diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3f8ff6519c9d..0301b231fd02 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,12 +355,49 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, bool in_low_reclaim) { if (mem_cgroup_disabled()) return 0; + /* + * There is no reclaim protection applied to a targeted reclaim. + * We are special casing this specific case here because + * mem_cgroup_protected calculation is not robust enough to keep + * the protection invariant for calculated effective values for + * parallel reclaimers with different reclaim target. This is + * especially a problem for tail memcgs (as they have pages on LRU) + * which would want to have effective values 0 for targeted reclaim + * but a different value for external reclaim. + * + * Example + * Let's have global and A's reclaim in parallel: + * | + * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) + * |\ + * | C (low = 1G, usage = 2.5G) + * B (low = 1G, usage = 0.5G) + * + * For the global reclaim + * A.elow = A.low + * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow + * C.elow = min(C.usage, C.low) + * + * With the effective values resetting we have A reclaim + * A.elow = 0 + * B.elow = B.low + * C.elow = C.low + * + * If the global reclaim races with A's reclaim then + * B.elow = C.elow = 0 because children_low_usage > A.elow) + * is possible and reclaiming B would be violating the protection. + * + */ + if (root == memcg) + return 0; + if (in_low_reclaim) return READ_ONCE(memcg->memory.emin); @@ -891,7 +928,8 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, bool in_low_reclaim) { return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b4cb1bb61d46..c610617bb19a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6605,6 +6605,14 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, if (!root) root = root_mem_cgroup; + + /* + * Effective values of the reclaim targets are ignored so they + * can be stale. Have a look at mem_cgroup_protection for more + * details. + * TODO: calculation should be more robust so that we do not need + * that special casing. + */ if (memcg == root) return MEMCG_PROT_NONE; diff --git a/mm/vmscan.c b/mm/vmscan.c index 2ac43664aba4..9f0811d24255 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2331,7 +2331,8 @@ out: unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(memcg, + protection = mem_cgroup_protection(sc->target_mem_cgroup, + memcg, sc->memcg_low_reclaim); if (protection) {