2 files changed, 50 insertions, 10 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fb5b2a41bd45..b6d0b68f5503 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,17 +356,54 @@ 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,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
+	*min = *low = 0;
+
 	if (mem_cgroup_disabled())
-		return 0;
+		return;
 
-	if (in_low_reclaim)
-		return READ_ONCE(memcg->memory.emin);
+	/*
+	 * 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;
 
-	return max(READ_ONCE(memcg->memory.emin),
-		   READ_ONCE(memcg->memory.elow));
+	*min = READ_ONCE(memcg->memory.emin);
+	*low = READ_ONCE(memcg->memory.elow);
 }
 
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
@@ -847,10 +884,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
-	return 0;
+	*min = *low = 0;
 }
 
 static inline enum mem_cgroup_protection mem_cgroup_protected(
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 15f906e4a748..7c075463c7f2 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -111,6 +111,7 @@ struct virtio_device {
 	bool config_enabled;
 	bool config_change_pending;
 	spinlock_t config_lock;
+	spinlock_t vqs_list_lock; /* Protects VQs list access */
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;