summaryrefslogtreecommitdiff
path: root/include/linux/mmzone.h
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2017-07-07 01:37:56 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-07 02:24:32 +0300
commit2d070eab2e8270c8a84d480bb91e4f739315f03d (patch)
tree18c8db141506d2a6a505eda7c45ec5dc032aa034 /include/linux/mmzone.h
parent8b0662f245a328df8873be949b0087760420f40c (diff)
downloadlinux-2d070eab2e8270c8a84d480bb91e4f739315f03d.tar.xz
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>
Diffstat (limited to 'include/linux/mmzone.h')
-rw-r--r--include/linux/mmzone.h35
1 files changed, 29 insertions, 6 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 976a1202bec1..2aaf7e08c5a8 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1144,9 +1144,10 @@ extern unsigned long usemap_size(void);
*/
#define SECTION_MARKED_PRESENT (1UL<<0)
#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_NID_SHIFT 2
+#define SECTION_NID_SHIFT 3
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));
}
+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)
{
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
/*
* 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
- * 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.
+ * associated with it or not. This means that a struct page exists for this
+ * pfn. The caller cannot assume the page is fully initialized in general.
+ * Hotplugable pages might not have been onlined yet. pfn_to_online_page()
+ * 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
* free memmap backing holes to save memory on the assumption the memmap is