memory unplug: page isolation

Implement generic chunk-of-pages isolation method by using page grouping ops.

This patch add MIGRATE_ISOLATE to MIGRATE_TYPES. By this
 - MIGRATE_TYPES increases.
 - bitmap for migratetype is enlarged.

pages of MIGRATE_ISOLATE migratetype will not be allocated even if it is free.
By this, you can isolated *freed* pages from users. How-to-free pages is not
a purpose of this patch. You may use reclaim and migrate codes to free pages.

If start_isolate_page_range(start,end) is called,
 - migratetype of the range turns to be MIGRATE_ISOLATE  if
   its type is MIGRATE_MOVABLE. (*) this check can be updated if other
   memory reclaiming works make progress.
 - MIGRATE_ISOLATE is not on migratetype fallback list.
 - All free pages and will-be-freed pages are isolated.
To check all pages in the range are isolated or not,  use test_pages_isolated(),
To cancel isolation, use undo_isolate_page_range().

Changes V6 -> V7
 - removed unnecessary #ifdef

There are HOLES_IN_ZONE handling codes...I'm glad if we can remove them..

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 138 insertions, 0 deletions

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
new file mode 100644
index 000000000000..8f92a29695cc
--- /dev/null
+++ b/mm/page_isolation.c
@@ -0,0 +1,138 @@
+/*
+ * linux/mm/page_isolation.c
+ */
+
+#include <stddef.h>
+#include <linux/mm.h>
+#include <linux/page-isolation.h>
+#include <linux/pageblock-flags.h>
+#include "internal.h"
+
+static inline struct page *
+__first_valid_page(unsigned long pfn, unsigned long nr_pages)
+{
+        int i;
+        for (i = 0; i < nr_pages; i++)
+                if (pfn_valid_within(pfn + i))
+                        break;
+        if (unlikely(i == nr_pages))
+                return NULL;
+        return pfn_to_page(pfn + i);
+}
+
+/*
+ * start_isolate_page_range() -- make page-allocation-type of range of pages
+ * to be MIGRATE_ISOLATE.
+ * @start_pfn: The lower PFN of the range to be isolated.
+ * @end_pfn: The upper PFN of the range to be isolated.
+ *
+ * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
+ * the range will never be allocated. Any free pages and pages freed in the
+ * future will not be allocated again.
+ *
+ * start_pfn/end_pfn must be aligned to pageblock_order.
+ * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
+ */
+int
+start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long pfn;
+        unsigned long undo_pfn;
+        struct page *page;
+
+        BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+        BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+
+        for (pfn = start_pfn;
+             pfn < end_pfn;
+             pfn += pageblock_nr_pages) {
+                page = __first_valid_page(pfn, pageblock_nr_pages);
+                if (page && set_migratetype_isolate(page)) {
+                        undo_pfn = pfn;
+                        goto undo;
+                }
+        }
+        return 0;
+undo:
+        for (pfn = start_pfn;
+             pfn <= undo_pfn;
+             pfn += pageblock_nr_pages)
+                unset_migratetype_isolate(pfn_to_page(pfn));
+
+        return -EBUSY;
+}
+
+/*
+ * Make isolated pages available again.
+ */
+int
+undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long pfn;
+        struct page *page;
+        BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+        BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+        for (pfn = start_pfn;
+             pfn < end_pfn;
+             pfn += pageblock_nr_pages) {
+                page = __first_valid_page(pfn, pageblock_nr_pages);
+                if (!page || get_pageblock_flags(page) != MIGRATE_ISOLATE)
+                        continue;
+                unset_migratetype_isolate(page);
+        }
+        return 0;
+}
+/*
+ * Test all pages in the range is free(means isolated) or not.
+ * all pages in [start_pfn...end_pfn) must be in the same zone.
+ * zone->lock must be held before call this.
+ *
+ * Returns 0 if all pages in the range is isolated.
+ */
+static int
+__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
+{
+        struct page *page;
+
+        while (pfn < end_pfn) {
+                if (!pfn_valid_within(pfn)) {
+                        pfn++;
+                        continue;
+                }
+                page = pfn_to_page(pfn);
+                if (PageBuddy(page))
+                        pfn += 1 << page_order(page);
+                else if (page_count(page) == 0 &&
+                                page_private(page) == MIGRATE_ISOLATE)
+                        pfn += 1;
+                else
+                        break;
+        }
+        if (pfn < end_pfn)
+                return 0;
+        return 1;
+}
+
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long pfn;
+        struct page *page;
+
+        pfn = start_pfn;
+        /*
+         * Note: pageblock_nr_page != MAX_ORDER. Then, chunks of free page
+         * is not aligned to pageblock_nr_pages.
+         * Then we just check pagetype fist.
+         */
+        for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+                page = __first_valid_page(pfn, pageblock_nr_pages);
+                if (page && get_pageblock_flags(page) != MIGRATE_ISOLATE)
+                        break;
+        }
+        if (pfn < end_pfn)
+                return -EBUSY;
+        /* Check all pages are free or Marked as ISOLATED */
+        if (__test_page_isolated_in_pageblock(start_pfn, end_pfn))
+                return 0;
+        return -EBUSY;
+}