From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/compaction.c | 1476 ++++++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 1,165 insertions(+), 311 deletions(-)
diff --git a/kernel/mm/compaction.c b/kernel/mm/compaction.c
index 120e555..dc96fad 100644
--- a/kernel/mm/compaction.c
+++ b/kernel/mm/compaction.c
@@ -45,10 +45,33 @@
#define CREATE_TRACE_POINTS
#include <trace/events/compaction.h>
+#undef CREATE_TRACE_POINTS
+#ifndef __GENKSYMS__
+#include <trace/hooks/mm.h>
+#endif
+
#define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order))
#define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order))
#define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order)
#define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order)
+
+/*
+ * Fragmentation score check interval for proactive compaction purposes.
+ */
+static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+
+/*
+ * Page order with-respect-to which proactive compaction
+ * calculates external fragmentation, which is used as
+ * the "fragmentation score" of a node/zone.
+ */
+#if defined CONFIG_TRANSPARENT_HUGEPAGE
+#define COMPACTION_HPAGE_ORDER HPAGE_PMD_ORDER
+#elif defined CONFIG_HUGETLBFS
+#define COMPACTION_HPAGE_ORDER HUGETLB_PAGE_ORDER
+#else
+#define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT)
+#endif
static unsigned long release_freepages(struct list_head *freelist)
{
@@ -66,7 +89,7 @@
return high_pfn;
}
-static void map_pages(struct list_head *list)
+static void split_map_pages(struct list_head *list)
{
unsigned int i, order, nr_pages;
struct page *page, *next;
@@ -136,7 +159,7 @@
/*
* Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * allocation success. 1 << compact_defer_shift, compactions are skipped up
* to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
*/
void defer_compaction(struct zone *zone, int order)
@@ -162,11 +185,10 @@
return false;
/* Avoid possible overflow */
- if (++zone->compact_considered > defer_limit)
+ if (++zone->compact_considered >= defer_limit) {
zone->compact_considered = defer_limit;
-
- if (zone->compact_considered >= defer_limit)
return false;
+ }
trace_mm_compaction_deferred(zone, order);
@@ -237,6 +259,78 @@
return false;
}
+static bool
+__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
+ bool check_target)
+{
+ struct page *page = pfn_to_online_page(pfn);
+ struct page *block_page;
+ struct page *end_page;
+ unsigned long block_pfn;
+
+ if (!page)
+ return false;
+ if (zone != page_zone(page))
+ return false;
+ if (pageblock_skip_persistent(page))
+ return false;
+
+ /*
+ * If skip is already cleared do no further checking once the
+ * restart points have been set.
+ */
+ if (check_source && check_target && !get_pageblock_skip(page))
+ return true;
+
+ /*
+ * If clearing skip for the target scanner, do not select a
+ * non-movable pageblock as the starting point.
+ */
+ if (!check_source && check_target &&
+ get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+ return false;
+
+ /* Ensure the start of the pageblock or zone is online and valid */
+ block_pfn = pageblock_start_pfn(pfn);
+ block_pfn = max(block_pfn, zone->zone_start_pfn);
+ block_page = pfn_to_online_page(block_pfn);
+ if (block_page) {
+ page = block_page;
+ pfn = block_pfn;
+ }
+
+ /* Ensure the end of the pageblock or zone is online and valid */
+ block_pfn = pageblock_end_pfn(pfn) - 1;
+ block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
+ end_page = pfn_to_online_page(block_pfn);
+ if (!end_page)
+ return false;
+
+ /*
+ * Only clear the hint if a sample indicates there is either a
+ * free page or an LRU page in the block. One or other condition
+ * is necessary for the block to be a migration source/target.
+ */
+ do {
+ if (pfn_valid_within(pfn)) {
+ if (check_source && PageLRU(page)) {
+ clear_pageblock_skip(page);
+ return true;
+ }
+
+ if (check_target && PageBuddy(page)) {
+ clear_pageblock_skip(page);
+ return true;
+ }
+ }
+
+ page += (1 << PAGE_ALLOC_COSTLY_ORDER);
+ pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
+ } while (page <= end_page);
+
+ return false;
+}
+
/*
* This function is called to clear all cached information on pageblocks that
* should be skipped for page isolation when the migrate and free page scanner
@@ -244,30 +338,54 @@
*/
static void __reset_isolation_suitable(struct zone *zone)
{
- unsigned long start_pfn = zone->zone_start_pfn;
- unsigned long end_pfn = zone_end_pfn(zone);
- unsigned long pfn;
+ unsigned long migrate_pfn = zone->zone_start_pfn;
+ unsigned long free_pfn = zone_end_pfn(zone) - 1;
+ unsigned long reset_migrate = free_pfn;
+ unsigned long reset_free = migrate_pfn;
+ bool source_set = false;
+ bool free_set = false;
+
+ if (!zone->compact_blockskip_flush)
+ return;
zone->compact_blockskip_flush = false;
- /* Walk the zone and mark every pageblock as suitable for isolation */
- for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
- struct page *page;
-
+ /*
+ * Walk the zone and update pageblock skip information. Source looks
+ * for PageLRU while target looks for PageBuddy. When the scanner
+ * is found, both PageBuddy and PageLRU are checked as the pageblock
+ * is suitable as both source and target.
+ */
+ for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages,
+ free_pfn -= pageblock_nr_pages) {
cond_resched();
- page = pfn_to_online_page(pfn);
- if (!page)
- continue;
- if (zone != page_zone(page))
- continue;
- if (pageblock_skip_persistent(page))
- continue;
+ /* Update the migrate PFN */
+ if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) &&
+ migrate_pfn < reset_migrate) {
+ source_set = true;
+ reset_migrate = migrate_pfn;
+ zone->compact_init_migrate_pfn = reset_migrate;
+ zone->compact_cached_migrate_pfn[0] = reset_migrate;
+ zone->compact_cached_migrate_pfn[1] = reset_migrate;
+ }
- clear_pageblock_skip(page);
+ /* Update the free PFN */
+ if (__reset_isolation_pfn(zone, free_pfn, free_set, true) &&
+ free_pfn > reset_free) {
+ free_set = true;
+ reset_free = free_pfn;
+ zone->compact_init_free_pfn = reset_free;
+ zone->compact_cached_free_pfn = reset_free;
+ }
}
- reset_cached_positions(zone);
+ /* Leave no distance if no suitable block was reset */
+ if (reset_migrate >= reset_free) {
+ zone->compact_cached_migrate_pfn[0] = migrate_pfn;
+ zone->compact_cached_migrate_pfn[1] = migrate_pfn;
+ zone->compact_cached_free_pfn = free_pfn;
+ }
}
void reset_isolation_suitable(pg_data_t *pgdat)
@@ -286,15 +404,53 @@
}
/*
+ * Sets the pageblock skip bit if it was clear. Note that this is a hint as
+ * locks are not required for read/writers. Returns true if it was already set.
+ */
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+ unsigned long pfn)
+{
+ bool skip;
+
+ /* Do no update if skip hint is being ignored */
+ if (cc->ignore_skip_hint)
+ return false;
+
+ if (!IS_ALIGNED(pfn, pageblock_nr_pages))
+ return false;
+
+ skip = get_pageblock_skip(page);
+ if (!skip && !cc->no_set_skip_hint)
+ set_pageblock_skip(page);
+
+ return skip;
+}
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+ struct zone *zone = cc->zone;
+
+ pfn = pageblock_end_pfn(pfn);
+
+ /* Set for isolation rather than compaction */
+ if (cc->no_set_skip_hint)
+ return;
+
+ if (pfn > zone->compact_cached_migrate_pfn[0])
+ zone->compact_cached_migrate_pfn[0] = pfn;
+ if (cc->mode != MIGRATE_ASYNC &&
+ pfn > zone->compact_cached_migrate_pfn[1])
+ zone->compact_cached_migrate_pfn[1] = pfn;
+}
+
+/*
* If no pages were isolated then mark this pageblock to be skipped in the
* future. The information is later cleared by __reset_isolation_suitable().
