mm: Add notifier in pageblock isolation for balloon drivers

Memory balloon drivers can allocate a large amount of memory which is not
movable but could be freed to accomodate memory hotplug remove.

Prior to calling the memory hotplug notifier chain the memory in the
pageblock is isolated.  Currently, if the migrate type is not
MIGRATE_MOVABLE the isolation will not proceed, causing the memory removal
for that page range to fail.

Rather than failing pageblock isolation if the migrateteype is not
MIGRATE_MOVABLE, this patch checks if all of the pages in the pageblock,
and not on the LRU, are owned by a registered balloon driver (or other
entity) using a notifier chain.  If all of the non-movable pages are owned
by a balloon, they can be freed later through the memory notifier chain
and the range can still be isolated in set_migratetype_isolate().

Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Brian King <brking@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Gerald Schaefer <geralds@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 50 insertions, 7 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 74af449b1f1d..998eacc1e4c3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
+#include <linux/memory.h>
 #include <trace/events/kmem.h>
 
 #include <asm/tlbflush.h>
@@ -5008,23 +5009,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 int set_migratetype_isolate(struct page *page)
 {
         struct zone *zone;
-        unsigned long flags;
+        struct page *curr_page;
+        unsigned long flags, pfn, iter;
+        unsigned long immobile = 0;
+        struct memory_isolate_notify arg;
+        int notifier_ret;
         int ret = -EBUSY;
         int zone_idx;
 
         zone = page_zone(page);
         zone_idx = zone_idx(zone);
+
         spin_lock_irqsave(&zone->lock, flags);
+        if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
+            zone_idx == ZONE_MOVABLE) {
+                ret = 0;
+                goto out;
+        }
+
+        pfn = page_to_pfn(page);
+        arg.start_pfn = pfn;
+        arg.nr_pages = pageblock_nr_pages;
+        arg.pages_found = 0;
+
         /*
-         * In future, more migrate types will be able to be isolation target.
+         * It may be possible to isolate a pageblock even if the
+         * migratetype is not MIGRATE_MOVABLE. The memory isolation
+         * notifier chain is used by balloon drivers to return the
+         * number of pages in a range that are held by the balloon
+         * driver to shrink memory. If all the pages are accounted for
+         * by balloons, are free, or on the LRU, isolation can continue.
+         * Later, for example, when memory hotplug notifier runs, these
+         * pages reported as "can be isolated" should be isolated(freed)
+         * by the balloon driver through the memory notifier chain.
          */
-        if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE &&
-            zone_idx != ZONE_MOVABLE)
+        notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+        notifier_ret = notifier_to_errno(notifier_ret);
+        if (notifier_ret || !arg.pages_found)
                 goto out;
-        set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-        move_freepages_block(zone, page, MIGRATE_ISOLATE);
-        ret = 0;
+
+        for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
+                if (!pfn_valid_within(pfn))
+                        continue;
+
+                curr_page = pfn_to_page(iter);
+                if (!page_count(curr_page) || PageLRU(curr_page))
+                        continue;
+
+                immobile++;
+        }
+
+        if (arg.pages_found == immobile)
+                ret = 0;
+
 out:
+        if (!ret) {
+                set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+                move_freepages_block(zone, page, MIGRATE_ISOLATE);
+        }
+
         spin_unlock_irqrestore(&zone->lock, flags);
         if (!ret)
                 drain_all_pages();