Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b6d0b68..1f467fb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,19 +23,16 @@
#include <linux/page-flags.h>
struct mem_cgroup;
+struct obj_cgroup;
struct page;
struct mm_struct;
struct kmem_cache;
/* Cgroup-specific page state, on top of universal node page state */
enum memcg_stat_item {
- MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS,
- MEMCG_RSS,
- MEMCG_RSS_HUGE,
- MEMCG_SWAP,
+ 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,
};
@@ -45,20 +42,14 @@
MEMCG_MAX,
MEMCG_OOM,
MEMCG_OOM_KILL,
+ MEMCG_SWAP_HIGH,
MEMCG_SWAP_MAX,
MEMCG_SWAP_FAIL,
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;
unsigned int generation;
};
@@ -74,14 +65,13 @@
/*
* 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 {
MEM_CGROUP_TARGET_THRESH,
MEM_CGROUP_TARGET_SOFTLIMIT,
- MEM_CGROUP_TARGET_NUMAINFO,
MEM_CGROUP_NTARGETS,
};
@@ -108,11 +98,11 @@
*/
struct memcg_shrinker_map {
struct rcu_head rcu;
- unsigned long map[0];
+ unsigned long map[];
};
/*
- * per-zone information in memory controller.
+ * per-node information in memory controller.
*/
struct mem_cgroup_per_node {
struct lruvec lruvec;
@@ -126,7 +116,7 @@
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
- struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
+ struct mem_cgroup_reclaim_iter iter;
struct memcg_shrinker_map __rcu *shrinker_map;
@@ -134,9 +124,6 @@
unsigned long usage_in_excess;/* Set to the value by which */
/* the soft limit is exceeded*/
bool on_tree;
- bool congested; /* memcg has many dirty pages */
- /* backed by a congested BDI */
-
struct mem_cgroup *memcg; /* Back pointer, we cannot */
/* use container_of */
};
@@ -153,7 +140,7 @@
/* Size of entries[] */
unsigned int size;
/* Array of thresholds */
- struct mem_cgroup_threshold entries[0];
+ struct mem_cgroup_threshold entries[];
};
struct mem_cgroup_thresholds {
@@ -200,6 +187,22 @@
};
/*
+ * 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; /* protected by objcg_lock */
+ 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,
@@ -212,16 +215,16 @@
struct mem_cgroup_id id;
/* Accounted resources */
- struct page_counter memory;
- struct page_counter swap;
+ struct page_counter memory; /* Both v1 & v2 */
+
+ union {
+ struct page_counter swap; /* v2 only */
+ struct page_counter memsw; /* v1 only */
+ };
/* Legacy consumer-oriented counters */
- struct page_counter memsw;
- struct page_counter kmem;
- struct page_counter tcpmem;
-
- /* Upper bound of normal memory consumption range */
- unsigned long high;
+ struct page_counter kmem; /* v1 only */
+ struct page_counter tcpmem; /* v1 only */
/* Range enforcement for interrupt charges */
struct work_struct high_work;
@@ -279,20 +282,6 @@
MEMCG_PADDING(_pad1_);
- /*
- * set > 0 if pages under this cgroup are moving to other cgroup.
- */
- atomic_t moving_account;
- struct task_struct *move_lock_task;
-
- /* 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 vmstats[MEMCG_NR_STAT];
atomic_long_t vmevents[NR_VM_EVENT_ITEMS];
@@ -310,15 +299,24 @@
/* 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;
+ /* list of inherited objcgs, protected by objcg_lock */
+ struct list_head objcg_list;
#endif
- int last_scanned_node;
-#if MAX_NUMNODES > 1
- nodemask_t scan_nodes;
- atomic_t numainfo_events;
- atomic_t numainfo_updating;
-#endif
+ MEMCG_PADDING(_pad2_);
+
+ /*
+ * set > 0 if pages under this cgroup are moving to other cgroup.
+ */
+ atomic_t moving_account;
+ struct task_struct *move_lock_task;
+
+ /* 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;
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
@@ -346,6 +344,13 @@
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);
@@ -406,19 +411,39 @@
*low = 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);
-int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask, struct mem_cgroup **memcgp,
- bool compound);
-int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask, struct mem_cgroup **memcgp,
- bool compound);
-void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
- bool lrucare, bool compound);
-void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
- bool compound);
+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);
+
void mem_cgroup_uncharge(struct page *page);
void mem_cgroup_uncharge_list(struct list_head *page_list);
@@ -431,25 +456,27 @@
}
/**
- * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
- * @node: node of the wanted lruvec
+ * mem_cgroup_lruvec - get the lru list vector for a memcg & node
* @memcg: memcg of the wanted lruvec
*
- * Returns the lru list vector holding pages for a given @node or a given
- * @memcg and @zone. This can be the node lruvec, if the memory controller
- * is disabled.
+ * Returns the lru list vector holding pages for a given @memcg &
+ * @node combination. This can be the node lruvec, if the memory
+ * controller is disabled.
