本篇了解一下内核是怎样触发页面回收的。
触发内存回收的方式有两种，同步和异步回收。alloc_pages在分配内存的时候，如果内存短缺会主动回收内存，这是同步回收；内核有一个或多个kswapd内核线程负责在后台回收内存，这是异步。
看一下shrink_active_list
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;
bool proportional_reclaim;
struct blk_plug plug;
if (lru_gen_enabled() && !root_reclaim(sc)) {
lru_gen_shrink_lruvec(lruvec, sc);
return;
}
//计算各个lru链表需要扫描的page个数
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.
*/
proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || //active file也要被回收
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;
//shrink_list会调用shrink active list或者shrink inactive list
nr_reclaimed += shrink_list(lru, nr_to_scan,
lruvec, sc);
}
}
cond_resched();
if (nr_reclaimed < nr_to_reclaim || proportional_reclaim)
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);
}
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);
}
看看shrink_list
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);
}
如果当前是active lru且允许deactive当前的lru那么调用shrink_active_list。
/*
* 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);
//排空lru per cpu cache
lru_add_drain();
spin_lock_irq(&lruvec->lru_lock);
//把要扫描的页面先从lru上分离到l_hold中备用，我觉得这是为了减少对lru锁的使用时长
nr_taken = isolate_lru_folios(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);
//遍历l_hold
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;
}
//容我日后分析
if (unlikely(buffer_heads_over_limit)) {
if (folio_needs_release(folio) &&
folio_trylock(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.
*/
//可执行文件cache如果被引用过那就先放回active list
if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
nr_rotated += folio_nr_pages(folio);
list_add(&folio->lru, &l_active);
continue;
}
}
//将folio的active标志清掉
folio_clear_active(folio); /* we are de-activating */
folio_set_workingset(folio);
//将folio加到inactive tmp list中
list_add(&folio->lru, &l_inactive);
}
/*
* Move folios back to the lru list.
*/
spin_lock_irq(&lruvec->lru_lock);
nr_activate = move_folios_to_lru(lruvec, &l_active);
nr_deactivate = move_folios_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);
if (nr_rotated)
lru_note_cost(lruvec, file, 0, nr_rotated);
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);
}
看看shrink_inactive_list
static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
struct lruvec *lruvec, struct scan_control *sc,
enum lru_list lru)
{
LIST_HEAD(folio_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);
//分离要扫描的lru folio到folio_list
nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list,
&nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
item = PGSCAN_KSWAPD + reclaimer_offset();
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;
//回收folio_list里面的folio，返回回收的page数量
nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false);
spin_lock_irq(&lruvec->lru_lock);
//没有被回收的folio放回lru
move_folios_to_lru(lruvec, &folio_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
item = PGSTEAL_KSWAPD + reclaimer_offset();
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, nr_scanned - nr_reclaimed);
mem_cgroup_uncharge_list(&folio_list);
//folio_list还有东西，free到伙伴系统
free_unref_page_list(&folio_list);
/*
* If dirty folios 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 folios 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 folios 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);
/*
* For cgroupv1 dirty throttling is achieved by waking up
* the kernel flusher here and later waiting on folios
* which are in writeback to finish (see shrink_folio_list()).
*
* Flusher may not be able to issue writeback quickly
* enough for cgroupv1 writeback throttling to work
* on a large system.
*/
if (!writeback_throttling_sane(sc))
reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
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_inactive_list调用shrink_folio_list去回收页。
看一下shrink_folio_list
static unsigned int shrink_folio_list(struct list_head *folio_list,
struct pglist_data *pgdat, struct scan_control *sc,
struct reclaim_stat *stat, bool ignore_references)
{
LIST_HEAD(ret_folios);
LIST_HEAD(free_folios);
LIST_HEAD(demote_folios);
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:
//扫描folio_list
while (!list_empty(folio_list)) {
struct address_space *mapping;
struct folio *folio;
enum folio_references references = FOLIOREF_RECLAIM;
bool dirty, writeback;
unsigned int nr_pages;
cond_resched();
folio = lru_to_folio(folio_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;
/* folio_update_gen() tried to promote this page? */
if (lru_gen_enabled() && !ignore_references &&
folio_mapped(folio) && folio_test_referenced(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, folio_list);
continue;
}
}
if (!ignore_references)
//判断需要如何处理当前folio
references = folio_check_references(folio, sc);
switch (references) {
case FOLIOREF_ACTIVATE:
goto activate_locked;
case FOLIOREF_KEEP:
stat->nr_ref_keep += nr_pages;
goto keep_locked;
case FOLIOREF_RECLAIM:
case FOLIOREF_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))) {
//可以迁移到其他node
list_add(&folio->lru, &demote_folios);
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,
folio_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,
folio_list))
goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1);
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, folio_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;
}
}
/*
* Folio is unmapped now so it cannot be newly pinned anymore.