*/
static void update_pageblock_skip(struct compact_control *cc,
- struct page *page, unsigned long nr_isolated,
- bool migrate_scanner)
+ struct page *page, unsigned long pfn)
{
struct zone *zone = cc->zone;
- unsigned long pfn;
if (cc->no_set_skip_hint)
return;
@@ -302,24 +458,11 @@
if (!page)
return;
- if (nr_isolated)
- return;
-
set_pageblock_skip(page);
- pfn = page_to_pfn(page);
-
/* Update where async and sync compaction should restart */
- if (migrate_scanner) {
- if (pfn > zone->compact_cached_migrate_pfn[0])
- zone->compact_cached_migrate_pfn[0] = pfn;
- if (cc->mode != MIGRATE_ASYNC &&
- pfn > zone->compact_cached_migrate_pfn[1])
- zone->compact_cached_migrate_pfn[1] = pfn;
- } else {
- if (pfn < zone->compact_cached_free_pfn)
- zone->compact_cached_free_pfn = pfn;
- }
+ if (pfn < zone->compact_cached_free_pfn)
+ zone->compact_cached_free_pfn = pfn;
}
#else
static inline bool isolation_suitable(struct compact_control *cc,
@@ -334,32 +477,43 @@
}
static inline void update_pageblock_skip(struct compact_control *cc,
- struct page *page, unsigned long nr_isolated,
- bool migrate_scanner)
+ struct page *page, unsigned long pfn)
{
+}
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+}
+
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+ unsigned long pfn)
+{
+ return false;
}
#endif /* CONFIG_COMPACTION */
/*
* Compaction requires the taking of some coarse locks that are potentially
- * very heavily contended. For async compaction, back out if the lock cannot
- * be taken immediately. For sync compaction, spin on the lock if needed.
+ * very heavily contended. For async compaction, trylock and record if the
+ * lock is contended. The lock will still be acquired but compaction will
+ * abort when the current block is finished regardless of success rate.
+ * Sync compaction acquires the lock.
*
- * Returns true if the lock is held
- * Returns false if the lock is not held and compaction should abort
+ * Always returns true which makes it easier to track lock state in callers.
*/
-static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
+static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
struct compact_control *cc)
+ __acquires(lock)
{
- if (cc->mode == MIGRATE_ASYNC) {
- if (!spin_trylock_irqsave(lock, *flags)) {
- cc->contended = true;
- return false;
- }
- } else {
- spin_lock_irqsave(lock, *flags);
+ /* Track if the lock is contended in async mode */
+ if (cc->mode == MIGRATE_ASYNC && !cc->contended) {
+ if (spin_trylock_irqsave(lock, *flags))
+ return true;
+
+ cc->contended = true;
}
+ spin_lock_irqsave(lock, *flags);
return true;
}
@@ -391,37 +545,7 @@
return true;
}
- if (need_resched()) {
- if (cc->mode == MIGRATE_ASYNC) {
- cc->contended = true;
- return true;
- }
- cond_resched();
- }
-
- return false;
-}
-
-/*
- * Aside from avoiding lock contention, compaction also periodically checks
- * need_resched() and either schedules in sync compaction or aborts async
- * compaction. This is similar to what compact_unlock_should_abort() does, but
- * is used where no lock is concerned.
- *
- * Returns false when no scheduling was needed, or sync compaction scheduled.
- * Returns true when async compaction should abort.
- */
-static inline bool compact_should_abort(struct compact_control *cc)
-{
- /* async compaction aborts if contended */
- if (need_resched()) {
- if (cc->mode == MIGRATE_ASYNC) {
- cc->contended = true;
- return true;
- }
-
- cond_resched();
- }
+ cond_resched();
return false;
}
@@ -435,19 +559,24 @@
unsigned long *start_pfn,
unsigned long end_pfn,
struct list_head *freelist,
+ unsigned int stride,
bool strict)
{
int nr_scanned = 0, total_isolated = 0;
- struct page *cursor, *valid_page = NULL;
+ struct page *cursor;
unsigned long flags = 0;
bool locked = false;
unsigned long blockpfn = *start_pfn;
unsigned int order;
+ /* Strict mode is for isolation, speed is secondary */
+ if (strict)
+ stride = 1;
+
cursor = pfn_to_page(blockpfn);
/* Isolate free pages. */
- for (; blockpfn < end_pfn; blockpfn++, cursor++) {
+ for (; blockpfn < end_pfn; blockpfn += stride, cursor += stride) {
int isolated;
struct page *page = cursor;
@@ -464,9 +593,6 @@
nr_scanned++;
if (!pfn_valid_within(blockpfn))
goto isolate_fail;
-
- if (!valid_page)
- valid_page = page;
/*
* For compound pages such as THP and hugetlbfs, we can save
@@ -495,18 +621,8 @@
* recheck as well.
*/
if (!locked) {
- /*
- * The zone lock must be held to isolate freepages.
- * Unfortunately this is a very coarse lock and can be
- * heavily contended if there are parallel allocations
- * or parallel compactions. For async compaction do not
- * spin on the lock and we acquire the lock as late as
- * possible.
- */
- locked = compact_trylock_irqsave(&cc->zone->lock,
+ locked = compact_lock_irqsave(&cc->zone->lock,
&flags, cc);
- if (!locked)
- break;
/* Recheck this is a buddy page under lock */
if (!PageBuddy(page))
@@ -514,7 +630,7 @@
}
/* Found a free page, will break it into order-0 pages */
- order = page_order(page);
+ order = buddy_order(page);
isolated = __isolate_free_page(page, order);
if (!isolated)
break;
@@ -564,10 +680,6 @@
*/
if (strict && blockpfn < end_pfn)
total_isolated = 0;
-
- /* Update the pageblock-skip if the whole pageblock was scanned */
- if (blockpfn == end_pfn)
- update_pageblock_skip(cc, valid_page, total_isolated, false);
cc->total_free_scanned += nr_scanned;
if (total_isolated)
@@ -626,7 +738,7 @@
break;
isolated = isolate_freepages_block(cc, &isolate_start_pfn,
- block_end_pfn, &freelist, true);
+ block_end_pfn, &freelist, 0, true);
/*
* In strict mode, isolate_freepages_block() returns 0 if
@@ -644,7 +756,7 @@
}
/* __isolate_free_page() does not map the pages */
- map_pages(&freelist);
+ split_map_pages(&freelist);
if (pfn < end_pfn) {
/* Loop terminated early, cleanup. */
@@ -656,17 +768,42 @@
return pfn;
}
+#ifdef CONFIG_COMPACTION
+unsigned long isolate_and_split_free_page(struct page *page,
+ struct list_head *list)
+{
+ unsigned long isolated;
+ unsigned int order;
+
+ if (!PageBuddy(page))
+ return 0;
+
+ order = buddy_order(page);
+ isolated = __isolate_free_page(page, order);
+ if (!isolated)
+ return 0;
+
+ set_page_private(page, order);
+ list_add(&page->lru, list);
+
+ split_map_pages(list);
+
+ return isolated;
+}
+EXPORT_SYMBOL_GPL(isolate_and_split_free_page);
+#endif
+
/* Similar to reclaim, but different enough that they don't share logic */
-static bool too_many_isolated(struct zone *zone)
+static bool too_many_isolated(pg_data_t *pgdat)
{
unsigned long active, inactive, isolated;
- inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
- node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
- active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
- node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
- isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
- node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON);
+ inactive = node_page_state(pgdat, NR_INACTIVE_FILE) +
+ node_page_state(pgdat, NR_INACTIVE_ANON);
+ active = node_page_state(pgdat, NR_ACTIVE_FILE) +
+ node_page_state(pgdat, NR_ACTIVE_ANON);
+ isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
+ node_page_state(pgdat, NR_ISOLATED_ANON);
return isolated > (inactive + active) / 2;
}
@@ -693,7 +830,7 @@
isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
unsigned long end_pfn, isolate_mode_t isolate_mode)
{
- struct zone *zone = cc->zone;
+ pg_data_t *pgdat = cc->zone->zone_pgdat;
unsigned long nr_scanned = 0, nr_isolated = 0;
struct lruvec *lruvec;
unsigned long flags = 0;
@@ -702,13 +839,18 @@
unsigned long start_pfn = low_pfn;
bool skip_on_failure = false;
unsigned long next_skip_pfn = 0;
+ bool skip_updated = false;
/*
* Ensure that there are not too many pages isolated from the LRU
* list by either parallel reclaimers or compaction. If there are,
* delay for some time until fewer pages are isolated
*/
- while (unlikely(too_many_isolated(zone))) {
+ while (unlikely(too_many_isolated(pgdat))) {
+ /* stop isolation if there are still pages not migrated */
+ if (cc->nr_migratepages)
+ return 0;
+
/* async migration should just abort */
if (cc->mode == MIGRATE_ASYNC)
return 0;
@@ -719,8 +861,7 @@
return 0;
}
- if (compact_should_abort(cc))
- return 0;
+ cond_resched();
if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) {
skip_on_failure = true;
@@ -754,13 +895,15 @@
/*
* Periodically drop the lock (if held) regardless of its
- * contention, to give chance to IRQs. Abort async compaction
- * if contended.
+ * contention, to give chance to IRQs. Abort completely if
+ * a fatal signal is pending.
*/
if (!(low_pfn % SWAP_CLUSTER_MAX)
- && compact_unlock_should_abort(zone_lru_lock(zone), flags,
- &locked, cc))
- break;
+ && compact_unlock_should_abort(&pgdat->lru_lock,
+ flags, &locked, cc)) {
+ low_pfn = 0;
+ goto fatal_pending;
+ }
if (!pfn_valid_within(low_pfn))
goto isolate_fail;
@@ -768,8 +911,19 @@
page = pfn_to_page(low_pfn);
- if (!valid_page)
+ /*
+ * Check if the pageblock has already been marked skipped.
+ * Only the aligned PFN is checked as the caller isolates
+ * COMPACT_CLUSTER_MAX at a time so the second call must
+ * not falsely conclude that the block should be skipped.
+ */
+ if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
+ if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
+ low_pfn = end_pfn;
+ goto isolate_abort;
+ }
valid_page = page;
+ }
/*
* Skip if free. We read page order here without zone lock
@@ -778,7 +932,7 @@
* potential isolation targets.
*/
if (PageBuddy(page)) {
- unsigned long freepage_order = page_order_unsafe(page);
+ unsigned long freepage_order = buddy_order_unsafe(page);
/*
* Without lock, we cannot be sure that what we got is
@@ -792,12 +946,13 @@
/*
* Regardless of being on LRU, compound pages such as THP and
- * hugetlbfs are not to be compacted. We can potentially save
- * a lot of iterations if we skip them at once. The check is
- * racy, but we can consider only valid values and the only
- * danger is skipping too much.
+ * hugetlbfs are not to be compacted unless we are attempting
+ * an allocation much larger than the huge page size (eg CMA).
+ * We can potentially save a lot of iterations if we skip them
+ * at once. The check is racy, but we can consider only valid
+ * values and the only danger is skipping too much.
*/
- if (PageCompound(page)) {
+ if (PageCompound(page) && !cc->alloc_contig) {
const unsigned int order = compound_order(page);
if (likely(order < MAX_ORDER))
@@ -818,7 +973,7 @@
if (unlikely(__PageMovable(page)) &&
!PageIsolated(page)) {
if (locked) {
- spin_unlock_irqrestore(zone_lru_lock(zone),
+ spin_unlock_irqrestore(&pgdat->lru_lock,
flags);
locked = false;
}
@@ -848,10 +1003,15 @@
/* If we already hold the lock, we can skip some rechecking */
if (!locked) {
- locked = compact_trylock_irqsave(zone_lru_lock(zone),
+ locked = compact_lock_irqsave(&pgdat->lru_lock,
&flags, cc);
- if (!locked)
- break;
+
+ /* Try get exclusive access under lock */
+ if (!skip_updated) {
+ skip_updated = true;
+ if (test_and_set_skip(cc, page, low_pfn))
+ goto isolate_abort;
+ }
/* Recheck PageLRU and PageCompound under lock */
if (!PageLRU(page))
@@ -862,41 +1022,41 @@
* and it's on LRU. It can only be a THP so the order
* is safe to read and it's 0 for tail pages.
*/
- if (unlikely(PageCompound(page))) {
- low_pfn += (1UL << compound_order(page)) - 1;
+ if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
+ low_pfn += compound_nr(page) - 1;
goto isolate_fail;
}
}
- lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+ lruvec = mem_cgroup_page_lruvec(page, pgdat);
/* Try isolate the page */
if (__isolate_lru_page(page, isolate_mode) != 0)
goto isolate_fail;
- VM_BUG_ON_PAGE(PageCompound(page), page);
+ /* The whole page is taken off the LRU; skip the tail pages. */
+ if (PageCompound(page))
+ low_pfn += compound_nr(page) - 1;
/* Successfully isolated */
del_page_from_lru_list(page, lruvec, page_lru(page));
- inc_node_page_state(page,
- NR_ISOLATED_ANON + page_is_file_cache(page));
+ mod_node_page_state(page_pgdat(page),
+ NR_ISOLATED_ANON + page_is_file_lru(page),
+ thp_nr_pages(page));
isolate_success:
list_add(&page->lru, &cc->migratepages);
- cc->nr_migratepages++;
- nr_isolated++;
+ cc->nr_migratepages += compound_nr(page);
+ nr_isolated += compound_nr(page);
/*
- * Record where we could have freed pages by migration and not
- * yet flushed them to buddy allocator.
- * - this is the lowest page that was isolated and likely be
- * then freed by migration.
+ * Avoid isolating too much unless this block is being
+ * rescanned (e.g. dirty/writeback pages, parallel allocation)
+ * or a lock is contended. For contention, isolate quickly to
+ * potentially remove one source of contention.
*/
- if (!cc->last_migrated_pfn)
- cc->last_migrated_pfn = low_pfn;
-
- /* Avoid isolating too much */
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
+ !cc->rescan && !cc->contended) {
++low_pfn;
break;
}
@@ -913,12 +1073,11 @@
*/
if (nr_isolated) {
if (locked) {
- spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+ spin_unlock_irqrestore(&pgdat->lru_lock, flags);
locked = false;
}
putback_movable_pages(&cc->migratepages);
cc->nr_migratepages = 0;
- cc->last_migrated_pfn = 0;
nr_isolated = 0;
}
@@ -939,19 +1098,28 @@
if (unlikely(low_pfn > end_pfn))
low_pfn = end_pfn;
+isolate_abort:
if (locked)
- spin_unlock_irqrestore(zone_lru_lock(zone), flags);
+ spin_unlock_irqrestore(&pgdat->lru_lock, flags);
/*
- * Update the pageblock-skip information and cached scanner pfn,
- * if the whole pageblock was scanned without isolating any page.
+ * Updated the cached scanner pfn once the pageblock has been scanned
+ * Pages will either be migrated in which case there is no point
+ * scanning in the near future or migration failed in which case the
+ * failure reason may persist. The block is marked for skipping if
+ * there were no pages isolated in the block or if the block is
+ * rescanned twice in a row.
*/
- if (low_pfn == end_pfn)
- update_pageblock_skip(cc, valid_page, nr_isolated, true);
+ if (low_pfn == end_pfn && (!nr_isolated || cc->rescan)) {
+ if (valid_page && !skip_updated)
+ set_pageblock_skip(valid_page);
+ update_cached_migrate(cc, low_pfn);
+ }
trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
nr_scanned, nr_isolated);
+fatal_pending:
cc->total_migrate_scanned += nr_scanned;
if (nr_isolated)
count_compact_events(COMPACTISOLATED, nr_isolated);
@@ -998,7 +1166,7 @@
if (!pfn)
break;
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
break;
}
@@ -1012,6 +1180,9 @@
struct page *page)
{
int block_mt;
+
+ if (pageblock_skip_persistent(page))
+ return false;
if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction)
return true;
@@ -1035,7 +1206,7 @@
* the only small danger is that we skip a potentially suitable
* pageblock, so it's not worth to check order for valid range.
*/
- if (page_order_unsafe(page) >= pageblock_order)
+ if (buddy_order_unsafe(page) >= pageblock_order)
return false;
}
@@ -1050,6 +1221,14 @@
return false;
}
+static inline unsigned int
+freelist_scan_limit(struct compact_control *cc)
+{
+ unsigned short shift = BITS_PER_LONG - 1;
+
+ return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1;
+}
+
/*
* Test whether the free scanner has reached the same or lower pageblock than
* the migration scanner, and compaction should thus terminate.
@@ -1058,6 +1237,249 @@
{
return (cc->free_pfn >> pageblock_order)
<= (cc->migrate_pfn >> pageblock_order);
+}
+
+/*
+ * Used when scanning for a suitable migration target which scans freelists
+ * in reverse. Reorders the list such as the unscanned pages are scanned
+ * first on the next iteration of the free scanner
+ */
+static void
+move_freelist_head(struct list_head *freelist, struct page *freepage)
+{
+ LIST_HEAD(sublist);
+
+ if (!list_is_last(freelist, &freepage->lru)) {
+ list_cut_before(&sublist, freelist, &freepage->lru);
+ if (!list_empty(&sublist))
+ list_splice_tail(&sublist, freelist);
+ }
+}
+
+/*
+ * Similar to move_freelist_head except used by the migration scanner
+ * when scanning forward. It's possible for these list operations to
+ * move against each other if they search the free list exactly in
+ * lockstep.
+ */
+static void
+move_freelist_tail(struct list_head *freelist, struct page *freepage)
+{
+ LIST_HEAD(sublist);
+
+ if (!list_is_first(freelist, &freepage->lru)) {
+ list_cut_position(&sublist, freelist, &freepage->lru);
+ if (!list_empty(&sublist))
+ list_splice_tail(&sublist, freelist);
+ }
+}
+
+static void
+fast_isolate_around(struct compact_control *cc, unsigned long pfn)
+{
+ unsigned long start_pfn, end_pfn;
+ struct page *page;
+
+ /* Do not search around if there are enough pages already */
+ if (cc->nr_freepages >= cc->nr_migratepages)
+ return;
+
+ /* Minimise scanning during async compaction */
+ if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC)
+ return;
+
+ /* Pageblock boundaries */
+ start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn);
+ end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone));
+
+ page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone);
+ if (!page)
+ return;
+
+ isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
+
+ /* Skip this pageblock in the future as it's full or nearly full */
+ if (cc->nr_freepages < cc->nr_migratepages)
+ set_pageblock_skip(page);
+
+ return;
+}
+
+/* Search orders in round-robin fashion */
+static int next_search_order(struct compact_control *cc, int order)
+{
+ order--;
+ if (order < 0)
+ order = cc->order - 1;
+
+ /* Search wrapped around? */
+ if (order == cc->search_order) {
+ cc->search_order--;
+ if (cc->search_order < 0)
+ cc->search_order = cc->order - 1;
+ return -1;
+ }
+
+ return order;
+}
+
+static unsigned long
+fast_isolate_freepages(struct compact_control *cc)
+{
+ unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
+ unsigned int nr_scanned = 0;
+ unsigned long low_pfn, min_pfn, highest = 0;
+ unsigned long nr_isolated = 0;
+ unsigned long distance;
+ struct page *page = NULL;
+ bool scan_start = false;
+ int order;
+
+ /* Full compaction passes in a negative order */
+ if (cc->order <= 0)
+ return cc->free_pfn;
+
+ /*
+ * If starting the scan, use a deeper search and use the highest
+ * PFN found if a suitable one is not found.
+ */
+ if (cc->free_pfn >= cc->zone->compact_init_free_pfn) {
+ limit = pageblock_nr_pages >> 1;
+ scan_start = true;
+ }
+
+ /*
+ * Preferred point is in the top quarter of the scan space but take
+ * a pfn from the top half if the search is problematic.
+ */
+ distance = (cc->free_pfn - cc->migrate_pfn);
+ low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2));
+ min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1));
+
+ if (WARN_ON_ONCE(min_pfn > low_pfn))
+ low_pfn = min_pfn;
+
+ /*
+ * Search starts from the last successful isolation order or the next
+ * order to search after a previous failure
+ */
+ cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order);
+
+ for (order = cc->search_order;
+ !page && order >= 0;
+ order = next_search_order(cc, order)) {
+ struct free_area *area = &cc->zone->free_area[order];
+ struct list_head *freelist;
+ struct page *freepage;
+ unsigned long flags;
+ unsigned int order_scanned = 0;
+ unsigned long high_pfn = 0;
+
+ if (!area->nr_free)
+ continue;
+
+ spin_lock_irqsave(&cc->zone->lock, flags);
+ freelist = &area->free_list[MIGRATE_MOVABLE];
+ list_for_each_entry_reverse(freepage, freelist, lru) {
+ unsigned long pfn;
+
+ order_scanned++;
+ nr_scanned++;
+ pfn = page_to_pfn(freepage);
+
+ if (pfn >= highest)
+ highest = max(pageblock_start_pfn(pfn),
+ cc->zone->zone_start_pfn);
+
+ if (pfn >= low_pfn) {
+ cc->fast_search_fail = 0;
+ cc->search_order = order;
+ page = freepage;
+ break;
+ }
+
+ if (pfn >= min_pfn && pfn > high_pfn) {
+ high_pfn = pfn;
+
+ /* Shorten the scan if a candidate is found */
+ limit >>= 1;
+ }
+
+ if (order_scanned >= limit)
+ break;
+ }
+
+ /* Use a minimum pfn if a preferred one was not found */
+ if (!page && high_pfn) {
+ page = pfn_to_page(high_pfn);
+
+ /* Update freepage for the list reorder below */
+ freepage = page;
+ }
+
+ /* Reorder to so a future search skips recent pages */
+ move_freelist_head(freelist, freepage);
+
+ /* Isolate the page if available */
+ if (page) {
+ if (__isolate_free_page(page, order)) {
+ set_page_private(page, order);
+ nr_isolated = 1 << order;
+ cc->nr_freepages += nr_isolated;
+ list_add_tail(&page->lru, &cc->freepages);
+ count_compact_events(COMPACTISOLATED, nr_isolated);
+ } else {
+ /* If isolation fails, abort the search */
+ order = cc->search_order + 1;
+ page = NULL;
+ }
+ }
+
+ spin_unlock_irqrestore(&cc->zone->lock, flags);
+
+ /*
+ * Smaller scan on next order so the total scan ig related
+ * to freelist_scan_limit.
+ */
+ if (order_scanned >= limit)
+ limit = min(1U, limit >> 1);
+ }
+
+ if (!page) {
+ cc->fast_search_fail++;
+ if (scan_start) {
+ /*
+ * Use the highest PFN found above min. If one was
+ * not found, be pessimistic for direct compaction
+ * and use the min mark.
+ */
+ if (highest) {
+ page = pfn_to_page(highest);
+ cc->free_pfn = highest;
+ } else {
+ if (cc->direct_compaction && pfn_valid(min_pfn)) {
+ page = pageblock_pfn_to_page(min_pfn,
+ min(pageblock_end_pfn(min_pfn),
+ zone_end_pfn(cc->zone)),
+ cc->zone);
+ cc->free_pfn = min_pfn;
+ }
+ }
+ }
+ }
+
+ if (highest && highest >= cc->zone->compact_cached_free_pfn) {
+ highest -= pageblock_nr_pages;
+ cc->zone->compact_cached_free_pfn = highest;
+ }
+
+ cc->total_free_scanned += nr_scanned;
+ if (!page)
+ return cc->free_pfn;
+
+ low_pfn = page_to_pfn(page);
+ fast_isolate_around(cc, low_pfn);
+ return low_pfn;
}
/*
@@ -1073,6 +1495,12 @@
unsigned long block_end_pfn; /* end of current pageblock */
unsigned long low_pfn; /* lowest pfn scanner is able to scan */
struct list_head *freelist = &cc->freepages;
+ unsigned int stride;
+
+ /* Try a small search of the free lists for a candidate */
+ isolate_start_pfn = fast_isolate_freepages(cc);
+ if (cc->nr_freepages)
+ goto splitmap;
/*
* Initialise the free scanner. The starting point is where we last
@@ -1081,15 +1509,16 @@
* this pfn aligned down to the pageblock boundary, because we do
* block_start_pfn -= pageblock_nr_pages in the for loop.
* For ending point, take care when isolating in last pageblock of a
- * a zone which ends in the middle of a pageblock.
+ * zone which ends in the middle of a pageblock.
* The low boundary is the end of the pageblock the migration scanner
* is using.
*/
isolate_start_pfn = cc->free_pfn;
- block_start_pfn = pageblock_start_pfn(cc->free_pfn);
+ block_start_pfn = pageblock_start_pfn(isolate_start_pfn);
block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
zone_end_pfn(zone));
low_pfn = pageblock_end_pfn(cc->migrate_pfn);
+ stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1;
/*
* Isolate free pages until enough are available to migrate the
@@ -1100,14 +1529,14 @@
block_end_pfn = block_start_pfn,
block_start_pfn -= pageblock_nr_pages,
isolate_start_pfn = block_start_pfn) {
+ unsigned long nr_isolated;
+
/*
* This can iterate a massively long zone without finding any
- * suitable migration targets, so periodically check if we need
- * to schedule, or even abort async compaction.
+ * suitable migration targets, so periodically check resched.
*/
- if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
- && compact_should_abort(cc))
- break;
+ if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)))
+ cond_resched();
page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
zone);
@@ -1123,15 +1552,15 @@
continue;
/* Found a block suitable for isolating free pages from. */
- isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
- freelist, false);
+ nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+ block_end_pfn, freelist, stride, false);
- /*
- * If we isolated enough freepages, or aborted due to lock
- * contention, terminate.
- */
- if ((cc->nr_freepages >= cc->nr_migratepages)
- || cc->contended) {
+ /* Update the skip hint if the full pageblock was scanned */
+ if (isolate_start_pfn == block_end_pfn)
+ update_pageblock_skip(cc, page, block_start_pfn);
+
+ /* Are enough freepages isolated? */
+ if (cc->nr_freepages >= cc->nr_migratepages) {
if (isolate_start_pfn >= block_end_pfn) {
/*
* Restart at previous pageblock if more
@@ -1148,10 +1577,14 @@
*/
break;
}
- }
- /* __isolate_free_page() does not map the pages */
- map_pages(freelist);
+ /* Adjust stride depending on isolation */
+ if (nr_isolated) {
+ stride = 1;
+ continue;
+ }
+ stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1);
+ }
/*
* Record where the free scanner will restart next time. Either we
@@ -1160,6 +1593,10 @@
* and the loop terminated due to isolate_start_pfn < low_pfn
*/
cc->free_pfn = isolate_start_pfn;
+
+splitmap:
+ /* __isolate_free_page() does not map the pages */
+ split_map_pages(freelist);
}
/*
@@ -1172,13 +1609,8 @@
struct compact_control *cc = (struct compact_control *)data;
struct page *freepage;
- /*
- * Isolate free pages if necessary, and if we are not aborting due to
- * contention.
- */
if (list_empty(&cc->freepages)) {
- if (!cc->contended)
- isolate_freepages(cc);
+ isolate_freepages(cc);
if (list_empty(&cc->freepages))
return NULL;
@@ -1215,15 +1647,158 @@
* Allow userspace to control policy on scanning the unevictable LRU for
* compactable pages.
*/
+#ifdef CONFIG_PREEMPT_RT
+int sysctl_compact_unevictable_allowed __read_mostly = 0;
+#else
int sysctl_compact_unevictable_allowed __read_mostly = 1;
+#endif
+
+static inline void
+update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
+{
+ if (cc->fast_start_pfn == ULONG_MAX)
+ return;
+
+ if (!cc->fast_start_pfn)
+ cc->fast_start_pfn = pfn;
+
+ cc->fast_start_pfn = min(cc->fast_start_pfn, pfn);
+}
+
+static inline unsigned long
+reinit_migrate_pfn(struct compact_control *cc)
+{
+ if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX)
+ return cc->migrate_pfn;
+
+ cc->migrate_pfn = cc->fast_start_pfn;
+ cc->fast_start_pfn = ULONG_MAX;
+
+ return cc->migrate_pfn;
+}
+
+/*
+ * Briefly search the free lists for a migration source that already has
+ * some free pages to reduce the number of pages that need migration
+ * before a pageblock is free.
+ */
+static unsigned long fast_find_migrateblock(struct compact_control *cc)
+{
+ unsigned int limit = freelist_scan_limit(cc);
+ unsigned int nr_scanned = 0;
+ unsigned long distance;
+ unsigned long pfn = cc->migrate_pfn;
+ unsigned long high_pfn;
+ int order;
+ bool found_block = false;
+
+ /* Skip hints are relied on to avoid repeats on the fast search */
+ if (cc->ignore_skip_hint)
+ return pfn;
+
+ /*
+ * If the migrate_pfn is not at the start of a zone or the start
+ * of a pageblock then assume this is a continuation of a previous
+ * scan restarted due to COMPACT_CLUSTER_MAX.
+ */
+ if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn))
+ return pfn;
+
+ /*
+ * For smaller orders, just linearly scan as the number of pages
+ * to migrate should be relatively small and does not necessarily
+ * justify freeing up a large block for a small allocation.
+ */
+ if (cc->order <= PAGE_ALLOC_COSTLY_ORDER)
+ return pfn;
+
+ /*
+ * Only allow kcompactd and direct requests for movable pages to
+ * quickly clear out a MOVABLE pageblock for allocation. This
+ * reduces the risk that a large movable pageblock is freed for
+ * an unmovable/reclaimable small allocation.
+ */
+ if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE)
+ return pfn;
+
+ /*
+ * When starting the migration scanner, pick any pageblock within the
+ * first half of the search space. Otherwise try and pick a pageblock
+ * within the first eighth to reduce the chances that a migration
+ * target later becomes a source.
+ */
+ distance = (cc->free_pfn - cc->migrate_pfn) >> 1;
+ if (cc->migrate_pfn != cc->zone->zone_start_pfn)
+ distance >>= 2;
+ high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance);
+
+ for (order = cc->order - 1;
+ order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit;
+ order--) {
+ struct free_area *area = &cc->zone->free_area[order];
+ struct list_head *freelist;
+ unsigned long flags;
+ struct page *freepage;
+
+ if (!area->nr_free)
+ continue;
+
+ spin_lock_irqsave(&cc->zone->lock, flags);
+ freelist = &area->free_list[MIGRATE_MOVABLE];
+ list_for_each_entry(freepage, freelist, lru) {
+ unsigned long free_pfn;
+
+ if (nr_scanned++ >= limit) {
+ move_freelist_tail(freelist, freepage);
+ break;
+ }
+
+ free_pfn = page_to_pfn(freepage);
+ if (free_pfn < high_pfn) {
+ /*
+ * Avoid if skipped recently. Ideally it would
+ * move to the tail but even safe iteration of
+ * the list assumes an entry is deleted, not
+ * reordered.
+ */
+ if (get_pageblock_skip(freepage))
+ continue;
+
+ /* Reorder to so a future search skips recent pages */
+ move_freelist_tail(freelist, freepage);
+
+ update_fast_start_pfn(cc, free_pfn);
+ pfn = pageblock_start_pfn(free_pfn);
+ if (pfn < cc->zone->zone_start_pfn)
+ pfn = cc->zone->zone_start_pfn;
+ cc->fast_search_fail = 0;
+ found_block = true;
+ set_pageblock_skip(freepage);
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&cc->zone->lock, flags);
+ }
+
+ cc->total_migrate_scanned += nr_scanned;
+
+ /*
+ * If fast scanning failed then use a cached entry for a page block
+ * that had free pages as the basis for starting a linear scan.
+ */
+ if (!found_block) {
+ cc->fast_search_fail++;
+ pfn = reinit_migrate_pfn(cc);
+ }
+ return pfn;
+}
/*
* Isolate all pages that can be migrated from the first suitable block,
* starting at the block pointed to by the migrate scanner pfn within
* compact_control.
*/
-static isolate_migrate_t isolate_migratepages(struct zone *zone,
- struct compact_control *cc)
+static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
{
unsigned long block_start_pfn;
unsigned long block_end_pfn;
@@ -1232,15 +1807,24 @@
const isolate_mode_t isolate_mode =
(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
(cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0);
+ bool fast_find_block;
/*
* Start at where we last stopped, or beginning of the zone as
- * initialized by compact_zone()
+ * initialized by compact_zone(). The first failure will use
+ * the lowest PFN as the starting point for linear scanning.
*/
- low_pfn = cc->migrate_pfn;
+ low_pfn = fast_find_migrateblock(cc);
block_start_pfn = pageblock_start_pfn(low_pfn);
- if (block_start_pfn < zone->zone_start_pfn)
- block_start_pfn = zone->zone_start_pfn;
+ if (block_start_pfn < cc->zone->zone_start_pfn)
+ block_start_pfn = cc->zone->zone_start_pfn;
+
+ /*
+ * fast_find_migrateblock marks a pageblock skipped so to avoid
+ * the isolation_suitable check below, check whether the fast
+ * search was successful.
+ */
+ fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail;
/* Only scan within a pageblock boundary */
block_end_pfn = pageblock_end_pfn(low_pfn);
@@ -1250,6 +1834,7 @@
* Do not cross the free scanner.
*/
for (; block_end_pfn <= cc->free_pfn;
+ fast_find_block = false,
low_pfn = block_end_pfn,
block_start_pfn = block_end_pfn,
block_end_pfn += pageblock_nr_pages) {
@@ -1257,34 +1842,45 @@
/*
* This can potentially iterate a massively long zone with
* many pageblocks unsuitable, so periodically check if we
- * need to schedule, or even abort async compaction.
+ * need to schedule.
*/
- if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
- && compact_should_abort(cc))
- break;
+ if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)))
+ cond_resched();
- page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
- zone);
+ page = pageblock_pfn_to_page(block_start_pfn,
+ block_end_pfn, cc->zone);
if (!page)
continue;
- /* If isolation recently failed, do not retry */
- if (!isolation_suitable(cc, page))
+ /*
+ * If isolation recently failed, do not retry. Only check the
+ * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock
+ * to be visited multiple times. Assume skip was checked
+ * before making it "skip" so other compaction instances do
+ * not scan the same block.
+ */
+ if (IS_ALIGNED(low_pfn, pageblock_nr_pages) &&
+ !fast_find_block && !isolation_suitable(cc, page))
continue;
/*
- * For async compaction, also only scan in MOVABLE blocks.
- * Async compaction is optimistic to see if the minimum amount
- * of work satisfies the allocation.
+ * For async compaction, also only scan in MOVABLE blocks
+ * without huge pages. Async compaction is optimistic to see
+ * if the minimum amount of work satisfies the allocation.
+ * The cached PFN is updated as it's possible that all
+ * remaining blocks between source and target are unsuitable
+ * and the compaction scanners fail to meet.
*/
- if (!suitable_migration_source(cc, page))
+ if (!suitable_migration_source(cc, page)) {
+ update_cached_migrate(cc, block_end_pfn);
continue;
+ }
/* Perform the isolation */
low_pfn = isolate_migratepages_block(cc, low_pfn,
block_end_pfn, isolate_mode);
- if (!low_pfn || cc->contended)
+ if (!low_pfn)
return ISOLATE_ABORT;
/*
@@ -1310,19 +1906,95 @@
return order == -1;
}
-static enum compact_result __compact_finished(struct zone *zone,
- struct compact_control *cc)
+static bool kswapd_is_running(pg_data_t *pgdat)
+{
+ return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING);
+}
+
+/*
+ * A zone's fragmentation score is the external fragmentation wrt to the
+ * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
+ */
+static unsigned int fragmentation_score_zone(struct zone *zone)
+{
+ return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+}
+
+/*
+ * A weighted zone's fragmentation score is the external fragmentation
+ * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
+ * returns a value in the range [0, 100].
+ *
+ * The scaling factor ensures that proactive compaction focuses on larger
+ * zones like ZONE_NORMAL, rather than smaller, specialized zones like
+ * ZONE_DMA32. For smaller zones, the score value remains close to zero,
+ * and thus never exceeds the high threshold for proactive compaction.
+ */
+static unsigned int fragmentation_score_zone_weighted(struct zone *zone)
+{
+ unsigned long score;
+
+ score = zone->present_pages * fragmentation_score_zone(zone);
+ return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
+}
+
+/*
+ * The per-node proactive (background) compaction process is started by its
+ * corresponding kcompactd thread when the node's fragmentation score
+ * exceeds the high threshold. The compaction process remains active till
+ * the node's score falls below the low threshold, or one of the back-off
+ * conditions is met.
+ */
+static unsigned int fragmentation_score_node(pg_data_t *pgdat)
+{
+ unsigned int score = 0;
+ int zoneid;
+
+ for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+ struct zone *zone;
+
+ zone = &pgdat->node_zones[zoneid];
+ score += fragmentation_score_zone_weighted(zone);
+ }
+
+ return score;
+}
+
+static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+{
+ unsigned int wmark_low;
+
+ /*
+ * Cap the low watermak to avoid excessive compaction
+ * activity in case a user sets the proactivess tunable
+ * close to 100 (maximum).
+ */
+ wmark_low = max(100U - sysctl_compaction_proactiveness, 5U);
+ return low ? wmark_low : min(wmark_low + 10, 100U);
+}
+
+static bool should_proactive_compact_node(pg_data_t *pgdat)
+{
+ int wmark_high;
+
+ if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
+ return false;
+
+ wmark_high = fragmentation_score_wmark(pgdat, false);
+ return fragmentation_score_node(pgdat) > wmark_high;
+}
+
+static enum compact_result __compact_finished(struct compact_control *cc)
{
unsigned int order;
const int migratetype = cc->migratetype;
-
- if (cc->contended || fatal_signal_pending(current))
- return COMPACT_CONTENDED;
+ int ret;
+ bool abort_compact = false;
/* Compaction run completes if the migrate and free scanner meet */
if (compact_scanners_met(cc)) {
/* Let the next compaction start anew. */
- reset_cached_positions(zone);
+ reset_cached_positions(cc->zone);
/*
* Mark that the PG_migrate_skip information should be cleared
@@ -1331,7 +2003,7 @@
* based on an allocation request.
*/
if (cc->direct_compaction)
- zone->compact_blockskip_flush = true;
+ cc->zone->compact_blockskip_flush = true;
if (cc->whole_zone)
return COMPACT_COMPLETE;
@@ -1339,33 +2011,51 @@
return COMPACT_PARTIAL_SKIPPED;
}
+ if (cc->proactive_compaction) {
+ int score, wmark_low;
+ pg_data_t *pgdat;
+
+ pgdat = cc->zone->zone_pgdat;
+ if (kswapd_is_running(pgdat))
+ return COMPACT_PARTIAL_SKIPPED;
+
+ score = fragmentation_score_zone(cc->zone);
+ wmark_low = fragmentation_score_wmark(pgdat, true);
+
+ if (score > wmark_low)
+ ret = COMPACT_CONTINUE;
+ else
+ ret = COMPACT_SUCCESS;
+
+ goto out;
+ }
+
if (is_via_compact_memory(cc->order))
return COMPACT_CONTINUE;
- if (cc->finishing_block) {
- /*
- * We have finished the pageblock, but better check again that
- * we really succeeded.
- */
- if (IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
- cc->finishing_block = false;
- else
- return COMPACT_CONTINUE;
- }
+ /*
+ * Always finish scanning a pageblock to reduce the possibility of
+ * fallbacks in the future. This is particularly important when
+ * migration source is unmovable/reclaimable but it's not worth
+ * special casing.
+ */
+ if (!IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
+ return COMPACT_CONTINUE;
/* Direct compactor: Is a suitable page free? */
+ ret = COMPACT_NO_SUITABLE_PAGE;
for (order = cc->order; order < MAX_ORDER; order++) {
- struct free_area *area = &zone->free_area[order];
+ struct free_area *area = &cc->zone->free_area[order];
bool can_steal;
/* Job done if page is free of the right migratetype */
- if (!list_empty(&area->free_list[migratetype]))
+ if (!free_area_empty(area, migratetype))
return COMPACT_SUCCESS;
#ifdef CONFIG_CMA
/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
if (migratetype == MIGRATE_MOVABLE &&
- !list_empty(&area->free_list[MIGRATE_CMA]))
+ !free_area_empty(area, MIGRATE_CMA))
return COMPACT_SUCCESS;
#endif
/*
@@ -1393,21 +2083,25 @@
return COMPACT_SUCCESS;
}
- cc->finishing_block = true;
- return COMPACT_CONTINUE;
+ ret = COMPACT_CONTINUE;
+ break;
}
}
- return COMPACT_NO_SUITABLE_PAGE;
+out:
+ trace_android_vh_compact_finished(&abort_compact);
+ if (cc->contended || fatal_signal_pending(current) || abort_compact)
+ ret = COMPACT_CONTENDED;
+
+ return ret;
}
-static enum compact_result compact_finished(struct zone *zone,
- struct compact_control *cc)
+static enum compact_result compact_finished(struct compact_control *cc)
{
int ret;
- ret = __compact_finished(zone, cc);
- trace_mm_compaction_finished(zone, cc->order, ret);
+ ret = __compact_finished(cc);
+ trace_mm_compaction_finished(cc->zone, cc->order, ret);
if (ret == COMPACT_NO_SUITABLE_PAGE)
ret = COMPACT_CONTINUE;
@@ -1423,7 +2117,7 @@
*/
static enum compact_result __compaction_suitable(struct zone *zone, int order,
unsigned int alloc_flags,
- int classzone_idx,
+ int highest_zoneidx,
unsigned long wmark_target)
{
unsigned long watermark;
@@ -1431,12 +2125,12 @@
if (is_via_compact_memory(order))
return COMPACT_CONTINUE;
- watermark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
/*
* If watermarks for high-order allocation are already met, there
* should be no need for compaction at all.
*/
- if (zone_watermark_ok(zone, order, watermark, classzone_idx,
+ if (zone_watermark_ok(zone, order, watermark, highest_zoneidx,
alloc_flags))
return COMPACT_SUCCESS;
@@ -1446,9 +2140,9 @@
* watermark and alloc_flags have to match, or be more pessimistic than
* the check in __isolate_free_page(). We don't use the direct
* compactor's alloc_flags, as they are not relevant for freepage
- * isolation. We however do use the direct compactor's classzone_idx to
- * skip over zones where lowmem reserves would prevent allocation even
- * if compaction succeeds.
+ * isolation. We however do use the direct compactor's highest_zoneidx
+ * to skip over zones where lowmem reserves would prevent allocation
+ * even if compaction succeeds.
* For costly orders, we require low watermark instead of min for
* compaction to proceed to increase its chances.
* ALLOC_CMA is used, as pages in CMA pageblocks are considered
@@ -1457,7 +2151,7 @@
watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
low_wmark_pages(zone) : min_wmark_pages(zone);
watermark += compact_gap(order);
- if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
+ if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx,
ALLOC_CMA, wmark_target))
return COMPACT_SKIPPED;
@@ -1466,12 +2160,12 @@
enum compact_result compaction_suitable(struct zone *zone, int order,
unsigned int alloc_flags,
- int classzone_idx)
+ int highest_zoneidx)
{
enum compact_result ret;
int fragindex;
- ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx,
+ ret = __compaction_suitable(zone, order, alloc_flags, highest_zoneidx,
zone_page_state(zone, NR_FREE_PAGES));
/*
* fragmentation index determines if allocation failures are due to
@@ -1512,8 +2206,8 @@
* Make sure at least one zone would pass __compaction_suitable if we continue
* retrying the reclaim.
*/
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
unsigned long available;
enum compact_result compact_result;
@@ -1526,7 +2220,7 @@
available = zone_reclaimable_pages(zone) / order;
available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
compact_result = __compaction_suitable(zone, order, alloc_flags,
- ac_classzone_idx(ac), available);
+ ac->highest_zoneidx, available);
if (compact_result != COMPACT_SKIPPED)
return true;
}
@@ -1534,12 +2228,15 @@
return false;
}
-static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc)
+static enum compact_result
+compact_zone(struct compact_control *cc, struct capture_control *capc)
{
enum compact_result ret;
- unsigned long start_pfn = zone->zone_start_pfn;
- unsigned long end_pfn = zone_end_pfn(zone);
+ unsigned long start_pfn = cc->zone->zone_start_pfn;
+ unsigned long end_pfn = zone_end_pfn(cc->zone);
+ unsigned long last_migrated_pfn;
const bool sync = cc->mode != MIGRATE_ASYNC;
+ bool update_cached;
/*
* These counters track activities during zone compaction. Initialize
@@ -1552,9 +2249,9 @@
INIT_LIST_HEAD(&cc->freepages);
INIT_LIST_HEAD(&cc->migratepages);
- cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask);
- ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
- cc->classzone_idx);
+ cc->migratetype = gfp_migratetype(cc->gfp_mask);
+ ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags,
+ cc->highest_zoneidx);
/* Compaction is likely to fail */
if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED)
return ret;
@@ -1566,8 +2263,8 @@
* Clear pageblock skip if there were failures recently and compaction
* is about to be retried after being deferred.
*/
- if (compaction_restarting(zone, cc->order))
- __reset_isolation_suitable(zone);
+ if (compaction_restarting(cc->zone, cc->order))
+ __reset_isolation_suitable(cc->zone);
/*
* Setup to move all movable pages to the end of the zone. Used cached
@@ -1575,43 +2272,76 @@
* want to compact the whole zone), but check that it is initialised
* by ensuring the values are within zone boundaries.
*/
+ cc->fast_start_pfn = 0;
if (cc->whole_zone) {
cc->migrate_pfn = start_pfn;
cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
} else {
- cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
- cc->free_pfn = zone->compact_cached_free_pfn;
+ cc->migrate_pfn = cc->zone->compact_cached_migrate_pfn[sync];
+ cc->free_pfn = cc->zone->compact_cached_free_pfn;
if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
- zone->compact_cached_free_pfn = cc->free_pfn;
+ cc->zone->compact_cached_free_pfn = cc->free_pfn;
}
if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
cc->migrate_pfn = start_pfn;
- zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
- zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
+ cc->zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+ cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
}
- if (cc->migrate_pfn == start_pfn)
+ if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn)
cc->whole_zone = true;
}
- cc->last_migrated_pfn = 0;
+ last_migrated_pfn = 0;
+
+ /*
+ * Migrate has separate cached PFNs for ASYNC and SYNC* migration on
+ * the basis that some migrations will fail in ASYNC mode. However,
+ * if the cached PFNs match and pageblocks are skipped due to having
+ * no isolation candidates, then the sync state does not matter.
+ * Until a pageblock with isolation candidates is found, keep the
+ * cached PFNs in sync to avoid revisiting the same blocks.
+ */
+ update_cached = !sync &&
+ cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1];
trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
cc->free_pfn, end_pfn, sync);
- migrate_prep_local();
+ /* lru_add_drain_all could be expensive with involving other CPUs */
+ lru_add_drain();
- while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
+ while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) {
int err;
+ unsigned long start_pfn = cc->migrate_pfn;
- switch (isolate_migratepages(zone, cc)) {
+ /*
+ * Avoid multiple rescans which can happen if a page cannot be
+ * isolated (dirty/writeback in async mode) or if the migrated
+ * pages are being allocated before the pageblock is cleared.
+ * The first rescan will capture the entire pageblock for
+ * migration. If it fails, it'll be marked skip and scanning
+ * will proceed as normal.
+ */
+ cc->rescan = false;
+ if (pageblock_start_pfn(last_migrated_pfn) ==
+ pageblock_start_pfn(start_pfn)) {
+ cc->rescan = true;
+ }
+
+ switch (isolate_migratepages(cc)) {
case ISOLATE_ABORT:
ret = COMPACT_CONTENDED;
putback_movable_pages(&cc->migratepages);
cc->nr_migratepages = 0;
goto out;
case ISOLATE_NONE:
+ if (update_cached) {
+ cc->zone->compact_cached_migrate_pfn[1] =
+ cc->zone->compact_cached_migrate_pfn[0];
+ }
+
/*
* We haven't isolated and migrated anything, but
* there might still be unflushed migrations from
@@ -1619,6 +2349,8 @@
*/
goto check_drain;
case ISOLATE_SUCCESS:
+ update_cached = false;
+ last_migrated_pfn = start_pfn;
;
}
@@ -1650,8 +2382,7 @@
cc->migrate_pfn = block_end_pfn(
cc->migrate_pfn - 1, cc->order);
/* Draining pcplists is useless in this case */
- cc->last_migrated_pfn = 0;
-
+ last_migrated_pfn = 0;
}
}
@@ -1663,21 +2394,22 @@
* compact_finished() can detect immediately if allocation
* would succeed.
*/
- if (cc->order > 0 && cc->last_migrated_pfn) {
- int cpu;
+ if (cc->order > 0 && last_migrated_pfn) {
unsigned long current_block_start =
block_start_pfn(cc->migrate_pfn, cc->order);
- if (cc->last_migrated_pfn < current_block_start) {
- cpu = get_cpu();
- lru_add_drain_cpu(cpu);
- drain_local_pages(zone);
- put_cpu();
+ if (last_migrated_pfn < current_block_start) {
+ lru_add_drain_cpu_zone(cc->zone);
/* No more flushing until we migrate again */
- cc->last_migrated_pfn = 0;
+ last_migrated_pfn = 0;
}
}
+ /* Stop if a page has been captured */
+ if (capc && capc->page) {
+ ret = COMPACT_SUCCESS;
+ break;
+ }
}
out:
@@ -1696,8 +2428,8 @@
* Only go back, not forward. The cached pfn might have been
* already reset to zone end in compact_finished()
*/
- if (free_pfn > zone->compact_cached_free_pfn)
- zone->compact_cached_free_pfn = free_pfn;
+ if (free_pfn > cc->zone->compact_cached_free_pfn)
+ cc->zone->compact_cached_free_pfn = free_pfn;
}
count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned);
@@ -1711,27 +2443,49 @@
static enum compact_result compact_zone_order(struct zone *zone, int order,
gfp_t gfp_mask, enum compact_priority prio,
- unsigned int alloc_flags, int classzone_idx)
+ unsigned int alloc_flags, int highest_zoneidx,
+ struct page **capture)
{
enum compact_result ret;
struct compact_control cc = {
.order = order,
+ .search_order = order,
.gfp_mask = gfp_mask,
.zone = zone,
.mode = (prio == COMPACT_PRIO_ASYNC) ?
MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT,
.alloc_flags = alloc_flags,
- .classzone_idx = classzone_idx,
+ .highest_zoneidx = highest_zoneidx,
.direct_compaction = true,
.whole_zone = (prio == MIN_COMPACT_PRIORITY),
.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
};
+ struct capture_control capc = {
+ .cc = &cc,
+ .page = NULL,
+ };
- ret = compact_zone(zone, &cc);
+ /*
+ * Make sure the structs are really initialized before we expose the
+ * capture control, in case we are interrupted and the interrupt handler
+ * frees a page.
+ */
+ barrier();
+ WRITE_ONCE(current->capture_control, &capc);
+
+ ret = compact_zone(&cc, &capc);
VM_BUG_ON(!list_empty(&cc.freepages));
VM_BUG_ON(!list_empty(&cc.migratepages));
+
+ /*
+ * Make sure we hide capture control first before we read the captured
+ * page pointer, otherwise an interrupt could free and capture a page
+ * and we would leak it.
+ */
+ WRITE_ONCE(current->capture_control, NULL);
+ *capture = READ_ONCE(capc.page);
return ret;
}
@@ -1745,12 +2499,13 @@
* @alloc_flags: The allocation flags of the current allocation
* @ac: The context of current allocation
* @prio: Determines how hard direct compaction should try to succeed
+ * @capture: Pointer to free page created by compaction will be stored here
*
* This is the main entry point for direct page compaction.
*/
enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
- enum compact_priority prio)
+ enum compact_priority prio, struct page **capture)
{
int may_perform_io = gfp_mask & __GFP_IO;
struct zoneref *z;
@@ -1767,8 +2522,8 @@
trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
/* Compact each zone in the list */
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
enum compact_result status;
if (prio > MIN_COMPACT_PRIORITY
@@ -1778,7 +2533,7 @@
}
status = compact_zone_order(zone, order, gfp_mask, prio,
- alloc_flags, ac_classzone_idx(ac));
+ alloc_flags, ac->highest_zoneidx, capture);
rc = max(status, rc);
/* The allocation should succeed, stop compacting */
@@ -1816,6 +2571,41 @@
return rc;
}
+/*
+ * Compact all zones within a node till each zone's fragmentation score
+ * reaches within proactive compaction thresholds (as determined by the
+ * proactiveness tunable).
+ *
+ * It is possible that the function returns before reaching score targets
+ * due to various back-off conditions, such as, contention on per-node or
+ * per-zone locks.
+ */
+static void proactive_compact_node(pg_data_t *pgdat)
+{
+ int zoneid;
+ struct zone *zone;
+ struct compact_control cc = {
+ .order = -1,
+ .mode = MIGRATE_SYNC_LIGHT,
+ .ignore_skip_hint = true,
+ .whole_zone = true,
+ .gfp_mask = GFP_KERNEL,
+ .proactive_compaction = true,
+ };
+
+ for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+ zone = &pgdat->node_zones[zoneid];
+ if (!populated_zone(zone))
+ continue;
+
+ cc.zone = zone;
+
+ compact_zone(&cc, NULL);
+
+ VM_BUG_ON(!list_empty(&cc.freepages));
+ VM_BUG_ON(!list_empty(&cc.migratepages));
+ }
+}
/* Compact all zones within a node */
static void compact_node(int nid)
@@ -1840,7 +2630,7 @@
cc.zone = zone;
- compact_zone(zone, &cc);
+ compact_zone(&cc, NULL);
VM_BUG_ON(!list_empty(&cc.freepages));
VM_BUG_ON(!list_empty(&cc.migratepages));
@@ -1863,22 +2653,45 @@
int sysctl_compact_memory;
/*
- * This is the entry point for compacting all nodes via
- * /proc/sys/vm/compact_memory
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
*/
-int sysctl_compaction_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
+
+int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
{
- if (write)
- compact_nodes();
+ int rc, nid;
+
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
+ if (rc)
+ return rc;
+
+ if (write && sysctl_compaction_proactiveness) {
+ for_each_online_node(nid) {
+ pg_data_t *pgdat = NODE_DATA(nid);
+
+ if (pgdat->proactive_compact_trigger)
+ continue;
+
+ pgdat->proactive_compact_trigger = true;
+ wake_up_interruptible(&pgdat->kcompactd_wait);
+ }
+ }
return 0;
}
-int sysctl_extfrag_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+/*
+ * This is the entry point for compacting all nodes via
+ * /proc/sys/vm/compact_memory
+ */
+int sysctl_compaction_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec_minmax(table, write, buffer, length, ppos);
+ if (write)
+ compact_nodes();
return 0;
}
@@ -1914,23 +2727,24 @@
static inline bool kcompactd_work_requested(pg_data_t *pgdat)
{
- return pgdat->kcompactd_max_order > 0 || kthread_should_stop();
+ return pgdat->kcompactd_max_order > 0 || kthread_should_stop() ||
+ pgdat->proactive_compact_trigger;
}
static bool kcompactd_node_suitable(pg_data_t *pgdat)
{
int zoneid;
struct zone *zone;
- enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx;
+ enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx;
- for (zoneid = 0; zoneid <= classzone_idx; zoneid++) {
+ for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) {
zone = &pgdat->node_zones[zoneid];
if (!populated_zone(zone))
continue;
if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0,
- classzone_idx) == COMPACT_CONTINUE)
+ highest_zoneidx) == COMPACT_CONTINUE)
return true;
}
@@ -1947,16 +2761,17 @@
struct zone *zone;
struct compact_control cc = {
.order = pgdat->kcompactd_max_order,
- .classzone_idx = pgdat->kcompactd_classzone_idx,
+ .search_order = pgdat->kcompactd_max_order,
+ .highest_zoneidx = pgdat->kcompactd_highest_zoneidx,
.mode = MIGRATE_SYNC_LIGHT,
.ignore_skip_hint = false,
.gfp_mask = GFP_KERNEL,
};
trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
- cc.classzone_idx);
+ cc.highest_zoneidx);
count_compact_event(KCOMPACTD_WAKE);
- for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) {
+ for (zoneid = 0; zoneid <= cc.highest_zoneidx; zoneid++) {
int status;
zone = &pgdat->node_zones[zoneid];
@@ -1974,7 +2789,7 @@
return;
cc.zone = zone;
- status = compact_zone(zone, &cc);
+ status = compact_zone(&cc, NULL);
if (status == COMPACT_SUCCESS) {
compaction_defer_reset(zone, cc.order, false);
@@ -2005,16 +2820,16 @@
/*
* Regardless of success, we are done until woken up next. But remember
- * the requested order/classzone_idx in case it was higher/tighter than
- * our current ones
+ * the requested order/highest_zoneidx in case it was higher/tighter
+ * than our current ones
*/
if (pgdat->kcompactd_max_order <= cc.order)
pgdat->kcompactd_max_order = 0;
- if (pgdat->kcompactd_classzone_idx >= cc.classzone_idx)
- pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+ if (pgdat->kcompactd_highest_zoneidx >= cc.highest_zoneidx)
+ pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1;
}
-void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
+void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx)
{
if (!order)
return;
@@ -2022,8 +2837,8 @@
if (pgdat->kcompactd_max_order < order)
pgdat->kcompactd_max_order = order;
- if (pgdat->kcompactd_classzone_idx > classzone_idx)
- pgdat->kcompactd_classzone_idx = classzone_idx;
+ if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx)
+ pgdat->kcompactd_highest_zoneidx = highest_zoneidx;
/*
* Pairs with implicit barrier in wait_event_freezable()
@@ -2036,7 +2851,7 @@
return;
trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order,
- classzone_idx);
+ highest_zoneidx);
wake_up_interruptible(&pgdat->kcompactd_wait);
}
@@ -2048,6 +2863,7 @@
{
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
+ unsigned int proactive_defer = 0;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
@@ -2057,18 +2873,56 @@
set_freezable();
pgdat->kcompactd_max_order = 0;
- pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+ pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1;
while (!kthread_should_stop()) {
unsigned long pflags;
+ long timeout;
+ timeout = sysctl_compaction_proactiveness ?
+ msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC) :
+ MAX_SCHEDULE_TIMEOUT;
trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
- wait_event_freezable(pgdat->kcompactd_wait,
- kcompactd_work_requested(pgdat));
+ if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
+ kcompactd_work_requested(pgdat), timeout) &&
+ !pgdat->proactive_compact_trigger) {
- psi_memstall_enter(&pflags);
- kcompactd_do_work(pgdat);
- psi_memstall_leave(&pflags);
+ psi_memstall_enter(&pflags);
+ kcompactd_do_work(pgdat);
+ psi_memstall_leave(&pflags);
+ continue;
+ }
+
+ /* kcompactd wait timeout */
+ if (should_proactive_compact_node(pgdat)) {
+ unsigned int prev_score, score;
+
+ /*
+ * On wakeup of proactive compaction by sysctl
+ * write, ignore the accumulated defer score.
+ * Anyway, if the proactive compaction didn't
+ * make any progress for the new value, it will
+ * be further deferred by 2^COMPACT_MAX_DEFER_SHIFT
+ * times.
+ */
+ if (proactive_defer &&
+ !pgdat->proactive_compact_trigger) {
+ proactive_defer--;
+ continue;
+ }
+
+ prev_score = fragmentation_score_node(pgdat);
+ proactive_compact_node(pgdat);
+ score = fragmentation_score_node(pgdat);
+ /*
+ * Defer proactive compaction if the fragmentation
+ * score did not go down i.e. no progress made.
+ */
+ proactive_defer = score < prev_score ?
+ 0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+ }
+ if (pgdat->proactive_compact_trigger)
+ pgdat->proactive_compact_trigger = false;
}
return 0;
--
Gitblit v1.6.2