mm: compaction: abort compaction if too many pages are isolated and caller is asynchronous V2

Asynchronous compaction is used when promoting to huge pages.  This is all
very nice but if there are a number of processes in compacting memory, a
large number of pages can be isolated.  An "asynchronous" process can
stall for long periods of time as a result with a user reporting that
firefox can stall for 10s of seconds.  This patch aborts asynchronous
compaction if too many pages are isolated as it's better to fail a
hugepage promotion than stall a process.

[minchan.kim@gmail.com: return COMPACT_PARTIAL for abort]
Reported-and-tested-by: Ury Stankevich <urykhy@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 24 insertions, 5 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 9b94eaf537e4..6cc604bd5649 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,11 +251,18 @@ static bool too_many_isolated(struct zone *zone)
         return isolated > (inactive + active) / 2;
 }
 
+/* possible outcome of isolate_migratepages */
+typedef enum {
+        ISOLATE_ABORT,          /* Abort compaction now */
+        ISOLATE_NONE,           /* No pages isolated, continue scanning */
+        ISOLATE_SUCCESS,        /* Pages isolated, migrate */
+} isolate_migrate_t;
+
 /*
  * Isolate all pages that can be migrated from the block pointed to by
  * the migrate scanner within compact_control.
  */
-static unsigned long isolate_migratepages(struct zone *zone,
+static isolate_migrate_t isolate_migratepages(struct zone *zone,
                                         struct compact_control *cc)
 {
         unsigned long low_pfn, end_pfn;
@@ -272,7 +279,7 @@ static unsigned long isolate_migratepages(struct zone *zone,
         /* Do not cross the free scanner or scan within a memory hole */
         if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
                 cc->migrate_pfn = end_pfn;
-                return 0;
+                return ISOLATE_NONE;
         }
 
         /*
@@ -281,10 +288,14 @@ static unsigned long isolate_migratepages(struct zone *zone,
          * delay for some time until fewer pages are isolated
          */
         while (unlikely(too_many_isolated(zone))) {
+                /* async migration should just abort */
+                if (!cc->sync)
+                        return ISOLATE_ABORT;
+
                 congestion_wait(BLK_RW_ASYNC, HZ/10);
 
                 if (fatal_signal_pending(current))
-                        return 0;
+                        return ISOLATE_ABORT;
         }
 
         /* Time to isolate some pages for migration */
@@ -369,7 +380,7 @@ static unsigned long isolate_migratepages(struct zone *zone,
 
         trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
-        return cc->nr_migratepages;
+        return ISOLATE_SUCCESS;
 }
 
 /*
@@ -535,8 +546,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
                 unsigned long nr_migrate, nr_remaining;
                 int err;
 
-                if (!isolate_migratepages(zone, cc))
+                switch (isolate_migratepages(zone, cc)) {
+                case ISOLATE_ABORT:
+                        ret = COMPACT_PARTIAL;
+                        goto out;
+                case ISOLATE_NONE:
                         continue;
+                case ISOLATE_SUCCESS:
+                        ;
+                }
 
                 nr_migrate = cc->nr_migratepages;
                 err = migrate_pages(&cc->migratepages, compaction_alloc,
@@ -560,6 +578,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
         }
 
+out:
         /* Release free pages and check accounting */
         cc->nr_freepages -= release_freepages(&cc->freepages);
         VM_BUG_ON(cc->nr_freepages != 0);