blob: f29157288b7dd68a51ebf19f2d361aa66132d675 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/* memcontrol.c - Memory Controller
*
* Copyright IBM Corporation, 2007
* Author Balbir Singh <balbir@linux.vnet.ibm.com>
*
* Copyright 2007 OpenVZ SWsoft Inc
* Author: Pavel Emelianov <xemul@openvz.org>
*
* Memory thresholds
* Copyright (C) 2009 Nokia Corporation
* Author: Kirill A. Shutemov
*
* Kernel Memory Controller
* Copyright (C) 2012 Parallels Inc. and Google Inc.
* Authors: Glauber Costa and Suleiman Souhlal
*
* Native page reclaim
* Charge lifetime sanitation
* Lockless page tracking & accounting
* Unified hierarchy configuration model
* Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
*
* Per memcg lru locking
* Copyright (C) 2020 Alibaba, Inc, Alex Shi
*/
#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/vm_event_item.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/parser.h>
#include <linux/vmpressure.h>
#include <linux/memremap.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/resume_user_mode.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
#include <linux/sched/isolation.h>
#include <linux/kmemleak.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include "slab.h"
#include "memcontrol-v1.h"
#include <linux/uaccess.h>
#include <trace/events/vmscan.h>
struct cgroup_subsys memory_cgrp_subsys __read_mostly;
EXPORT_SYMBOL(memory_cgrp_subsys);
struct mem_cgroup *root_mem_cgroup __read_mostly;
/* Active memory cgroup to use from an interrupt context */
DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
/* Socket memory accounting disabled? */
static bool cgroup_memory_nosocket __ro_after_init;
/* Kernel memory accounting disabled? */
static bool cgroup_memory_nokmem __ro_after_init;
/* BPF memory accounting disabled? */
static bool cgroup_memory_nobpf __ro_after_init;
#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif
#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
static inline bool task_is_dying(void)
{
return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
(current->flags & PF_EXITING);
}
/* Some nice accessors for the vmpressure. */
struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
{
if (!memcg)
memcg = root_mem_cgroup;
return &memcg->vmpressure;
}
struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
{
return container_of(vmpr, struct mem_cgroup, vmpressure);
}
#define CURRENT_OBJCG_UPDATE_BIT 0
#define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT)
static DEFINE_SPINLOCK(objcg_lock);
bool mem_cgroup_kmem_disabled(void)
{
return cgroup_memory_nokmem;
}
static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
unsigned int nr_pages);
static void obj_cgroup_release(struct percpu_ref *ref)
{
struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
unsigned int nr_bytes;
unsigned int nr_pages;
unsigned long flags;
/*
* At this point all allocated objects are freed, and
* objcg->nr_charged_bytes can't have an arbitrary byte value.
* However, it can be PAGE_SIZE or (x * PAGE_SIZE).
*
* The following sequence can lead to it:
* 1) CPU0: objcg == stock->cached_objcg
* 2) CPU1: we do a small allocation (e.g. 92 bytes),
* PAGE_SIZE bytes are charged
* 3) CPU1: a process from another memcg is allocating something,
* the stock if flushed,
* objcg->nr_charged_bytes = PAGE_SIZE - 92
* 5) CPU0: we do release this object,
* 92 bytes are added to stock->nr_bytes
* 6) CPU0: stock is flushed,
* 92 bytes are added to objcg->nr_charged_bytes
*
* In the result, nr_charged_bytes == PAGE_SIZE.
* This page will be uncharged in obj_cgroup_release().
*/
nr_bytes = atomic_read(&objcg->nr_charged_bytes);
WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
nr_pages = nr_bytes >> PAGE_SHIFT;
if (nr_pages)
obj_cgroup_uncharge_pages(objcg, nr_pages);
spin_lock_irqsave(&objcg_lock, flags);
list_del(&objcg->list);
spin_unlock_irqrestore(&objcg_lock, flags);
percpu_ref_exit(ref);
kfree_rcu(objcg, rcu);
}
static struct obj_cgroup *obj_cgroup_alloc(void)
{
struct obj_cgroup *objcg;
int ret;
objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
if (!objcg)
return NULL;
ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
GFP_KERNEL);
if (ret) {
kfree(objcg);
return NULL;
}
INIT_LIST_HEAD(&objcg->list);
return objcg;
}
static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
struct mem_cgroup *parent)
{
struct obj_cgroup *objcg, *iter;
objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
spin_lock_irq(&objcg_lock);
/* 1) Ready to reparent active objcg. */
list_add(&objcg->list, &memcg->objcg_list);
/* 2) Reparent active objcg and already reparented objcgs to parent. */
list_for_each_entry(iter, &memcg->objcg_list, list)
WRITE_ONCE(iter->memcg, parent);
/* 3) Move already reparented objcgs to the parent's list */
list_splice(&memcg->objcg_list, &parent->objcg_list);
spin_unlock_irq(&objcg_lock);
percpu_ref_kill(&objcg->refcnt);
}
/*
* A lot of the calls to the cache allocation functions are expected to be
* inlined by the compiler. Since the calls to memcg_slab_post_alloc_hook() are
* conditional to this static branch, we'll have to allow modules that does
* kmem_cache_alloc and the such to see this symbol as well
*/
DEFINE_STATIC_KEY_FALSE(memcg_kmem_online_key);
EXPORT_SYMBOL(memcg_kmem_online_key);
DEFINE_STATIC_KEY_FALSE(memcg_bpf_enabled_key);
EXPORT_SYMBOL(memcg_bpf_enabled_key);
/**
* mem_cgroup_css_from_folio - css of the memcg associated with a folio
* @folio: folio of interest
*
* If memcg is bound to the default hierarchy, css of the memcg associated
* with @folio is returned. The returned css remains associated with @folio
* until it is released.
*
* If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
* is returned.
*/
struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio)
{
struct mem_cgroup *memcg = folio_memcg(folio);
if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg = root_mem_cgroup;
return &memcg->css;
}
/**
* page_cgroup_ino - return inode number of the memcg a page is charged to
* @page: the page
*
* Look up the closest online ancestor of the memory cgroup @page is charged to
* and return its inode number or 0 if @page is not charged to any cgroup. It
* is safe to call this function without holding a reference to @page.
*
* Note, this function is inherently racy, because there is nothing to prevent
* the cgroup inode from getting torn down and potentially reallocated a moment
* after page_cgroup_ino() returns, so it only should be used by callers that
* do not care (such as procfs interfaces).
*/
ino_t page_cgroup_ino(struct page *page)
{
struct mem_cgroup *memcg;
unsigned long ino = 0;
rcu_read_lock();
/* page_folio() is racy here, but the entire function is racy anyway */
memcg = folio_memcg_check(page_folio(page));
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg);
if (memcg)
ino = cgroup_ino(memcg->css.cgroup);
rcu_read_unlock();
return ino;
}
/* Subset of node_stat_item for memcg stats */
static const unsigned int memcg_node_stat_items[] = {
NR_INACTIVE_ANON,
NR_ACTIVE_ANON,
NR_INACTIVE_FILE,
NR_ACTIVE_FILE,
NR_UNEVICTABLE,
NR_SLAB_RECLAIMABLE_B,
NR_SLAB_UNRECLAIMABLE_B,
WORKINGSET_REFAULT_ANON,
WORKINGSET_REFAULT_FILE,
WORKINGSET_ACTIVATE_ANON,
WORKINGSET_ACTIVATE_FILE,
WORKINGSET_RESTORE_ANON,
WORKINGSET_RESTORE_FILE,
WORKINGSET_NODERECLAIM,
NR_ANON_MAPPED,
NR_FILE_MAPPED,
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
NR_SHMEM,
NR_SHMEM_THPS,
NR_FILE_THPS,
NR_ANON_THPS,
NR_KERNEL_STACK_KB,
NR_PAGETABLE,
NR_SECONDARY_PAGETABLE,
#ifdef CONFIG_SWAP
NR_SWAPCACHE,
#endif
};
static const unsigned int memcg_stat_items[] = {
MEMCG_SWAP,
MEMCG_SOCK,
MEMCG_PERCPU_B,
MEMCG_VMALLOC,
MEMCG_KMEM,
MEMCG_ZSWAP_B,
MEMCG_ZSWAPPED,
};
#define NR_MEMCG_NODE_STAT_ITEMS ARRAY_SIZE(memcg_node_stat_items)
#define MEMCG_VMSTAT_SIZE (NR_MEMCG_NODE_STAT_ITEMS + \
ARRAY_SIZE(memcg_stat_items))
static int8_t mem_cgroup_stats_index[MEMCG_NR_STAT] __read_mostly;
static void init_memcg_stats(void)
{
int8_t i, j = 0;
BUILD_BUG_ON(MEMCG_NR_STAT >= S8_MAX);
for (i = 0; i < NR_MEMCG_NODE_STAT_ITEMS; ++i)
mem_cgroup_stats_index[memcg_node_stat_items[i]] = ++j;
for (i = 0; i < ARRAY_SIZE(memcg_stat_items); ++i)
mem_cgroup_stats_index[memcg_stat_items[i]] = ++j;
}
static inline int memcg_stats_index(int idx)
{
return mem_cgroup_stats_index[idx] - 1;
}
struct lruvec_stats_percpu {
/* Local (CPU and cgroup) state */
long state[NR_MEMCG_NODE_STAT_ITEMS];
/* Delta calculation for lockless upward propagation */
long state_prev[NR_MEMCG_NODE_STAT_ITEMS];
};
struct lruvec_stats {
/* Aggregated (CPU and subtree) state */
long state[NR_MEMCG_NODE_STAT_ITEMS];
/* Non-hierarchical (CPU aggregated) state */
long state_local[NR_MEMCG_NODE_STAT_ITEMS];
/* Pending child counts during tree propagation */
long state_pending[NR_MEMCG_NODE_STAT_ITEMS];
};
unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
long x;
int i;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
i = memcg_stats_index(idx);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return 0;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
x = READ_ONCE(pn->lruvec_stats->state[i]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
long x;
int i;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
i = memcg_stats_index(idx);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return 0;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
x = READ_ONCE(pn->lruvec_stats->state_local[i]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
/* Subset of vm_event_item to report for memcg event stats */
static const unsigned int memcg_vm_event_stat[] = {
PGPGIN,
PGPGOUT,
PGSCAN_KSWAPD,
PGSCAN_DIRECT,
PGSCAN_KHUGEPAGED,
PGSTEAL_KSWAPD,
PGSTEAL_DIRECT,
PGSTEAL_KHUGEPAGED,
PGFAULT,
PGMAJFAULT,
PGREFILL,
PGACTIVATE,
PGDEACTIVATE,
PGLAZYFREE,
PGLAZYFREED,
#ifdef CONFIG_ZSWAP
ZSWPIN,
ZSWPOUT,
ZSWPWB,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
THP_FAULT_ALLOC,
THP_COLLAPSE_ALLOC,
THP_SWPOUT,
THP_SWPOUT_FALLBACK,
#endif
};
#define NR_MEMCG_EVENTS ARRAY_SIZE(memcg_vm_event_stat)
static int8_t mem_cgroup_events_index[NR_VM_EVENT_ITEMS] __read_mostly;
static void init_memcg_events(void)
{
int8_t i;
BUILD_BUG_ON(NR_VM_EVENT_ITEMS >= S8_MAX);
for (i = 0; i < NR_MEMCG_EVENTS; ++i)
mem_cgroup_events_index[memcg_vm_event_stat[i]] = i + 1;
}
static inline int memcg_events_index(enum vm_event_item idx)
{
return mem_cgroup_events_index[idx] - 1;
}
struct memcg_vmstats_percpu {
/* Stats updates since the last flush */
unsigned int stats_updates;
/* Cached pointers for fast iteration in memcg_rstat_updated() */
struct memcg_vmstats_percpu *parent;
struct memcg_vmstats *vmstats;
/* The above should fit a single cacheline for memcg_rstat_updated() */
/* Local (CPU and cgroup) page state & events */
long state[MEMCG_VMSTAT_SIZE];
unsigned long events[NR_MEMCG_EVENTS];
/* Delta calculation for lockless upward propagation */
long state_prev[MEMCG_VMSTAT_SIZE];
unsigned long events_prev[NR_MEMCG_EVENTS];
/* Cgroup1: threshold notifications & softlimit tree updates */
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
} ____cacheline_aligned;
struct memcg_vmstats {
/* Aggregated (CPU and subtree) page state & events */
long state[MEMCG_VMSTAT_SIZE];
unsigned long events[NR_MEMCG_EVENTS];
/* Non-hierarchical (CPU aggregated) page state & events */
long state_local[MEMCG_VMSTAT_SIZE];
unsigned long events_local[NR_MEMCG_EVENTS];
/* Pending child counts during tree propagation */
long state_pending[MEMCG_VMSTAT_SIZE];
unsigned long events_pending[NR_MEMCG_EVENTS];
/* Stats updates since the last flush */
atomic64_t stats_updates;
};
/*
* memcg and lruvec stats flushing
*
* Many codepaths leading to stats update or read are performance sensitive and
* adding stats flushing in such codepaths is not desirable. So, to optimize the
* flushing the kernel does:
*
* 1) Periodically and asynchronously flush the stats every 2 seconds to not let
* rstat update tree grow unbounded.
