mm, memcg: decouple e{low,min} state mutations from protection checks

mem_cgroup_protected currently is both used to set effective low and min
and return a mem_cgroup_protection based on the result.  As a user, this
can be a little unexpected: it appears to be a simple predicate function,
if not for the big warning in the comment above about the order in which
it must be executed.

This change makes it so that we separate the state mutations from the
actual protection checks, which makes it more obvious where we need to be
careful mutating internal state, and where we are simply checking and
don't need to worry about that.

[mhocko@suse.com - don't check protection on root memcgs]

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: http://lkml.kernel.org/r/ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.name
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 11 insertions, 34 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c610617bb19a..b30a52db6b2d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6587,21 +6587,15 @@ static unsigned long effective_protection(unsigned long usage,
  *
  * WARNING: This function is not stateless! It can only be used as part
  *          of a top-down tree iteration, not for isolated queries.
- *
- * Returns one of the following:
- *   MEMCG_PROT_NONE: cgroup memory is not protected
- *   MEMCG_PROT_LOW: cgroup memory is protected as long there is
- *     an unprotected supply of reclaimable memory from other cgroups.
- *   MEMCG_PROT_MIN: cgroup memory is protected
  */
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg)
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg)
 {
 	unsigned long usage, parent_usage;
 	struct mem_cgroup *parent;
 
 	if (mem_cgroup_disabled())
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -6614,21 +6608,21 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 	 * that special casing.
 	 */
 	if (memcg == root)
-		return MEMCG_PROT_NONE;
+		return;
 
 	usage = page_counter_read(&memcg->memory);
 	if (!usage)
-		return MEMCG_PROT_NONE;
+		return;
 
 	parent = parent_mem_cgroup(memcg);
 	/* No parent means a non-hierarchical mode on v1 memcg */
 	if (!parent)
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (parent == root) {
 		memcg->memory.emin = READ_ONCE(memcg->memory.min);
 		memcg->memory.elow = READ_ONCE(memcg->memory.low);
-		goto out;
+		return;
 	}
 
 	parent_usage = page_counter_read(&parent->memory);
@@ -6642,14 +6636,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 			READ_ONCE(memcg->memory.low),
 			READ_ONCE(parent->memory.elow),
 			atomic_long_read(&parent->memory.children_low_usage)));
-
-out:
-	if (usage <= memcg->memory.emin)
-		return MEMCG_PROT_MIN;
-	else if (usage <= memcg->memory.elow)
-		return MEMCG_PROT_LOW;
-	else
-		return MEMCG_PROT_NONE;
 }
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9f0811d24255..5747867f0082 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2620,14 +2620,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
-		switch (mem_cgroup_protected(target_memcg, memcg)) {
-		case MEMCG_PROT_MIN:
+		mem_cgroup_calculate_protection(target_memcg, memcg);
+
+		if (mem_cgroup_below_min(memcg)) {
 			/*
 			 * Hard protection.
 			 * If there is no reclaimable memory, OOM.
 			 */
 			continue;
-		case MEMCG_PROT_LOW:
+		} else if (mem_cgroup_below_low(memcg)) {
 			/*
 			 * Soft protection.
 			 * Respect the protection only as long as
@@ -2639,16 +2640,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 				continue;
 			}
 			memcg_memory_event(memcg, MEMCG_LOW);
-			break;
-		case MEMCG_PROT_NONE:
-			/*
-			 * All protection thresholds breached. We may
-			 * still choose to vary the scan pressure
-			 * applied based on by how much the cgroup in
-			 * question has exceeded its protection
-			 * thresholds (see get_scan_count).
-			 */
-			break;
 		}
 
 		reclaimed = sc->nr_reclaimed;