mm/page_owner: keep track of page owners

This is the page owner tracking code which is introduced so far ago.  It
is resident on Andrew's tree, though, nobody tried to upstream so it
remain as is.  Our company uses this feature actively to debug memory leak
or to find a memory hogger so I decide to upstream this feature.

This functionality help us to know who allocates the page.  When
allocating a page, we store some information about allocation in extra
memory.  Later, if we need to know status of all pages, we can get and
analyze it from this stored information.

In previous version of this feature, extra memory is statically defined in
struct page, but, in this version, extra memory is allocated outside of
struct page.  It enables us to turn on/off this feature at boottime
without considerable memory waste.

Although we already have tracepoint for tracing page allocation/free,
using it to analyze page owner is rather complex.  We need to enlarge the
trace buffer for preventing overlapping until userspace program launched.
And, launched program continually dump out the trace buffer for later
analysis and it would change system behaviour with more possibility rather
than just keeping it in memory, so bad for debug.

Moreover, we can use page_owner feature further for various purposes.  For
example, we can use it for fragmentation statistics implemented in this
patch.  And, I also plan to implement some CMA failure debugging feature
using this interface.

I'd like to give the credit for all developers contributed this feature,
but, it's not easy because I don't know exact history.  Sorry about that.
Below is people who has "Signed-off-by" in the patches in Andrew's tree.

Contributor:
Alexander Nyberg <alexn@dsv.su.se>
Mel Gorman <mgorman@suse.de>
Dave Hansen <dave@linux.vnet.ibm.com>
Minchan Kim <minchan@kernel.org>
Michal Nazarewicz <mina86@mina86.com>
Andrew Morton <akpm@linux-foundation.org>
Jungsoo Son <jungsoo.son@lge.com>

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 101 insertions, 0 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1b12d390dc6..b090e9e3d62 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -22,6 +22,8 @@
 #include <linux/writeback.h>
 #include <linux/compaction.h>
 #include <linux/mm_inline.h>
+#include <linux/page_ext.h>
+#include <linux/page_owner.h>
 
 #include "internal.h"
 
@@ -1017,6 +1019,104 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_OWNER
+static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
+							pg_data_t *pgdat,
+							struct zone *zone)
+{
+	struct page *page;
+	struct page_ext *page_ext;
+	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
+	unsigned long end_pfn = pfn + zone->spanned_pages;
+	unsigned long count[MIGRATE_TYPES] = { 0, };
+	int pageblock_mt, page_mt;
+	int i;
+
+	/* Scan block by block. First and last block may be incomplete */
+	pfn = zone->zone_start_pfn;
+
+	/*
+	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
+	 * a zone boundary, it will be double counted between zones. This does
+	 * not matter as the mixed block count will still be correct
+	 */
+	for (; pfn < end_pfn; ) {
+		if (!pfn_valid(pfn)) {
+			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			continue;
+		}
+
+		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = min(block_end_pfn, end_pfn);
+
+		page = pfn_to_page(pfn);
+		pageblock_mt = get_pfnblock_migratetype(page, pfn);
+
+		for (; pfn < block_end_pfn; pfn++) {
+			if (!pfn_valid_within(pfn))
+				continue;
+
+			page = pfn_to_page(pfn);
+			if (PageBuddy(page)) {
+				pfn += (1UL << page_order(page)) - 1;
+				continue;
+			}
+
+			if (PageReserved(page))
+				continue;
+
+			page_ext = lookup_page_ext(page);
+
+			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
+				continue;
+
+			page_mt = gfpflags_to_migratetype(page_ext->gfp_mask);
+			if (pageblock_mt != page_mt) {
+				if (is_migrate_cma(pageblock_mt))
+					count[MIGRATE_MOVABLE]++;
+				else
+					count[pageblock_mt]++;
+
+				pfn = block_end_pfn;
+				break;
+			}
+			pfn += (1UL << page_ext->order) - 1;
+		}
+	}
+
+	/* Print counts */
+	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+	for (i = 0; i < MIGRATE_TYPES; i++)
+		seq_printf(m, "%12lu ", count[i]);
+	seq_putc(m, '\n');
+}
+#endif /* CONFIG_PAGE_OWNER */
+
+/*
+ * Print out the number of pageblocks for each migratetype that contain pages
+ * of other types. This gives an indication of how well fallbacks are being
+ * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
+ * to determine what is going on
+ */
+static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
+{
+#ifdef CONFIG_PAGE_OWNER
+	int mtype;
+
+	if (!page_owner_inited)
+		return;
+
+	drain_all_pages(NULL);
+
+	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
+	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
+		seq_printf(m, "%12s ", migratetype_names[mtype]);
+	seq_putc(m, '\n');
+
+	walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print);
+#endif /* CONFIG_PAGE_OWNER */
+}
+
 /*
  * This prints out statistics in relation to grouping pages by mobility.
  * It is expensive to collect so do not constantly read the file.
@@ -1034,6 +1134,7 @@ static int pagetypeinfo_show(struct seq_file *m, void *arg)
 	seq_putc(m, '\n');
 	pagetypeinfo_showfree(m, pgdat);
 	pagetypeinfo_showblockcount(m, pgdat);
+	pagetypeinfo_showmixedcount(m, pgdat);
 
 	return 0;
 }