*
* 2) Flush the stats synchronously on reader side only when there are more than
* (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
* will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
* only for 2 seconds due to (1).
*/
static void flush_memcg_stats_dwork(struct work_struct *w);
static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
static u64 flush_last_time;
#define FLUSH_TIME (2UL*HZ)
/*
* Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
* not rely on this as part of an acquired spinlock_t lock. These functions are
* never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
* is sufficient.
*/
static void memcg_stats_lock(void)
{
preempt_disable_nested();
VM_WARN_ON_IRQS_ENABLED();
}
static void __memcg_stats_lock(void)
{
preempt_disable_nested();
}
static void memcg_stats_unlock(void)
{
preempt_enable_nested();
}
static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
{
return atomic64_read(&vmstats->stats_updates) >
MEMCG_CHARGE_BATCH * num_online_cpus();
}
static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
{
struct memcg_vmstats_percpu *statc;
int cpu = smp_processor_id();
unsigned int stats_updates;
if (!val)
return;
cgroup_rstat_updated(memcg->css.cgroup, cpu);
statc = this_cpu_ptr(memcg->vmstats_percpu);
for (; statc; statc = statc->parent) {
stats_updates = READ_ONCE(statc->stats_updates) + abs(val);
WRITE_ONCE(statc->stats_updates, stats_updates);
if (stats_updates < MEMCG_CHARGE_BATCH)
continue;
/*
* If @memcg is already flush-able, increasing stats_updates is
* redundant. Avoid the overhead of the atomic update.
*/
if (!memcg_vmstats_needs_flush(statc->vmstats))
atomic64_add(stats_updates,
&statc->vmstats->stats_updates);
WRITE_ONCE(statc->stats_updates, 0);
}
}
static void do_flush_stats(struct mem_cgroup *memcg)
{
if (mem_cgroup_is_root(memcg))
WRITE_ONCE(flush_last_time, jiffies_64);
cgroup_rstat_flush(memcg->css.cgroup);
}
/*
* mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree
* @memcg: root of the subtree to flush
*
* Flushing is serialized by the underlying global rstat lock. There is also a
* minimum amount of work to be done even if there are no stat updates to flush.
* Hence, we only flush the stats if the updates delta exceeds a threshold. This
* avoids unnecessary work and contention on the underlying lock.
*/
void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return;
if (!memcg)
memcg = root_mem_cgroup;
if (memcg_vmstats_needs_flush(memcg->vmstats))
do_flush_stats(memcg);
}
void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
{
/* Only flush if the periodic flusher is one full cycle late */
if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
mem_cgroup_flush_stats(memcg);
}
static void flush_memcg_stats_dwork(struct work_struct *w)
{
/*
* Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
* in latency-sensitive paths is as cheap as possible.
*/
do_flush_stats(root_mem_cgroup);
queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
}
unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{
long x;
int i = memcg_stats_index(idx);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return 0;
x = READ_ONCE(memcg->vmstats->state[i]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static int memcg_page_state_unit(int item);
/*
* Normalize the value passed into memcg_rstat_updated() to be in pages. Round
* up non-zero sub-page updates to 1 page as zero page updates are ignored.
*/
static int memcg_state_val_in_pages(int idx, int val)
{
int unit = memcg_page_state_unit(idx);
if (!val || unit == PAGE_SIZE)
return val;
else
return max(val * unit / PAGE_SIZE, 1UL);
}
/**
* __mod_memcg_state - update cgroup memory statistics
* @memcg: the memory cgroup
* @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
* @val: delta to add to the counter, can be negative
*/
void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
int val)
{
int i = memcg_stats_index(idx);
if (mem_cgroup_disabled())
return;
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return;
__this_cpu_add(memcg->vmstats_percpu->state[i], val);
memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val));
}
/* idx can be of type enum memcg_stat_item or node_stat_item. */
unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
{
long x;
int i = memcg_stats_index(idx);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return 0;
x = READ_ONCE(memcg->vmstats->state_local[i]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static void __mod_memcg_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx,
int val)
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup *memcg;
int i = memcg_stats_index(idx);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
memcg = pn->memcg;
/*
* The caller from rmap relies on disabled preemption because they never
* update their counter from in-interrupt context. For these two
* counters we check that the update is never performed from an
* interrupt context while other caller need to have disabled interrupt.
*/
__memcg_stats_lock();
if (IS_ENABLED(CONFIG_DEBUG_VM)) {
switch (idx) {
case NR_ANON_MAPPED:
case NR_FILE_MAPPED:
case NR_ANON_THPS:
WARN_ON_ONCE(!in_task());
break;
default:
VM_WARN_ON_IRQS_ENABLED();
}
}
/* Update memcg */
__this_cpu_add(memcg->vmstats_percpu->state[i], val);
/* Update lruvec */
__this_cpu_add(pn->lruvec_stats_percpu->state[i], val);
memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val));
memcg_stats_unlock();
}
/**
* __mod_lruvec_state - update lruvec memory statistics
* @lruvec: the lruvec
* @idx: the stat item
* @val: delta to add to the counter, can be negative
*
* The lruvec is the intersection of the NUMA node and a cgroup. This
* function updates the all three counters that are affected by a
* change of state at this level: per-node, per-cgroup, per-lruvec.
*/
void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val)
{
/* Update node */
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
/* Update memcg and lruvec */
if (!mem_cgroup_disabled())
__mod_memcg_lruvec_state(lruvec, idx, val);
}
void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx,
int val)
{
struct mem_cgroup *memcg;
pg_data_t *pgdat = folio_pgdat(folio);
struct lruvec *lruvec;
rcu_read_lock();
memcg = folio_memcg(folio);
/* Untracked pages have no memcg, no lruvec. Update only the node */
if (!memcg) {
rcu_read_unlock();
__mod_node_page_state(pgdat, idx, val);
return;
}
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
rcu_read_unlock();
}
EXPORT_SYMBOL(__lruvec_stat_mod_folio);
void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
{
pg_data_t *pgdat = page_pgdat(virt_to_page(p));
struct mem_cgroup *memcg;
struct lruvec *lruvec;
rcu_read_lock();
memcg = mem_cgroup_from_slab_obj(p);
/*
* Untracked pages have no memcg, no lruvec. Update only the
* node. If we reparent the slab objects to the root memcg,
* when we free the slab object, we need to update the per-memcg
* vmstats to keep it correct for the root memcg.
*/
if (!memcg) {
__mod_node_page_state(pgdat, idx, val);
} else {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
rcu_read_unlock();
}
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
* @idx: the event item
* @count: the number of events that occurred
*/
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
unsigned long count)
{
int i = memcg_events_index(idx);
if (mem_cgroup_disabled())
return;
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
return;
memcg_stats_lock();
__this_cpu_add(memcg->vmstats_percpu->events[i], count);
memcg_rstat_updated(memcg, count);
memcg_stats_unlock();
}
unsigned long memcg_events(struct mem_cgroup *memcg, int event)
{
int i = memcg_events_index(event);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, event))
return 0;
return READ_ONCE(memcg->vmstats->events[i]);
}
unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
{
int i = memcg_events_index(event);
if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, event))
return 0;
return READ_ONCE(memcg->vmstats->events_local[i]);
}
void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, int nr_pages)
{
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
__count_memcg_events(memcg, PGPGIN, 1);
else {
__count_memcg_events(memcg, PGPGOUT, 1);
nr_pages = -nr_pages; /* for event */
}
__this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages);
}
bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
enum mem_cgroup_events_target target)
{
unsigned long val, next;
val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events);
next = __this_cpu_read(memcg->vmstats_percpu->targets[target]);
/* from time_after() in jiffies.h */
if ((long)(next - val) < 0) {
switch (target) {
case MEM_CGROUP_TARGET_THRESH:
next = val + THRESHOLDS_EVENTS_TARGET;
break;
case MEM_CGROUP_TARGET_SOFTLIMIT:
next = val + SOFTLIMIT_EVENTS_TARGET;
break;
default:
break;
}
__this_cpu_write(memcg->vmstats_percpu->targets[target], next);
return true;
}
return false;
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
/*
* mm_update_next_owner() may clear mm->owner to NULL
* if it races with swapoff, page migration, etc.
