mm: memory-hotplug: enable memory hotplug to handle hugepage

Until now we can't offline memory blocks which contain hugepages because a
hugepage is considered as an unmovable page.  But now with this patch
series, a hugepage has become movable, so by using hugepage migration we
can offline such memory blocks.

What's different from other users of hugepage migration is that we need to
decompose all the hugepages inside the target memory block into free buddy
pages after hugepage migration, because otherwise free hugepages remaining
in the memory block intervene the memory offlining.  For this reason we
introduce new functions dissolve_free_huge_page() and
dissolve_free_huge_pages().

Other than that, what this patch does is straightforwardly to add hugepage
migration code, that is, adding hugepage code to the functions which scan
over pfn and collect hugepages to be migrated, and adding a hugepage
allocation function to alloc_migrate_target().

As for larger hugepages (1GB for x86_64), it's not easy to do hotremove
over them because it's larger than memory block.  So we now simply leave
it to fail as it is.

[yongjun_wei@trendmicro.com.cn: remove duplicated include]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 35 insertions, 7 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index d595606728f9..0eb1a1df649d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -30,6 +30,7 @@
 #include <linux/mm_inline.h>
 #include <linux/firmware-map.h>
 #include <linux/stop_machine.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 
@@ -1230,10 +1231,12 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /*
- * Scanning pfn is much easier than scanning lru list.
- * Scan pfn from start to end and Find LRU page.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
+ * and hugepages). We scan pfn because it's much easier than scanning over
+ * linked list. This function returns the pfn of the first found movable
+ * page if it's found, otherwise 0.
  */
-static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
+static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 {
         unsigned long pfn;
         struct page *page;
@@ -1242,6 +1245,13 @@ static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
                         page = pfn_to_page(pfn);
                         if (PageLRU(page))
                                 return pfn;
+                        if (PageHuge(page)) {
+                                if (is_hugepage_active(page))
+                                        return pfn;
+                                else
+                                        pfn = round_up(pfn + 1,
+                                                1 << compound_order(page)) - 1;
+                        }
                 }
         }
         return 0;
@@ -1262,6 +1272,19 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                 if (!pfn_valid(pfn))
                         continue;
                 page = pfn_to_page(pfn);
+
+                if (PageHuge(page)) {
+                        struct page *head = compound_head(page);
+                        pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
+                        if (compound_order(head) > PFN_SECTION_SHIFT) {
+                                ret = -EBUSY;
+                                break;
+                        }
+                        if (isolate_huge_page(page, &source))
+                                move_pages -= 1 << compound_order(head);
+                        continue;
+                }
+
                 if (!get_page_unless_zero(page))
                         continue;
                 /*
@@ -1294,7 +1317,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
         }
         if (!list_empty(&source)) {
                 if (not_managed) {
-                        putback_lru_pages(&source);
+                        putback_movable_pages(&source);
                         goto out;
                 }
 
@@ -1305,7 +1328,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                 ret = migrate_pages(&source, alloc_migrate_target, 0,
                                         MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
                 if (ret)
-                        putback_lru_pages(&source);
+                        putback_movable_pages(&source);
         }
 out:
         return ret;
@@ -1548,8 +1571,8 @@ repeat:
                 drain_all_pages();
         }
 
-        pfn = scan_lru_pages(start_pfn, end_pfn);
-        if (pfn) { /* We have page on LRU */
+        pfn = scan_movable_pages(start_pfn, end_pfn);
+        if (pfn) { /* We have movable pages */
                 ret = do_migrate_range(pfn, end_pfn);
                 if (!ret) {
                         drain = 1;
@@ -1568,6 +1591,11 @@ repeat:
         yield();
         /* drain pcp pages, this is synchronous. */
         drain_all_pages();
+        /*
+         * dissolve free hugepages in the memory block before doing offlining
+         * actually in order to make hugetlbfs's object counting consistent.
+         */
+        dissolve_free_huge_pages(start_pfn, end_pfn);
         /* check again */
         offlined_pages = check_pages_isolated(start_pfn, end_pfn);
         if (offlined_pages < 0) {