Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 652f602..ae703ea 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
/* memcontrol.h - Memory Controller
*
* Copyright IBM Corporation, 2007
@@ -5,16 +6,6 @@
*
* Copyright 2007 OpenVZ SWsoft Inc
* Author: Pavel Emelianov <xemul@openvz.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#ifndef _LINUX_MEMCONTROL_H
@@ -78,7 +69,7 @@
struct mem_cgroup_id {
int id;
- atomic_t ref;
+ refcount_t ref;
};
/*
@@ -94,8 +85,8 @@
MEM_CGROUP_NTARGETS,
};
-struct mem_cgroup_stat_cpu {
- long count[MEMCG_NR_STAT];
+struct memcg_vmstats_percpu {
+ long stat[MEMCG_NR_STAT];
unsigned long events[NR_VM_EVENT_ITEMS];
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
@@ -126,6 +117,10 @@
struct mem_cgroup_per_node {
struct lruvec lruvec;
+ /* Legacy local VM stats */
+ struct lruvec_stat __percpu *lruvec_stat_local;
+
+ /* Subtree VM stats (batched updates) */
struct lruvec_stat __percpu *lruvec_stat_cpu;
atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS];
@@ -133,9 +128,8 @@
struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
-#ifdef CONFIG_MEMCG_KMEM
struct memcg_shrinker_map __rcu *shrinker_map;
-#endif
+
struct rb_node tree_node; /* RB tree node */
unsigned long usage_in_excess;/* Set to the value by which */
/* the soft limit is exceeded*/
@@ -189,6 +183,23 @@
#endif
/*
+ * Remember four most recent foreign writebacks with dirty pages in this
+ * cgroup. Inode sharing is expected to be uncommon and, even if we miss
+ * one in a given round, we're likely to catch it later if it keeps
+ * foreign-dirtying, so a fairly low count should be enough.
+ *
+ * See mem_cgroup_track_foreign_dirty_slowpath() for details.
+ */
+#define MEMCG_CGWB_FRN_CNT 4
+
+struct memcg_cgwb_frn {
+ u64 bdi_id; /* bdi->id of the foreign inode */
+ int memcg_id; /* memcg->css.id of foreign inode */
+ u64 at; /* jiffies_64 at the time of dirtying */
+ struct wb_completion done; /* tracks in-flight foreign writebacks */
+};
+
+/*
* 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,
@@ -238,8 +249,9 @@
/* OOM-Killer disable */
int oom_kill_disable;
- /* memory.events */
+ /* memory.events and memory.events.local */
struct cgroup_file events_file;
+ struct cgroup_file events_local_file;
/* handle for "memory.swap.events" */
struct cgroup_file swap_events_file;
@@ -273,14 +285,20 @@
atomic_t moving_account;
struct task_struct *move_lock_task;
- /* memory.stat */
- struct mem_cgroup_stat_cpu __percpu *stat_cpu;
+ /* Legacy local VM stats and events */
+ struct memcg_vmstats_percpu __percpu *vmstats_local;
+
+ /* Subtree VM stats and events (batched updates) */
+ struct memcg_vmstats_percpu __percpu *vmstats_percpu;
MEMCG_PADDING(_pad2_);
- atomic_long_t stat[MEMCG_NR_STAT];
- atomic_long_t events[NR_VM_EVENT_ITEMS];
- atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
+ atomic_long_t vmstats[MEMCG_NR_STAT];
+ atomic_long_t vmevents[NR_VM_EVENT_ITEMS];
+
+ /* memory.events */
+ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
+ atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS];
unsigned long socket_pressure;
@@ -305,12 +323,17 @@
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
struct wb_domain cgwb_domain;
+ struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
#endif
/* List of events which userspace want to receive */
struct list_head event_list;
spinlock_t event_list_lock;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ struct deferred_split deferred_split_queue;
+#endif
+
struct mem_cgroup_per_node *nodeinfo[0];
/* WARNING: nodeinfo must be the last member here */
};
@@ -333,6 +356,19 @@
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+ bool in_low_reclaim)
+{
+ if (mem_cgroup_disabled())
+ return 0;
+
+ if (in_low_reclaim)
+ return READ_ONCE(memcg->memory.emin);
+
+ return max(READ_ONCE(memcg->memory.emin),
+ READ_ONCE(memcg->memory.elow));
+}
+
enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
struct mem_cgroup *memcg);
@@ -392,7 +428,6 @@
struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
-bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -429,6 +464,11 @@
}
struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
+static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
+{
+ return mem_cgroup_from_css(seq_css(m));
+}
+
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
struct mem_cgroup_per_node *mz;
@@ -496,22 +536,6 @@
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zid, int nr_pages);
-unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
- int nid, unsigned int lru_mask);
-
-static inline
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
-{
- struct mem_cgroup_per_node *mz;
- unsigned long nr_pages = 0;
- int zid;
-
- mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- for (zid = 0; zid < MAX_NR_ZONES; zid++)
- nr_pages += mz->lru_zone_size[zid][lru];
- return nr_pages;
-}
-
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
enum lru_list lru, int zone_idx)
@@ -526,9 +550,13 @@
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
+
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
struct task_struct *p);
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
+
static inline void mem_cgroup_enter_user_fault(void)
{
WARN_ON(current->in_user_fault);
@@ -559,11 +587,13 @@
void __unlock_page_memcg(struct mem_cgroup *memcg);
void unlock_page_memcg(struct page *page);
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
- int idx)
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page_state().