* So this can be called with p == NULL.
*/
if (unlikely(!p))
return NULL;
return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
}
EXPORT_SYMBOL(mem_cgroup_from_task);
static __always_inline struct mem_cgroup *active_memcg(void)
{
if (!in_task())
return this_cpu_read(int_active_memcg);
else
return current->active_memcg;
}
/**
* get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg.
* @mm: mm from which memcg should be extracted. It can be NULL.
*
* Obtain a reference on mm->memcg and returns it if successful. If mm
* is NULL, then the memcg is chosen as follows:
* 1) The active memcg, if set.
* 2) current->mm->memcg, if available
* 3) root memcg
* If mem_cgroup is disabled, NULL is returned.
*/
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return NULL;
/*
* Page cache insertions can happen without an
* actual mm context, e.g. during disk probing
* on boot, loopback IO, acct() writes etc.
*
* No need to css_get on root memcg as the reference
* counting is disabled on the root level in the
* cgroup core. See CSS_NO_REF.
*/
if (unlikely(!mm)) {
memcg = active_memcg();
if (unlikely(memcg)) {
/* remote memcg must hold a ref */
css_get(&memcg->css);
return memcg;
}
mm = current->mm;
if (unlikely(!mm))
return root_mem_cgroup;
}
rcu_read_lock();
do {
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (unlikely(!memcg))
memcg = root_mem_cgroup;
} while (!css_tryget(&memcg->css));
rcu_read_unlock();
return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);
/**
* get_mem_cgroup_from_current - Obtain a reference on current task's memcg.
*/
struct mem_cgroup *get_mem_cgroup_from_current(void)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return NULL;
again:
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
if (!css_tryget(&memcg->css)) {
rcu_read_unlock();
goto again;
}
rcu_read_unlock();
return memcg;
}
/**
* mem_cgroup_iter - iterate over memory cgroup hierarchy
* @root: hierarchy root
* @prev: previously returned memcg, NULL on first invocation
* @reclaim: cookie for shared reclaim walks, NULL for full walks
*
* Returns references to children of the hierarchy below @root, or
* @root itself, or %NULL after a full round-trip.
*
* Caller must pass the return value in @prev on subsequent
* invocations for reference counting, or use mem_cgroup_iter_break()
* to cancel a hierarchy walk before the round-trip is complete.
*
* Reclaimers can specify a node in @reclaim to divide up the memcgs
* in the hierarchy among all concurrent reclaimers operating on the
* same node.
*/
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
struct mem_cgroup *prev,
struct mem_cgroup_reclaim_cookie *reclaim)
{
struct mem_cgroup_reclaim_iter *iter;
struct cgroup_subsys_state *css = NULL;
struct mem_cgroup *memcg = NULL;
struct mem_cgroup *pos = NULL;
if (mem_cgroup_disabled())
return NULL;
if (!root)
root = root_mem_cgroup;
rcu_read_lock();
if (reclaim) {
struct mem_cgroup_per_node *mz;
mz = root->nodeinfo[reclaim->pgdat->node_id];
iter = &mz->iter;
/*
* On start, join the current reclaim iteration cycle.
* Exit when a concurrent walker completes it.
*/
if (!prev)
reclaim->generation = iter->generation;
else if (reclaim->generation != iter->generation)
goto out_unlock;
while (1) {
pos = READ_ONCE(iter->position);
if (!pos || css_tryget(&pos->css))
break;
/*
* css reference reached zero, so iter->position will
* be cleared by ->css_released. However, we should not
* rely on this happening soon, because ->css_released
* is called from a work queue, and by busy-waiting we
* might block it. So we clear iter->position right
* away.
*/
(void)cmpxchg(&iter->position, pos, NULL);
}
} else if (prev) {
pos = prev;
}
if (pos)
css = &pos->css;
for (;;) {
css = css_next_descendant_pre(css, &root->css);
if (!css) {
/*
* Reclaimers share the hierarchy walk, and a
* new one might jump in right at the end of
* the hierarchy - make sure they see at least
* one group and restart from the beginning.
*/
if (!prev)
continue;
break;
}
/*
* Verify the css and acquire a reference. The root
* is provided by the caller, so we know it's alive
* and kicking, and don't take an extra reference.
*/
if (css == &root->css || css_tryget(css)) {
memcg = mem_cgroup_from_css(css);
break;
}
}
if (reclaim) {
/*
* The position could have already been updated by a competing
* thread, so check that the value hasn't changed since we read
* it to avoid reclaiming from the same cgroup twice.
*/
(void)cmpxchg(&iter->position, pos, memcg);
if (pos)
css_put(&pos->css);
if (!memcg)
iter->generation++;
}
out_unlock:
rcu_read_unlock();
if (prev && prev != root)
css_put(&prev->css);
return memcg;
}
/**
* mem_cgroup_iter_break - abort a hierarchy walk prematurely
* @root: hierarchy root
* @prev: last visited hierarchy member as returned by mem_cgroup_iter()
*/
void mem_cgroup_iter_break(struct mem_cgroup *root,
struct mem_cgroup *prev)
{
if (!root)
root = root_mem_cgroup;
if (prev && prev != root)
css_put(&prev->css);
}
static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
struct mem_cgroup *dead_memcg)
{
struct mem_cgroup_reclaim_iter *iter;
struct mem_cgroup_per_node *mz;
int nid;
for_each_node(nid) {
mz = from->nodeinfo[nid];
iter = &mz->iter;
cmpxchg(&iter->position, dead_memcg, NULL);
}
}
static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
{
struct mem_cgroup *memcg = dead_memcg;
struct mem_cgroup *last;
do {
__invalidate_reclaim_iterators(memcg, dead_memcg);
last = memcg;
} while ((memcg = parent_mem_cgroup(memcg)));
/*
* When cgroup1 non-hierarchy mode is used,
* parent_mem_cgroup() does not walk all the way up to the
* cgroup root (root_mem_cgroup). So we have to handle
* dead_memcg from cgroup root separately.
*/
if (!mem_cgroup_is_root(last))
__invalidate_reclaim_iterators(root_mem_cgroup,
dead_memcg);
}
/**
* mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
* @memcg: hierarchy root
* @fn: function to call for each task
* @arg: argument passed to @fn
*
* This function iterates over tasks attached to @memcg or to any of its
* descendants and calls @fn for each task. If @fn returns a non-zero
* value, the function breaks the iteration loop. Otherwise, it will iterate
* over all tasks and return 0.
*
* This function must not be called for the root memory cgroup.
*/
void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
int (*fn)(struct task_struct *, void *), void *arg)
{
struct mem_cgroup *iter;
int ret = 0;
BUG_ON(mem_cgroup_is_root(memcg));
for_each_mem_cgroup_tree(iter, memcg) {
struct css_task_iter it;
struct task_struct *task;
css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
while (!ret && (task = css_task_iter_next(&it)))
ret = fn(task, arg);
css_task_iter_end(&it);
if (ret) {
mem_cgroup_iter_break(memcg, iter);
break;
}
}
}
#ifdef CONFIG_DEBUG_VM
void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
memcg = folio_memcg(folio);
if (!memcg)
VM_BUG_ON_FOLIO(!mem_cgroup_is_root(lruvec_memcg(lruvec)), folio);
else
VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
}
#endif
/**
* folio_lruvec_lock - Lock the lruvec for a folio.
* @folio: Pointer to the folio.
*
* These functions are safe to use under any of the following conditions:
* - folio locked
* - folio_test_lru false
* - folio_memcg_lock()
* - folio frozen (refcount of 0)
*
* Return: The lruvec this folio is on with its lock held.
*/
struct lruvec *folio_lruvec_lock(struct folio *folio)
{
struct lruvec *lruvec = folio_lruvec(folio);
spin_lock(&lruvec->lru_lock);
lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
/**
* folio_lruvec_lock_irq - Lock the lruvec for a folio.
* @folio: Pointer to the folio.
*
* These functions are safe to use under any of the following conditions:
* - folio locked
* - folio_test_lru false
* - folio_memcg_lock()
* - folio frozen (refcount of 0)
*
* Return: The lruvec this folio is on with its lock held and interrupts
* disabled.
*/
struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
struct lruvec *lruvec = folio_lruvec(folio);
spin_lock_irq(&lruvec->lru_lock);
lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
/**
* folio_lruvec_lock_irqsave - Lock the lruvec for a folio.
* @folio: Pointer to the folio.
* @flags: Pointer to irqsave flags.
*
* These functions are safe to use under any of the following conditions:
* - folio locked
* - folio_test_lru false
* - folio_memcg_lock()
* - folio frozen (refcount of 0)
*
* Return: The lruvec this folio is on with its lock held and interrupts
* disabled.
*/
struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags)
{
struct lruvec *lruvec = folio_lruvec(folio);
spin_lock_irqsave(&lruvec->lru_lock, *flags);
lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
/**
* mem_cgroup_update_lru_size - account for adding or removing an lru page
* @lruvec: mem_cgroup per zone lru vector
* @lru: index of lru list the page is sitting on
* @zid: zone id of the accounted pages
* @nr_pages: positive when adding or negative when removing
*
* This function must be called under lru_lock, just before a page is added
* to or just after a page is removed from an lru list.
*/
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zid, int nr_pages)
{
struct mem_cgroup_per_node *mz;
unsigned long *lru_size;
long size;
if (mem_cgroup_disabled())
return;
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
lru_size = &mz->lru_zone_size[zid][lru];
if (nr_pages < 0)
*lru_size += nr_pages;
size = *lru_size;
if (WARN_ONCE(size < 0,
"%s(%p, %d, %d): lru_size %ld\n",
__func__, lruvec, lru, nr_pages, size)) {
VM_BUG_ON(1);
*lru_size = 0;
}
if (nr_pages > 0)
*lru_size += nr_pages;
}
/**
* mem_cgroup_margin - calculate chargeable space of a memory cgroup
* @memcg: the memory cgroup
*
* Returns the maximum amount of memory @mem can be charged with, in
* pages.
*/
static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
{
unsigned long margin = 0;
unsigned long count;
unsigned long limit;
count = page_counter_read(&memcg->memory);
limit = READ_ONCE(memcg->memory.max);
if (count < limit)
margin = limit - count;
if (do_memsw_account()) {
count = page_counter_read(&memcg->memsw);
limit = READ_ONCE(memcg->memsw.max);
if (count < limit)
margin = min(margin, limit - count);
else
margin = 0;
}
return margin;
}
struct memory_stat {
const char *name;
unsigned int idx;
};
static const struct memory_stat memory_stats[] = {
{ "anon", NR_ANON_MAPPED },
{ "file", NR_FILE_PAGES },
{ "kernel", MEMCG_KMEM },
{ "kernel_stack", NR_KERNEL_STACK_KB },
{ "pagetables", NR_PAGETABLE },
{ "sec_pagetables", NR_SECONDARY_PAGETABLE },
{ "percpu", MEMCG_PERCPU_B },
{ "sock", MEMCG_SOCK },
{ "vmalloc", MEMCG_VMALLOC },
{ "shmem", NR_SHMEM },
#ifdef CONFIG_ZSWAP
{ "zswap", MEMCG_ZSWAP_B },
{ "zswapped", MEMCG_ZSWAPPED },
#endif
{ "file_mapped", NR_FILE_MAPPED },
{ "file_dirty", NR_FILE_DIRTY },
{ "file_writeback", NR_WRITEBACK },
#ifdef CONFIG_SWAP
{ "swapcached", NR_SWAPCACHE },
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
{ "anon_thp", NR_ANON_THPS },
{ "file_thp", NR_FILE_THPS },
{ "shmem_thp", NR_SHMEM_THPS },
#endif
{ "inactive_anon", NR_INACTIVE_ANON },
{ "active_anon", NR_ACTIVE_ANON },
{ "inactive_file", NR_INACTIVE_FILE },
{ "active_file", NR_ACTIVE_FILE },
{ "unevictable", NR_UNEVICTABLE },
{ "slab_reclaimable", NR_SLAB_RECLAIMABLE_B },
{ "slab_unreclaimable", NR_SLAB_UNRECLAIMABLE_B },
/* The memory events */
{ "workingset_refault_anon", WORKINGSET_REFAULT_ANON },
{ "workingset_refault_file", WORKINGSET_REFAULT_FILE },
{ "workingset_activate_anon", WORKINGSET_ACTIVATE_ANON },
{ "workingset_activate_file", WORKINGSET_ACTIVATE_FILE },
{ "workingset_restore_anon", WORKINGSET_RESTORE_ANON },
{ "workingset_restore_file", WORKINGSET_RESTORE_FILE },
{ "workingset_nodereclaim", WORKINGSET_NODERECLAIM },
};
/* The actual unit of the state item, not the same as the output unit */
static int memcg_page_state_unit(int item)
{
switch (item) {
case MEMCG_PERCPU_B:
case MEMCG_ZSWAP_B:
case NR_SLAB_RECLAIMABLE_B:
case NR_SLAB_UNRECLAIMABLE_B:
return 1;
case NR_KERNEL_STACK_KB:
return SZ_1K;
default:
return PAGE_SIZE;
}
}
/* Translate stat items to the correct unit for memory.stat output */
static int memcg_page_state_output_unit(int item)
{
/*
* Workingset state is actually in pages, but we export it to userspace
* as a scalar count of events, so special case it here.
*/
switch (item) {
case WORKINGSET_REFAULT_ANON:
case WORKINGSET_REFAULT_FILE:
case WORKINGSET_ACTIVATE_ANON:
case WORKINGSET_ACTIVATE_FILE:
case WORKINGSET_RESTORE_ANON:
case WORKINGSET_RESTORE_FILE:
case WORKINGSET_NODERECLAIM:
return 1;
default:
return memcg_page_state_unit(item);
}
}
unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item)
{
return memcg_page_state(memcg, item) *
memcg_page_state_output_unit(item);
}
unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item)
{
return memcg_page_state_local(memcg, item) *
memcg_page_state_output_unit(item);
}
static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
int i;
/*
* Provide statistics on the state of the memory subsystem as
* well as cumulative event counters that show past behavior.
*
* This list is ordered following a combination of these gradients:
* 1) generic big picture -> specifics and details
* 2) reflecting userspace activity -> reflecting kernel heuristics
*
* Current memory state:
*/
mem_cgroup_flush_stats(memcg);
for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
u64 size;
size = memcg_page_state_output(memcg, memory_stats[i].idx);
seq_buf_printf(s, "%s %llu\n", memory_stats[i].name, size);
if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) {
size += memcg_page_state_output(memcg,
NR_SLAB_RECLAIMABLE_B);
seq_buf_printf(s, "slab %llu\n", size);
}
}
/* Accumulated memory events */
seq_buf_printf(s, "pgscan %lu\n",
memcg_events(memcg, PGSCAN_KSWAPD) +
memcg_events(memcg, PGSCAN_DIRECT) +
memcg_events(memcg, PGSCAN_KHUGEPAGED));
seq_buf_printf(s, "pgsteal %lu\n",
memcg_events(memcg, PGSTEAL_KSWAPD) +
memcg_events(memcg, PGSTEAL_DIRECT) +
memcg_events(memcg, PGSTEAL_KHUGEPAGED));
for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) {
if (memcg_vm_event_stat[i] == PGPGIN ||
memcg_vm_event_stat[i] == PGPGOUT)
continue;
seq_buf_printf(s, "%s %lu\n",
vm_event_name(memcg_vm_event_stat[i]),
memcg_events(memcg, memcg_vm_event_stat[i]));
}
}
static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg_stat_format(memcg, s);
else
memcg1_stat_format(memcg, s);
if (seq_buf_has_overflowed(s))
pr_warn("%s: Warning, stat buffer overflow, please report\n", __func__);
}
/**
* mem_cgroup_print_oom_context: Print OOM information relevant to
* memory controller.
* @memcg: The memory cgroup that went over limit
* @p: Task that is going to be killed
*
* NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
* enabled
*/
void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
{
rcu_read_lock();
if (memcg) {
pr_cont(",oom_memcg=");
pr_cont_cgroup_path(memcg->css.cgroup);
} else
pr_cont(",global_oom");
if (p) {
pr_cont(",task_memcg=");
pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
}
rcu_read_unlock();
}
/**
* mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
* memory controller.
* @memcg: The memory cgroup that went over limit
*/
void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{
/* Use static buffer, for the caller is holding oom_lock. */
static char buf[PAGE_SIZE];
struct seq_buf s;
lockdep_assert_held(&oom_lock);
pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
K((u64)page_counter_read(&memcg->memory)),
K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt);
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n",
K((u64)page_counter_read(&memcg->swap)),
K((u64)READ_ONCE(memcg->swap.max)), memcg->swap.failcnt);
#ifdef CONFIG_MEMCG_V1
else {
pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
K((u64)page_counter_read(&memcg->memsw)),
K((u64)memcg->memsw.max), memcg->memsw.failcnt);
pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
K((u64)page_counter_read(&memcg->kmem)),
K((u64)memcg->kmem.max), memcg->kmem.failcnt);
}
#endif
pr_info("Memory cgroup stats for ");
pr_cont_cgroup_path(memcg->css.cgroup);
pr_cont(":");
seq_buf_init(&s, buf, sizeof(buf));
memory_stat_format(memcg, &s);
seq_buf_do_printk(&s, KERN_INFO);
}
/*
* Return the memory (and swap, if configured) limit for a memcg.
*/
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
unsigned long max = READ_ONCE(memcg->memory.max);
if (do_memsw_account()) {
if (mem_cgroup_swappiness(memcg)) {
/* Calculate swap excess capacity from memsw limit */
unsigned long swap = READ_ONCE(memcg->memsw.max) - max;
max += min(swap, (unsigned long)total_swap_pages);
}
} else {
if (mem_cgroup_swappiness(memcg))
max += min(READ_ONCE(memcg->swap.max),
(unsigned long)total_swap_pages);
}
return max;
}
unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
{
return page_counter_read(&memcg->memory);
}
static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
int order)
{
struct oom_control oc = {
.zonelist = NULL,
.nodemask = NULL,
.memcg = memcg,
.gfp_mask = gfp_mask,
.order = order,
};
bool ret = true;
if (mutex_lock_killable(&oom_lock))
return true;
if (mem_cgroup_margin(memcg) >= (1 << order))
goto unlock;
/*
* A few threads which were not waiting at mutex_lock_killable() can
* fail to bail out. Therefore, check again after holding oom_lock.
*/
ret = task_is_dying() || out_of_memory(&oc);
unlock:
mutex_unlock(&oom_lock);
return ret;
}
/*
* Returns true if successfully killed one or more processes. Though in some
* corner cases it can return true even without killing any process.
*/
static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
bool locked, ret;
if (order > PAGE_ALLOC_COSTLY_ORDER)
return false;
memcg_memory_event(memcg, MEMCG_OOM);
if (!memcg1_oom_prepare(memcg, &locked))
return false;
ret = mem_cgroup_out_of_memory(memcg, mask, order);
memcg1_oom_finish(memcg, locked);
return ret;
}
/**
* mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM
* @victim: task to be killed by the OOM killer
* @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM
*
* Returns a pointer to a memory cgroup, which has to be cleaned up
* by killing all belonging OOM-killable tasks.
*
* Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
*/
struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
struct mem_cgroup *oom_domain)
{
struct mem_cgroup *oom_group = NULL;
struct mem_cgroup *memcg;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
return NULL;
if (!oom_domain)
oom_domain = root_mem_cgroup;
rcu_read_lock();
memcg = mem_cgroup_from_task(victim);
if (mem_cgroup_is_root(memcg))
goto out;
/*
* If the victim task has been asynchronously moved to a different
* memory cgroup, we might end up killing tasks outside oom_domain.
* In this case it's better to ignore memory.group.oom.
*/
if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain)))
goto out;
/*
* Traverse the memory cgroup hierarchy from the victim task's
* cgroup up to the OOMing cgroup (or root) to find the
* highest-level memory cgroup with oom.group set.
*/
for (; memcg; memcg = parent_mem_cgroup(memcg)) {
if (READ_ONCE(memcg->oom_group))
oom_group = memcg;
if (memcg == oom_domain)
break;
}
if (oom_group)
css_get(&oom_group->css);
out:
rcu_read_unlock();
return oom_group;
}
void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
{
pr_info("Tasks in ");
pr_cont_cgroup_path(memcg->css.cgroup);
pr_cont(" are going to be killed due to memory.oom.group set\n");
}
struct memcg_stock_pcp {
local_lock_t stock_lock;
struct mem_cgroup *cached; /* this never be root cgroup */
unsigned int nr_pages;
struct obj_cgroup *cached_objcg;
struct pglist_data *cached_pgdat;
unsigned int nr_bytes;
int nr_slab_reclaimable_b;
int nr_slab_unreclaimable_b;
struct work_struct work;
unsigned long flags;
#define FLUSHING_CACHED_CHARGE 0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
.stock_lock = INIT_LOCAL_LOCK(stock_lock),
};
static DEFINE_MUTEX(percpu_charge_mutex);
static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock);
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
struct mem_cgroup *root_memcg);
/**
* consume_stock: Try to consume stocked charge on this cpu.
* @memcg: memcg to consume from.
* @nr_pages: how many pages to charge.
*
* The charges will only happen if @memcg matches the current cpu's memcg
* stock, and at least @nr_pages are available in that stock. Failure to
* service an allocation will refill the stock.
*
* returns true if successful, false otherwise.
*/
static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock;
unsigned int stock_pages;
unsigned long flags;
bool ret = false;
if (nr_pages > MEMCG_CHARGE_BATCH)
return ret;
local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
stock_pages = READ_ONCE(stock->nr_pages);
if (memcg == READ_ONCE(stock->cached) && stock_pages >= nr_pages) {
WRITE_ONCE(stock->nr_pages, stock_pages - nr_pages);
ret = true;
}
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
/*
* Returns stocks cached in percpu and reset cached information.
*/
static void drain_stock(struct memcg_stock_pcp *stock)
{
unsigned int stock_pages = READ_ONCE(stock->nr_pages);
struct mem_cgroup *old = READ_ONCE(stock->cached);
if (!old)
return;
if (stock_pages) {
page_counter_uncharge(&old->memory, stock_pages);
if (do_memsw_account())
page_counter_uncharge(&old->memsw, stock_pages);
WRITE_ONCE(stock->nr_pages, 0);
}
css_put(&old->css);
WRITE_ONCE(stock->cached, NULL);
}
static void drain_local_stock(struct work_struct *dummy)
{
struct memcg_stock_pcp *stock;
struct obj_cgroup *old = NULL;
unsigned long flags;
/*
* The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
* drain_stock races is that we always operate on local CPU stock
* here with IRQ disabled
*/
local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
old = drain_obj_stock(stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
}
/*
* Cache charges(val) to local per_cpu area.
* This will be consumed by consume_stock() function, later.
*/
static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock;
unsigned int stock_pages;
stock = this_cpu_ptr(&memcg_stock);
if (READ_ONCE(stock->cached) != memcg) { /* reset if necessary */
drain_stock(stock);
css_get(&memcg->css);
WRITE_ONCE(stock->cached, memcg);
}
stock_pages = READ_ONCE(stock->nr_pages) + nr_pages;
WRITE_ONCE(stock->nr_pages, stock_pages);
if (stock_pages > MEMCG_CHARGE_BATCH)
drain_stock(stock);
}
static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
unsigned long flags;
local_lock_irqsave(&memcg_stock.stock_lock, flags);
__refill_stock(memcg, nr_pages);
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
}
/*
* Drains all per-CPU charge caches for given root_memcg resp. subtree
* of the hierarchy under it.
*/
void drain_all_stock(struct mem_cgroup *root_memcg)
{
int cpu, curcpu;
/* If someone's already draining, avoid adding running more workers. */
if (!mutex_trylock(&percpu_charge_mutex))
return;
/*
* Notify other cpus that system-wide "drain" is running
* We do not care about races with the cpu hotplug because cpu down
* as well as workers from this path always operate on the local
* per-cpu data. CPU up doesn't touch memcg_stock at all.
*/
migrate_disable();
curcpu = smp_processor_id();
for_each_online_cpu(cpu) {
struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
struct mem_cgroup *memcg;
bool flush = false;
rcu_read_lock();
memcg = READ_ONCE(stock->cached);
if (memcg && READ_ONCE(stock->nr_pages) &&
mem_cgroup_is_descendant(memcg, root_memcg))
flush = true;
else if (obj_stock_flush_required(stock, root_memcg))
flush = true;
rcu_read_unlock();
if (flush &&
!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
if (cpu == curcpu)
drain_local_stock(&stock->work);
else if (!cpu_is_isolated(cpu))
schedule_work_on(cpu, &stock->work);
}
}
migrate_enable();
mutex_unlock(&percpu_charge_mutex);
}
static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
struct memcg_stock_pcp *stock;
stock = &per_cpu(memcg_stock, cpu);
drain_stock(stock);
return 0;
}
static unsigned long reclaim_high(struct mem_cgroup *memcg,
unsigned int nr_pages,
gfp_t gfp_mask)
{
unsigned long nr_reclaimed = 0;
do {
unsigned long pflags;
if (page_counter_read(&memcg->memory) <=
READ_ONCE(memcg->memory.high))
continue;
memcg_memory_event(memcg, MEMCG_HIGH);
psi_memstall_enter(&pflags);
nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
gfp_mask,
MEMCG_RECLAIM_MAY_SWAP,
NULL);
psi_memstall_leave(&pflags);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
return nr_reclaimed;
}
static void high_work_func(struct work_struct *work)
{
struct mem_cgroup *memcg;
memcg = container_of(work, struct mem_cgroup, high_work);
reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}
/*
* Clamp the maximum sleep time per allocation batch to 2 seconds. This is
* enough to still cause a significant slowdown in most cases, while still
* allowing diagnostics and tracing to proceed without becoming stuck.
*/
#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)
/*
* When calculating the delay, we use these either side of the exponentiation to
* maintain precision and scale to a reasonable number of jiffies (see the table
* below.
*
* - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
* overage ratio to a delay.
* - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the
* proposed penalty in order to reduce to a reasonable number of jiffies, and
* to produce a reasonable delay curve.
*
* MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
* reasonable delay curve compared to precision-adjusted overage, not
* penalising heavily at first, but still making sure that growth beyond the
* limit penalises misbehaviour cgroups by slowing them down exponentially. For
* example, with a high of 100 megabytes:
*
* +-------+------------------------+
* | usage | time to allocate in ms |
* +-------+------------------------+
* | 100M | 0 |
* | 101M | 6 |
* | 102M | 25 |
* | 103M | 57 |
* | 104M | 102 |
* | 105M | 159 |
* | 106M | 230 |
* | 107M | 313 |
* | 108M | 409 |
* | 109M | 518 |
* | 110M | 639 |
* | 111M | 774 |
* | 112M | 921 |
* | 113M | 1081 |
* | 114M | 1254 |
* | 115M | 1439 |
* | 116M | 1638 |
* | 117M | 1849 |
* | 118M | 2000 |
* | 119M | 2000 |
* | 120M | 2000 |
* +-------+------------------------+
*/
#define MEMCG_DELAY_PRECISION_SHIFT 20
#define MEMCG_DELAY_SCALING_SHIFT 14
static u64 calculate_overage(unsigned long usage, unsigned long high)
{
u64 overage;
if (usage <= high)
return 0;
/*
* Prevent division by 0 in overage calculation by acting as if
* it was a threshold of 1 page
*/
high = max(high, 1UL);
overage = usage - high;
overage <<= MEMCG_DELAY_PRECISION_SHIFT;
return div64_u64(overage, high);
}
static u64 mem_find_max_overage(struct mem_cgroup *memcg)
{
u64 overage, max_overage = 0;
do {
overage = calculate_overage(page_counter_read(&memcg->memory),
READ_ONCE(memcg->memory.high));
max_overage = max(overage, max_overage);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
return max_overage;
}
static u64 swap_find_max_overage(struct mem_cgroup *memcg)
{
u64 overage, max_overage = 0;
do {
overage = calculate_overage(page_counter_read(&memcg->swap),
READ_ONCE(memcg->swap.high));
if (overage)
memcg_memory_event(memcg, MEMCG_SWAP_HIGH);
max_overage = max(overage, max_overage);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
return max_overage;
}
/*
* Get the number of jiffies that we should penalise a mischievous cgroup which
* is exceeding its memory.high by checking both it and its ancestors.
*/
static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
unsigned int nr_pages,
u64 max_overage)
{
unsigned long penalty_jiffies;
if (!max_overage)
return 0;
/*
* We use overage compared to memory.high to calculate the number of
* jiffies to sleep (penalty_jiffies). Ideally this value should be
* fairly lenient on small overages, and increasingly harsh when the
* memcg in question makes it clear that it has no intention of stopping
* its crazy behaviour, so we exponentially increase the delay based on
* overage amount.
*/
penalty_jiffies = max_overage * max_overage * HZ;
penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;
/*
* Factor in the task's own contribution to the overage, such that four
* N-sized allocations are throttled approximately the same as one
* 4N-sized allocation.
*
* MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
* larger the current charge patch is than that.
*/
return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
}
/*
* Reclaims memory over the high limit. Called directly from
* try_charge() (context permitting), as well as from the userland
* return path where reclaim is always able to block.
*/
void mem_cgroup_handle_over_high(gfp_t gfp_mask)
{
unsigned long penalty_jiffies;
unsigned long pflags;
unsigned long nr_reclaimed;
unsigned int nr_pages = current->memcg_nr_pages_over_high;
int nr_retries = MAX_RECLAIM_RETRIES;
struct mem_cgroup *memcg;
bool in_retry = false;
if (likely(!nr_pages))
return;
memcg = get_mem_cgroup_from_mm(current->mm);
current->memcg_nr_pages_over_high = 0;
retry_reclaim:
/*
* Bail if the task is already exiting. Unlike memory.max,
* memory.high enforcement isn't as strict, and there is no
* OOM killer involved, which means the excess could already
* be much bigger (and still growing) than it could for
* memory.max; the dying task could get stuck in fruitless
* reclaim for a long time, which isn't desirable.
*/
if (task_is_dying())
goto out;
/*
* The allocating task should reclaim at least the batch size, but for
* subsequent retries we only want to do what's necessary to prevent oom
* or breaching resource isolation.
*
* This is distinct from memory.max or page allocator behaviour because
* memory.high is currently batched, whereas memory.max and the page
* allocator run every time an allocation is made.
