page) != zone)

		return NULL;

		return NULL;
@@ -7656,6 +7658,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) 
			break;

			break;

	if (pfn == end_pfn)

	if (pfn == end_pfn)

		return;

		return;

	offline_mem_sections(pfn, end_pfn);

	zone = page_zone(pfn_to_page(pfn));

	zone = page_zone(pfn_to_page(pfn));

	spin_lock_irqsave(&zone->lock, flags);

	spin_lock_irqsave(&zone->lock, flags);

	pfn = start_pfn;

	pfn = start_pfn;

mm/sparse.c

+44 −1
Original line number Original line Diff line number Diff line
@@ -222,7 +222,8 @@ void __init memory_present(int nid, unsigned long start, unsigned long end) 




		ms = __nr_to_section(section);

		ms = __nr_to_section(section);

		if (!ms->section_mem_map) {

		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);

			section_mark_present(ms);

		}

		}

	}

	}
@@ -622,6 +623,48 @@ void __init sparse_init(void) 
}

}





#ifdef CONFIG_MEMORY_HOTPLUG

#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

#ifdef CONFIG_SPARSEMEM_VMEMMAP

static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)

static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)

{

{

CRA Git | Maintained and supported by SUSTech CRA and CCSE