+ */
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{
- long x = atomic_long_read(&memcg->stat[idx]);
+ long x = atomic_long_read(&memcg->vmstats[idx]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
@@ -571,23 +601,27 @@
return x;
}
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __mod_memcg_state(struct mem_cgroup *memcg,
- int idx, int val)
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page_state().
+ */
+static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
+ int idx)
{
- long x;
+ long x = 0;
+ int cpu;
- if (mem_cgroup_disabled())
- return;
-
- x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
- if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
- atomic_long_add(x, &memcg->stat[idx]);
+ for_each_possible_cpu(cpu)
+ x += per_cpu(memcg->vmstats_local->stat[idx], cpu);
+#ifdef CONFIG_SMP
+ if (x < 0)
x = 0;
- }
- __this_cpu_write(memcg->stat_cpu->count[idx], x);
+#endif
+ return x;
}
+void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
+
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void mod_memcg_state(struct mem_cgroup *memcg,
int idx, int val)
@@ -648,32 +682,30 @@
return x;
}
-static inline void __mod_lruvec_state(struct lruvec *lruvec,
- enum node_stat_item idx, int val)
+static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+ enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
- long x;
-
- /* Update node */
- __mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+ long x = 0;
+ int cpu;
if (mem_cgroup_disabled())
- return;
+ return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-
- /* Update memcg */
- __mod_memcg_state(pn->memcg, idx, val);
-
- /* Update lruvec */
- x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
- if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
- atomic_long_add(x, &pn->lruvec_stat[idx]);
+ for_each_possible_cpu(cpu)
+ x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
+#ifdef CONFIG_SMP
+ if (x < 0)
x = 0;
- }
- __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
+#endif
+ return x;
}
+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);
+
static inline void mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
@@ -714,22 +746,8 @@
gfp_t gfp_mask,
unsigned long *total_scanned);
-static inline void __count_memcg_events(struct mem_cgroup *memcg,
- enum vm_event_item idx,
- unsigned long count)
-{
- unsigned long x;
-
- if (mem_cgroup_disabled())
- return;
-
- x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
- if (unlikely(x > MEMCG_CHARGE_BATCH)) {
- atomic_long_add(x, &memcg->events[idx]);
- x = 0;
- }
- __this_cpu_write(memcg->stat_cpu->events[idx], x);
-}
+void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
+ unsigned long count);
static inline void count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
@@ -767,8 +785,17 @@
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
- atomic_long_inc(&memcg->memory_events[event]);
- cgroup_file_notify(&memcg->events_file);
+ atomic_long_inc(&memcg->memory_events_local[event]);
+ cgroup_file_notify(&memcg->events_local_file);
+
+ do {
+ atomic_long_inc(&memcg->memory_events[event]);
+ cgroup_file_notify(&memcg->events_file);
+
+ if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
+ break;
+ } while ((memcg = parent_mem_cgroup(memcg)) &&
+ !mem_cgroup_is_root(memcg));
}
static inline void memcg_memory_event_mm(struct mm_struct *mm,
@@ -817,6 +844,12 @@
{
}
+static inline unsigned long mem_cgroup_protection(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)
{
@@ -884,12 +917,6 @@
return true;
}
-static inline bool task_in_mem_cgroup(struct task_struct *task,
- const struct mem_cgroup *memcg)
-{
- return true;
-}
-
static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
return NULL;
@@ -935,6 +962,11 @@
return NULL;
}
+static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
+{
+ return NULL;
+}
+
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
return NULL;
@@ -945,11 +977,6 @@
return true;
}
-static inline unsigned long
-mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
-{
- return 0;
-}
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
enum lru_list lru, int zone_idx)
@@ -957,20 +984,23 @@
return 0;
}
-static inline unsigned long
-mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
- int nid, unsigned int lru_mask)
-{
- return 0;
-}
-
static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
return 0;
}
+static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
+{
+ return 0;
+}
+
static inline void
-mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
+{
+}
+
+static inline void
+mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{
}
@@ -1019,8 +1049,13 @@
{
}
-static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
- int idx)
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+{
