mm: memcontrol: Add force_reclaim to reclaim tasks' memory in memcg

These days, platforms tend to manage memory on low memory state
like andloid's lowmemory killer. These platforms might want to
reclaim memory from background tasks as well as kill victims
to guarantee free memory at use space level. This patch provides
an interface to reclaim a given memcg. After platform's low memory
handler moves tasks that the platform wants to reclaim to
a memcg and decides how many pages should be reclaimed, it can
reclaim the pages from the tasks by writing the number of pages
at memory.force_reclaim.

Signed-off-by: Hyunhee Kim <hyunhee.kim@xxxxxxxxxxx>
Signed-off-by: Kyungmin Park <kyungmin.park@xxxxxxxxxxx>
[dwoo08.lee: ported from mailing list https://www.spinics.net/lists/cgroups/msg07874.html]

Change-Id: I40b1322dfe2628ca306690a15958881b3026606f
Signed-off-by: Dongwoo Lee <dwoo08.lee@samsung.com>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4bb2a4c..db473e7 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3531,6 +3531,36 @@ static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
        return mem_cgroup_force_empty(memcg) ?: nbytes;
 }
 
+#ifdef CONFIG_MEMCG_SWAP
+static int mem_cgroup_force_reclaim(struct cgroup_subsys_state *css,
+                              struct cftype *cft, u64 val)
+{
+       struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+       unsigned long nr_to_reclaim = val;
+       unsigned long total = 0;
+       int loop;
+
+       for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) {
+               total += try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim,
+                                               GFP_KERNEL, true);
+
+               /*
+                * If nothing was reclaimed after two attempts, there
+                * may be no reclaimable pages in this hierarchy.
+                * If more than nr_to_reclaim pages were already reclaimed,
+                * finish force reclaim.
+                */
+               if (loop && (!total || total > nr_to_reclaim))
+                       break;
+       }
+
+       pr_info("%s: [Mem_reclaim] Loop: %d - Total_reclaimed: %lu - nr_to_reclaim: %lu\n",
+               __func__, loop, total, nr_to_reclaim);
+
+       return total;
+}
+#endif
+
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
                                     struct cftype *cft)
 {
@@ -7490,6 +7520,10 @@ static struct cftype memsw_files[] = {
                .write = mem_cgroup_reset,
                .read_u64 = mem_cgroup_read_u64,
        },
+       {
+               .name = "force_reclaim",
+               .write_u64 = mem_cgroup_force_reclaim,
+       },
        { },    /* terminate */
 };