Merge tag 'v5.9-rc2' into regulator-5.9

Linux 5.9-rc2

1 files changed, 193 insertions, 24 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e77197a62809..d0b036123c6a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,7 @@
 #include <linux/page-flags.h>
 
 struct mem_cgroup;
+struct obj_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
@@ -31,8 +32,7 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
-	/* XXX: why are these zone and not node counters? */
-	MEMCG_KERNEL_STACK_KB,
+	MEMCG_PERCPU_B,
 	MEMCG_NR_STAT,
 };
 
@@ -48,12 +48,6 @@ 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;
 	unsigned int generation;
@@ -71,8 +65,8 @@ struct mem_cgroup_id {
 
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremated by the number of pages. This counter is used for
- * for trigger some periodic events. This is straightforward and better
+ * it will be incremented by the number of pages. This counter is used
+ * to trigger some periodic events. This is straightforward and better
  * than using jiffies etc. to handle periodic memcg event.
  */
 enum mem_cgroup_events_target {
@@ -193,6 +187,22 @@ struct memcg_cgwb_frn {
 };
 
 /*
+ * Bucket for arbitrarily byte-sized objects charged to a memory
+ * cgroup. The bucket can be reparented in one piece when the cgroup
+ * is destroyed, without having to round up the individual references
+ * of all live memory objects in the wild.
+ */
+struct obj_cgroup {
+	struct percpu_ref refcnt;
+	struct mem_cgroup *memcg;
+	atomic_t nr_charged_bytes;
+	union {
+		struct list_head list;
+		struct rcu_head rcu;
+	};
+};
+
+/*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
  * statistics based on the statistics developed by Rik Van Riel for clock-pro,
@@ -300,7 +310,8 @@ struct mem_cgroup {
         /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
 	enum memcg_kmem_state kmem_state;
-	struct list_head kmem_caches;
+	struct obj_cgroup __rcu *objcg;
+	struct list_head objcg_list; /* list of inherited objcgs */
 #endif
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -329,6 +340,13 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+static __always_inline bool memcg_stat_item_in_bytes(int idx)
+{
+	if (idx == MEMCG_PERCPU_B)
+		return true;
+	return vmstat_item_in_bytes(idx);
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
@@ -339,12 +357,49 @@ 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);
 
@@ -352,8 +407,36 @@ 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_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
 
@@ -416,6 +499,33 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
+{
+	return percpu_ref_tryget(&objcg->refcnt);
+}
+
+static inline void obj_cgroup_get(struct obj_cgroup *objcg)
+{
+	percpu_ref_get(&objcg->refcnt);
+}
+
+static inline void obj_cgroup_put(struct obj_cgroup *objcg)
+{
+	percpu_ref_put(&objcg->refcnt);
+}
+
+/*
+ * After the initialization objcg->memcg is always pointing at
+ * a valid memcg, but can be atomically swapped to the parent memcg.
+ *
+ * The caller must ensure that the returned memcg won't be released:
+ * e.g. acquire the rcu_read_lock or css_set_lock.
+ */
+static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
+{
+	return READ_ONCE(objcg->memcg);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -520,7 +630,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	struct mem_cgroup_per_node *mz;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return mz->lru_zone_size[zone_idx][lru];
+	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
 void mem_cgroup_handle_over_high(void);
@@ -679,11 +789,34 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
+void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			      int val);
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
+
 void mod_memcg_obj_state(void *p, int idx, int val);
 
+static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+					 int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_slab_state(p, idx, val);
+	local_irq_restore(flags);
+}
+
+static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
+					  enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_memcg_lruvec_state(lruvec, idx, val);
+	local_irq_restore(flags);
+}
+
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
 {
@@ -825,16 +958,26 @@ 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;
 }
 
-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)
+{
+}
+
+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 MEMCG_PROT_NONE;
+	return false;
 }
 
 static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
@@ -1057,6 +1200,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
+static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
+					    enum node_stat_item idx, int val)
+{
+}
+
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
 				      enum node_stat_item idx, int val)
 {
@@ -1089,6 +1237,14 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 	__mod_node_page_state(page_pgdat(page), idx, val);
 }
 
+static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+					 int val)
+{
+	struct page *page = virt_to_head_page(p);
+
+	mod_node_page_state(page_pgdat(page), idx, val);
+}
+
 static inline void mod_memcg_obj_state(void *p, int idx, int val)
 {
 }
@@ -1341,9 +1497,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 }
 #endif
 
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
-void memcg_kmem_put_cache(struct kmem_cache *cachep);
-
 #ifdef CONFIG_MEMCG_KMEM
 int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
 			unsigned int nr_pages);
@@ -1351,8 +1504,12 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
+struct obj_cgroup *get_obj_cgroup_from_current(void);
+
+int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
+void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
+
 extern struct static_key_false memcg_kmem_enabled_key;
-extern struct workqueue_struct *memcg_kmem_cache_wq;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
@@ -1368,7 +1525,19 @@ void memcg_put_cache_ids(void);
 
 static inline bool memcg_kmem_enabled(void)
 {
-	return static_branch_unlikely(&memcg_kmem_enabled_key);
+	return static_branch_likely(&memcg_kmem_enabled_key);
+}
+
+static inline bool memcg_kmem_bypass(void)
+{
+	if (in_interrupt())
+		return true;
+
+	/* Allow remote memcg charging in kthread contexts. */
+	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
+	     !current->active_memcg)
+		return true;
+	return false;
 }
 
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,