+ return 0;
+}
+
+static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
+ int idx)
{
return 0;
}
@@ -1055,6 +1090,12 @@
return node_page_state(lruvec_pgdat(lruvec), idx);
}
+static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+ enum node_stat_item idx)
+{
+ return node_page_state(lruvec_pgdat(lruvec), idx);
+}
+
static inline void __mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
@@ -1079,6 +1120,14 @@
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
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
@@ -1097,6 +1146,12 @@
{
}
+static inline void __count_memcg_events(struct mem_cgroup *memcg,
+ enum vm_event_item idx,
+ unsigned long count)
+{
+}
+
static inline void count_memcg_page_event(struct page *page,
int idx)
{
@@ -1160,6 +1215,16 @@
__mod_lruvec_page_state(page, idx, -1);
}
+static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx)
+{
+ __mod_lruvec_slab_state(p, idx, 1);
+}
+
+static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx)
+{
+ __mod_lruvec_slab_state(p, idx, -1);
+}
+
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_state(struct mem_cgroup *memcg,
int idx)
@@ -1219,6 +1284,21 @@
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+ struct bdi_writeback *wb);
+
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+ struct bdi_writeback *wb)
+{
+ if (mem_cgroup_disabled())
+ return;
+
+ if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
+ mem_cgroup_track_foreign_dirty_slowpath(page, wb);
+}
+
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
+
#else /* CONFIG_CGROUP_WRITEBACK */
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
@@ -1234,6 +1314,15 @@
{
}
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+ struct bdi_writeback *wb)
+{
+}
+
+static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+}
+
#endif /* CONFIG_CGROUP_WRITEBACK */
struct sock;
@@ -1254,6 +1343,11 @@
} while ((memcg = parent_mem_cgroup(memcg)));
return false;
}
+
+extern int memcg_expand_shrinker_maps(int new_id);
+
+extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
+ int nid, int shrinker_id);
#else
#define mem_cgroup_sockets_enabled 0
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
@@ -1262,16 +1356,24 @@
{
return false;
}
+
+static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
+ int nid, int shrinker_id)
+{
+}
#endif
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
void memcg_kmem_put_cache(struct kmem_cache *cachep);
-int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
- struct mem_cgroup *memcg);
-int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
-void memcg_kmem_uncharge(struct page *page, int order);
#ifdef CONFIG_MEMCG_KMEM
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
+void __memcg_kmem_uncharge(struct page *page, int order);
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+ struct mem_cgroup *memcg);
+void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg,
+ unsigned int nr_pages);
+
extern struct static_key_false memcg_kmem_enabled_key;
extern struct workqueue_struct *memcg_kmem_cache_wq;
@@ -1292,6 +1394,34 @@
return static_branch_unlikely(&memcg_kmem_enabled_key);
}
+static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+ if (memcg_kmem_enabled())
+ return __memcg_kmem_charge(page, gfp, order);
+ return 0;
+}
+
+static inline void memcg_kmem_uncharge(struct page *page, int order)
+{
+ if (memcg_kmem_enabled())
+ __memcg_kmem_uncharge(page, order);
+}
+
+static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp,
+ int order, struct mem_cgroup *memcg)
+{
+ if (memcg_kmem_enabled())
+ return __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ return 0;
+}
+
+static inline void memcg_kmem_uncharge_memcg(struct page *page, int order,
+ struct mem_cgroup *memcg)
+{
+ if (memcg_kmem_enabled())
+ __memcg_kmem_uncharge_memcg(memcg, 1 << order);
+}
+
/*
* helper for accessing a memcg's index. It will be used as an index in the
* child cache array in kmem_cache, and also to derive its name. This function
@@ -1302,11 +1432,26 @@
return memcg ? memcg->kmemcg_id : -1;
}
-extern int memcg_expand_shrinker_maps(int new_id);
-
-extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
- int nid, int shrinker_id);
#else
+
+static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+ return 0;
+}
+
+static inline void memcg_kmem_uncharge(struct page *page, int order)
+{
+}
+
+static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+ return 0;
+}
+
+static inline void __memcg_kmem_uncharge(struct page *page, int order)
+{
+}
+
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
@@ -1328,8 +1473,6 @@
{
}
-static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
- int nid, int shrinker_id) { }
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */