OpenCloudOS-Kernel/mm/vmscan.c

4917 lines
139 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Swap reorganised 29.12.95, Stephen Tweedie.
* kswapd added: 7.1.96 sct
* Removed kswapd_ctl limits, and swap out as many pages as needed
* to bring the system back to freepages.high: 2.4.97, Rik van Riel.
* Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
* Multiqueue VM started 5.8.00, Rik van Riel.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmpressure.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h> /* for buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/compaction.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/migrate.h>
#include <linux/delayacct.h>
#include <linux/sysctl.h>
#include <linux/oom.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/printk.h>
#include <linux/dax.h>
#include <linux/psi.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
#include <linux/balloon_compaction.h>
#include <linux/sched/sysctl.h>
#include "internal.h"
#include "swap.h"
#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>
struct scan_control {
/* How many pages shrink_list() should reclaim */
unsigned long nr_to_reclaim;
/*
* Nodemask of nodes allowed by the caller. If NULL, all nodes
* are scanned.
*/
nodemask_t *nodemask;
/*
* The memory cgroup that hit its limit and as a result is the
* primary target of this reclaim invocation.
*/
struct mem_cgroup *target_mem_cgroup;
/*
* Scan pressure balancing between anon and file LRUs
*/
unsigned long anon_cost;
unsigned long file_cost;
/* Can active pages be deactivated as part of reclaim? */
#define DEACTIVATE_ANON 1
#define DEACTIVATE_FILE 2
unsigned int may_deactivate:2;
unsigned int force_deactivate:1;
unsigned int skipped_deactivate:1;
/* Writepage batching in laptop mode; RECLAIM_WRITE */
unsigned int may_writepage:1;
/* Can mapped pages be reclaimed? */
unsigned int may_unmap:1;
/* Can pages be swapped as part of reclaim? */
unsigned int may_swap:1;
/* Proactive reclaim invoked by userspace through memory.reclaim */
unsigned int proactive:1;
/*
* Cgroup memory below memory.low is protected as long as we
* don't threaten to OOM. If any cgroup is reclaimed at
* reduced force or passed over entirely due to its memory.low
* setting (memcg_low_skipped), and nothing is reclaimed as a
* result, then go back for one more cycle that reclaims the protected
* memory (memcg_low_reclaim) to avert OOM.
*/
unsigned int memcg_low_reclaim:1;
unsigned int memcg_low_skipped:1;
unsigned int hibernation_mode:1;
/* One of the zones is ready for compaction */
unsigned int compaction_ready:1;
/* There is easily reclaimable cold cache in the current node */
unsigned int cache_trim_mode:1;
/* The file pages on the current node are dangerously low */
unsigned int file_is_tiny:1;
/* Always discard instead of demoting to lower tier memory */
unsigned int no_demotion:1;
/* Allocation order */
s8 order;
/* Scan (total_size >> priority) pages at once */
s8 priority;
/* The highest zone to isolate pages for reclaim from */
s8 reclaim_idx;
/* This context's GFP mask */
gfp_t gfp_mask;
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
/* Number of pages freed so far during a call to shrink_zones() */
unsigned long nr_reclaimed;
struct {
unsigned int dirty;
unsigned int unqueued_dirty;
unsigned int congested;
unsigned int writeback;
unsigned int immediate;
unsigned int file_taken;
unsigned int taken;
} nr;
/* for recording the reclaimed slab by now */
struct reclaim_state reclaim_state;
};
#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_folio(_folio, _base, _field) \
do { \
if ((_folio)->lru.prev != _base) { \
struct folio *prev; \
\
prev = lru_to_folio(&(_folio->lru)); \
prefetchw(&prev->_field); \
} \
} while (0)
#else
#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0)
#endif
/*
* From 0 .. 200. Higher means more swappy.
*/
int vm_swappiness = 60;
static void set_task_reclaim_state(struct task_struct *task,
struct reclaim_state *rs)
{
/* Check for an overwrite */
WARN_ON_ONCE(rs && task->reclaim_state);
/* Check for the nulling of an already-nulled member */
WARN_ON_ONCE(!rs && !task->reclaim_state);
task->reclaim_state = rs;
}
LIST_HEAD(shrinker_list);
DECLARE_RWSEM(shrinker_rwsem);
#ifdef CONFIG_MEMCG
static int shrinker_nr_max;
/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
static inline int shrinker_map_size(int nr_items)
{
return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long));
}
static inline int shrinker_defer_size(int nr_items)
{
return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t));
}
static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
int nid)
{
return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
lockdep_is_held(&shrinker_rwsem));
}
static int expand_one_shrinker_info(struct mem_cgroup *memcg,
int map_size, int defer_size,
int old_map_size, int old_defer_size)
{
struct shrinker_info *new, *old;
struct mem_cgroup_per_node *pn;
int nid;
int size = map_size + defer_size;
for_each_node(nid) {
pn = memcg->nodeinfo[nid];
old = shrinker_info_protected(memcg, nid);
/* Not yet online memcg */
if (!old)
return 0;
new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
if (!new)
return -ENOMEM;
new->nr_deferred = (atomic_long_t *)(new + 1);
new->map = (void *)new->nr_deferred + defer_size;
/* map: set all old bits, clear all new bits */
memset(new->map, (int)0xff, old_map_size);
memset((void *)new->map + old_map_size, 0, map_size - old_map_size);
/* nr_deferred: copy old values, clear all new values */
memcpy(new->nr_deferred, old->nr_deferred, old_defer_size);
memset((void *)new->nr_deferred + old_defer_size, 0,
defer_size - old_defer_size);
rcu_assign_pointer(pn->shrinker_info, new);
kvfree_rcu(old, rcu);
}
return 0;
}
void free_shrinker_info(struct mem_cgroup *memcg)
{
struct mem_cgroup_per_node *pn;
struct shrinker_info *info;
int nid;
for_each_node(nid) {
pn = memcg->nodeinfo[nid];
info = rcu_dereference_protected(pn->shrinker_info, true);
kvfree(info);
rcu_assign_pointer(pn->shrinker_info, NULL);
}
}
int alloc_shrinker_info(struct mem_cgroup *memcg)
{
struct shrinker_info *info;
int nid, size, ret = 0;
int map_size, defer_size = 0;
down_write(&shrinker_rwsem);
map_size = shrinker_map_size(shrinker_nr_max);
defer_size = shrinker_defer_size(shrinker_nr_max);
size = map_size + defer_size;
for_each_node(nid) {
info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
if (!info) {
free_shrinker_info(memcg);
ret = -ENOMEM;
break;
}
info->nr_deferred = (atomic_long_t *)(info + 1);
info->map = (void *)info->nr_deferred + defer_size;
rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
}
up_write(&shrinker_rwsem);
return ret;
}
static inline bool need_expand(int nr_max)
{
return round_up(nr_max, BITS_PER_LONG) >
round_up(shrinker_nr_max, BITS_PER_LONG);
}
static int expand_shrinker_info(int new_id)
{
int ret = 0;
int new_nr_max = new_id + 1;
int map_size, defer_size = 0;
int old_map_size, old_defer_size = 0;
struct mem_cgroup *memcg;
if (!need_expand(new_nr_max))
goto out;
if (!root_mem_cgroup)
goto out;
lockdep_assert_held(&shrinker_rwsem);
map_size = shrinker_map_size(new_nr_max);
defer_size = shrinker_defer_size(new_nr_max);
old_map_size = shrinker_map_size(shrinker_nr_max);
old_defer_size = shrinker_defer_size(shrinker_nr_max);
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
ret = expand_one_shrinker_info(memcg, map_size, defer_size,
old_map_size, old_defer_size);
if (ret) {
mem_cgroup_iter_break(NULL, memcg);
goto out;
}
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
out:
if (!ret)
shrinker_nr_max = new_nr_max;
return ret;
}
void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
{
if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
struct shrinker_info *info;
rcu_read_lock();
info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
/* Pairs with smp mb in shrink_slab() */
smp_mb__before_atomic();
set_bit(shrinker_id, info->map);
rcu_read_unlock();
}
}
static DEFINE_IDR(shrinker_idr);
static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
int id, ret = -ENOMEM;
if (mem_cgroup_disabled())
return -ENOSYS;
down_write(&shrinker_rwsem);
/* This may call shrinker, so it must use down_read_trylock() */
id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL);
if (id < 0)
goto unlock;
if (id >= shrinker_nr_max) {
if (expand_shrinker_info(id)) {
idr_remove(&shrinker_idr, id);
goto unlock;
}
}
shrinker->id = id;
ret = 0;
unlock:
up_write(&shrinker_rwsem);
return ret;
}
static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
int id = shrinker->id;
BUG_ON(id < 0);
lockdep_assert_held(&shrinker_rwsem);
idr_remove(&shrinker_idr, id);
}
static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
struct shrinker_info *info;
info = shrinker_info_protected(memcg, nid);
return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0);
}
static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
struct shrinker_info *info;
info = shrinker_info_protected(memcg, nid);
return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]);
}
void reparent_shrinker_deferred(struct mem_cgroup *memcg)
{
int i, nid;
long nr;
struct mem_cgroup *parent;
struct shrinker_info *child_info, *parent_info;
parent = parent_mem_cgroup(memcg);
if (!parent)
parent = root_mem_cgroup;
/* Prevent from concurrent shrinker_info expand */
down_read(&shrinker_rwsem);
for_each_node(nid) {
child_info = shrinker_info_protected(memcg, nid);
parent_info = shrinker_info_protected(parent, nid);
for (i = 0; i < shrinker_nr_max; i++) {
nr = atomic_long_read(&child_info->nr_deferred[i]);
atomic_long_add(nr, &parent_info->nr_deferred[i]);
}
}
up_read(&shrinker_rwsem);
}
static bool cgroup_reclaim(struct scan_control *sc)
{
return sc->target_mem_cgroup;
}
/**
* writeback_throttling_sane - is the usual dirty throttling mechanism available?
* @sc: scan_control in question
*
* The normal page dirty throttling mechanism in balance_dirty_pages() is
* completely broken with the legacy memcg and direct stalling in
* shrink_page_list() is used for throttling instead, which lacks all the
* niceties such as fairness, adaptive pausing, bandwidth proportional
* allocation and configurability.
*
* This function tests whether the vmscan currently in progress can assume
* that the normal dirty throttling mechanism is operational.
*/
static bool writeback_throttling_sane(struct scan_control *sc)
{
if (!cgroup_reclaim(sc))
return true;
#ifdef CONFIG_CGROUP_WRITEBACK
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return true;
#endif
return false;
}
#else
static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
return -ENOSYS;
}
static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
}
static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
return 0;
}
static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
return 0;
}
static bool cgroup_reclaim(struct scan_control *sc)
{
return false;
}
static bool writeback_throttling_sane(struct scan_control *sc)
{
return true;
}
#endif
static long xchg_nr_deferred(struct shrinker *shrinker,
struct shrink_control *sc)
{
int nid = sc->nid;
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
nid = 0;
if (sc->memcg &&
(shrinker->flags & SHRINKER_MEMCG_AWARE))
return xchg_nr_deferred_memcg(nid, shrinker,
sc->memcg);
return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
}
static long add_nr_deferred(long nr, struct shrinker *shrinker,
struct shrink_control *sc)
{
int nid = sc->nid;
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
nid = 0;
if (sc->memcg &&
(shrinker->flags & SHRINKER_MEMCG_AWARE))
return add_nr_deferred_memcg(nr, nid, shrinker,
sc->memcg);
return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
}
static bool can_demote(int nid, struct scan_control *sc)
{
if (!numa_demotion_enabled)
return false;
if (sc && sc->no_demotion)
return false;
if (next_demotion_node(nid) == NUMA_NO_NODE)
return false;
return true;
}
static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
int nid,
struct scan_control *sc)
{
if (memcg == NULL) {
/*
* For non-memcg reclaim, is there
* space in any swap device?
*/
if (get_nr_swap_pages() > 0)
return true;
} else {
/* Is the memcg below its swap limit? */
if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
return true;
}
/*
* The page can not be swapped.
*
* Can it be reclaimed from this node via demotion?
*/
return can_demote(nid, sc);
}
/*
* This misses isolated pages which are not accounted for to save counters.
* As the data only determines if reclaim or compaction continues, it is
* not expected that isolated pages will be a dominating factor.
*/
unsigned long zone_reclaimable_pages(struct zone *zone)
{
unsigned long nr;
nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
return nr;
}
/**
* lruvec_lru_size - Returns the number of pages on the given LRU list.
* @lruvec: lru vector
* @lru: lru to use
* @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list)
*/
static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zone_idx)
{
unsigned long size = 0;
int zid;
for (zid = 0; zid <= zone_idx; zid++) {
struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
if (!managed_zone(zone))
continue;
if (!mem_cgroup_disabled())
size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
else
size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
}
return size;
}
/*
* Add a shrinker callback to be called from the vm.
*/
static int __prealloc_shrinker(struct shrinker *shrinker)
{
unsigned int size;
int err;
if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
err = prealloc_memcg_shrinker(shrinker);
if (err != -ENOSYS)
return err;
shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
}
size = sizeof(*shrinker->nr_deferred);
if (shrinker->flags & SHRINKER_NUMA_AWARE)
size *= nr_node_ids;
shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
if (!shrinker->nr_deferred)
return -ENOMEM;
return 0;
}
#ifdef CONFIG_SHRINKER_DEBUG
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
va_list ap;
int err;
va_start(ap, fmt);
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
va_end(ap);
if (!shrinker->name)
return -ENOMEM;
err = __prealloc_shrinker(shrinker);
if (err) {
kfree_const(shrinker->name);
shrinker->name = NULL;
}
return err;
}
#else
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
return __prealloc_shrinker(shrinker);
}
#endif
void free_prealloced_shrinker(struct shrinker *shrinker)
{
#ifdef CONFIG_SHRINKER_DEBUG
kfree_const(shrinker->name);
shrinker->name = NULL;
#endif
if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
down_write(&shrinker_rwsem);
unregister_memcg_shrinker(shrinker);
up_write(&shrinker_rwsem);
return;
}
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
void register_shrinker_prepared(struct shrinker *shrinker)
{
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
shrinker->flags |= SHRINKER_REGISTERED;
shrinker_debugfs_add(shrinker);
up_write(&shrinker_rwsem);
}
static int __register_shrinker(struct shrinker *shrinker)
{
int err = __prealloc_shrinker(shrinker);
if (err)
return err;
register_shrinker_prepared(shrinker);
return 0;
}
#ifdef CONFIG_SHRINKER_DEBUG
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
va_list ap;
int err;
va_start(ap, fmt);
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
va_end(ap);
if (!shrinker->name)
return -ENOMEM;
err = __register_shrinker(shrinker);
if (err) {
kfree_const(shrinker->name);
shrinker->name = NULL;
}
return err;
}
#else
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
return __register_shrinker(shrinker);
}
#endif
EXPORT_SYMBOL(register_shrinker);
/*
* Remove one
*/
void unregister_shrinker(struct shrinker *shrinker)
{
if (!(shrinker->flags & SHRINKER_REGISTERED))
return;
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
shrinker->flags &= ~SHRINKER_REGISTERED;
if (shrinker->flags & SHRINKER_MEMCG_AWARE)
unregister_memcg_shrinker(shrinker);
shrinker_debugfs_remove(shrinker);
up_write(&shrinker_rwsem);
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);
/**
* synchronize_shrinkers - Wait for all running shrinkers to complete.
*
* This is equivalent to calling unregister_shrink() and register_shrinker(),
* but atomically and with less overhead. This is useful to guarantee that all
* shrinker invocations have seen an update, before freeing memory, similar to
* rcu.
*/
void synchronize_shrinkers(void)
{
down_write(&shrinker_rwsem);
up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(synchronize_shrinkers);
#define SHRINK_BATCH 128
static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
struct shrinker *shrinker, int priority)
{
unsigned long freed = 0;
unsigned long long delta;
long total_scan;
long freeable;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
long scanned = 0, next_deferred;
freeable = shrinker->count_objects(shrinker, shrinkctl);
if (freeable == 0 || freeable == SHRINK_EMPTY)
return freeable;
/*
* copy the current shrinker scan count into a local variable
* and zero it so that other concurrent shrinker invocations
* don't also do this scanning work.
*/
nr = xchg_nr_deferred(shrinker, shrinkctl);
if (shrinker->seeks) {
delta = freeable >> priority;
delta *= 4;
do_div(delta, shrinker->seeks);
} else {
/*
* These objects don't require any IO to create. Trim
* them aggressively under memory pressure to keep
* them from causing refetches in the IO caches.
*/
delta = freeable / 2;
}
total_scan = nr >> priority;
total_scan += delta;
total_scan = min(total_scan, (2 * freeable));
trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
freeable, delta, total_scan, priority);
/*
* Normally, we should not scan less than batch_size objects in one
* pass to avoid too frequent shrinker calls, but if the slab has less
* than batch_size objects in total and we are really tight on memory,
* we will try to reclaim all available objects, otherwise we can end
* up failing allocations although there are plenty of reclaimable
* objects spread over several slabs with usage less than the
* batch_size.
*
* We detect the "tight on memory" situations by looking at the total
* number of objects we want to scan (total_scan). If it is greater
* than the total number of objects on slab (freeable), we must be
* scanning at high prio and therefore should try to reclaim as much as
* possible.
*/
while (total_scan >= batch_size ||
total_scan >= freeable) {
unsigned long ret;
unsigned long nr_to_scan = min(batch_size, total_scan);
shrinkctl->nr_to_scan = nr_to_scan;
shrinkctl->nr_scanned = nr_to_scan;
ret = shrinker->scan_objects(shrinker, shrinkctl);
if (ret == SHRINK_STOP)
break;
freed += ret;
count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned);
total_scan -= shrinkctl->nr_scanned;
scanned += shrinkctl->nr_scanned;
cond_resched();
}
/*
* The deferred work is increased by any new work (delta) that wasn't
* done, decreased by old deferred work that was done now.
*
* And it is capped to two times of the freeable items.
*/
next_deferred = max_t(long, (nr + delta - scanned), 0);
next_deferred = min(next_deferred, (2 * freeable));
/*
* move the unused scan count back into the shrinker in a
* manner that handles concurrent updates.
*/
new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);
trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
return freed;
}
#ifdef CONFIG_MEMCG
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
struct shrinker_info *info;
unsigned long ret, freed = 0;
int i;
if (!mem_cgroup_online(memcg))
return 0;
if (!down_read_trylock(&shrinker_rwsem))
return 0;
info = shrinker_info_protected(memcg, nid);
if (unlikely(!info))
goto unlock;
for_each_set_bit(i, info->map, shrinker_nr_max) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
struct shrinker *shrinker;
shrinker = idr_find(&shrinker_idr, i);
if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) {
if (!shrinker)
clear_bit(i, info->map);
continue;
}
/* Call non-slab shrinkers even though kmem is disabled */
if (!memcg_kmem_enabled() &&
!(shrinker->flags & SHRINKER_NONSLAB))
continue;
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY) {
clear_bit(i, info->map);
/*
* After the shrinker reported that it had no objects to
* free, but before we cleared the corresponding bit in
* the memcg shrinker map, a new object might have been
* added. To make sure, we have the bit set in this
* case, we invoke the shrinker one more time and reset
* the bit if it reports that it is not empty anymore.
* The memory barrier here pairs with the barrier in
* set_shrinker_bit():
*
* list_lru_add() shrink_slab_memcg()
* list_add_tail() clear_bit()
* <MB> <MB>
* set_bit() do_shrink_slab()
*/
smp_mb__after_atomic();
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
else
set_shrinker_bit(memcg, nid, i);
}
freed += ret;
if (rwsem_is_contended(&shrinker_rwsem)) {
freed = freed ? : 1;
break;
}
}
unlock:
up_read(&shrinker_rwsem);
return freed;
}
#else /* CONFIG_MEMCG */
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
return 0;
}
#endif /* CONFIG_MEMCG */
/**
* shrink_slab - shrink slab caches
* @gfp_mask: allocation context
* @nid: node whose slab caches to target
* @memcg: memory cgroup whose slab caches to target
* @priority: the reclaim priority
*
* Call the shrink functions to age shrinkable caches.
*
* @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
* unaware shrinkers will receive a node id of 0 instead.
*
* @memcg specifies the memory cgroup to target. Unaware shrinkers
* are called only if it is the root cgroup.
*
* @priority is sc->priority, we take the number of objects and >> by priority
* in order to get the scan target.
*
* Returns the number of reclaimed slab objects.
*/
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
int priority)
{
unsigned long ret, freed = 0;
struct shrinker *shrinker;
/*
* The root memcg might be allocated even though memcg is disabled
* via "cgroup_disable=memory" boot parameter. This could make
* mem_cgroup_is_root() return false, then just run memcg slab
* shrink, but skip global shrink. This may result in premature
* oom.
*/
if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
if (!down_read_trylock(&shrinker_rwsem))
goto out;
list_for_each_entry(shrinker, &shrinker_list, list) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
freed += ret;
/*
* Bail out if someone want to register a new shrinker to
* prevent the registration from being stalled for long periods
* by parallel ongoing shrinking.
*/
if (rwsem_is_contended(&shrinker_rwsem)) {
freed = freed ? : 1;
break;
}
}
up_read(&shrinker_rwsem);
out:
cond_resched();
return freed;
}
static void drop_slab_node(int nid)
{
unsigned long freed;
int shift = 0;
do {
struct mem_cgroup *memcg = NULL;
if (fatal_signal_pending(current))
return;
freed = 0;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
} while ((freed >> shift++) > 1);
}
void drop_slab(void)
{
int nid;
for_each_online_node(nid)
drop_slab_node(nid);
}
static inline int is_page_cache_freeable(struct folio *folio)
{
/*
* A freeable page cache page is referenced only by the caller
* that isolated the page, the page cache and optional buffer
* heads at page->private.
*/
return folio_ref_count(folio) - folio_test_private(folio) ==
1 + folio_nr_pages(folio);
}
/*
* We detected a synchronous write error writing a folio out. Probably
* -ENOSPC. We need to propagate that into the address_space for a subsequent
* fsync(), msync() or close().
*
* The tricky part is that after writepage we cannot touch the mapping: nothing
* prevents it from being freed up. But we have a ref on the folio and once
* that folio is locked, the mapping is pinned.
*
* We're allowed to run sleeping folio_lock() here because we know the caller has
* __GFP_FS.
*/
static void handle_write_error(struct address_space *mapping,
struct folio *folio, int error)
{
folio_lock(folio);
if (folio_mapping(folio) == mapping)
mapping_set_error(mapping, error);
folio_unlock(folio);
}
static bool skip_throttle_noprogress(pg_data_t *pgdat)
{
int reclaimable = 0, write_pending = 0;
int i;
/*
* If kswapd is disabled, reschedule if necessary but do not
* throttle as the system is likely near OOM.
*/
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
/*
* If there are a lot of dirty/writeback pages then do not
* throttle as throttling will occur when the pages cycle
* towards the end of the LRU if still under writeback.
*/
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
reclaimable += zone_reclaimable_pages(zone);
write_pending += zone_page_state_snapshot(zone,
NR_ZONE_WRITE_PENDING);
}
if (2 * write_pending <= reclaimable)
return true;
return false;
}
void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
{
wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
long timeout, ret;
DEFINE_WAIT(wait);
/*
* Do not throttle IO workers, kthreads other than kswapd or
* workqueues. They may be required for reclaim to make
* forward progress (e.g. journalling workqueues or kthreads).
*/
if (!current_is_kswapd() &&
current->flags & (PF_IO_WORKER|PF_KTHREAD)) {
cond_resched();
return;
}
/*
* These figures are pulled out of thin air.
* VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
* parallel reclaimers which is a short-lived event so the timeout is
* short. Failing to make progress or waiting on writeback are
* potentially long-lived events so use a longer timeout. This is shaky
* logic as a failure to make progress could be due to anything from
* writeback to a slow device to excessive references pages at the tail
* of the inactive LRU.
*/
switch(reason) {
case VMSCAN_THROTTLE_WRITEBACK:
timeout = HZ/10;
if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
WRITE_ONCE(pgdat->nr_reclaim_start,
node_page_state(pgdat, NR_THROTTLED_WRITTEN));
}
break;
case VMSCAN_THROTTLE_CONGESTED:
fallthrough;
case VMSCAN_THROTTLE_NOPROGRESS:
if (skip_throttle_noprogress(pgdat)) {
cond_resched();
return;
}
timeout = 1;
break;
case VMSCAN_THROTTLE_ISOLATED:
timeout = HZ/50;
break;
default:
WARN_ON_ONCE(1);
timeout = HZ;
break;
}
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = schedule_timeout(timeout);
finish_wait(wqh, &wait);
if (reason == VMSCAN_THROTTLE_WRITEBACK)
atomic_dec(&pgdat->nr_writeback_throttled);
trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
jiffies_to_usecs(timeout - ret),
reason);
}
/*
* Account for pages written if tasks are throttled waiting on dirty
* pages to clean. If enough pages have been cleaned since throttling
* started then wakeup the throttled tasks.
*/
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
int nr_throttled)
{
unsigned long nr_written;
node_stat_add_folio(folio, NR_THROTTLED_WRITTEN);
/*
* This is an inaccurate read as the per-cpu deltas may not
* be synchronised. However, given that the system is
* writeback throttled, it is not worth taking the penalty
* of getting an accurate count. At worst, the throttle
* timeout guarantees forward progress.
*/
nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) -
READ_ONCE(pgdat->nr_reclaim_start);
if (nr_written > SWAP_CLUSTER_MAX * nr_throttled)
wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]);
}
/* possible outcome of pageout() */
typedef enum {
/* failed to write page out, page is locked */
PAGE_KEEP,
/* move page to the active list, page is locked */
PAGE_ACTIVATE,
/* page has been sent to the disk successfully, page is unlocked */
PAGE_SUCCESS,
/* page is clean and locked */
PAGE_CLEAN,
} pageout_t;
/*
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
static pageout_t pageout(struct folio *folio, struct address_space *mapping,
struct swap_iocb **plug)
{
/*
* If the folio is dirty, only perform writeback if that write
* will be non-blocking. To prevent this allocation from being
* stalled by pagecache activity. But note that there may be
* stalls if we need to run get_block(). We could test
* PagePrivate for that.
*
* If this process is currently in __generic_file_write_iter() against
* this folio's queue, we can perform writeback even if that
* will block.
*
* If the folio is swapcache, write it back even if that would
* block, for some throttling. This happens by accident, because
* swap_backing_dev_info is bust: it doesn't reflect the
* congestion state of the swapdevs. Easy to fix, if needed.
*/
if (!is_page_cache_freeable(folio))
return PAGE_KEEP;
if (!mapping) {
/*
* Some data journaling orphaned folios can have
* folio->mapping == NULL while being dirty with clean buffers.
*/
if (folio_test_private(folio)) {
if (try_to_free_buffers(folio)) {
folio_clear_dirty(folio);
pr_info("%s: orphaned folio\n", __func__);
return PAGE_CLEAN;
}
}
return PAGE_KEEP;
}
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
if (folio_clear_dirty_for_io(folio)) {
int res;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
.for_reclaim = 1,
.swap_plug = plug,
};
folio_set_reclaim(folio);
res = mapping->a_ops->writepage(&folio->page, &wbc);
if (res < 0)
handle_write_error(mapping, folio, res);
if (res == AOP_WRITEPAGE_ACTIVATE) {
folio_clear_reclaim(folio);
return PAGE_ACTIVATE;
}
if (!folio_test_writeback(folio)) {
/* synchronous write or broken a_ops? */
folio_clear_reclaim(folio);
}
trace_mm_vmscan_write_folio(folio);
node_stat_add_folio(folio, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
return PAGE_CLEAN;
}
/*
* Same as remove_mapping, but if the page is removed from the mapping, it
* gets returned with a refcount of 0.
*/
static int __remove_mapping(struct address_space *mapping, struct folio *folio,
bool reclaimed, struct mem_cgroup *target_memcg)
{
int refcount;
void *shadow = NULL;
BUG_ON(!folio_test_locked(folio));
BUG_ON(mapping != folio_mapping(folio));
if (!folio_test_swapcache(folio))
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
/*
* The non racy check for a busy page.
*
* Must be careful with the order of the tests. When someone has
* a ref to the page, it may be possible that they dirty it then
* drop the reference. So if PageDirty is tested before page_count
* here, then the following race may occur:
*
* get_user_pages(&page);
* [user mapping goes away]
* write_to(page);
* !PageDirty(page) [good]
* SetPageDirty(page);
* put_page(page);
* !page_count(page) [good, discard it]
*
* [oops, our write_to data is lost]
*
* Reversing the order of the tests ensures such a situation cannot
* escape unnoticed. The smp_rmb is needed to ensure the page->flags
* load is not satisfied before that of page->_refcount.
*
* Note that if SetPageDirty is always performed via set_page_dirty,
* and thus under the i_pages lock, then this ordering is not required.
*/
refcount = 1 + folio_nr_pages(folio);
if (!folio_ref_freeze(folio, refcount))
goto cannot_free;
/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */
if (unlikely(folio_test_dirty(folio))) {
folio_ref_unfreeze(folio, refcount);
goto cannot_free;
}
if (folio_test_swapcache(folio)) {
swp_entry_t swap = folio_swap_entry(folio);
mem_cgroup_swapout(folio, swap);
if (reclaimed && !mapping_exiting(mapping))
shadow = workingset_eviction(folio, target_memcg);
__delete_from_swap_cache(folio, swap, shadow);
xa_unlock_irq(&mapping->i_pages);
put_swap_page(&folio->page, swap);
} else {
void (*free_folio)(struct folio *);
free_folio = mapping->a_ops->free_folio;
/*
* Remember a shadow entry for reclaimed file cache in
* order to detect refaults, thus thrashing, later on.
*
* But don't store shadows in an address space that is
* already exiting. This is not just an optimization,
* inode reclaim needs to empty out the radix tree or
* the nodes are lost. Don't plant shadows behind its
* back.
*
* We also don't store shadows for DAX mappings because the
* only page cache pages found in these are zero pages
* covering holes, and because we don't want to mix DAX
* exceptional entries and shadow exceptional entries in the
* same address_space.
*/
if (reclaimed && folio_is_file_lru(folio) &&
!mapping_exiting(mapping) && !dax_mapping(mapping))
shadow = workingset_eviction(folio, target_memcg);
__filemap_remove_folio(folio, shadow);
xa_unlock_irq(&mapping->i_pages);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
if (free_folio)
free_folio(folio);
}
return 1;
cannot_free:
xa_unlock_irq(&mapping->i_pages);
if (!folio_test_swapcache(folio))
spin_unlock(&mapping->host->i_lock);
return 0;
}
/**
* remove_mapping() - Attempt to remove a folio from its mapping.
* @mapping: The address space.
* @folio: The folio to remove.
*
* If the folio is dirty, under writeback or if someone else has a ref
* on it, removal will fail.
* Return: The number of pages removed from the mapping. 0 if the folio
* could not be removed.
* Context: The caller should have a single refcount on the folio and
* hold its lock.
*/
long remove_mapping(struct address_space *mapping, struct folio *folio)
{
if (__remove_mapping(mapping, folio, false, NULL)) {
/*
* Unfreezing the refcount with 1 effectively
* drops the pagecache ref for us without requiring another
* atomic operation.
*/
folio_ref_unfreeze(folio, 1);
return folio_nr_pages(folio);
}
return 0;
}
/**
* folio_putback_lru - Put previously isolated folio onto appropriate LRU list.
* @folio: Folio to be returned to an LRU list.
*
* Add previously isolated @folio to appropriate LRU list.
* The folio may still be unevictable for other reasons.
*
* Context: lru_lock must not be held, interrupts must be enabled.
*/
void folio_putback_lru(struct folio *folio)
{
folio_add_lru(folio);
folio_put(folio); /* drop ref from isolate */
}
enum page_references {
PAGEREF_RECLAIM,
PAGEREF_RECLAIM_CLEAN,
PAGEREF_KEEP,
PAGEREF_ACTIVATE,
};
static enum page_references folio_check_references(struct folio *folio,
struct scan_control *sc)
{
int referenced_ptes, referenced_folio;
unsigned long vm_flags;
referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
&vm_flags);
referenced_folio = folio_test_clear_referenced(folio);
/*
* The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
* Let the folio, now marked Mlocked, be moved to the unevictable list.
*/
if (vm_flags & VM_LOCKED)
return PAGEREF_ACTIVATE;
/* rmap lock contention: rotate */
if (referenced_ptes == -1)
return PAGEREF_KEEP;
if (referenced_ptes) {
/*
* All mapped folios start out with page table
* references from the instantiating fault, so we need
* to look twice if a mapped file/anon folio is used more
* than once.
*
* Mark it and spare it for another trip around the
* inactive list. Another page table reference will
* lead to its activation.
*
* Note: the mark is set for activated folios as well
* so that recently deactivated but used folios are
* quickly recovered.
*/
folio_set_referenced(folio);
if (referenced_folio || referenced_ptes > 1)
return PAGEREF_ACTIVATE;
/*
* Activate file-backed executable folios after first usage.
*/
if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio))
return PAGEREF_ACTIVATE;
return PAGEREF_KEEP;
}
/* Reclaim if clean, defer dirty folios to writeback */
if (referenced_folio && folio_is_file_lru(folio))
return PAGEREF_RECLAIM_CLEAN;
return PAGEREF_RECLAIM;
}
/* Check if a page is dirty or under writeback */
static void folio_check_dirty_writeback(struct folio *folio,
bool *dirty, bool *writeback)
{
struct address_space *mapping;
/*
* Anonymous pages are not handled by flushers and must be written
* from reclaim context. Do not stall reclaim based on them.
* MADV_FREE anonymous pages are put into inactive file list too.
* They could be mistakenly treated as file lru. So further anon
* test is needed.
*/
if (!folio_is_file_lru(folio) ||
(folio_test_anon(folio) && !folio_test_swapbacked(folio))) {
*dirty = false;
*writeback = false;
return;
}
/* By default assume that the folio flags are accurate */
*dirty = folio_test_dirty(folio);
*writeback = folio_test_writeback(folio);
/* Verify dirty/writeback state if the filesystem supports it */
if (!folio_test_private(folio))
return;
mapping = folio_mapping(folio);
if (mapping && mapping->a_ops->is_dirty_writeback)
mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
}
static struct page *alloc_demote_page(struct page *page, unsigned long node)
{
struct migration_target_control mtc = {
/*
* Allocate from 'node', or fail quickly and quietly.
* When this happens, 'page' will likely just be discarded
* instead of migrated.
*/
.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
__GFP_THISNODE | __GFP_NOWARN |
__GFP_NOMEMALLOC | GFP_NOWAIT,
.nid = node
};
return alloc_migration_target(page, (unsigned long)&mtc);
}
/*
* Take pages on @demote_list and attempt to demote them to
* another node. Pages which are not demoted are left on
* @demote_pages.
*/
static unsigned int demote_page_list(struct list_head *demote_pages,
struct pglist_data *pgdat)
{
int target_nid = next_demotion_node(pgdat->node_id);
unsigned int nr_succeeded;
if (list_empty(demote_pages))
return 0;
if (target_nid == NUMA_NO_NODE)
return 0;
/* Demotion ignores all cpuset and mempolicy settings */
migrate_pages(demote_pages, alloc_demote_page, NULL,
target_nid, MIGRATE_ASYNC, MR_DEMOTION,
&nr_succeeded);
if (current_is_kswapd())
__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);
else
__count_vm_events(PGDEMOTE_DIRECT, nr_succeeded);
return nr_succeeded;
}
static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
{
if (gfp_mask & __GFP_FS)
return true;
if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
return false;
/*
* We can "enter_fs" for swap-cache with only __GFP_IO
* providing this isn't SWP_FS_OPS.
* ->flags can be updated non-atomicially (scan_swap_map_slots),
* but that will never affect SWP_FS_OPS, so the data_race
* is safe.
*/
return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
}
/*
* shrink_page_list() returns the number of reclaimed pages
*/
static unsigned int shrink_page_list(struct list_head *page_list,
struct pglist_data *pgdat,
struct scan_control *sc,
struct reclaim_stat *stat,
bool ignore_references)
{
LIST_HEAD(ret_pages);
LIST_HEAD(free_pages);
LIST_HEAD(demote_pages);
unsigned int nr_reclaimed = 0;
unsigned int pgactivate = 0;
bool do_demote_pass;
struct swap_iocb *plug = NULL;
memset(stat, 0, sizeof(*stat));
cond_resched();
do_demote_pass = can_demote(pgdat->node_id, sc);
retry:
while (!list_empty(page_list)) {
struct address_space *mapping;
struct folio *folio;
enum page_references references = PAGEREF_RECLAIM;
bool dirty, writeback;
unsigned int nr_pages;
cond_resched();
folio = lru_to_folio(page_list);
list_del(&folio->lru);
if (!folio_trylock(folio))
goto keep;
VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
nr_pages = folio_nr_pages(folio);
/* Account the number of base pages */
sc->nr_scanned += nr_pages;
if (unlikely(!folio_evictable(folio)))
goto activate_locked;
if (!sc->may_unmap && folio_mapped(folio))
goto keep_locked;
/*
* The number of dirty pages determines if a node is marked
* reclaim_congested. kswapd will stall and start writing
* folios if the tail of the LRU is all dirty unqueued folios.
*/
folio_check_dirty_writeback(folio, &dirty, &writeback);
if (dirty || writeback)
stat->nr_dirty += nr_pages;
if (dirty && !writeback)
stat->nr_unqueued_dirty += nr_pages;
/*
* Treat this folio as congested if folios are cycling
* through the LRU so quickly that the folios marked
* for immediate reclaim are making it to the end of
* the LRU a second time.
*/
if (writeback && folio_test_reclaim(folio))
stat->nr_congested += nr_pages;
/*
* If a folio at the tail of the LRU is under writeback, there
* are three cases to consider.
*
* 1) If reclaim is encountering an excessive number
* of folios under writeback and this folio has both
* the writeback and reclaim flags set, then it
* indicates that folios are being queued for I/O but
* are being recycled through the LRU before the I/O
* can complete. Waiting on the folio itself risks an
* indefinite stall if it is impossible to writeback
* the folio due to I/O error or disconnected storage
* so instead note that the LRU is being scanned too
* quickly and the caller can stall after the folio
* list has been processed.
*
* 2) Global or new memcg reclaim encounters a folio that is
* not marked for immediate reclaim, or the caller does not
* have __GFP_FS (or __GFP_IO if it's simply going to swap,
* not to fs). In this case mark the folio for immediate
* reclaim and continue scanning.
*
* Require may_enter_fs() because we would wait on fs, which
* may not have submitted I/O yet. And the loop driver might
* enter reclaim, and deadlock if it waits on a folio for
* which it is needed to do the write (loop masks off
* __GFP_IO|__GFP_FS for this reason); but more thought
* would probably show more reasons.
*
* 3) Legacy memcg encounters a folio that already has the
* reclaim flag set. memcg does not have any dirty folio
* throttling so we could easily OOM just because too many
* folios are in writeback and there is nothing else to
* reclaim. Wait for the writeback to complete.
*
* In cases 1) and 2) we activate the folios to get them out of
* the way while we continue scanning for clean folios on the
* inactive list and refilling from the active list. The
* observation here is that waiting for disk writes is more
* expensive than potentially causing reloads down the line.
* Since they're marked for immediate reclaim, they won't put
* memory pressure on the cache working set any longer than it
* takes to write them to disk.
*/
if (folio_test_writeback(folio)) {
/* Case 1 above */
if (current_is_kswapd() &&
folio_test_reclaim(folio) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
stat->nr_immediate += nr_pages;
goto activate_locked;
/* Case 2 above */
} else if (writeback_throttling_sane(sc) ||
!folio_test_reclaim(folio) ||
!may_enter_fs(folio, sc->gfp_mask)) {
/*
* This is slightly racy -
* folio_end_writeback() might have
* just cleared the reclaim flag, then
* setting the reclaim flag here ends up
* interpreted as the readahead flag - but
* that does not matter enough to care.
* What we do want is for this folio to
* have the reclaim flag set next time
* memcg reclaim reaches the tests above,
* so it will then wait for writeback to
* avoid OOM; and it's also appropriate
* in global reclaim.
*/
folio_set_reclaim(folio);
stat->nr_writeback += nr_pages;
goto activate_locked;
/* Case 3 above */
} else {
folio_unlock(folio);
folio_wait_writeback(folio);
/* then go back and try same folio again */
list_add_tail(&folio->lru, page_list);
continue;
}
}
if (!ignore_references)
references = folio_check_references(folio, sc);
switch (references) {
case PAGEREF_ACTIVATE:
goto activate_locked;
case PAGEREF_KEEP:
stat->nr_ref_keep += nr_pages;
goto keep_locked;
case PAGEREF_RECLAIM:
case PAGEREF_RECLAIM_CLEAN:
; /* try to reclaim the folio below */
}
/*
* Before reclaiming the folio, try to relocate
* its contents to another node.
*/
if (do_demote_pass &&
(thp_migration_supported() || !folio_test_large(folio))) {
list_add(&folio->lru, &demote_pages);
folio_unlock(folio);
continue;
}
/*
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
* Lazyfree folio could be freed directly
*/
if (folio_test_anon(folio) && folio_test_swapbacked(folio)) {
if (!folio_test_swapcache(folio)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (folio_maybe_dma_pinned(folio))
goto keep_locked;
if (folio_test_large(folio)) {
/* cannot split folio, skip it */
if (!can_split_folio(folio, NULL))
goto activate_locked;
/*
* Split folios without a PMD map right
* away. Chances are some or all of the
* tail pages can be freed without IO.
*/
if (!folio_entire_mapcount(folio) &&
split_folio_to_list(folio,
page_list))
goto activate_locked;
}
if (!add_to_swap(folio)) {
if (!folio_test_large(folio))
goto activate_locked_split;
/* Fallback to swap normal pages */
if (split_folio_to_list(folio,
page_list))
goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_vm_event(THP_SWPOUT_FALLBACK);
#endif
if (!add_to_swap(folio))
goto activate_locked_split;
}
}
} else if (folio_test_swapbacked(folio) &&
folio_test_large(folio)) {
/* Split shmem folio */
if (split_folio_to_list(folio, page_list))
goto keep_locked;
}
/*
* If the folio was split above, the tail pages will make
* their own pass through this function and be accounted
* then.
*/
if ((nr_pages > 1) && !folio_test_large(folio)) {
sc->nr_scanned -= (nr_pages - 1);
nr_pages = 1;
}
/*
* The folio is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
if (folio_mapped(folio)) {
enum ttu_flags flags = TTU_BATCH_FLUSH;
bool was_swapbacked = folio_test_swapbacked(folio);
if (folio_test_pmd_mappable(folio))
flags |= TTU_SPLIT_HUGE_PMD;
try_to_unmap(folio, flags);
if (folio_mapped(folio)) {
stat->nr_unmap_fail += nr_pages;
if (!was_swapbacked &&
folio_test_swapbacked(folio))
stat->nr_lazyfree_fail += nr_pages;
goto activate_locked;
}
}
mapping = folio_mapping(folio);
if (folio_test_dirty(folio)) {
/*
* Only kswapd can writeback filesystem folios
* to avoid risk of stack overflow. But avoid
* injecting inefficient single-folio I/O into
* flusher writeback as much as possible: only
* write folios when we've encountered many
* dirty folios, and when we've already scanned
* the rest of the LRU for clean folios and see
* the same dirty folios again (with the reclaim
* flag set).
*/
if (folio_is_file_lru(folio) &&
(!current_is_kswapd() ||
!folio_test_reclaim(folio) ||
!test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
* Similar in principle to deactivate_page()
* except we already have the folio isolated
* and know it's dirty
*/
node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
nr_pages);
folio_set_reclaim(folio);
goto activate_locked;
}
if (references == PAGEREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs(folio, sc->gfp_mask))
goto keep_locked;
if (!sc->may_writepage)
goto keep_locked;
/*
* Folio is dirty. Flush the TLB if a writable entry
* potentially exists to avoid CPU writes after I/O
* starts and then write it out here.
*/
try_to_unmap_flush_dirty();
switch (pageout(folio, mapping, &plug)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
goto activate_locked;
case PAGE_SUCCESS:
stat->nr_pageout += nr_pages;
if (folio_test_writeback(folio))
goto keep;
if (folio_test_dirty(folio))
goto keep;
/*
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the folio.
*/
if (!folio_trylock(folio))
goto keep;
if (folio_test_dirty(folio) ||
folio_test_writeback(folio))
goto keep_locked;
mapping = folio_mapping(folio);
fallthrough;
case PAGE_CLEAN:
; /* try to free the folio below */
}
}
/*
* If the folio has buffers, try to free the buffer
* mappings associated with this folio. If we succeed
* we try to free the folio as well.
*
* We do this even if the folio is dirty.
* filemap_release_folio() does not perform I/O, but it
* is possible for a folio to have the dirty flag set,
* but it is actually clean (all its buffers are clean).
* This happens if the buffers were written out directly,
* with submit_bh(). ext3 will do this, as well as
* the blockdev mapping. filemap_release_folio() will
* discover that cleanness and will drop the buffers
* and mark the folio clean - it can be freed.
*
* Rarely, folios can have buffers and no ->mapping.
* These are the folios which were not successfully
* invalidated in truncate_cleanup_folio(). We try to
* drop those buffers here and if that worked, and the
* folio is no longer mapped into process address space
* (refcount == 1) it can be freed. Otherwise, leave
* the folio on the LRU so it is swappable.
*/
if (folio_has_private(folio)) {
if (!filemap_release_folio(folio, sc->gfp_mask))
goto activate_locked;
if (!mapping && folio_ref_count(folio) == 1) {
folio_unlock(folio);
if (folio_put_testzero(folio))
goto free_it;
else {
/*
* rare race with speculative reference.
* the speculative reference will free
* this folio shortly, so we may
* increment nr_reclaimed here (and
* leave it off the LRU).
*/
nr_reclaimed += nr_pages;
continue;
}
}
}
if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
/* follow __remove_mapping for reference */
if (!folio_ref_freeze(folio, 1))
goto keep_locked;
/*
* The folio has only one reference left, which is
* from the isolation. After the caller puts the
* folio back on the lru and drops the reference, the
* folio will be freed anyway. It doesn't matter
* which lru it goes on. So we don't bother checking
* the dirty flag here.
*/
count_vm_events(PGLAZYFREED, nr_pages);
count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
} else if (!mapping || !__remove_mapping(mapping, folio, true,
sc->target_mem_cgroup))
goto keep_locked;
folio_unlock(folio);
free_it:
/*
* Folio may get swapped out as a whole, need to account
* all pages in it.
*/
nr_reclaimed += nr_pages;
/*
* Is there need to periodically free_page_list? It would
* appear not as the counts should be low
*/
if (unlikely(folio_test_large(folio)))
destroy_large_folio(folio);
else
list_add(&folio->lru, &free_pages);
continue;
activate_locked_split:
/*
* The tail pages that are failed to add into swap cache
* reach here. Fixup nr_scanned and nr_pages.
*/
if (nr_pages > 1) {
sc->nr_scanned -= (nr_pages - 1);
nr_pages = 1;
}
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (folio_test_swapcache(folio) &&
(mem_cgroup_swap_full(&folio->page) ||
folio_test_mlocked(folio)))
try_to_free_swap(&folio->page);
VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
if (!folio_test_mlocked(folio)) {
int type = folio_is_file_lru(folio);
folio_set_active(folio);
stat->nr_activate[type] += nr_pages;
count_memcg_folio_events(folio, PGACTIVATE, nr_pages);
}
keep_locked:
folio_unlock(folio);
keep:
list_add(&folio->lru, &ret_pages);
VM_BUG_ON_FOLIO(folio_test_lru(folio) ||
folio_test_unevictable(folio), folio);
}
/* 'page_list' is always empty here */
/* Migrate folios selected for demotion */
nr_reclaimed += demote_page_list(&demote_pages, pgdat);
/* Folios that could not be demoted are still in @demote_pages */
if (!list_empty(&demote_pages)) {
/* Folios which weren't demoted go back on @page_list for retry: */
list_splice_init(&demote_pages, page_list);
do_demote_pass = false;
goto retry;
}
pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
mem_cgroup_uncharge_list(&free_pages);
try_to_unmap_flush();
free_unref_page_list(&free_pages);
list_splice(&ret_pages, page_list);
count_vm_events(PGACTIVATE, pgactivate);
if (plug)
swap_write_unplug(plug);
return nr_reclaimed;
}
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *folio_list)
{
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
};
struct reclaim_stat stat;
unsigned int nr_reclaimed;
struct folio *folio, *next;
LIST_HEAD(clean_folios);
unsigned int noreclaim_flag;
list_for_each_entry_safe(folio, next, folio_list, lru) {
if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) &&
!folio_test_dirty(folio) && !__folio_test_movable(folio) &&
!folio_test_unevictable(folio)) {
folio_clear_active(folio);
list_move(&folio->lru, &clean_folios);
}
}
/*
* We should be safe here since we are only dealing with file pages and
* we are not kswapd and therefore cannot write dirty file pages. But
* call memalloc_noreclaim_save() anyway, just in case these conditions
* change in the future.
*/
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = shrink_page_list(&clean_folios, zone->zone_pgdat, &sc,
&stat, true);
memalloc_noreclaim_restore(noreclaim_flag);
list_splice(&clean_folios, folio_list);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-(long)nr_reclaimed);
/*
* Since lazyfree pages are isolated from file LRU from the beginning,
* they will rotate back to anonymous LRU in the end if it failed to
* discard so isolated count will be mismatched.
* Compensate the isolated count for both LRU lists.
*/
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
stat.nr_lazyfree_fail);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-(long)stat.nr_lazyfree_fail);
return nr_reclaimed;
}
/*
* Update LRU sizes after isolating pages. The LRU size updates must
* be complete before mem_cgroup_update_lru_size due to a sanity check.
*/
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
enum lru_list lru, unsigned long *nr_zone_taken)
{
int zid;
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
if (!nr_zone_taken[zid])
continue;
update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
}
}
/*
* Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
*
* lruvec->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
* For pagecache intensive workloads, this function is the hottest
* spot in the kernel (apart from copy_*_user functions).
*
* Lru_lock must be held before calling this function.
*
* @nr_to_scan: The number of eligible pages to look through on the list.
* @lruvec: The LRU vector to pull pages from.
* @dst: The temp list to put pages on to.
* @nr_scanned: The number of pages that were scanned.
* @sc: The scan_control struct for this reclaim session
* @lru: LRU list id for isolating
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct lruvec *lruvec, struct list_head *dst,
unsigned long *nr_scanned, struct scan_control *sc,
enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long skipped = 0;
unsigned long scan, total_scan, nr_pages;
LIST_HEAD(folios_skipped);
total_scan = 0;
scan = 0;
while (scan < nr_to_scan && !list_empty(src)) {
struct list_head *move_to = src;
struct folio *folio;
folio = lru_to_folio(src);
prefetchw_prev_lru_folio(folio, src, flags);
nr_pages = folio_nr_pages(folio);
total_scan += nr_pages;
if (folio_zonenum(folio) > sc->reclaim_idx) {
nr_skipped[folio_zonenum(folio)] += nr_pages;
move_to = &folios_skipped;
goto move;
}
/*
* Do not count skipped folios because that makes the function
* return with no isolated folios if the LRU mostly contains
* ineligible folios. This causes the VM to not reclaim any
* folios, triggering a premature OOM.
* Account all pages in a folio.
*/
scan += nr_pages;
if (!folio_test_lru(folio))
goto move;
if (!sc->may_unmap && folio_mapped(folio))
goto move;
/*
* Be careful not to clear the lru flag until after we're
* sure the folio is not being freed elsewhere -- the
* folio release code relies on it.
*/
if (unlikely(!folio_try_get(folio)))
goto move;
if (!folio_test_clear_lru(folio)) {
/* Another thread is already isolating this folio */
folio_put(folio);
goto move;
}
nr_taken += nr_pages;
nr_zone_taken[folio_zonenum(folio)] += nr_pages;
move_to = dst;
move:
list_move(&folio->lru, move_to);
}
/*
* Splice any skipped folios to the start of the LRU list. Note that
* this disrupts the LRU order when reclaiming for lower zones but
* we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
* scanning would soon rescan the same folios to skip and waste lots
* of cpu cycles.
*/
if (!list_empty(&folios_skipped)) {
int zid;
list_splice(&folios_skipped, src);
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
if (!nr_skipped[zid])
continue;
__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
skipped += nr_skipped[zid];
}
}
*nr_scanned = total_scan;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
total_scan, skipped, nr_taken,
sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru);
update_lru_sizes(lruvec, lru, nr_zone_taken);
return nr_taken;
}
/**
* folio_isolate_lru() - Try to isolate a folio from its LRU list.
* @folio: Folio to isolate from its LRU list.
*
* Isolate a @folio from an LRU list and adjust the vmstat statistic
* corresponding to whatever LRU list the folio was on.
*
* The folio will have its LRU flag cleared. If it was found on the
* active list, it will have the Active flag set. If it was found on the
* unevictable list, it will have the Unevictable flag set. These flags
* may need to be cleared by the caller before letting the page go.
*
* Context:
*
* (1) Must be called with an elevated refcount on the page. This is a
* fundamental difference from isolate_lru_pages() (which is called
* without a stable reference).
* (2) The lru_lock must not be held.
* (3) Interrupts must be enabled.
*
* Return: 0 if the folio was removed from an LRU list.
* -EBUSY if the folio was not on an LRU list.
*/
int folio_isolate_lru(struct folio *folio)
{
int ret = -EBUSY;
VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio);
if (folio_test_clear_lru(folio)) {
struct lruvec *lruvec;
folio_get(folio);
lruvec = folio_lruvec_lock_irq(folio);
lruvec_del_folio(lruvec, folio);
unlock_page_lruvec_irq(lruvec);
ret = 0;
}
return ret;
}
/*
* A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
* then get rescheduled. When there are massive number of tasks doing page
* allocation, such sleeping direct reclaimers may keep piling up on each CPU,
* the LRU list will go small and be scanned faster than necessary, leading to
* unnecessary swapping, thrashing and OOM.
*/
static int too_many_isolated(struct pglist_data *pgdat, int file,
struct scan_control *sc)
{
unsigned long inactive, isolated;
bool too_many;
if (current_is_kswapd())
return 0;
if (!writeback_throttling_sane(sc))
return 0;
if (file) {
inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
} else {
inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
}
/*
* GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
* won't get blocked by normal direct-reclaimers, forming a circular
* deadlock.
*/
if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
inactive >>= 3;
too_many = isolated > inactive;
/* Wake up tasks throttled due to too_many_isolated. */
if (!too_many)
wake_throttle_isolated(pgdat);
return too_many;
}
/*
* move_pages_to_lru() moves folios from private @list to appropriate LRU list.
* On return, @list is reused as a list of folios to be freed by the caller.
*
* Returns the number of pages moved to the given lruvec.
*/
static unsigned int move_pages_to_lru(struct lruvec *lruvec,
struct list_head *list)
{
int nr_pages, nr_moved = 0;
LIST_HEAD(folios_to_free);
while (!list_empty(list)) {
struct folio *folio = lru_to_folio(list);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
list_del(&folio->lru);
if (unlikely(!folio_evictable(folio))) {
spin_unlock_irq(&lruvec->lru_lock);
folio_putback_lru(folio);
spin_lock_irq(&lruvec->lru_lock);
continue;
}
/*
* The folio_set_lru needs to be kept here for list integrity.
* Otherwise:
* #0 move_pages_to_lru #1 release_pages
* if (!folio_put_testzero())
* if (folio_put_testzero())
* !lru //skip lru_lock
* folio_set_lru()
* list_add(&folio->lru,)
* list_add(&folio->lru,)
*/
folio_set_lru(folio);
if (unlikely(folio_put_testzero(folio))) {
__folio_clear_lru_flags(folio);
if (unlikely(folio_test_large(folio))) {
spin_unlock_irq(&lruvec->lru_lock);
destroy_large_folio(folio);
spin_lock_irq(&lruvec->lru_lock);
} else
list_add(&folio->lru, &folios_to_free);
continue;
}
/*
* All pages were isolated from the same lruvec (and isolation
* inhibits memcg migration).
*/
VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
lruvec_add_folio(lruvec, folio);
nr_pages = folio_nr_pages(folio);
nr_moved += nr_pages;
if (folio_test_active(folio))
workingset_age_nonresident(lruvec, nr_pages);
}
/*
* To save our caller's stack, now use input list for pages to free.
*/
list_splice(&folios_to_free, list);
return nr_moved;
}
/*
* If a kernel thread (such as nfsd for loop-back mounts) services a backing
* device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case
* we should not throttle. Otherwise it is safe to do so.
*/
static int current_may_throttle(void)
{
return !(current->flags & PF_LOCAL_THROTTLE);
}
/*
* shrink_inactive_list() is a helper for shrink_node(). It returns the number
* of reclaimed pages
*/
static unsigned long
shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
struct scan_control *sc, enum lru_list lru)
{
LIST_HEAD(page_list);
unsigned long nr_scanned;
unsigned int nr_reclaimed = 0;
unsigned long nr_taken;
struct reclaim_stat stat;
bool file = is_file_lru(lru);
enum vm_event_item item;
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
bool stalled = false;
while (unlikely(too_many_isolated(pgdat, file, sc))) {
if (stalled)
return 0;
/* wait a bit for the reclaimer. */
stalled = true;
reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
return SWAP_CLUSTER_MAX;
}
lru_add_drain();
spin_lock_irq(&lruvec->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
&nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_scanned);
__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
__count_vm_events(PGSCAN_ANON + file, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
if (nr_taken == 0)
return 0;
nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
spin_lock_irq(&lruvec->lru_lock);
move_pages_to_lru(lruvec, &page_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_reclaimed);
__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
spin_unlock_irq(&lruvec->lru_lock);
lru_note_cost(lruvec, file, stat.nr_pageout);
mem_cgroup_uncharge_list(&page_list);
free_unref_page_list(&page_list);
/*
* If dirty pages are scanned that are not queued for IO, it
* implies that flushers are not doing their job. This can
* happen when memory pressure pushes dirty pages to the end of
* the LRU before the dirty limits are breached and the dirty
* data has expired. It can also happen when the proportion of
* dirty pages grows not through writes but through memory
* pressure reclaiming all the clean cache. And in some cases,
* the flushers simply cannot keep up with the allocation
* rate. Nudge the flusher threads in case they are asleep.
*/
if (stat.nr_unqueued_dirty == nr_taken)
wakeup_flusher_threads(WB_REASON_VMSCAN);
sc->nr.dirty += stat.nr_dirty;
sc->nr.congested += stat.nr_congested;
sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
sc->nr.writeback += stat.nr_writeback;
sc->nr.immediate += stat.nr_immediate;
sc->nr.taken += nr_taken;
if (file)
sc->nr.file_taken += nr_taken;
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
nr_scanned, nr_reclaimed, &stat, sc->priority, file);
return nr_reclaimed;
}
/*
* shrink_active_list() moves folios from the active LRU to the inactive LRU.
*
* We move them the other way if the folio is referenced by one or more
* processes.
*
* If the folios are mostly unmapped, the processing is fast and it is
* appropriate to hold lru_lock across the whole operation. But if
* the folios are mapped, the processing is slow (folio_referenced()), so
* we should drop lru_lock around each folio. It's impossible to balance
* this, so instead we remove the folios from the LRU while processing them.
* It is safe to rely on the active flag against the non-LRU folios in here
* because nobody will play with that bit on a non-LRU folio.
*
* The downside is that we have to touch folio->_refcount against each folio.
* But we had to alter folio->flags anyway.
*/
static void shrink_active_list(unsigned long nr_to_scan,
struct lruvec *lruvec,
struct scan_control *sc,
enum lru_list lru)
{
unsigned long nr_taken;
unsigned long nr_scanned;
unsigned long vm_flags;
LIST_HEAD(l_hold); /* The folios which were snipped off */
LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
unsigned nr_deactivate, nr_activate;
unsigned nr_rotated = 0;
int file = is_file_lru(lru);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
lru_add_drain();
spin_lock_irq(&lruvec->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
if (!cgroup_reclaim(sc))
__count_vm_events(PGREFILL, nr_scanned);
__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
while (!list_empty(&l_hold)) {
struct folio *folio;
cond_resched();
folio = lru_to_folio(&l_hold);
list_del(&folio->lru);
if (unlikely(!folio_evictable(folio))) {
folio_putback_lru(folio);
continue;
}
if (unlikely(buffer_heads_over_limit)) {
if (folio_test_private(folio) && folio_trylock(folio)) {
if (folio_test_private(folio))
filemap_release_folio(folio, 0);
folio_unlock(folio);
}
}
/* Referenced or rmap lock contention: rotate */
if (folio_referenced(folio, 0, sc->target_mem_cgroup,
&vm_flags) != 0) {
/*
* Identify referenced, file-backed active folios and
* give them one more trip around the active list. So
* that executable code get better chances to stay in
* memory under moderate memory pressure. Anon folios
* are not likely to be evicted by use-once streaming
* IO, plus JVM can create lots of anon VM_EXEC folios,
* so we ignore them here.
*/
if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
nr_rotated += folio_nr_pages(folio);
list_add(&folio->lru, &l_active);
continue;
}
}
folio_clear_active(folio); /* we are de-activating */
folio_set_workingset(folio);
list_add(&folio->lru, &l_inactive);
}
/*
* Move folios back to the lru list.
*/
spin_lock_irq(&lruvec->lru_lock);
nr_activate = move_pages_to_lru(lruvec, &l_active);
nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
/* Keep all free folios in l_active list */
list_splice(&l_inactive, &l_active);
__count_vm_events(PGDEACTIVATE, nr_deactivate);
__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&lruvec->lru_lock);
mem_cgroup_uncharge_list(&l_active);
free_unref_page_list(&l_active);
trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
nr_deactivate, nr_rotated, sc->priority, file);
}
static unsigned int reclaim_page_list(struct list_head *page_list,
struct pglist_data *pgdat)
{
struct reclaim_stat dummy_stat;
unsigned int nr_reclaimed;
struct folio *folio;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_writepage = 1,
.may_unmap = 1,
.may_swap = 1,
.no_demotion = 1,
};
nr_reclaimed = shrink_page_list(page_list, pgdat, &sc, &dummy_stat, false);
while (!list_empty(page_list)) {
folio = lru_to_folio(page_list);
list_del(&folio->lru);
folio_putback_lru(folio);
}
return nr_reclaimed;
}
unsigned long reclaim_pages(struct list_head *folio_list)
{
int nid;
unsigned int nr_reclaimed = 0;
LIST_HEAD(node_folio_list);
unsigned int noreclaim_flag;
if (list_empty(folio_list))
return nr_reclaimed;
noreclaim_flag = memalloc_noreclaim_save();
nid = folio_nid(lru_to_folio(folio_list));
do {
struct folio *folio = lru_to_folio(folio_list);
if (nid == folio_nid(folio)) {
folio_clear_active(folio);
list_move(&folio->lru, &node_folio_list);
continue;
}
nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid));
nid = folio_nid(lru_to_folio(folio_list));
} while (!list_empty(folio_list));
nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid));
memalloc_noreclaim_restore(noreclaim_flag);
return nr_reclaimed;
}
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct lruvec *lruvec, struct scan_control *sc)
{
if (is_active_lru(lru)) {
if (sc->may_deactivate & (1 << is_file_lru(lru)))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
else
sc->skipped_deactivate = 1;
return 0;
}
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
/*
* The inactive anon list should be small enough that the VM never has
* to do too much work.
*
* The inactive file list should be small enough to leave most memory
* to the established workingset on the scan-resistant active list,
* but large enough to avoid thrashing the aggregate readahead window.
*
* Both inactive lists should also be large enough that each inactive
* page has a chance to be referenced again before it is reclaimed.
*
* If that fails and refaulting is observed, the inactive list grows.
*
* The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages
* on this LRU, maintained by the pageout code. An inactive_ratio
* of 3 means 3:1 or 25% of the pages are kept on the inactive list.
*
* total target max
* memory ratio inactive
* -------------------------------------
* 10MB 1 5MB
* 100MB 1 50MB
* 1GB 3 250MB
* 10GB 10 0.9GB
* 100GB 31 3GB
* 1TB 101 10GB
* 10TB 320 32GB
*/
static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
{
enum lru_list active_lru = inactive_lru + LRU_ACTIVE;
unsigned long inactive, active;
unsigned long inactive_ratio;
unsigned long gb;
inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
gb = (inactive + active) >> (30 - PAGE_SHIFT);
if (gb)
inactive_ratio = int_sqrt(10 * gb);
else
inactive_ratio = 1;
return inactive * inactive_ratio < active;
}
enum scan_balance {
SCAN_EQUAL,
SCAN_FRACT,
SCAN_ANON,
SCAN_FILE,
};
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned.
*
* nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
* nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
*/
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
unsigned long *nr)
{
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
unsigned long anon_cost, file_cost, total_cost;
int swappiness = mem_cgroup_swappiness(memcg);
u64 fraction[ANON_AND_FILE];
u64 denominator = 0; /* gcc */
enum scan_balance scan_balance;
unsigned long ap, fp;
enum lru_list lru;
/* If we have no swap space, do not bother scanning anon pages. */
if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Global reclaim will swap to prevent OOM even with no
* swappiness, but memcg users want to use this knob to
* disable swapping for individual groups completely when
* using the memory controller's swap limit feature would be
* too expensive.
*/
if (cgroup_reclaim(sc) && !swappiness) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Do not apply any pressure balancing cleverness when the
* system is close to OOM, scan both anon and file equally
* (unless the swappiness setting disagrees with swapping).
*/
if (!sc->priority && swappiness) {
scan_balance = SCAN_EQUAL;
goto out;
}
/*
* If the system is almost out of file pages, force-scan anon.
*/
if (sc->file_is_tiny) {
scan_balance = SCAN_ANON;
goto out;
}
/*
* If there is enough inactive page cache, we do not reclaim
* anything from the anonymous working right now.
*/
if (sc->cache_trim_mode) {
scan_balance = SCAN_FILE;
goto out;
}
scan_balance = SCAN_FRACT;
/*
* Calculate the pressure balance between anon and file pages.
*
* The amount of pressure we put on each LRU is inversely
* proportional to the cost of reclaiming each list, as
* determined by the share of pages that are refaulting, times
* the relative IO cost of bringing back a swapped out
* anonymous page vs reloading a filesystem page (swappiness).
*
* Although we limit that influence to ensure no list gets
* left behind completely: at least a third of the pressure is
* applied, before swappiness.
*
* With swappiness at 100, anon and file have equal IO cost.
*/
total_cost = sc->anon_cost + sc->file_cost;
anon_cost = total_cost + sc->anon_cost;
file_cost = total_cost + sc->file_cost;
total_cost = anon_cost + file_cost;
ap = swappiness * (total_cost + 1);
ap /= anon_cost + 1;
fp = (200 - swappiness) * (total_cost + 1);
fp /= file_cost + 1;
fraction[0] = ap;
fraction[1] = fp;
denominator = ap + fp;
out:
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
unsigned long lruvec_size;
unsigned long low, min;
unsigned long scan;
lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
mem_cgroup_protection(sc->target_mem_cgroup, memcg,
&min, &low);
if (min || low) {
/*
* Scale a cgroup's reclaim pressure by proportioning
* its current usage to its memory.low or memory.min
* setting.
*
* This is important, as otherwise scanning aggression
* becomes extremely binary -- from nothing as we
* approach the memory protection threshold, to totally
* nominal as we exceed it. This results in requiring
* setting extremely liberal protection thresholds. It
* also means we simply get no protection at all if we
* set it too low, which is not ideal.
*
* If there is any protection in place, we reduce scan
* pressure by how much of the total memory used is
* within protection thresholds.
*
* There is one special case: in the first reclaim pass,
* we skip over all groups that are within their low
* protection. If that fails to reclaim enough pages to
* satisfy the reclaim goal, we come back and override
* the best-effort low protection. However, we still
* ideally want to honor how well-behaved groups are in
* that case instead of simply punishing them all
* equally. As such, we reclaim them based on how much
* memory they are using, reducing the scan pressure
* again by how much of the total memory used is under
* hard protection.
*/
unsigned long cgroup_size = mem_cgroup_size(memcg);
unsigned long protection;
/* memory.low scaling, make sure we retry before OOM */
if (!sc->memcg_low_reclaim && low > min) {
protection = low;
sc->memcg_low_skipped = 1;
} else {
protection = min;
}
/* Avoid TOCTOU with earlier protection check */
cgroup_size = max(cgroup_size, protection);
scan = lruvec_size - lruvec_size * protection /
(cgroup_size + 1);
/*
* Minimally target SWAP_CLUSTER_MAX pages to keep
* reclaim moving forwards, avoiding decrementing
* sc->priority further than desirable.
*/
scan = max(scan, SWAP_CLUSTER_MAX);
} else {
scan = lruvec_size;
}
scan >>= sc->priority;
/*
* If the cgroup's already been deleted, make sure to
* scrape out the remaining cache.
*/
if (!scan && !mem_cgroup_online(memcg))
scan = min(lruvec_size, SWAP_CLUSTER_MAX);
switch (scan_balance) {
case SCAN_EQUAL:
/* Scan lists relative to size */
break;
case SCAN_FRACT:
/*
* Scan types proportional to swappiness and
* their relative recent reclaim efficiency.
* Make sure we don't miss the last page on
* the offlined memory cgroups because of a
* round-off error.
*/
scan = mem_cgroup_online(memcg) ?
div64_u64(scan * fraction[file], denominator) :
DIV64_U64_ROUND_UP(scan * fraction[file],
denominator);
break;
case SCAN_FILE:
case SCAN_ANON:
/* Scan one type exclusively */
if ((scan_balance == SCAN_FILE) != file)
scan = 0;
break;
default:
/* Look ma, no brain */
BUG();
}
nr[lru] = scan;
}
}
/*
* Anonymous LRU management is a waste if there is
* ultimately no way to reclaim the memory.
*/
static bool can_age_anon_pages(struct pglist_data *pgdat,
struct scan_control *sc)
{
/* Aging the anon LRU is valuable if swap is present: */
if (total_swap_pages > 0)
return true;
/* Also valuable if anon pages can be demoted: */
return can_demote(pgdat->node_id, sc);
}
static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list lru;
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct blk_plug plug;
bool scan_adjusted;
get_scan_count(lruvec, sc, nr);
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
/*
* Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
* event that can occur when there is little memory pressure e.g.
* multiple streaming readers/writers. Hence, we do not abort scanning
* when the requested number of pages are reclaimed when scanning at
* DEF_PRIORITY on the assumption that the fact we are direct
* reclaiming implies that kswapd is not keeping up and it is best to
* do a batch of work at once. For memcg reclaim one check is made to
* abort proportional reclaim if either the file or anon lru has already
* dropped to zero at the first pass.
*/
scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
unsigned long nr_anon, nr_file, percentage;
unsigned long nr_scanned;
for_each_evictable_lru(lru) {
if (nr[lru]) {
nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
lruvec, sc);
}
}
cond_resched();
if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
continue;
/*
* For kswapd and memcg, reclaim at least the number of pages
* requested. Ensure that the anon and file LRUs are scanned
* proportionally what was requested by get_scan_count(). We
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
*/
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
/*
* It's just vindictive to attack the larger once the smaller
* has gone to zero. And given the way we stop scanning the
* smaller below, this makes sure that we only make one nudge
* towards proportionality once we've got nr_to_reclaim.
*/
if (!nr_file || !nr_anon)
break;
if (nr_file > nr_anon) {
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
targets[LRU_ACTIVE_ANON] + 1;
lru = LRU_BASE;
percentage = nr_anon * 100 / scan_target;
} else {
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
targets[LRU_ACTIVE_FILE] + 1;
lru = LRU_FILE;
percentage = nr_file * 100 / scan_target;
}
/* Stop scanning the smaller of the LRU */
nr[lru] = 0;
nr[lru + LRU_ACTIVE] = 0;
/*
* Recalculate the other LRU scan count based on its original
* scan target and the percentage scanning already complete
*/
lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
lru += LRU_ACTIVE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
scan_adjusted = true;
}
blk_finish_plug(&plug);
sc->nr_reclaimed += nr_reclaimed;
/*
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) &&
inactive_is_low(lruvec, LRU_INACTIVE_ANON))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
sc->priority < DEF_PRIORITY - 2))
return true;
return false;
}
/*
* Reclaim/compaction is used for high-order allocation requests. It reclaims
* order-0 pages before compacting the zone. should_continue_reclaim() returns
* true if more pages should be reclaimed such that when the page allocator
* calls try_to_compact_pages() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
static inline bool should_continue_reclaim(struct pglist_data *pgdat,
unsigned long nr_reclaimed,
struct scan_control *sc)
{
unsigned long pages_for_compaction;
unsigned long inactive_lru_pages;
int z;
/* If not in reclaim/compaction mode, stop */
if (!in_reclaim_compaction(sc))
return false;
/*
* Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX
* number of pages that were scanned. This will return to the caller
* with the risk reclaim/compaction and the resulting allocation attempt
* fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL
* allocations through requiring that the full LRU list has been scanned
* first, by assuming that zero delta of sc->nr_scanned means full LRU
* scan, but that approximation was wrong, and there were corner cases
* where always a non-zero amount of pages were scanned.
*/
if (!nr_reclaimed)
return false;
/* If compaction would go ahead or the allocation would succeed, stop */
for (z = 0; z <= sc->reclaim_idx; z++) {
struct zone *zone = &pgdat->node_zones[z];
if (!managed_zone(zone))
continue;
switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
case COMPACT_SUCCESS:
case COMPACT_CONTINUE:
return false;
default:
/* check next zone */
;
}
}
/*
* If we have not reclaimed enough pages for compaction and the
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = compact_gap(sc->order);
inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
return inactive_lru_pages > pages_for_compaction;
}
static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
{
struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
struct mem_cgroup *memcg;
memcg = mem_cgroup_iter(target_memcg, NULL, NULL);
do {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
unsigned long reclaimed;
unsigned long scanned;
/*
* This loop can become CPU-bound when target memcgs
* aren't eligible for reclaim - either because they
* don't have any reclaimable pages, or because their
* memory is explicitly protected. Avoid soft lockups.
*/
cond_resched();
mem_cgroup_calculate_protection(target_memcg, memcg);
if (mem_cgroup_below_min(memcg)) {
/*
* Hard protection.
* If there is no reclaimable memory, OOM.
*/
continue;
} else if (mem_cgroup_below_low(memcg)) {
/*
* Soft protection.
* Respect the protection only as long as
* there is an unprotected supply
* of reclaimable memory from other cgroups.
*/
if (!sc->memcg_low_reclaim) {
sc->memcg_low_skipped = 1;
continue;
}
memcg_memory_event(memcg, MEMCG_LOW);
}
reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
shrink_lruvec(lruvec, sc);
shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
sc->priority);
/* Record the group's reclaim efficiency */
if (!sc->proactive)
vmpressure(sc->gfp_mask, memcg, false,
sc->nr_scanned - scanned,
sc->nr_reclaimed - reclaimed);
} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
}
static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
struct lruvec *target_lruvec;
bool reclaimable = false;
unsigned long file;
target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
again:
/*
* Flush the memory cgroup stats, so that we read accurate per-memcg
* lruvec stats for heuristics.
*/
mem_cgroup_flush_stats();
memset(&sc->nr, 0, sizeof(sc->nr));
nr_reclaimed = sc->nr_reclaimed;
nr_scanned = sc->nr_scanned;
/*
* Determine the scan balance between anon and file LRUs.
*/
spin_lock_irq(&target_lruvec->lru_lock);
sc->anon_cost = target_lruvec->anon_cost;
sc->file_cost = target_lruvec->file_cost;
spin_unlock_irq(&target_lruvec->lru_lock);
/*
* Target desirable inactive:active list ratios for the anon
* and file LRU lists.
*/
if (!sc->force_deactivate) {
unsigned long refaults;
refaults = lruvec_page_state(target_lruvec,
WORKINGSET_ACTIVATE_ANON);
if (refaults != target_lruvec->refaults[0] ||
inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
sc->may_deactivate |= DEACTIVATE_ANON;
else
sc->may_deactivate &= ~DEACTIVATE_ANON;
/*
* When refaults are being observed, it means a new
* workingset is being established. Deactivate to get
* rid of any stale active pages quickly.
*/
refaults = lruvec_page_state(target_lruvec,
WORKINGSET_ACTIVATE_FILE);
if (refaults != target_lruvec->refaults[1] ||
inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
sc->may_deactivate |= DEACTIVATE_FILE;
else
sc->may_deactivate &= ~DEACTIVATE_FILE;
} else
sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
/*
* If we have plenty of inactive file pages that aren't
* thrashing, try to reclaim those first before touching
* anonymous pages.
*/
file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
sc->cache_trim_mode = 1;
else
sc->cache_trim_mode = 0;
/*
* Prevent the reclaimer from falling into the cache trap: as
* cache pages start out inactive, every cache fault will tip
* the scan balance towards the file LRU. And as the file LRU
* shrinks, so does the window for rotation from references.
* This means we have a runaway feedback loop where a tiny
* thrashing file LRU becomes infinitely more attractive than
* anon pages. Try to detect this based on file LRU size.
*/
if (!cgroup_reclaim(sc)) {
unsigned long total_high_wmark = 0;
unsigned long free, anon;
int z;
free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
file = node_page_state(pgdat, NR_ACTIVE_FILE) +
node_page_state(pgdat, NR_INACTIVE_FILE);
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = &pgdat->node_zones[z];
if (!managed_zone(zone))
continue;
total_high_wmark += high_wmark_pages(zone);
}
/*
* Consider anon: if that's low too, this isn't a
* runaway file reclaim problem, but rather just
* extreme pressure. Reclaim as per usual then.
*/
anon = node_page_state(pgdat, NR_INACTIVE_ANON);
sc->file_is_tiny =
file + free <= total_high_wmark &&
!(sc->may_deactivate & DEACTIVATE_ANON) &&
anon >> sc->priority;
}
shrink_node_memcgs(pgdat, sc);
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
/* Record the subtree's reclaim efficiency */
if (!sc->proactive)
vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
sc->nr_scanned - nr_scanned,
sc->nr_reclaimed - nr_reclaimed);
if (sc->nr_reclaimed - nr_reclaimed)
reclaimable = true;
if (current_is_kswapd()) {
/*
* If reclaim is isolating dirty pages under writeback,
* it implies that the long-lived page allocation rate
* is exceeding the page laundering rate. Either the
* global limits are not being effective at throttling
* processes due to the page distribution throughout
* zones or there is heavy usage of a slow backing
* device. The only option is to throttle from reclaim
* context which is not ideal as there is no guarantee
* the dirtying process is throttled in the same way
* balance_dirty_pages() manages.
*
* Once a node is flagged PGDAT_WRITEBACK, kswapd will
* count the number of pages under pages flagged for
* immediate reclaim and stall if any are encountered
* in the nr_immediate check below.
*/
if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
set_bit(PGDAT_WRITEBACK, &pgdat->flags);
/* Allow kswapd to start writing pages during reclaim.*/
if (sc->nr.unqueued_dirty == sc->nr.file_taken)
set_bit(PGDAT_DIRTY, &pgdat->flags);
/*
* If kswapd scans pages marked for immediate
* reclaim and under writeback (nr_immediate), it
* implies that pages are cycling through the LRU
* faster than they are written so forcibly stall
* until some pages complete writeback.
*/
if (sc->nr.immediate)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
/*
* Tag a node/memcg as congested if all the dirty pages were marked
* for writeback and immediate reclaim (counted in nr.congested).
*
* Legacy memcg will stall in page writeback so avoid forcibly
* stalling in reclaim_throttle().
*/
if ((current_is_kswapd() ||
(cgroup_reclaim(sc) && writeback_throttling_sane(sc))) &&
sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
set_bit(LRUVEC_CONGESTED, &target_lruvec->flags);
/*
* Stall direct reclaim for IO completions if the lruvec is
* node is congested. Allow kswapd to continue until it
* starts encountering unqueued dirty pages or cycling through
* the LRU too quickly.
*/
if (!current_is_kswapd() && current_may_throttle() &&
!sc->hibernation_mode &&
test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);
if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc))
goto again;
/*
* Kswapd gives up on balancing particular nodes after too
* many failures to reclaim anything from them and goes to
* sleep. On reclaim progress, reset the failure counter. A
* successful direct reclaim run will revive a dormant kswapd.
*/
if (reclaimable)
pgdat->kswapd_failures = 0;
}
/*
* Returns true if compaction should go ahead for a costly-order request, or
* the allocation would already succeed without compaction. Return false if we
* should reclaim first.
*/
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
unsigned long watermark;
enum compact_result suitable;
suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
if (suitable == COMPACT_SUCCESS)
/* Allocation should succeed already. Don't reclaim. */
return true;
if (suitable == COMPACT_SKIPPED)
/* Compaction cannot yet proceed. Do reclaim. */
return false;
/*
* Compaction is already possible, but it takes time to run and there
* are potentially other callers using the pages just freed. So proceed
* with reclaim to make a buffer of free pages available to give
* compaction a reasonable chance of completing and allocating the page.
* Note that we won't actually reclaim the whole buffer in one attempt
* as the target watermark in should_continue_reclaim() is lower. But if
* we are already above the high+gap watermark, don't reclaim at all.
*/
watermark = high_wmark_pages(zone) + compact_gap(sc->order);
return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
}
static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
{
/*
* If reclaim is making progress greater than 12% efficiency then
* wake all the NOPROGRESS throttled tasks.
*/
if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) {
wait_queue_head_t *wqh;
wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS];
if (waitqueue_active(wqh))
wake_up(wqh);
return;
}
/*
* Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will
* throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages
* under writeback and marked for immediate reclaim at the tail of the
* LRU.
*/
if (current_is_kswapd() || cgroup_reclaim(sc))
return;
/* Throttle if making no progress at high prioities. */
if (sc->priority == 1 && !sc->nr_reclaimed)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
}
/*
* This is the direct reclaim path, for page-allocating processes. We only
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
{
struct zoneref *z;
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
gfp_t orig_mask;
pg_data_t *last_pgdat = NULL;
pg_data_t *first_pgdat = NULL;
/*
* If the number of buffer_heads in the machine exceeds the maximum
* allowed level, force direct reclaim to scan the highmem zone as
* highmem pages could be pinning lowmem pages storing buffer_heads
*/
orig_mask = sc->gfp_mask;
if (buffer_heads_over_limit) {
sc->gfp_mask |= __GFP_HIGHMEM;
sc->reclaim_idx = gfp_zone(sc->gfp_mask);
}
for_each_zone_zonelist_nodemask(zone, z, zonelist,
sc->reclaim_idx, sc->nodemask) {
/*
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
if (!cgroup_reclaim(sc)) {
if (!cpuset_zone_allowed(zone,
GFP_KERNEL | __GFP_HARDWALL))
continue;
/*
* If we already have plenty of memory free for
* compaction in this zone, don't free any more.
* Even though compaction is invoked for any
* non-zero order, only frequent costly order
* reclamation is disruptive enough to become a
* noticeable problem, like transparent huge
* page allocations.
*/
if (IS_ENABLED(CONFIG_COMPACTION) &&
sc->order > PAGE_ALLOC_COSTLY_ORDER &&
compaction_ready(zone, sc)) {
sc->compaction_ready = true;
continue;
}
/*
* Shrink each node in the zonelist once. If the
* zonelist is ordered by zone (not the default) then a
* node may be shrunk multiple times but in that case
* the user prefers lower zones being preserved.
*/
if (zone->zone_pgdat == last_pgdat)
continue;
/*
* This steals pages from memory cgroups over softlimit
* and returns the number of reclaimed pages and
* scanned pages. This works for global memory pressure
* and balancing, not for a memcg's limit.
*/
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat,
sc->order, sc->gfp_mask,
&nr_soft_scanned);
sc->nr_reclaimed += nr_soft_reclaimed;
sc->nr_scanned += nr_soft_scanned;
/* need some check for avoid more shrink_zone() */
}
if (!first_pgdat)
first_pgdat = zone->zone_pgdat;
/* See comment about same check for global reclaim above */
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
shrink_node(zone->zone_pgdat, sc);
}
if (first_pgdat)
consider_reclaim_throttle(first_pgdat, sc);
/*
* Restore to original mask to avoid the impact on the caller if we
* promoted it to __GFP_HIGHMEM.
*/
sc->gfp_mask = orig_mask;
}
static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
{
struct lruvec *target_lruvec;
unsigned long refaults;
target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
target_lruvec->refaults[0] = refaults;
refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
target_lruvec->refaults[1] = refaults;
}
/*
* This is the main entry point to direct page reclaim.
*
* If a full scan of the inactive list fails to free enough memory then we
* are "out of memory" and something needs to be killed.
*
* If the caller is !__GFP_FS then the probability of a failure is reasonably
* high - the zone may be full of dirty or under-writeback pages, which this
* caller can't do much about. We kick the writeback threads and take explicit
* naps in the hope that some of these pages can be written. But if the
* allocating task holds filesystem locks which prevent writeout this might not
* work, and the allocation attempt will fail.
*
* returns: 0, if no pages reclaimed
* else, the number of pages reclaimed
*/
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
struct scan_control *sc)
{
int initial_priority = sc->priority;
pg_data_t *last_pgdat;
struct zoneref *z;
struct zone *zone;
retry:
delayacct_freepages_start();
if (!cgroup_reclaim(sc))
__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
do {
if (!sc->proactive)
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
sc->priority);
sc->nr_scanned = 0;
shrink_zones(zonelist, sc);
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
break;
if (sc->compaction_ready)
break;
/*
* If we're getting trouble reclaiming, start doing
* writepage even in laptop mode.
*/
if (sc->priority < DEF_PRIORITY - 2)
sc->may_writepage = 1;
} while (--sc->priority >= 0);
last_pgdat = NULL;
for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx,
sc->nodemask) {
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);
if (cgroup_reclaim(sc)) {
struct lruvec *lruvec;
lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup,
zone->zone_pgdat);
clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
}
}
delayacct_freepages_end();
if (sc->nr_reclaimed)
return sc->nr_reclaimed;
/* Aborted reclaim to try compaction? don't OOM, then */
if (sc->compaction_ready)
return 1;
/*
* We make inactive:active ratio decisions based on the node's
* composition of memory, but a restrictive reclaim_idx or a
* memory.low cgroup setting can exempt large amounts of
* memory from reclaim. Neither of which are very common, so
* instead of doing costly eligibility calculations of the
* entire cgroup subtree up front, we assume the estimates are
* good, and retry with forcible deactivation if that fails.
*/
if (sc->skipped_deactivate) {
sc->priority = initial_priority;
sc->force_deactivate = 1;
sc->skipped_deactivate = 0;
goto retry;
}
/* Untapped cgroup reserves? Don't OOM, retry. */
if (sc->memcg_low_skipped) {
sc->priority = initial_priority;
sc->force_deactivate = 0;
sc->memcg_low_reclaim = 1;
sc->memcg_low_skipped = 0;
goto retry;
}
return 0;
}
static bool allow_direct_reclaim(pg_data_t *pgdat)
{
struct zone *zone;
unsigned long pfmemalloc_reserve = 0;
unsigned long free_pages = 0;
int i;
bool wmark_ok;
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
if (!managed_zone(zone))
continue;
if (!zone_reclaimable_pages(zone))
continue;
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
/* If there are no reserves (unexpected config) then do not throttle */
if (!pfmemalloc_reserve)
return true;
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL)
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL);
wake_up_interruptible(&pgdat->kswapd_wait);
}
return wmark_ok;
}
/*
* Throttle direct reclaimers if backing storage is backed by the network
* and the PFMEMALLOC reserve for the preferred node is getting dangerously
* depleted. kswapd will continue to make progress and wake the processes
* when the low watermark is reached.
*
* Returns true if a fatal signal was delivered during throttling. If this
* happens, the page allocator should not consider triggering the OOM killer.
*/
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
struct zoneref *z;
struct zone *zone;
pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
* responsible for cleaning pages necessary for reclaim to make forward
* progress. kjournald for example may enter direct reclaim while
* committing a transaction where throttling it could forcing other
* processes to block on log_wait_commit().
*/
if (current->flags & PF_KTHREAD)
goto out;
/*
* If a fatal signal is pending, this process should not throttle.
* It should return quickly so it can exit and free its memory
*/
if (fatal_signal_pending(current))
goto out;
/*
* Check if the pfmemalloc reserves are ok by finding the first node
* with a usable ZONE_NORMAL or lower zone. The expectation is that
* GFP_KERNEL will be required for allocating network buffers when
* swapping over the network so ZONE_HIGHMEM is unusable.
*
* Throttling is based on the first usable node and throttled processes
* wait on a queue until kswapd makes progress and wakes them. There
* is an affinity then between processes waking up and where reclaim
* progress has been made assuming the process wakes on the same node.
* More importantly, processes running on remote nodes will not compete
* for remote pfmemalloc reserves and processes on different nodes
* should make reasonable progress.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(gfp_mask), nodemask) {
if (zone_idx(zone) > ZONE_NORMAL)
continue;
/* Throttle based on the first usable node */
pgdat = zone->zone_pgdat;
if (allow_direct_reclaim(pgdat))
goto out;
break;
}
/* If no zone was usable by the allocation flags then do not throttle */
if (!pgdat)
goto out;
/* Account for the throttling */
count_vm_event(PGSCAN_DIRECT_THROTTLE);
/*
* If the caller cannot enter the filesystem, it's possible that it
* is due to the caller holding an FS lock or performing a journal
* transaction in the case of a filesystem like ext[3|4]. In this case,
* it is not safe to block on pfmemalloc_wait as kswapd could be
* blocked waiting on the same lock. Instead, throttle for up to a
* second before continuing.
*/
if (!(gfp_mask & __GFP_FS))
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
allow_direct_reclaim(pgdat), HZ);
else
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
allow_direct_reclaim(pgdat));
if (fatal_signal_pending(current))
return true;
out:
return false;
}
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *nodemask)
{
unsigned long nr_reclaimed;
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.gfp_mask = current_gfp_context(gfp_mask),
.reclaim_idx = gfp_zone(gfp_mask),
.order = order,
.nodemask = nodemask,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = 1,
};
/*
* scan_control uses s8 fields for order, priority, and reclaim_idx.
* Confirm they are large enough for max values.
*/
BUILD_BUG_ON(MAX_ORDER > S8_MAX);
BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
/*
* Do not enter reclaim if fatal signal was delivered while throttled.
* 1 is returned so that the page allocator does not OOM kill at this
* point.
*/
if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
return 1;
set_task_reclaim_state(current, &sc.reclaim_state);
trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
#ifdef CONFIG_MEMCG
/* Only used by soft limit reclaim. Do not reuse for anything else. */
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
unsigned long *nr_scanned)
{
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.target_mem_cgroup = memcg,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.reclaim_idx = MAX_NR_ZONES - 1,
.may_swap = !noswap,
};
WARN_ON_ONCE(!current->reclaim_state);
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
sc.gfp_mask);
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
* if we don't reclaim here, the shrink_node from balance_pgdat
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
shrink_lruvec(lruvec, &sc);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
*nr_scanned = sc.nr_scanned;
return sc.nr_reclaimed;
}
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
unsigned int reclaim_options)
{
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
.reclaim_idx = MAX_NR_ZONES - 1,
.target_mem_cgroup = memcg,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
};
/*
* Traverse the ZONELIST_FALLBACK zonelist of the current node to put
* equal pressure on all the nodes. This is based on the assumption that
* the reclaim does not bail out early.
*/
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
set_task_reclaim_state(current, &sc.reclaim_state);
trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
memalloc_noreclaim_restore(noreclaim_flag);
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
#endif
static void age_active_anon(struct pglist_data *pgdat,
struct scan_control *sc)
{
struct mem_cgroup *memcg;
struct lruvec *lruvec;
if (!can_age_anon_pages(pgdat, sc))
return;
lruvec = mem_cgroup_lruvec(NULL, pgdat);
if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON))
return;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
memcg = mem_cgroup_iter(NULL, memcg, NULL);
} while (memcg);
}
static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx)
{
int i;
struct zone *zone;
/*
* Check for watermark boosts top-down as the higher zones
* are more likely to be boosted. Both watermarks and boosts
* should not be checked at the same time as reclaim would
* start prematurely when there is no boosting and a lower
* zone is balanced.
*/
for (i = highest_zoneidx; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (zone->watermark_boost)
return true;
}
return false;
}
/*
* Returns true if there is an eligible zone balanced for the request order
* and highest_zoneidx
*/
static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long mark = -1;
struct zone *zone;
/*
* Check watermarks bottom-up as lower zones are more likely to
* meet watermarks.
*/
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
mark = wmark_pages(zone, WMARK_PROMO);
else
mark = high_wmark_pages(zone);
if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx))
return true;
}
/*
* If a node has no managed zone within highest_zoneidx, it does not
* need balancing by definition. This can happen if a zone-restricted
* allocation tries to wake a remote kswapd.
*/
if (mark == -1)
return true;
return false;
}
/* Clear pgdat state for congested, dirty or under writeback. */
static void clear_pgdat_congested(pg_data_t *pgdat)
{
struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
clear_bit(PGDAT_DIRTY, &pgdat->flags);
clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
}
/*
* Prepare kswapd for sleeping. This verifies that there are no processes
* waiting in throttle_direct_reclaim() and that watermarks have been met.
*
* Returns true if kswapd is ready to sleep
*/
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order,
int highest_zoneidx)
{
/*
* The throttled processes are normally woken up in balance_pgdat() as
* soon as allow_direct_reclaim() is true. But there is a potential
* race between when kswapd checks the watermarks and a process gets
* throttled. There is also a potential race if processes get
* throttled, kswapd wakes, a large process exits thereby balancing the
* zones, which causes kswapd to exit balance_pgdat() before reaching
* the wake up checks. If kswapd is going to sleep, no process should
* be sleeping on pfmemalloc_wait, so wake them now if necessary. If
* the wake up is premature, processes will wake kswapd and get
* throttled again. The difference from wake ups in balance_pgdat() is
* that here we are under prepare_to_wait().
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Hopeless node, leave it to direct reclaim */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
clear_pgdat_congested(pgdat);
return true;
}
return false;
}
/*
* kswapd shrinks a node of pages that are at or below the highest usable
* zone that is currently unbalanced.
*
* Returns true if kswapd scanned at least the requested number of pages to
* reclaim or if the lack of progress was due to pages under writeback.
* This is used to determine if the scanning priority needs to be raised.
*/
static bool kswapd_shrink_node(pg_data_t *pgdat,
struct scan_control *sc)
{
struct zone *zone;
int z;
/* Reclaim a number of pages proportional to the number of zones */
sc->nr_to_reclaim = 0;
for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
if (!managed_zone(zone))
continue;
sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
}
/*
* Historically care was taken to put equal pressure on all zones but
* now pressure is applied based on node LRU order.
*/
shrink_node(pgdat, sc);
/*
* Fragmentation may mean that the system cannot be rebalanced for
* high-order allocations. If twice the allocation size has been
* reclaimed then recheck watermarks only at order-0 to prevent
* excessive reclaim. Assume that a process requested a high-order
* can direct reclaim/compact.
*/
if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
sc->order = 0;
return sc->nr_scanned >= sc->nr_to_reclaim;
}
/* Page allocator PCP high watermark is lowered if reclaim is active. */
static inline void
update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active)
{
int i;
struct zone *zone;
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (active)
set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
else
clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
}
}
static inline void
set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
update_reclaim_active(pgdat, highest_zoneidx, true);
}
static inline void
clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
update_reclaim_active(pgdat, highest_zoneidx, false);
}
/*
* For kswapd, balance_pgdat() will reclaim pages across a node from zones
* that are eligible for use by the caller until at least one zone is
* balanced.
*
* Returns the order kswapd finished reclaiming at.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
* found to have free_pages <= high_wmark_pages(zone), any page in that zone
* or lower is eligible for reclaim until at least one usable zone is
* balanced.
*/
static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
unsigned long pflags;
unsigned long nr_boost_reclaim;
unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
bool boosted;
struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.order = order,
.may_unmap = 1,
};
set_task_reclaim_state(current, &sc.reclaim_state);
psi_memstall_enter(&pflags);
__fs_reclaim_acquire(_THIS_IP_);
count_vm_event(PAGEOUTRUN);
/*
* Account for the reclaim boost. Note that the zone boost is left in
* place so that parallel allocations that are near the watermark will
* stall or direct reclaim until kswapd is finished.
*/
nr_boost_reclaim = 0;
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
nr_boost_reclaim += zone->watermark_boost;
zone_boosts[i] = zone->watermark_boost;
}
boosted = nr_boost_reclaim;
restart:
set_reclaim_active(pgdat, highest_zoneidx);
sc.priority = DEF_PRIORITY;
do {
unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
bool balanced;
bool ret;
sc.reclaim_idx = highest_zoneidx;
/*
* If the number of buffer_heads exceeds the maximum allowed
* then consider reclaiming from all zones. This has a dual
* purpose -- on 64-bit systems it is expected that
* buffer_heads are stripped during active rotation. On 32-bit
* systems, highmem pages can pin lowmem memory and shrinking
* buffers can relieve lowmem pressure. Reclaim may still not
* go ahead if all eligible zones for the original allocation
* request are balanced to avoid excessive reclaim from kswapd.
*/
if (buffer_heads_over_limit) {
for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
sc.reclaim_idx = i;
break;
}
}
/*
* If the pgdat is imbalanced then ignore boosting and preserve
* the watermarks for a later time and restart. Note that the
* zone watermarks will be still reset at the end of balancing
* on the grounds that the normal reclaim should be enough to
* re-evaluate if boosting is required when kswapd next wakes.
*/
balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx);
if (!balanced && nr_boost_reclaim) {
nr_boost_reclaim = 0;
goto restart;
}
/*
* If boosting is not active then only reclaim if there are no
* eligible zones. Note that sc.reclaim_idx is not used as
* buffer_heads_over_limit may have adjusted it.
*/
if (!nr_boost_reclaim && balanced)
goto out;
/* Limit the priority of boosting to avoid reclaim writeback */
if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2)
raise_priority = false;
/*
* Do not writeback or swap pages for boosted reclaim. The
* intent is to relieve pressure not issue sub-optimal IO
* from reclaim context. If no pages are reclaimed, the
* reclaim will be aborted.
*/
sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
sc.may_swap = !nr_boost_reclaim;
/*
* Do some background aging of the anon list, to give
* pages a chance to be referenced before reclaiming. All
* pages are rotated regardless of classzone as this is
* about consistent aging.
*/
age_active_anon(pgdat, &sc);
/*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
if (sc.priority < DEF_PRIORITY - 2)
sc.may_writepage = 1;
/* Call soft limit reclaim before calling shrink_node. */
sc.nr_scanned = 0;
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
sc.gfp_mask, &nr_soft_scanned);
sc.nr_reclaimed += nr_soft_reclaimed;
/*
* There should be no need to raise the scanning priority if
* enough pages are already being scanned that that high
* watermark would be met at 100% efficiency.
*/
if (kswapd_shrink_node(pgdat, &sc))
raise_priority = false;
/*
* If the low watermark is met there is no need for processes
* to be throttled on pfmemalloc_wait as they should not be
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
allow_direct_reclaim(pgdat))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Check if kswapd should be suspending */
__fs_reclaim_release(_THIS_IP_);
ret = try_to_freeze();
__fs_reclaim_acquire(_THIS_IP_);
if (ret || kthread_should_stop())
break;
/*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);
/*
* If reclaim made no progress for a boost, stop reclaim as
* IO cannot be queued and it could be an infinite loop in
* extreme circumstances.
*/
if (nr_boost_reclaim && !nr_reclaimed)
break;
if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
if (!sc.nr_reclaimed)
pgdat->kswapd_failures++;
out:
clear_reclaim_active(pgdat, highest_zoneidx);
/* If reclaim was boosted, account for the reclaim done in this pass */
if (boosted) {
unsigned long flags;
for (i = 0; i <= highest_zoneidx; i++) {
if (!zone_boosts[i])
continue;
/* Increments are under the zone lock */
zone = pgdat->node_zones + i;
spin_lock_irqsave(&zone->lock, flags);
zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
spin_unlock_irqrestore(&zone->lock, flags);
}
/*
* As there is now likely space, wakeup kcompact to defragment
* pageblocks.
*/
wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx);
}
snapshot_refaults(NULL, pgdat);
__fs_reclaim_release(_THIS_IP_);
psi_memstall_leave(&pflags);
set_task_reclaim_state(current, NULL);
/*
* Return the order kswapd stopped reclaiming at as
* prepare_kswapd_sleep() takes it into account. If another caller
* entered the allocator slow path while kswapd was awake, order will
* remain at the higher level.
*/
return sc.order;
}
/*
* The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to
* be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is
* not a valid index then either kswapd runs for first time or kswapd couldn't
* sleep after previous reclaim attempt (node is still unbalanced). In that
* case return the zone index of the previous kswapd reclaim cycle.
*/
static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
enum zone_type prev_highest_zoneidx)
{
enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
unsigned int highest_zoneidx)
{
long remaining = 0;
DEFINE_WAIT(wait);
if (freezing(current) || kthread_should_stop())
return;
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
/*
* Try to sleep for a short interval. Note that kcompactd will only be
* woken if it is possible to sleep for a short interval. This is
* deliberate on the assumption that if reclaim cannot keep an
* eligible zone balanced that it's also unlikely that compaction will
* succeed.
*/
if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
/*
* Compaction records what page blocks it recently failed to
* isolate pages from and skips them in the future scanning.
* When kswapd is going to sleep, it is reasonable to assume
* that pages and compaction may succeed so reset the cache.
*/
reset_isolation_suitable(pgdat);
/*
* We have freed the memory, now we should compact it to make
* allocation of the requested order possible.
*/
wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx);
remaining = schedule_timeout(HZ/10);
/*
* If woken prematurely then reset kswapd_highest_zoneidx and
* order. The values will either be from a wakeup request or
* the previous request that slept prematurely.
*/
if (remaining) {
WRITE_ONCE(pgdat->kswapd_highest_zoneidx,
kswapd_highest_zoneidx(pgdat,
highest_zoneidx));
if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
}
finish_wait(&pgdat->kswapd_wait, &wait);
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
}
/*
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
if (!remaining &&
prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
* vmstat counters are not perfectly accurate and the estimated
* value for counters such as NR_FREE_PAGES can deviate from the
* true value by nr_online_cpus * threshold. To avoid the zone
* watermarks being breached while under pressure, we reduce the
* per-cpu vmstat threshold while kswapd is awake and restore
* them before going back to sleep.
*/
set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
if (!kthread_should_stop())
schedule();
set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
} else {
if (remaining)
count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
else
count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
}
finish_wait(&pgdat->kswapd_wait, &wait);
}
/*
* The background pageout daemon, started as a kernel thread
* from the init process.
*
* This basically trickles out pages so that we have _some_
* free memory available even if there is no other activity
* that frees anything up. This is needed for things like routing
* etc, where we otherwise might have all activity going on in
* asynchronous contexts that cannot page things out.
*
* If there are applications that are active memory-allocators
* (most normal use), this basically shouldn't matter.
*/
static int kswapd(void *p)
{
unsigned int alloc_order, reclaim_order;
unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
pg_data_t *pgdat = (pg_data_t *)p;
struct task_struct *tsk = current;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
/*
* Tell the memory management that we're a "memory allocator",
* and that if we need more memory we should get access to it
* regardless (see "__alloc_pages()"). "kswapd" should
* never get caught in the normal page freeing logic.
*
* (Kswapd normally doesn't need memory anyway, but sometimes
* you need a small amount of memory in order to be able to
* page out something else, and this flag essentially protects
* us from recursively trying to free more memory as we're
* trying to free the first piece of memory in the first place).
*/
tsk->flags |= PF_MEMALLOC | PF_KSWAPD;
set_freezable();
WRITE_ONCE(pgdat->kswapd_order, 0);
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
atomic_set(&pgdat->nr_writeback_throttled, 0);
for ( ; ; ) {
bool ret;
alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
highest_zoneidx = kswapd_highest_zoneidx(pgdat,
highest_zoneidx);
kswapd_try_sleep:
kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
highest_zoneidx);
/* Read the new order and highest_zoneidx */
alloc_order = READ_ONCE(pgdat->kswapd_order);
highest_zoneidx = kswapd_highest_zoneidx(pgdat,
highest_zoneidx);
WRITE_ONCE(pgdat->kswapd_order, 0);
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
ret = try_to_freeze();
if (kthread_should_stop())
break;
/*
* We can speed up thawing tasks if we don't call balance_pgdat
* after returning from the refrigerator
*/
if (ret)
continue;
/*
* Reclaim begins at the requested order but if a high-order
* reclaim fails then kswapd falls back to reclaiming for
* order-0. If that happens, kswapd will consider sleeping
* for the order it finished reclaiming at (reclaim_order)
* but kcompactd is woken to compact for the original
* request (alloc_order).
*/
trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx,
alloc_order);
reclaim_order = balance_pgdat(pgdat, alloc_order,
highest_zoneidx);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
}
tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);
return 0;
}
/*
* A zone is low on free memory or too fragmented for high-order memory. If
* kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's
* pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim
* has failed or is not needed, still wake up kcompactd if only compaction is
* needed.
*/
void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
enum zone_type highest_zoneidx)
{
pg_data_t *pgdat;
enum zone_type curr_idx;
if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, gfp_flags))
return;
pgdat = zone->zone_pgdat;
curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx)
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx);
if (READ_ONCE(pgdat->kswapd_order) < order)
WRITE_ONCE(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
/* Hopeless node, leave it to direct reclaim if possible */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
(pgdat_balanced(pgdat, order, highest_zoneidx) &&
!pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
/*
* There may be plenty of free memory available, but it's too
* fragmented for high-order allocations. Wake up kcompactd
* and rely on compaction_suitable() to determine if it's
* needed. If it fails, it will defer subsequent attempts to
* ratelimit its work.
*/
if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
wakeup_kcompactd(pgdat, order, highest_zoneidx);
return;
}
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order,
gfp_flags);
wake_up_interruptible(&pgdat->kswapd_wait);
}
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
* freed pages.
*
* Rather than trying to age LRUs the aim is to preserve the overall
* LRU order by reclaiming preferentially
* inactive > active > active referenced > active mapped
*/
unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
{
struct scan_control sc = {
.nr_to_reclaim = nr_to_reclaim,
.gfp_mask = GFP_HIGHUSER_MOVABLE,
.reclaim_idx = MAX_NR_ZONES - 1,
.priority = DEF_PRIORITY,
.may_writepage = 1,
.may_unmap = 1,
.may_swap = 1,
.hibernation_mode = 1,
};
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
fs_reclaim_acquire(sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
set_task_reclaim_state(current, &sc.reclaim_state);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
set_task_reclaim_state(current, NULL);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */
/*
* This kswapd start function will be called by init and node-hot-add.
*/
void kswapd_run(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
if (pgdat->kswapd)
return;
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
if (IS_ERR(pgdat->kswapd)) {
/* failure at boot is fatal */
BUG_ON(system_state < SYSTEM_RUNNING);
pr_err("Failed to start kswapd on node %d\n", nid);
pgdat->kswapd = NULL;
}
}
/*
* Called by memory hotplug when all memory in a node is offlined. Caller must
* be holding mem_hotplug_begin/done().
*/
void kswapd_stop(int nid)
{
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
if (kswapd) {
kthread_stop(kswapd);
NODE_DATA(nid)->kswapd = NULL;
}
}
static int __init kswapd_init(void)
{
int nid;
swap_setup();
for_each_node_state(nid, N_MEMORY)
kswapd_run(nid);
return 0;
}
module_init(kswapd_init)
#ifdef CONFIG_NUMA
/*
* Node reclaim mode
*
* If non-zero call node_reclaim when the number of free pages falls below
* the watermarks.
*/
int node_reclaim_mode __read_mostly;
/*
* Priority for NODE_RECLAIM. This determines the fraction of pages
* of a node considered for each zone_reclaim. 4 scans 1/16th of
* a zone.
*/
#define NODE_RECLAIM_PRIORITY 4
/*
* Percentage of pages in a zone that must be unmapped for node_reclaim to
* occur.
*/
int sysctl_min_unmapped_ratio = 1;
/*
* If the number of slab pages in a zone grows beyond this percentage then
* slab reclaim needs to occur.
*/
int sysctl_min_slab_ratio = 5;
static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
{
unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED);
unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) +
node_page_state(pgdat, NR_ACTIVE_FILE);
/*
* It's possible for there to be more file mapped pages than
* accounted for by the pages on the file LRU lists because
* tmpfs pages accounted for as ANON can also be FILE_MAPPED
*/
return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
}
/* Work out how many page cache pages we can reclaim in this reclaim_mode */
static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat)
{
unsigned long nr_pagecache_reclaimable;
unsigned long delta = 0;
/*
* If RECLAIM_UNMAP is set, then all file pages are considered
* potentially reclaimable. Otherwise, we have to worry about
* pages like swapcache and node_unmapped_file_pages() provides
* a better estimate
*/
if (node_reclaim_mode & RECLAIM_UNMAP)
nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
else
nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);
/* If we can't clean pages, remove dirty pages from consideration */
if (!(node_reclaim_mode & RECLAIM_WRITE))
delta += node_page_state(pgdat, NR_FILE_DIRTY);
/* Watch for any possible underflows due to delta */
if (unlikely(delta > nr_pagecache_reclaimable))
delta = nr_pagecache_reclaimable;
return nr_pagecache_reclaimable - delta;
}
/*
* Try to free up some pages from this node through reclaim.
*/
static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
/* Minimum pages needed in order to stay on node */
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = current_gfp_context(gfp_mask),
.order = order,
.priority = NODE_RECLAIM_PRIORITY,
.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
.reclaim_idx = gfp_zone(gfp_mask),
};
unsigned long pflags;
trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
sc.gfp_mask);
cond_resched();
psi_memstall_enter(&pflags);
fs_reclaim_acquire(sc.gfp_mask);
/*
* We need to be able to allocate from the reserves for RECLAIM_UNMAP
*/
noreclaim_flag = memalloc_noreclaim_save();
set_task_reclaim_state(p, &sc.reclaim_state);
if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages ||
node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) {
/*
* Free memory by calling shrink node with increasing
* priorities until we have enough memory freed.
*/
do {
shrink_node(pgdat, &sc);
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
set_task_reclaim_state(p, NULL);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
psi_memstall_leave(&pflags);
trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);
return sc.nr_reclaimed >= nr_pages;
}
int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
int ret;
/*
* Node reclaim reclaims unmapped file backed pages and
* slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
* thrown out if the node is overallocated. So we do not reclaim
* if less than a specified percentage of the node is used by
* unmapped file backed pages.
*/
if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
return NODE_RECLAIM_NOSCAN;
/*
* Only run node reclaim on the local node or on nodes that do not
* have associated processors. This will favor the local processor
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
return NODE_RECLAIM_NOSCAN;
if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
return NODE_RECLAIM_NOSCAN;
ret = __node_reclaim(pgdat, gfp_mask, order);
clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
if (!ret)
count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
return ret;
}
#endif
void check_move_unevictable_pages(struct pagevec *pvec)
{
struct folio_batch fbatch;
unsigned i;
folio_batch_init(&fbatch);
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
if (PageTransTail(page))
continue;
folio_batch_add(&fbatch, page_folio(page));
}
check_move_unevictable_folios(&fbatch);
}
EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
/**
* check_move_unevictable_folios - Move evictable folios to appropriate zone
* lru list
* @fbatch: Batch of lru folios to check.
*
* Checks folios for evictability, if an evictable folio is in the unevictable
* lru list, moves it to the appropriate evictable lru list. This function
* should be only used for lru folios.
*/
void check_move_unevictable_folios(struct folio_batch *fbatch)
{
struct lruvec *lruvec = NULL;
int pgscanned = 0;
int pgrescued = 0;
int i;
for (i = 0; i < fbatch->nr; i++) {
struct folio *folio = fbatch->folios[i];
int nr_pages = folio_nr_pages(folio);
pgscanned += nr_pages;
/* block memcg migration while the folio moves between lrus */
if (!folio_test_clear_lru(folio))
continue;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (folio_evictable(folio) && folio_test_unevictable(folio)) {
lruvec_del_folio(lruvec, folio);
folio_clear_unevictable(folio);
lruvec_add_folio(lruvec, folio);
pgrescued += nr_pages;
}
folio_set_lru(folio);
}
if (lruvec) {
__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
unlock_page_lruvec_irq(lruvec);
} else if (pgscanned) {
count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
}
}
EXPORT_SYMBOL_GPL(check_move_unevictable_folios);