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>
Change-Id: I916c4cb713450129c7010659e44340bd81a0959e
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>
[backport of the commit 45c7f7e1ef17f09fe70bad4b705ce43772153fd7 from mainline]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d13d697..fa12e18 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -50,12 +50,6 @@ enum memcg_memory_event {
        MEMCG_NR_MEMORY_EVENTS,
 };
 
-enum mem_cgroup_protection {
-       MEMCG_PROT_NONE,
-       MEMCG_PROT_LOW,
-       MEMCG_PROT_MIN,
-};
-
 struct mem_cgroup_reclaim_cookie {
        pg_data_t *pgdat;
        int priority;
@@ -366,8 +360,36 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
                   READ_ONCE(memcg->memory.elow));
 }
 
-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);
+
+static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
+{
+       /*
+        * The root memcg doesn't account charges, and doesn't support
+        * protection.
+        */
+       return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
+
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+       if (!mem_cgroup_supports_protection(memcg))
+               return false;
+
+       return READ_ONCE(memcg->memory.elow) >=
+               page_counter_read(&memcg->memory);
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+       if (!mem_cgroup_supports_protection(memcg))
+               return false;
+
+       return READ_ONCE(memcg->memory.emin) >=
+               page_counter_read(&memcg->memory);
+}
 
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
                          gfp_t gfp_mask, struct mem_cgroup **memcgp,
@@ -852,10 +874,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
        return 0;
 }
 
-static inline enum mem_cgroup_protection mem_cgroup_protected(
-       struct mem_cgroup *root, struct mem_cgroup *memcg)
+static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+                                                  struct mem_cgroup *memcg)
 {
-       return MEMCG_PROT_NONE;
+}
+
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+{
+       return false;
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+       return false;
 }
 
 static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 984149c..b363847 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6450,8 +6450,8 @@ struct cgroup_subsys memory_cgrp_subsys = {
  * for next usage. This part is intentionally racy, but it's ok,
  * as memory.low is a best-effort mechanism.
  */
-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)
 {
        struct mem_cgroup *parent;
        unsigned long emin, parent_emin;
@@ -6459,16 +6459,16 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
        unsigned long usage;
 
        if (mem_cgroup_disabled())
-               return MEMCG_PROT_NONE;
+               return;
 
        if (!root)
                root = root_mem_cgroup;
        if (memcg == root)
-               return MEMCG_PROT_NONE;
+               return;
 
        usage = page_counter_read(&memcg->memory);
        if (!usage)
-               return MEMCG_PROT_NONE;
+               return;
 
        emin = memcg->memory.min;
        elow = memcg->memory.low;
@@ -6476,10 +6476,10 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
        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)
-               goto exit;
+               return;
 
        parent_emin = READ_ONCE(parent->memory.emin);
        emin = min(emin, parent_emin);
@@ -6509,16 +6509,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
                                   siblings_low_usage);
        }
 
-exit:
-       memcg->memory.emin = emin;
-       memcg->memory.elow = elow;
-
-       if (usage <= emin)
-               return MEMCG_PROT_MIN;
-       else if (usage <= elow)
-               return MEMCG_PROT_LOW;
-       else
-               return MEMCG_PROT_NONE;
 }
 
 /**

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f76353f..38ff2cb 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2641,14 +2641,15 @@ 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
@@ -2660,16 +2661,6 @@ 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;