4 files changed, 28 insertions, 0 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 902b4574acfb..9832ec52f859 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -21,6 +21,7 @@ Currently, these files are in /proc/sys/vm:
 - admin_reserve_kbytes
 - block_dump
 - compact_memory
+- compact_unevictable_allowed
 - dirty_background_bytes
 - dirty_background_ratio
 - dirty_bytes
@@ -106,6 +107,16 @@ huge pages although processes will also directly compact memory as required.
 
 ==============================================================
 
+compact_unevictable_allowed
+
+Available only when CONFIG_COMPACTION is set. When set to 1, compaction is
+allowed to examine the unevictable lru (mlocked pages) for pages to compact.
+This should be used on systems where stalls for minor page faults are an
+acceptable trade for large contiguous free memory.  Set to 0 to prevent
+compaction from moving pages that are unevictable.  Default value is 1.
+
+==============================================================
+
 dirty_background_bytes
 
 Contains the amount of dirty memory at which the background kernel
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index a014559e4a49..aa8f61cf3a19 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -34,6 +34,7 @@ extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 extern int sysctl_extfrag_threshold;
 extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
                         void __user *buffer, size_t *length, loff_t *ppos);
+extern int sysctl_compact_unevictable_allowed;
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8c0eabd41886..42b7fc2860c1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1335,6 +1335,15 @@ static struct ctl_table vm_table[] = {
                 .extra1         = &min_extfrag_threshold,
                 .extra2         = &max_extfrag_threshold,
         },
+        {
+                .procname       = "compact_unevictable_allowed",
+                .data           = &sysctl_compact_unevictable_allowed,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
 
 #endif /* CONFIG_COMPACTION */
         {
diff --git a/mm/compaction.c b/mm/compaction.c
index a18201a8124e..570426edcadf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1047,6 +1047,12 @@ typedef enum {
 } isolate_migrate_t;
 
 /*
+ * Allow userspace to control policy on scanning the unevictable LRU for
+ * compactable pages.
+ */
+int sysctl_compact_unevictable_allowed __read_mostly = 1;
+
+/*
  * Isolate all pages that can be migrated from the first suitable block,
  * starting at the block pointed to by the migrate scanner pfn within
  * compact_control.
@@ -1057,6 +1063,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
         unsigned long low_pfn, end_pfn;
         struct page *page;
         const isolate_mode_t isolate_mode =
+                (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
                 (cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);
 
         /*