*/
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
- struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
+ struct pglist_data *pgdat)
{
struct mem_cgroup_per_node *mz;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = node_lruvec(pgdat);
+ lruvec = &pgdat->__lruvec;
goto out;
}
+ if (!memcg)
+ memcg = root_mem_cgroup;
+
mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
lruvec = &mz->lruvec;
out:
@@ -476,6 +503,33 @@
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)
@@ -580,7 +634,7 @@
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);
@@ -617,7 +671,7 @@
void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
#ifdef CONFIG_MEMCG_SWAP
-extern int do_swap_account;
+extern bool cgroup_memory_noswap;
#endif
struct mem_cgroup *lock_page_memcg(struct page *page);
@@ -739,11 +793,34 @@
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)
{
@@ -757,16 +834,17 @@
static inline void __mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
+ struct page *head = compound_head(page); /* rmap on tail pages */
pg_data_t *pgdat = page_pgdat(page);
struct lruvec *lruvec;
/* Untracked pages have no memcg, no lruvec. Update only the node */
- if (!page->mem_cgroup) {
+ if (!head->mem_cgroup) {
__mod_node_page_state(pgdat, idx, val);
return;
}
- lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+ lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
@@ -823,12 +901,19 @@
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
+ bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
+ event == MEMCG_SWAP_FAIL;
+
atomic_long_inc(&memcg->memory_events_local[event]);
- cgroup_file_notify(&memcg->events_local_file);
+ if (!swap_event)
+ cgroup_file_notify(&memcg->events_local_file);
do {
atomic_long_inc(&memcg->memory_events[event]);
- cgroup_file_notify(&memcg->events_file);
+ if (swap_event)
+ cgroup_file_notify(&memcg->swap_events_file);
+ else
+ cgroup_file_notify(&memcg->events_file);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
break;
@@ -853,9 +938,7 @@
rcu_read_unlock();
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void mem_cgroup_split_huge_fixup(struct page *head);
-#endif
+void split_page_memcg(struct page *head, unsigned int nr);
#else /* CONFIG_MEMCG */
@@ -892,43 +975,27 @@
*min = *low = 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 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask,
- struct mem_cgroup **memcgp,
- bool compound)
+static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
{
- *memcgp = NULL;
+ return false;
+}
+
+static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
+static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+ gfp_t gfp_mask)
+{
return 0;
}
-static inline int mem_cgroup_try_charge_delay(struct page *page,
- struct mm_struct *mm,
- gfp_t gfp_mask,
- struct mem_cgroup **memcgp,
- bool compound)
-{
- *memcgp = NULL;
- return 0;
-}
-
-static inline void mem_cgroup_commit_charge(struct page *page,
- struct mem_cgroup *memcg,
- bool lrucare, bool compound)
-{
-}
-
-static inline void mem_cgroup_cancel_charge(struct page *page,
- struct mem_cgroup *memcg,
- bool compound)
-{
-}
-
static inline void mem_cgroup_uncharge(struct page *page)
{
}
@@ -941,16 +1008,21 @@
{
}
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
- struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
+ struct pglist_data *pgdat)
{
- return node_lruvec(pgdat);
+ return &pgdat->__lruvec;
}
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
struct pglist_data *pgdat)
{
- return &pgdat->lruvec;
+ return &pgdat->__lruvec;
+}
+
+static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+{
+ return NULL;
}
static inline bool mm_match_cgroup(struct mm_struct *mm,
@@ -1138,6 +1210,11 @@
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)
{
@@ -1170,6 +1247,14 @@
__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 void mod_memcg_obj_state(void *p, int idx, int val)
{
}
@@ -1182,7 +1267,7 @@
return 0;
}
-static inline void mem_cgroup_split_huge_fixup(struct page *head)
+static inline void split_page_memcg(struct page *head, unsigned int nr)
{
}
@@ -1323,6 +1408,19 @@
mod_lruvec_page_state(page, idx, -1);
}
+static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
+{
+ struct mem_cgroup *memcg;
+
+ memcg = lruvec_memcg(lruvec);
+ if (!memcg)
+ return NULL;
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ return NULL;
+ return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
+}
+
#ifdef CONFIG_CGROUP_WRITEBACK
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
@@ -1409,19 +1507,19 @@
}
#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 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);
+int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
+ unsigned int nr_pages);
+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);
@@ -1437,35 +1535,36 @@
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 int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
+ int order)
{
if (memcg_kmem_enabled())
- return __memcg_kmem_charge(page, gfp, order);
+ return __memcg_kmem_charge_page(page, gfp, order);
return 0;
}
-static inline void memcg_kmem_uncharge(struct page *page, int order)
+static inline void memcg_kmem_uncharge_page(struct page *page, int order)
{
if (memcg_kmem_enabled())
- __memcg_kmem_uncharge(page, order);
+ __memcg_kmem_uncharge_page(page, order);
}
-static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp,
- int order, struct mem_cgroup *memcg)
+static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
+ unsigned int nr_pages)
{
if (memcg_kmem_enabled())
- return __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ return __memcg_kmem_charge(memcg, gfp, nr_pages);
return 0;
}
-static inline void memcg_kmem_uncharge_memcg(struct page *page, int order,
- struct mem_cgroup *memcg)
+static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg,
+ unsigned int nr_pages)
{
if (memcg_kmem_enabled())
- __memcg_kmem_uncharge_memcg(memcg, 1 << order);
+ __memcg_kmem_uncharge(memcg, nr_pages);
}
/*
@@ -1482,21 +1581,23 @@
#else
-static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
+ int order)
{
return 0;
}
-static inline void memcg_kmem_uncharge(struct page *page, int order)
+static inline void memcg_kmem_uncharge_page(struct page *page, int order)
{
}
-static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp,
+ int order)
{
return 0;
}
-static inline void __memcg_kmem_uncharge(struct page *page, int order)
+static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
{
}