* No point in trying to reclaim folio if it is pinned.
* Furthermore we don't want to reclaim underlying fs metadata
* if the folio is pinned and thus potentially modified by the
* pinning process as that may upset the filesystem.
*/
if (folio_maybe_dma_pinned(folio))
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 folio_deactivate()
* 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 == FOLIOREF_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_needs_release(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_folio_list? It would
* appear not as the counts should be low
*/
if (unlikely(folio_test_large(folio)))
destroy_large_folio(folio);
else
//这是要被释放的页，放到free_folios list
list_add(&folio->lru, &free_folios);
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) || folio_test_mlocked(folio)))
folio_free_swap(folio);
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_folios);
VM_BUG_ON_FOLIO(folio_test_lru(folio) ||
folio_test_unevictable(folio), folio);
}
/* 'folio_list' is always empty here */
/* Migrate folios selected for demotion */
nr_reclaimed += demote_folio_list(&demote_folios, pgdat);
/* Folios that could not be demoted are still in @demote_folios */
if (!list_empty(&demote_folios)) {
/* Folios which weren't demoted go back on @folio_list */
list_splice_init(&demote_folios, folio_list);
/*
* goto retry to reclaim the undemoted folios in folio_list if
* desired.
*
* Reclaiming directly from top tier nodes is not often desired
* due to it breaking the LRU ordering: in general memory
* should be reclaimed from lower tier nodes and demoted from
* top tier nodes.
*
* However, disabling reclaim from top tier nodes entirely
* would cause ooms in edge scenarios where lower tier memory
* is unreclaimable for whatever reason, eg memory being
* mlocked or too hot to reclaim. We can disable reclaim
* from top tier nodes in proactive reclaim though as that is
* not real memory pressure.
*/
if (!sc->proactive) {
do_demote_pass = false;
goto retry;
}
}
pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
mem_cgroup_uncharge_list(&free_folios);
try_to_unmap_flush();
//释放页到伙伴系统，这才是真正的回收
free_unref_page_list(&free_folios);
list_splice(&ret_folios, folio_list);
count_vm_events(PGACTIVATE, pgactivate);
if (plug)
swap_write_unplug(plug);
return nr_reclaimed;
}
shrink_folio_list是一个很复杂的函数，现在还没完全看懂。回头看。
目前来看决定哪些页面被扫描的函数是
static unsigned long isolate_lru_folios(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 ||
skip_cma(folio, sc)) {
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, lru);
update_lru_sizes(lruvec, lru, nr_zone_taken);
return nr_taken;
}
扫描lru链表，满足要求就加到folio_list中，后面会扫描folio_list从中找出要回收的页面。get_scan_count函数会计算各lru链表需要扫描的数量。
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned.
*
* nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan
* nr[2] = file inactive folios to scan; nr[3] = file active folios 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 folios. */
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;
}
}
计算的关键参数是swappiness，这个值是0-100，默认60，越大需要被扫描的匿名页越多，100表示跟文件cache页一样多。这个值可以在/proc/sys/vm/swappiness中修改。
上面我们是按直接回收的路径分析的，下面看看异步回收的路径。
异步内存回收是通过一个内核线程kswapd，它的初始化路径是
static int __init kswapd_init(void)
{
int nid;
swap_setup();
for_each_node_state(nid, N_MEMORY)
//给每个node建一个kswapd线程
kswapd_run(nid);
return 0;
}
module_init(kswapd_init)
/*
* This kswapd start function will be called by init and node-hot-add.
*/
void __meminit kswapd_run(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
pgdat_kswapd_lock(pgdat);
if (!pgdat->kswapd) {
//创建并唤醒kswapd线程
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
if (IS_ERR(pgdat->kswapd)) {
/* failure at boot is fatal */
pr_err("Failed to start kswapd on node %d，ret=%ld\n",
nid, PTR_ERR(pgdat->kswapd));
BUG_ON(system_state < SYSTEM_RUNNING);
pgdat->kswapd = NULL;
}
}
pgdat_kswapd_unlock(pgdat);
}
在初始化node的时候会初始化kswapd_wait。
void __init free_area_init(unsigned long *max_zone_pfn)
{
...
for_each_node(nid) {
pg_data_t *pgdat;
if (!node_online(nid)) {
...
free_area_init_node(nid);
...
}
static void __init free_area_init_node(int nid)
{
...
free_area_init_core(pgdat);
lru_gen_init_pgdat(pgdat);
}
static void __init free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
pgdat_init_internals(pgdat);
...
}
static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
{
int i;
pgdat_resize_init(pgdat);
pgdat_kswapd_lock_init(pgdat);
pgdat_init_split_queue(pgdat);
pgdat_init_kcompactd(pgdat);
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
for (i = 0; i < NR_VMSCAN_THROTTLE; i++)
init_waitqueue_head(&pgdat->reclaim_wait[i]);
pgdat_page_ext_init(pgdat);
lruvec_init(&pgdat->__lruvec);
}
可知kswapd_wait是每个node都有一个。
但是光有一个等待队列头没用，还得把kswapd线程加进队列。
/*
* 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);
//上面的代码只是在第一次执行的时候运行
for ( ; ; ) {
//以后就呆在这个循环里了
bool ret;
alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
highest_zoneidx = kswapd_highest_zoneidx(pgdat,
highest_zoneidx);
kswapd_try_sleep:
//把自己加到等待队列中后schedule，等着被唤醒
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);
//开始做正事
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;
}
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;
//把自己加到kswapd_wait等待队列
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.
*/
//睡会儿
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);
}
唤醒kswapd的通常是在分配内存时，alloc_page()-->__alloc_pages_nodemask()-->__alloc_pages_slowpath()-->wake_all_kswapds()-->wakeup_kswapd()
/*
* 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);
}
下面看看balance_pgdat
/*
* 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;
//用于回收页面的控制结构
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.order = order,
.may_unmap = 1,
};
//设置当前task->reclaim_state成员
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:
//将当前node hzoneidx及以下的所有zone设置ZONE_RECLAIM_ACTIVE到flag
set_reclaim_active(pgdat, highest_zoneidx);
//控制需要扫描的页面数量，nrpage = lru_pages >> priority
sc.priority = DEF_PRIORITY; // 12
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.
*/
//有没有一个zone有足够的free page，free page > zone->wmark[high]且可以分配出2^order的页面
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.
*/
//没有boost且已经balanced，那就不用回收了
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, to give pages a chance to be
* referenced before reclaiming. All pages are rotated
* regardless of classzone as this is about consistent aging.
*/
//不是很明白？？？这又啥用？
kswapd_age_node(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.
*/
//进入回收路径
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
*/
//唤醒pfmemalloc，不过这是个啥？
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.
*/
//感觉是啥也没榨出来，放弃吧
if (nr_boost_reclaim && !nr_reclaimed)
break;
if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1); //每次我都多扫描一些页面
if (!sc.nr_reclaimed)
pgdat->kswapd_failures++; //卡在这里应该是没回收成功，在node中记录一下
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;
}
kswapd_shrink_node是shrink_node的包装。
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;
//这里有好多跟要回收页面数量有关的参数，傻傻分不清
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.
*/
//回收路径
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;
//扫描的数量比计划要扫描的数量多？
return sc->nr_scanned >= sc->nr_to_reclaim;
}
shrink_node_memcgs里面除了shrink_lruvec还有shrink_slab没有看。
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 {
...
shrink_lruvec(lruvec, sc);
shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
sc->priority);
...
} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
}
看看shrink_slab
/**
* 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.
*/
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);
/*
* lockless algorithm of global shrink.
*
* In the unregistration setp, the shrinker will be freed asynchronously
* via RCU after its refcount reaches 0. So both rcu_read_lock() and
* shrinker_try_get() can be used to ensure the existence of the shrinker.
*
* So in the global shrink:
* step 1: use rcu_read_lock() to guarantee existence of the shrinker
* and the validity of the shrinker_list walk.
* step 2: use shrinker_try_get() to try get the refcount, if successful,
* then the existence of the shrinker can also be guaranteed,
* so we can release the RCU lock to do do_shrink_slab() that
* may sleep.
* step 3: *MUST* to reacquire the RCU lock before calling shrinker_put(),
* which ensures that neither this shrinker nor the next shrinker
* will be freed in the next traversal operation.
* step 4: do shrinker_put() paired with step 2 to put the refcount,
* if the refcount reaches 0, then wake up the waiter in
* shrinker_free() by calling complete().
*/
rcu_read_lock();
//有一个全局shrink_list
list_for_each_entry_rcu(shrinker, &shrinker_list, list) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
if (!shrinker_try_get(shrinker))
continue;
rcu_read_unlock();
//shrink slab
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
freed += ret;
rcu_read_lock();
shrinker_put(shrinker);
}
rcu_read_unlock();
cond_resched();
return freed;
}
通过shrink_register很多模块会注册shrinker到shrinker_list，这里遍历shrinker_list，使用do_shrink_slab是回收slab。
/*
* A callback you can register to apply pressure to ageable caches.
*
* @count_objects should return the number of freeable items in the cache. If
* there are no objects to free, it should return SHRINK_EMPTY, while 0 is
* returned in cases of the number of freeable items cannot be determined
* or shrinker should skip this cache for this time (e.g., their number
* is below shrinkable limit). No deadlock checks should be done during the
* count callback - the shrinker relies on aggregating scan counts that couldn't
* be executed due to potential deadlocks to be run at a later call when the
* deadlock condition is no longer pending.
*
* @scan_objects will only be called if @count_objects returned a non-zero
* value for the number of freeable objects. The callout should scan the cache
* and attempt to free items from the cache. It should then return the number
* of objects freed during the scan, or SHRINK_STOP if progress cannot be made
* due to potential deadlocks. If SHRINK_STOP is returned, then no further
* attempts to call the @scan_objects will be made from the current reclaim
* context.
*
* @flags determine the shrinker abilities, like numa awareness
*/
struct shrinker {
unsigned long (*count_objects)(struct shrinker *,
struct shrink_control *sc);
unsigned long (*scan_objects)(struct shrinker *,
struct shrink_control *sc);
long batch; /* reclaim batch size, 0 = default */
int seeks; /* seeks to recreate an obj */
unsigned flags;
/*
* The reference count of this shrinker. Registered shrinker have an
* initial refcount of 1, then the lookup operations are now allowed
* to use it via shrinker_try_get(). Later in the unregistration step,
* the initial refcount will be discarded, and will free the shrinker
* asynchronously via RCU after its refcount reaches 0.
*/
refcount_t refcount;
struct completion done; /* use to wait for refcount to reach 0 */
struct rcu_head rcu;
void *private_data;
/* These are for internal use */
struct list_head list;
#ifdef CONFIG_MEMCG
/* ID in shrinker_idr */
int id;
#endif
#ifdef CONFIG_SHRINKER_DEBUG
int debugfs_id;
const char *name;
struct dentry *debugfs_entry;
#endif
/* objs pending delete, per node */
atomic_long_t *nr_deferred;
};
可以看到shrinker结构是一个cache的回调函数即一些参数，count_objects负责返回空闲项数量，scan_objects会去回收cache。
页面回收先分析到这里，非常简略，很多地方尚不清楚。
标签：folio,pgdat,lru,内存,linux,sc,nr,reclaim,页面 From： https://www.cnblogs.com/banshanjushi/p/18004102