*/
nr_reclaimed = reclaim_high(memcg,
in_retry ? SWAP_CLUSTER_MAX : nr_pages,
gfp_mask);
/*
* memory.high is breached and reclaim is unable to keep up. Throttle
* allocators proactively to slow down excessive growth.
*/
penalty_jiffies = calculate_high_delay(memcg, nr_pages,
mem_find_max_overage(memcg));
penalty_jiffies += calculate_high_delay(memcg, nr_pages,
swap_find_max_overage(memcg));
/*
* Clamp the max delay per usermode return so as to still keep the
* application moving forwards and also permit diagnostics, albeit
* extremely slowly.
*/
penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
/*
* Don't sleep if the amount of jiffies this memcg owes us is so low
* that it's not even worth doing, in an attempt to be nice to those who
* go only a small amount over their memory.high value and maybe haven't
* been aggressively reclaimed enough yet.
*/
if (penalty_jiffies <= HZ / 100)
goto out;
/*
* If reclaim is making forward progress but we're still over
* memory.high, we want to encourage that rather than doing allocator
* throttling.
*/
if (nr_reclaimed || nr_retries--) {
in_retry = true;
goto retry_reclaim;
}
/*
* Reclaim didn't manage to push usage below the limit, slow
* this allocating task down.
*
* If we exit early, we're guaranteed to die (since
* schedule_timeout_killable sets TASK_KILLABLE). This means we don't
* need to account for any ill-begotten jiffies to pay them off later.
*/
psi_memstall_enter(&pflags);
schedule_timeout_killable(penalty_jiffies);
psi_memstall_leave(&pflags);
out:
css_put(&memcg->css);
}
int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages)
{
unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
int nr_retries = MAX_RECLAIM_RETRIES;
struct mem_cgroup *mem_over_limit;
struct page_counter *counter;
unsigned long nr_reclaimed;
bool passed_oom = false;
unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP;
bool drained = false;
bool raised_max_event = false;
unsigned long pflags;
retry:
if (consume_stock(memcg, nr_pages))
return 0;
if (!do_memsw_account() ||
page_counter_try_charge(&memcg->memsw, batch, &counter)) {
if (page_counter_try_charge(&memcg->memory, batch, &counter))
goto done_restock;
if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, batch);
mem_over_limit = mem_cgroup_from_counter(counter, memory);
} else {
mem_over_limit = mem_cgroup_from_counter(counter, memsw);
reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP;
}
if (batch > nr_pages) {
batch = nr_pages;
goto retry;
}
/*
* Prevent unbounded recursion when reclaim operations need to
* allocate memory. This might exceed the limits temporarily,
* but we prefer facilitating memory reclaim and getting back
* under the limit over triggering OOM kills in these cases.
*/
if (unlikely(current->flags & PF_MEMALLOC))
goto force;
if (unlikely(task_in_memcg_oom(current)))
goto nomem;
if (!gfpflags_allow_blocking(gfp_mask))
goto nomem;
memcg_memory_event(mem_over_limit, MEMCG_MAX);
raised_max_event = true;
psi_memstall_enter(&pflags);
nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
gfp_mask, reclaim_options, NULL);
psi_memstall_leave(&pflags);
if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
goto retry;
if (!drained) {
drain_all_stock(mem_over_limit);
drained = true;
goto retry;
}
if (gfp_mask & __GFP_NORETRY)
goto nomem;
/*
* Even though the limit is exceeded at this point, reclaim
* may have been able to free some pages. Retry the charge
* before killing the task.
*
* Only for regular pages, though: huge pages are rather
* unlikely to succeed so close to the limit, and we fall back
* to regular pages anyway in case of failure.
*/
if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER))
goto retry;
/*
* At task move, charge accounts can be doubly counted. So, it's
* better to wait until the end of task_move if something is going on.
*/
if (memcg1_wait_acct_move(mem_over_limit))
goto retry;
if (nr_retries--)
goto retry;
if (gfp_mask & __GFP_RETRY_MAYFAIL)
goto nomem;
/* Avoid endless loop for tasks bypassed by the oom killer */
if (passed_oom && task_is_dying())
goto nomem;
/*
* keep retrying as long as the memcg oom killer is able to make
* a forward progress or bypass the charge if the oom killer
* couldn't make any progress.
*/
if (mem_cgroup_oom(mem_over_limit, gfp_mask,
get_order(nr_pages * PAGE_SIZE))) {
passed_oom = true;
nr_retries = MAX_RECLAIM_RETRIES;
goto retry;
}
nomem:
/*
* Memcg doesn't have a dedicated reserve for atomic
* allocations. But like the global atomic pool, we need to
* put the burden of reclaim on regular allocation requests
* and let these go through as privileged allocations.
*/
if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH)))
return -ENOMEM;
force:
/*
* If the allocation has to be enforced, don't forget to raise
* a MEMCG_MAX event.
*/
if (!raised_max_event)
memcg_memory_event(mem_over_limit, MEMCG_MAX);
/*
* The allocation either can't fail or will lead to more memory
* being freed very soon. Allow memory usage go over the limit
* temporarily by force charging it.
*/
page_counter_charge(&memcg->memory, nr_pages);
if (do_memsw_account())
page_counter_charge(&memcg->memsw, nr_pages);
return 0;
done_restock:
if (batch > nr_pages)
refill_stock(memcg, batch - nr_pages);
/*
* If the hierarchy is above the normal consumption range, schedule
* reclaim on returning to userland. We can perform reclaim here
* if __GFP_RECLAIM but let's always punt for simplicity and so that
* GFP_KERNEL can consistently be used during reclaim. @memcg is
* not recorded as it most likely matches current's and won't
* change in the meantime. As high limit is checked again before
* reclaim, the cost of mismatch is negligible.
*/
do {
bool mem_high, swap_high;
mem_high = page_counter_read(&memcg->memory) >
READ_ONCE(memcg->memory.high);
swap_high = page_counter_read(&memcg->swap) >
READ_ONCE(memcg->swap.high);
/* Don't bother a random interrupted task */
if (!in_task()) {
if (mem_high) {
schedule_work(&memcg->high_work);
break;
}
continue;
}
if (mem_high || swap_high) {
/*
* The allocating tasks in this cgroup will need to do
* reclaim or be throttled to prevent further growth
* of the memory or swap footprints.
*
* Target some best-effort fairness between the tasks,
* and distribute reclaim work and delay penalties
* based on how much each task is actually allocating.
*/
current->memcg_nr_pages_over_high += batch;
set_notify_resume(current);
break;
}
} while ((memcg = parent_mem_cgroup(memcg)));
/*
* Reclaim is set up above to be called from the userland
* return path. But also attempt synchronous reclaim to avoid
* excessive overrun while the task is still inside the
* kernel. If this is successful, the return path will see it
* when it rechecks the overage and simply bail out.
*/
if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
!(current->flags & PF_MEMALLOC) &&
gfpflags_allow_blocking(gfp_mask))
mem_cgroup_handle_over_high(gfp_mask);
return 0;
}
/**
* mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call.
* @memcg: memcg previously charged.
* @nr_pages: number of pages previously charged.
*/
void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
{
if (mem_cgroup_is_root(memcg))
return;
page_counter_uncharge(&memcg->memory, nr_pages);
if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
}
static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
VM_BUG_ON_FOLIO(folio_memcg(folio), folio);
/*
* Any of the following ensures page's memcg stability:
*
* - the page lock
* - LRU isolation
* - folio_memcg_lock()
* - exclusive reference
* - mem_cgroup_trylock_pages()
*/
folio->memcg_data = (unsigned long)memcg;
}
/**
* mem_cgroup_commit_charge - commit a previously successful try_charge().
* @folio: folio to commit the charge to.
* @memcg: memcg previously charged.
*/
void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
css_get(&memcg->css);
commit_charge(folio, memcg);
local_irq_disable();
mem_cgroup_charge_statistics(memcg, folio_nr_pages(folio));
memcg1_check_events(memcg, folio_nid(folio));
local_irq_enable();
}
static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg,
struct pglist_data *pgdat,
enum node_stat_item idx, int nr)
{
struct mem_cgroup *memcg;
struct lruvec *lruvec;
rcu_read_lock();
memcg = obj_cgroup_memcg(objcg);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_memcg_lruvec_state(lruvec, idx, nr);
rcu_read_unlock();
}
static __always_inline
struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
{
/*
* Slab objects are accounted individually, not per-page.
* Memcg membership data for each individual object is saved in
* slab->obj_exts.
*/
if (folio_test_slab(folio)) {
struct slabobj_ext *obj_exts;
struct slab *slab;
unsigned int off;
slab = folio_slab(folio);
obj_exts = slab_obj_exts(slab);
if (!obj_exts)
return NULL;
off = obj_to_index(slab->slab_cache, slab, p);
if (obj_exts[off].objcg)
return obj_cgroup_memcg(obj_exts[off].objcg);
return NULL;
}
/*
* folio_memcg_check() is used here, because in theory we can encounter
* a folio where the slab flag has been cleared already, but
* slab->obj_exts has not been freed yet
* folio_memcg_check() will guarantee that a proper memory
* cgroup pointer or NULL will be returned.
*/
return folio_memcg_check(folio);
}
/*
* Returns a pointer to the memory cgroup to which the kernel object is charged.
*
* A passed kernel object can be a slab object, vmalloc object or a generic
* kernel page, so different mechanisms for getting the memory cgroup pointer
* should be used.
*
* In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
* can not know for sure how the kernel object is implemented.
* mem_cgroup_from_obj() can be safely used in such cases.
*
* The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
* cgroup_mutex, etc.
*/
struct mem_cgroup *mem_cgroup_from_obj(void *p)
{
struct folio *folio;
if (mem_cgroup_disabled())
return NULL;
if (unlikely(is_vmalloc_addr(p)))
folio = page_folio(vmalloc_to_page(p));
else
folio = virt_to_folio(p);
return mem_cgroup_from_obj_folio(folio, p);
}
/*
* Returns a pointer to the memory cgroup to which the kernel object is charged.
* Similar to mem_cgroup_from_obj(), but faster and not suitable for objects,
* allocated using vmalloc().
*
* A passed kernel object must be a slab object or a generic kernel page.
*
* The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
* cgroup_mutex, etc.
*/
struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
{
if (mem_cgroup_disabled())
return NULL;
return mem_cgroup_from_obj_folio(virt_to_folio(p), p);
}
static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
{
struct obj_cgroup *objcg = NULL;
for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
objcg = rcu_dereference(memcg->objcg);
if (likely(objcg && obj_cgroup_tryget(objcg)))
break;
objcg = NULL;
}
return objcg;
}
static struct obj_cgroup *current_objcg_update(void)
{
struct mem_cgroup *memcg;
struct obj_cgroup *old, *objcg = NULL;
do {
/* Atomically drop the update bit. */
old = xchg(&current->objcg, NULL);
if (old) {
old = (struct obj_cgroup *)
((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG);
obj_cgroup_put(old);
old = NULL;
}
/* If new objcg is NULL, no reason for the second atomic update. */
if (!current->mm || (current->flags & PF_KTHREAD))
return NULL;
/*
* Release the objcg pointer from the previous iteration,
* if try_cmpxcg() below fails.
*/
if (unlikely(objcg)) {
obj_cgroup_put(objcg);
objcg = NULL;
}
/*
* Obtain the new objcg pointer. The current task can be
* asynchronously moved to another memcg and the previous
* memcg can be offlined. So let's get the memcg pointer
* and try get a reference to objcg under a rcu read lock.
*/
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
objcg = __get_obj_cgroup_from_memcg(memcg);
rcu_read_unlock();
/*
* Try set up a new objcg pointer atomically. If it
* fails, it means the update flag was set concurrently, so
* the whole procedure should be repeated.
*/
} while (!try_cmpxchg(&current->objcg, &old, objcg));
return objcg;
}
__always_inline struct obj_cgroup *current_obj_cgroup(void)
{
struct mem_cgroup *memcg;
struct obj_cgroup *objcg;
if (in_task()) {
memcg = current->active_memcg;
if (unlikely(memcg))
goto from_memcg;
objcg = READ_ONCE(current->objcg);
if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG))
objcg = current_objcg_update();
/*
* Objcg reference is kept by the task, so it's safe
* to use the objcg by the current task.
*/
return objcg;
}
memcg = this_cpu_read(int_active_memcg);
if (unlikely(memcg))
goto from_memcg;
return NULL;
from_memcg:
objcg = NULL;
for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
/*
* Memcg pointer is protected by scope (see set_active_memcg())
* and is pinning the corresponding objcg, so objcg can't go
* away and can be used within the scope without any additional
* protection.
*/
objcg = rcu_dereference_check(memcg->objcg, 1);
if (likely(objcg))
break;
}
return objcg;
}
struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
{
struct obj_cgroup *objcg;
if (!memcg_kmem_online())
return NULL;
if (folio_memcg_kmem(folio)) {
objcg = __folio_objcg(folio);
obj_cgroup_get(objcg);
} else {
struct mem_cgroup *memcg;
rcu_read_lock();
memcg = __folio_memcg(folio);
if (memcg)
objcg = __get_obj_cgroup_from_memcg(memcg);
else
objcg = NULL;
rcu_read_unlock();
}
return objcg;
}
/*
* obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
* @objcg: object cgroup to uncharge
* @nr_pages: number of pages to uncharge
*/
static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
unsigned int nr_pages)
{
struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_objcg(objcg);
mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
memcg1_account_kmem(memcg, -nr_pages);
refill_stock(memcg, nr_pages);
css_put(&memcg->css);
}
/*
* obj_cgroup_charge_pages: charge a number of kernel pages to a objcg
* @objcg: object cgroup to charge
* @gfp: reclaim mode
* @nr_pages: number of pages to charge
*
* Returns 0 on success, an error code on failure.
*/
static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
unsigned int nr_pages)
{
struct mem_cgroup *memcg;
int ret;
memcg = get_mem_cgroup_from_objcg(objcg);
ret = try_charge_memcg(memcg, gfp, nr_pages);
if (ret)
goto out;
mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
memcg1_account_kmem(memcg, nr_pages);
out:
css_put(&memcg->css);
return ret;
}
/**
* __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup
* @page: page to charge
* @gfp: reclaim mode
* @order: allocation order
*
* Returns 0 on success, an error code on failure.
*/
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
{
struct obj_cgroup *objcg;
int ret = 0;
objcg = current_obj_cgroup();
if (objcg) {
ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
if (!ret) {
obj_cgroup_get(objcg);
page->memcg_data = (unsigned long)objcg |
MEMCG_DATA_KMEM;
return 0;
}
}
return ret;
}
/**
* __memcg_kmem_uncharge_page: uncharge a kmem page
* @page: page to uncharge
* @order: allocation order
*/
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
struct folio *folio = page_folio(page);
struct obj_cgroup *objcg;
unsigned int nr_pages = 1 << order;
if (!folio_memcg_kmem(folio))
return;
objcg = __folio_objcg(folio);
obj_cgroup_uncharge_pages(objcg, nr_pages);
folio->memcg_data = 0;
obj_cgroup_put(objcg);
}
static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
enum node_stat_item idx, int nr)
{
struct memcg_stock_pcp *stock;
struct obj_cgroup *old = NULL;
unsigned long flags;
int *bytes;
local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
/*
* Save vmstat data in stock and skip vmstat array update unless
* accumulating over a page of vmstat data or when pgdat or idx
* changes.
*/
if (READ_ONCE(stock->cached_objcg) != objcg) {
old = drain_obj_stock(stock);
obj_cgroup_get(objcg);
stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
WRITE_ONCE(stock->cached_objcg, objcg);
stock->cached_pgdat = pgdat;
} else if (stock->cached_pgdat != pgdat) {
/* Flush the existing cached vmstat data */
struct pglist_data *oldpg = stock->cached_pgdat;
if (stock->nr_slab_reclaimable_b) {
__mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B,
stock->nr_slab_reclaimable_b);
stock->nr_slab_reclaimable_b = 0;
}
if (stock->nr_slab_unreclaimable_b) {
__mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B,
stock->nr_slab_unreclaimable_b);
stock->nr_slab_unreclaimable_b = 0;
}
stock->cached_pgdat = pgdat;
}
bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
: &stock->nr_slab_unreclaimable_b;
/*
* Even for large object >= PAGE_SIZE, the vmstat data will still be
* cached locally at least once before pushing it out.
*/
if (!*bytes) {
*bytes = nr;
nr = 0;
} else {
*bytes += nr;
if (abs(*bytes) > PAGE_SIZE) {
nr = *bytes;
*bytes = 0;
} else {
nr = 0;
}
}
if (nr)
__mod_objcg_mlstate(objcg, pgdat, idx, nr);
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
}
static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
{
struct memcg_stock_pcp *stock;
unsigned long flags;
bool ret = false;
local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
stock->nr_bytes -= nr_bytes;
ret = true;
}
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
{
struct obj_cgroup *old = READ_ONCE(stock->cached_objcg);
if (!old)
return NULL;
if (stock->nr_bytes) {
unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
if (nr_pages) {
struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_objcg(old);
mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
memcg1_account_kmem(memcg, -nr_pages);
__refill_stock(memcg, nr_pages);
css_put(&memcg->css);
}
/*
* The leftover is flushed to the centralized per-memcg value.
* On the next attempt to refill obj stock it will be moved
* to a per-cpu stock (probably, on an other CPU), see
* refill_obj_stock().
*
* How often it's flushed is a trade-off between the memory
* limit enforcement accuracy and potential CPU contention,
* so it might be changed in the future.
*/
atomic_add(nr_bytes, &old->nr_charged_bytes);
stock->nr_bytes = 0;
}
/*
* Flush the vmstat data in current stock
*/
if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) {
if (stock->nr_slab_reclaimable_b) {
__mod_objcg_mlstate(old, stock->cached_pgdat,
NR_SLAB_RECLAIMABLE_B,
stock->nr_slab_reclaimable_b);
stock->nr_slab_reclaimable_b = 0;
}
if (stock->nr_slab_unreclaimable_b) {
__mod_objcg_mlstate(old, stock->cached_pgdat,
NR_SLAB_UNRECLAIMABLE_B,
stock->nr_slab_unreclaimable_b);
stock->nr_slab_unreclaimable_b = 0;
}
stock->cached_pgdat = NULL;
}
WRITE_ONCE(stock->cached_objcg, NULL);
/*
* The `old' objects needs to be released by the caller via
* obj_cgroup_put() outside of memcg_stock_pcp::stock_lock.
*/
return old;
}
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
struct mem_cgroup *root_memcg)
{
struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg);
struct mem_cgroup *memcg;
if (objcg) {
memcg = obj_cgroup_memcg(objcg);
if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
return true;
}
return false;
}
static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
bool allow_uncharge)
{
struct memcg_stock_pcp *stock;
struct obj_cgroup *old = NULL;
unsigned long flags;
unsigned int nr_pages = 0;
local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
old = drain_obj_stock(stock);
obj_cgroup_get(objcg);
WRITE_ONCE(stock->cached_objcg, objcg);
stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
allow_uncharge = true; /* Allow uncharge when objcg changes */
}
stock->nr_bytes += nr_bytes;
if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
nr_pages = stock->nr_bytes >> PAGE_SHIFT;
stock->nr_bytes &= (PAGE_SIZE - 1);
}
local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
obj_cgroup_put(old);
if (nr_pages)
obj_cgroup_uncharge_pages(objcg, nr_pages);
}
int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
{
unsigned int nr_pages, nr_bytes;
int ret;
if (consume_obj_stock(objcg, size))
return 0;
/*
* In theory, objcg->nr_charged_bytes can have enough
* pre-charged bytes to satisfy the allocation. However,
* flushing objcg->nr_charged_bytes requires two atomic
* operations, and objcg->nr_charged_bytes can't be big.
* The shared objcg->nr_charged_bytes can also become a
* performance bottleneck if all tasks of the same memcg are
* trying to update it. So it's better to ignore it and try
* grab some new pages. The stock's nr_bytes will be flushed to
* objcg->nr_charged_bytes later on when objcg changes.
*
* The stock's nr_bytes may contain enough pre-charged bytes
* to allow one less page from being charged, but we can't rely
* on the pre-charged bytes not being changed outside of
* consume_obj_stock() or refill_obj_stock(). So ignore those
* pre-charged bytes as well when charging pages. To avoid a
* page uncharge right after a page charge, we set the
* allow_uncharge flag to false when calling refill_obj_stock()
* to temporarily allow the pre-charged bytes to exceed the page
* size limit. The maximum reachable value of the pre-charged
* bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data
* race.
*/
nr_pages = size >> PAGE_SHIFT;
nr_bytes = size & (PAGE_SIZE - 1);
if (nr_bytes)
nr_pages += 1;
ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages);
if (!ret && nr_bytes)
refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false);
return ret;
}
void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
{
refill_obj_stock(objcg, size, true);
}
static inline size_t obj_full_size(struct kmem_cache *s)
{
/*
* For each accounted object there is an extra space which is used
* to store obj_cgroup membership. Charge it too.
*/
return s->size + sizeof(struct obj_cgroup *);
}
bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
gfp_t flags, size_t size, void **p)
{
struct obj_cgroup *objcg;
struct slab *slab;
unsigned long off;
size_t i;
/*
* The obtained objcg pointer is safe to use within the current scope,
* defined by current task or set_active_memcg() pair.
* obj_cgroup_get() is used to get a permanent reference.
*/
objcg = current_obj_cgroup();
if (!objcg)
return true;
/*
* slab_alloc_node() avoids the NULL check, so we might be called with a
* single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill
* the whole requested size.
* return success as there's nothing to free back
*/
if (unlikely(*p == NULL))
return true;
flags &= gfp_allowed_mask;
if (lru) {
int ret;
struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_objcg(objcg);
ret = memcg_list_lru_alloc(memcg, lru, flags);
css_put(&memcg->css);
if (ret)
return false;
}
if (obj_cgroup_charge(objcg, flags, size * obj_full_size(s)))
return false;
for (i = 0; i < size; i++) {
slab = virt_to_slab(p[i]);
if (!slab_obj_exts(slab) &&
alloc_slab_obj_exts(slab, s, flags, false)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
}
off = obj_to_index(s, slab, p[i]);
obj_cgroup_get(objcg);
slab_obj_exts(slab)[off].objcg = objcg;
mod_objcg_state(objcg, slab_pgdat(slab),
cache_vmstat_idx(s), obj_full_size(s));
}
return true;
}
void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
void **p, int objects, struct slabobj_ext *obj_exts)
{
for (int i = 0; i < objects; i++) {
struct obj_cgroup *objcg;
unsigned int off;
off = obj_to_index(s, slab, p[i]);
objcg = obj_exts[off].objcg;
if (!objcg)
continue;
obj_exts[off].objcg = NULL;
obj_cgroup_uncharge(objcg, obj_full_size(s));
mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
-obj_full_size(s));
obj_cgroup_put(objcg);
}
}
/*
* Because folio_memcg(head) is not set on tails, set it now.
*/
void split_page_memcg(struct page *head, int old_order, int new_order)
{
struct folio *folio = page_folio(head);
struct mem_cgroup *memcg = folio_memcg(folio);
int i;
unsigned int old_nr = 1 << old_order;
unsigned int new_nr = 1 << new_order;
if (mem_cgroup_disabled() || !memcg)
return;
for (i = new_nr; i < old_nr; i += new_nr)
folio_page(folio, i)->memcg_data = folio->memcg_data;
if (folio_memcg_kmem(folio))
obj_cgroup_get_many(__folio_objcg(folio), old_nr / new_nr - 1);
else
css_get_many(&memcg->css, old_nr / new_nr - 1);
}
unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
unsigned long val;
if (mem_cgroup_is_root(memcg)) {
/*
* Approximate root's usage from global state. This isn't
* perfect, but the root usage was always an approximation.
*/
val = global_node_page_state(NR_FILE_PAGES) +
global_node_page_state(NR_ANON_MAPPED);
if (swap)
val += total_swap_pages - get_nr_swap_pages();
} else {
if (!swap)
val = page_counter_read(&memcg->memory);
else
val = page_counter_read(&memcg->memsw);
}
return val;
}
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
struct obj_cgroup *objcg;
if (mem_cgroup_kmem_disabled())
return 0;
if (unlikely(mem_cgroup_is_root(memcg)))
return 0;
objcg = obj_cgroup_alloc();
if (!objcg)
return -ENOMEM;
objcg->memcg = memcg;
rcu_assign_pointer(memcg->objcg, objcg);
obj_cgroup_get(objcg);
memcg->orig_objcg = objcg;
static_branch_enable(&memcg_kmem_online_key);
memcg->kmemcg_id = memcg->id.id;
return 0;
}
static void memcg_offline_kmem(struct mem_cgroup *memcg)
{
struct mem_cgroup *parent;
if (mem_cgroup_kmem_disabled())
return;
if (unlikely(mem_cgroup_is_root(memcg)))
return;
parent = parent_mem_cgroup(memcg);
if (!parent)
parent = root_mem_cgroup;
memcg_reparent_objcgs(memcg, parent);
/*
* After we have finished memcg_reparent_objcgs(), all list_lrus
* corresponding to this cgroup are guaranteed to remain empty.
* The ordering is imposed by list_lru_node->lock taken by
* memcg_reparent_list_lrus().
*/
memcg_reparent_list_lrus(memcg, parent);
}
#ifdef CONFIG_CGROUP_WRITEBACK
#include <trace/events/writeback.h>
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
return wb_domain_init(&memcg->cgwb_domain, gfp);
}
static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
{
wb_domain_exit(&memcg->cgwb_domain);
}
static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
{
wb_domain_size_changed(&memcg->cgwb_domain);
}
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
if (!memcg->css.parent)
return NULL;
return &memcg->cgwb_domain;
}
/**
* mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
* @wb: bdi_writeback in question
* @pfilepages: out parameter for number of file pages
* @pheadroom: out parameter for number of allocatable pages according to memcg
* @pdirty: out parameter for number of dirty pages
* @pwriteback: out parameter for number of pages under writeback
*
* Determine the numbers of file, headroom, dirty, and writeback pages in
* @wb's memcg. File, dirty and writeback are self-explanatory. Headroom
* is a bit more involved.
*
* A memcg's headroom is "min(max, high) - used". In the hierarchy, the
* headroom is calculated as the lowest headroom of itself and the
* ancestors. Note that this doesn't consider the actual amount of
* available memory in the system. The caller should further cap
* *@pheadroom accordingly.
*/
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
struct mem_cgroup *parent;
mem_cgroup_flush_stats_ratelimited(memcg);
*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
*pfilepages = memcg_page_state(memcg, NR_INACTIVE_FILE) +
memcg_page_state(memcg, NR_ACTIVE_FILE);
*pheadroom = PAGE_COUNTER_MAX;
while ((parent = parent_mem_cgroup(memcg))) {
unsigned long ceiling = min(READ_ONCE(memcg->memory.max),
READ_ONCE(memcg->memory.high));
unsigned long used = page_counter_read(&memcg->memory);
*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
memcg = parent;
}
}
/*
* Foreign dirty flushing
*
* There's an inherent mismatch between memcg and writeback. The former
* tracks ownership per-page while the latter per-inode. This was a
* deliberate design decision because honoring per-page ownership in the
* writeback path is complicated, may lead to higher CPU and IO overheads
* and deemed unnecessary given that write-sharing an inode across
* different cgroups isn't a common use-case.
*
* Combined with inode majority-writer ownership switching, this works well
* enough in most cases but there are some pathological cases. For
* example, let's say there are two cgroups A and B which keep writing to
* different but confined parts of the same inode. B owns the inode and
* A's memory is limited far below B's. A's dirty ratio can rise enough to
* trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
* triggering background writeback. A will be slowed down without a way to
* make writeback of the dirty pages happen.
*
* Conditions like the above can lead to a cgroup getting repeatedly and
* severely throttled after making some progress after each
* dirty_expire_interval while the underlying IO device is almost
* completely idle.
*
* Solving this problem completely requires matching the ownership tracking
* granularities between memcg and writeback in either direction. However,
* the more egregious behaviors can be avoided by simply remembering the
* most recent foreign dirtying events and initiating remote flushes on
* them when local writeback isn't enough to keep the memory clean enough.
*
* The following two functions implement such mechanism. When a foreign
* page - a page whose memcg and writeback ownerships don't match - is
* dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
* bdi_writeback on the page owning memcg. When balance_dirty_pages()
* decides that the memcg needs to sleep due to high dirty ratio, it calls
* mem_cgroup_flush_foreign() which queues writeback on the recorded
* foreign bdi_writebacks which haven't expired. Both the numbers of
* recorded bdi_writebacks and concurrent in-flight foreign writebacks are
* limited to MEMCG_CGWB_FRN_CNT.
*
* The mechanism only remembers IDs and doesn't hold any object references.
* As being wrong occasionally doesn't matter, updates and accesses to the
* records are lockless and racy.
*/
void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb)
{
struct mem_cgroup *memcg = folio_memcg(folio);
struct memcg_cgwb_frn *frn;
u64 now = get_jiffies_64();
u64 oldest_at = now;
int oldest = -1;
int i;
trace_track_foreign_dirty(folio, wb);
/*
* Pick the slot to use. If there is already a slot for @wb, keep
* using it. If not replace the oldest one which isn't being
* written out.
*/
for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
frn = &memcg->cgwb_frn[i];
if (frn->bdi_id == wb->bdi->id &&
frn->memcg_id == wb->memcg_css->id)
break;
if (time_before64(frn->at, oldest_at) &&
atomic_read(&frn->done.cnt) == 1) {
oldest = i;
oldest_at = frn->at;
}
}
if (i < MEMCG_CGWB_FRN_CNT) {
/*
* Re-using an existing one. Update timestamp lazily to
* avoid making the cacheline hot. We want them to be
* reasonably up-to-date and significantly shorter than
* dirty_expire_interval as that's what expires the record.
* Use the shorter of 1s and dirty_expire_interval / 8.
*/
unsigned long update_intv =
min_t(unsigned long, HZ,
msecs_to_jiffies(dirty_expire_interval * 10) / 8);
if (time_before64(frn->at, now - update_intv))
frn->at = now;
} else if (oldest >= 0) {
/* replace the oldest free one */
frn = &memcg->cgwb_frn[oldest];
frn->bdi_id = wb->bdi->id;
frn->memcg_id = wb->memcg_css->id;
frn->at = now;
}
}
/* issue foreign writeback flushes for recorded foreign dirtying events */
void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
u64 now = jiffies_64;
int i;
for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];
/*
* If the record is older than dirty_expire_interval,
* writeback on it has already started. No need to kick it
* off again. Also, don't start a new one if there's
* already one in flight.
*/
if (time_after64(frn->at, now - intv) &&
atomic_read(&frn->done.cnt) == 1) {
frn->at = 0;
trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
WB_REASON_FOREIGN_FLUSH,
&frn->done);
}
}
}
#else /* CONFIG_CGROUP_WRITEBACK */
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
return 0;
}
static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
{
}
static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
{
}