diff options
Diffstat (limited to 'mm/compaction.c')
| -rw-r--r-- | mm/compaction.c | 2591 |
1 files changed, 1881 insertions, 710 deletions
diff --git a/mm/compaction.c b/mm/compaction.c index ef29490b0f46..1e8f8eca318c 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -23,9 +23,15 @@ #include <linux/freezer.h> #include <linux/page_owner.h> #include <linux/psi.h> +#include <linux/cpuset.h> #include "internal.h" #ifdef CONFIG_COMPACTION +/* + * Fragmentation score check interval for proactive compaction purposes. + */ +#define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) + static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); @@ -35,9 +41,22 @@ static inline void count_compact_events(enum vm_event_item item, long delta) { count_vm_events(item, delta); } + +/* + * order == -1 is expected when compacting proactively via + * 1. /proc/sys/vm/compact_memory + * 2. /sys/devices/system/node/nodex/compact + * 3. /proc/sys/vm/compaction_proactiveness + */ +static inline bool is_via_compact_memory(int order) +{ + return order == -1; +} + #else #define count_compact_event(item) do { } while (0) #define count_compact_events(item, delta) do { } while (0) +static inline bool is_via_compact_memory(int order) { return false; } #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA @@ -47,99 +66,64 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #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) - -static unsigned long release_freepages(struct list_head *freelist) -{ - struct page *page, *next; - unsigned long high_pfn = 0; - list_for_each_entry_safe(page, next, freelist, lru) { - unsigned long pfn = page_to_pfn(page); - list_del(&page->lru); - __free_page(page); - if (pfn > high_pfn) - high_pfn = pfn; - } +/* + * 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 - return high_pfn; +static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) +{ + post_alloc_hook(page, order, __GFP_MOVABLE); + set_page_refcounted(page); + return page; } +#define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) -static void map_pages(struct list_head *list) +static unsigned long release_free_list(struct list_head *freepages) { - unsigned int i, order, nr_pages; - struct page *page, *next; - LIST_HEAD(tmp_list); - - list_for_each_entry_safe(page, next, list, lru) { - list_del(&page->lru); + int order; + unsigned long high_pfn = 0; - order = page_private(page); - nr_pages = 1 << order; + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct page *page, *next; - post_alloc_hook(page, order, __GFP_MOVABLE); - if (order) - split_page(page, order); + list_for_each_entry_safe(page, next, &freepages[order], lru) { + unsigned long pfn = page_to_pfn(page); - for (i = 0; i < nr_pages; i++) { - list_add(&page->lru, &tmp_list); - page++; + list_del(&page->lru); + /* + * Convert free pages into post allocation pages, so + * that we can free them via __free_page. + */ + mark_allocated(page, order, __GFP_MOVABLE); + __free_pages(page, order); + if (pfn > high_pfn) + high_pfn = pfn; } } - - list_splice(&tmp_list, list); + return high_pfn; } #ifdef CONFIG_COMPACTION -int PageMovable(struct page *page) -{ - struct address_space *mapping; - - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (!__PageMovable(page)) - return 0; - - mapping = page_mapping(page); - if (mapping && mapping->a_ops && mapping->a_ops->isolate_page) - return 1; - - return 0; -} -EXPORT_SYMBOL(PageMovable); - -void __SetPageMovable(struct page *page, struct address_space *mapping) -{ - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page); - page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE); -} -EXPORT_SYMBOL(__SetPageMovable); - -void __ClearPageMovable(struct page *page) -{ - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageMovable(page), page); - /* - * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE - * flag so that VM can catch up released page by driver after isolation. - * With it, VM migration doesn't try to put it back. - */ - page->mapping = (void *)((unsigned long)page->mapping & - PAGE_MAPPING_MOVABLE); -} -EXPORT_SYMBOL(__ClearPageMovable); - /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 /* * 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) +static void defer_compaction(struct zone *zone, int order) { zone->compact_considered = 0; zone->compact_defer_shift++; @@ -154,7 +138,7 @@ void defer_compaction(struct zone *zone, int order) } /* Returns true if compaction should be skipped this time */ -bool compaction_deferred(struct zone *zone, int order) +static bool compaction_deferred(struct zone *zone, int order) { unsigned long defer_limit = 1UL << zone->compact_defer_shift; @@ -162,11 +146,10 @@ bool compaction_deferred(struct zone *zone, int order) 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); @@ -192,7 +175,7 @@ void compaction_defer_reset(struct zone *zone, int order, } /* Returns true if restarting compaction after many failures */ -bool compaction_restarting(struct zone *zone, int order) +static bool compaction_restarting(struct zone *zone, int order) { if (order < zone->compact_order_failed) return false; @@ -219,8 +202,60 @@ static void reset_cached_positions(struct zone *zone) pageblock_start_pfn(zone_end_pfn(zone) - 1); } +#ifdef CONFIG_SPARSEMEM /* - * Compound pages of >= pageblock_order should consistenly be skipped until + * If the PFN falls into an offline section, return the start PFN of the + * next online section. If the PFN falls into an online section or if + * there is no next online section, return 0. + */ +static unsigned long skip_offline_sections(unsigned long start_pfn) +{ + unsigned long start_nr = pfn_to_section_nr(start_pfn); + + if (online_section_nr(start_nr)) + return 0; + + while (++start_nr <= __highest_present_section_nr) { + if (online_section_nr(start_nr)) + return section_nr_to_pfn(start_nr); + } + + return 0; +} + +/* + * If the PFN falls into an offline section, return the end PFN of the + * next online section in reverse. If the PFN falls into an online section + * or if there is no next online section in reverse, return 0. + */ +static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) +{ + unsigned long start_nr = pfn_to_section_nr(start_pfn); + + if (!start_nr || online_section_nr(start_nr)) + return 0; + + while (start_nr-- > 0) { + if (online_section_nr(start_nr)) + return section_nr_to_pfn(start_nr) + PAGES_PER_SECTION; + } + + return 0; +} +#else +static unsigned long skip_offline_sections(unsigned long start_pfn) +{ + return 0; +} + +static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) +{ + return 0; +} +#endif + +/* + * Compound pages of >= pageblock_order should consistently be skipped until * released. It is always pointless to compact pages of such order (if they are * migratable), and the pageblocks they occupy cannot contain any free pages. */ @@ -237,6 +272,75 @@ static bool pageblock_skip_persistent(struct page *page) 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 (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); + } 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 +348,55 @@ static bool pageblock_skip_persistent(struct page *page) */ 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; + + /* Only flush if a full compaction finished recently */ + 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) @@ -279,47 +408,63 @@ void reset_isolation_suitable(pg_data_t *pgdat) if (!populated_zone(zone)) continue; - /* Only flush if a full compaction finished recently */ - if (zone->compact_blockskip_flush) - __reset_isolation_suitable(zone); + __reset_isolation_suitable(zone); } } /* - * If no pages were isolated then mark this pageblock to be skipped in the - * future. The information is later cleared by __reset_isolation_suitable(). + * 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 void update_pageblock_skip(struct compact_control *cc, - struct page *page, unsigned long nr_isolated, - bool migrate_scanner) +static bool test_and_set_skip(struct compact_control *cc, struct page *page) +{ + bool skip; + + /* Do not update if skip hint is being ignored */ + if (cc->ignore_skip_hint) + 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; - unsigned long pfn; + /* Set for isolation rather than compaction */ if (cc->no_set_skip_hint) return; - if (!page) - return; + pfn = pageblock_end_pfn(pfn); - if (nr_isolated) + /* Update where async and sync compaction should restart */ + 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 pfn) +{ + struct zone *zone = cc->zone; + + if (cc->no_set_skip_hint) 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 +479,42 @@ static inline bool pageblock_skip_persistent(struct page *page) } 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) { + 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; } @@ -368,15 +523,12 @@ static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags, * very heavily contended. The lock should be periodically unlocked to avoid * having disabled IRQs for a long time, even when there is nobody waiting on * the lock. It might also be that allowing the IRQs will result in - * need_resched() becoming true. If scheduling is needed, async compaction - * aborts. Sync compaction schedules. + * need_resched() becoming true. If scheduling is needed, compaction schedules. * Either compaction type will also abort if a fatal signal is pending. * In either case if the lock was locked, it is dropped and not regained. * - * Returns true if compaction should abort due to fatal signal pending, or - * async compaction due to need_resched() - * Returns false when compaction can continue (sync compaction might have - * scheduled) + * Returns true if compaction should abort due to fatal signal pending. + * Returns false when compaction can continue. */ static bool compact_unlock_should_abort(spinlock_t *lock, unsigned long flags, bool *locked, struct compact_control *cc) @@ -391,37 +543,7 @@ static bool compact_unlock_should_abort(spinlock_t *lock, 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; } @@ -435,38 +557,37 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, 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 *page; unsigned long flags = 0; bool locked = false; unsigned long blockpfn = *start_pfn; unsigned int order; - cursor = pfn_to_page(blockpfn); + /* Strict mode is for isolation, speed is secondary */ + if (strict) + stride = 1; + + page = pfn_to_page(blockpfn); /* Isolate free pages. */ - for (; blockpfn < end_pfn; blockpfn++, cursor++) { + for (; blockpfn < end_pfn; blockpfn += stride, page += stride) { int isolated; - struct page *page = cursor; /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort if fatal signal - * pending or async compaction detects need_resched() + * pending. */ - if (!(blockpfn % SWAP_CLUSTER_MAX) + if (!(blockpfn % COMPACT_CLUSTER_MAX) && compact_unlock_should_abort(&cc->zone->lock, flags, &locked, cc)) break; 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 @@ -477,36 +598,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (likely(order < MAX_ORDER)) { + if ((order <= MAX_PAGE_ORDER) && + (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; - cursor += (1UL << order) - 1; + page += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; } + goto isolate_fail; } if (!PageBuddy(page)) goto isolate_fail; - /* - * If we already hold the lock, we can skip some rechecking. - * Note that if we hold the lock now, checked_pageblock was - * already set in some previous iteration (or strict is true), - * so it is correct to skip the suitable migration target - * recheck as well. - */ + /* If we already hold the lock, we can skip some rechecking. */ 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)) @@ -514,15 +622,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, } /* 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; set_page_private(page, order); + nr_scanned += isolated - 1; total_isolated += isolated; cc->nr_freepages += isolated; - list_add_tail(&page->lru, freelist); + list_add_tail(&page->lru, &freelist[order]); if (!strict && cc->nr_migratepages <= cc->nr_freepages) { blockpfn += isolated; @@ -530,14 +639,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, } /* Advance to the end of split page */ blockpfn += isolated - 1; - cursor += isolated - 1; + page += isolated - 1; continue; isolate_fail: if (strict) break; - else - continue; } @@ -545,8 +652,7 @@ isolate_fail: spin_unlock_irqrestore(&cc->zone->lock, flags); /* - * There is a tiny chance that we have read bogus compound_order(), - * so be careful to not go outside of the pageblock. + * Be careful to not go outside of the pageblock. */ if (unlikely(blockpfn > end_pfn)) blockpfn = end_pfn; @@ -565,10 +671,6 @@ isolate_fail: 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) count_compact_events(COMPACTISOLATED, total_isolated); @@ -583,18 +685,21 @@ isolate_fail: * * Non-free pages, invalid PFNs, or zone boundaries within the * [start_pfn, end_pfn) range are considered errors, cause function to - * undo its actions and return zero. + * undo its actions and return zero. cc->freepages[] are empty. * * Otherwise, function returns one-past-the-last PFN of isolated page * (which may be greater then end_pfn if end fell in a middle of - * a free page). + * a free page). cc->freepages[] contain free pages isolated. */ unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long isolated, pfn, block_start_pfn, block_end_pfn; - LIST_HEAD(freelist); + int order; + + for (order = 0; order < NR_PAGE_ORDERS; order++) + INIT_LIST_HEAD(&cc->freepages[order]); pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); @@ -608,8 +713,6 @@ isolate_freepages_range(struct compact_control *cc, /* Protect pfn from changing by isolate_freepages_block */ unsigned long isolate_start_pfn = pfn; - block_end_pfn = min(block_end_pfn, end_pfn); - /* * pfn could pass the block_end_pfn if isolated freepage * is more than pageblock order. In this case, we adjust @@ -618,15 +721,16 @@ isolate_freepages_range(struct compact_control *cc, if (pfn >= block_end_pfn) { block_start_pfn = pageblock_start_pfn(pfn); block_end_pfn = pageblock_end_pfn(pfn); - block_end_pfn = min(block_end_pfn, end_pfn); } + block_end_pfn = min(block_end_pfn, end_pfn); + if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone)) break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, &freelist, true); + block_end_pfn, cc->freepages, 0, true); /* * In strict mode, isolate_freepages_block() returns 0 if @@ -643,12 +747,9 @@ isolate_freepages_range(struct compact_control *cc, */ } - /* __isolate_free_page() does not map the pages */ - map_pages(&freelist); - if (pfn < end_pfn) { /* Loop terminated early, cleanup. */ - release_freepages(&freelist); + release_free_list(cc->freepages); return 0; } @@ -657,18 +758,62 @@ isolate_freepages_range(struct compact_control *cc, } /* 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(struct compact_control *cc) { + pg_data_t *pgdat = cc->zone->zone_pgdat; + bool too_many; + 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); + + /* + * Allow GFP_NOFS to isolate past the limit set for regular + * compaction runs. This prevents an ABBA deadlock when other + * compactors have already isolated to the limit, but are + * blocked on filesystem locks held by the GFP_NOFS thread. + */ + if (cc->gfp_mask & __GFP_FS) { + inactive >>= 3; + active >>= 3; + } + + too_many = isolated > (inactive + active) / 2; + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; +} - return isolated > (inactive + active) / 2; +/** + * skip_isolation_on_order() - determine when to skip folio isolation based on + * folio order and compaction target order + * @order: to-be-isolated folio order + * @target_order: compaction target order + * + * This avoids unnecessary folio isolations during compaction. + */ +static bool skip_isolation_on_order(int order, int target_order) +{ + /* + * Unless we are performing global compaction (i.e., + * is_via_compact_memory), skip any folios that are larger than the + * target order: we wouldn't be here if we'd have a free folio with + * the desired target_order, so migrating this folio would likely fail + * later. + */ + if (!is_via_compact_memory(target_order) && order >= target_order) + return true; + /* + * We limit memory compaction to pageblocks and won't try + * creating free blocks of memory that are larger than that. + */ + return order >= pageblock_order; } /** @@ -677,50 +822,58 @@ static bool too_many_isolated(struct zone *zone) * @cc: Compaction control structure. * @low_pfn: The first PFN to isolate * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock - * @isolate_mode: Isolation mode to be used. + * @mode: Isolation mode to be used. * * Isolate all pages that can be migrated from the range specified by * [low_pfn, end_pfn). The range is expected to be within same pageblock. - * Returns zero if there is a fatal signal pending, otherwise PFN of the - * first page that was not scanned (which may be both less, equal to or more - * than end_pfn). + * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion, + * -ENOMEM in case we could not allocate a page, or 0. + * cc->migrate_pfn will contain the next pfn to scan. * * The pages are isolated on cc->migratepages list (not required to be empty), - * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field - * is neither read nor updated. + * and cc->nr_migratepages is updated accordingly. */ -static unsigned long +static int isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, - unsigned long end_pfn, isolate_mode_t isolate_mode) + unsigned long end_pfn, isolate_mode_t 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; - bool locked = false; + struct lruvec *locked = NULL; + struct folio *folio = NULL; struct page *page = NULL, *valid_page = NULL; + struct address_space *mapping; unsigned long start_pfn = low_pfn; bool skip_on_failure = false; unsigned long next_skip_pfn = 0; + bool skip_updated = false; + int ret = 0; + + cc->migrate_pfn = low_pfn; /* * 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(cc))) { + /* stop isolation if there are still pages not migrated */ + if (cc->nr_migratepages) + return -EAGAIN; + /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) - return 0; + return -EAGAIN; - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); if (fatal_signal_pending(current)) - return 0; + return -EINTR; } - if (compact_should_abort(cc)) - return 0; + cond_resched(); if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) { skip_on_failure = true; @@ -729,6 +882,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* Time to isolate some pages for migration */ for (; low_pfn < end_pfn; low_pfn++) { + bool is_dirty, is_unevictable; if (skip_on_failure && low_pfn >= next_skip_pfn) { /* @@ -754,22 +908,98 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * 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; + if (!(low_pfn % COMPACT_CLUSTER_MAX)) { + if (locked) { + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; + } + + if (fatal_signal_pending(current)) { + cc->contended = true; + ret = -EINTR; + + goto fatal_pending; + } + + cond_resched(); + } - if (!pfn_valid_within(low_pfn)) - goto isolate_fail; nr_scanned++; page = pfn_to_page(low_pfn); - if (!valid_page) + /* + * Check if the pageblock has already been marked skipped. + * Only the first 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 && (pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn)) { + if (!isolation_suitable(cc, page)) { + low_pfn = end_pfn; + folio = NULL; + goto isolate_abort; + } valid_page = page; + } + + if (PageHuge(page)) { + const unsigned int order = compound_order(page); + /* + * skip hugetlbfs if we are not compacting for pages + * bigger than its order. THPs and other compound pages + * are handled below. + */ + if (!cc->alloc_contig) { + + if (order <= MAX_PAGE_ORDER) { + low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; + } + goto isolate_fail; + } + /* for alloc_contig case */ + if (locked) { + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; + } + + folio = page_folio(page); + ret = isolate_or_dissolve_huge_folio(folio, &cc->migratepages); + + /* + * Fail isolation in case isolate_or_dissolve_huge_folio() + * reports an error. In case of -ENOMEM, abort right away. + */ + if (ret < 0) { + /* Do not report -EBUSY down the chain */ + if (ret == -EBUSY) + ret = 0; + low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; + goto isolate_fail; + } + + if (folio_test_hugetlb(folio)) { + /* + * Hugepage was successfully isolated and placed + * on the cc->migratepages list. + */ + low_pfn += folio_nr_pages(folio) - folio_page_idx(folio, page) - 1; + goto isolate_success_no_list; + } + + /* + * Ok, the hugepage was dissolved. Now these pages are + * Buddy and cannot be re-allocated because they are + * isolated. Fall-through as the check below handles + * Buddy pages. + */ + } /* * Skip if free. We read page order here without zone lock @@ -778,31 +1008,39 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * 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 * a valid page order. Consider only values in the * valid order range to prevent low_pfn overflow. */ - if (freepage_order > 0 && freepage_order < MAX_ORDER) + if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) { low_pfn += (1UL << freepage_order) - 1; + nr_scanned += (1UL << freepage_order) - 1; + } continue; } /* - * 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. + * Regardless of being on LRU, compound pages such as THP + * (hugetlbfs is handled above) are not to be compacted unless + * we are attempting an allocation larger than the compound + * page size. 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)) - low_pfn += (1UL << order) - 1; - goto isolate_fail; + /* Skip based on page order and compaction target order. */ + if (skip_isolation_on_order(order, cc->order)) { + if (order <= MAX_PAGE_ORDER) { + low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; + } + goto isolate_fail; + } } /* @@ -811,99 +1049,190 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * Skip any other type of page */ if (!PageLRU(page)) { - /* - * __PageMovable can return false positive so we need - * to verify it under page_lock. - */ - if (unlikely(__PageMovable(page)) && - !PageIsolated(page)) { + /* Isolation code will deal with any races. */ + if (unlikely(page_has_movable_ops(page)) && + !PageMovableOpsIsolated(page)) { if (locked) { - spin_unlock_irqrestore(zone_lru_lock(zone), - flags); - locked = false; + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; } - if (!isolate_movable_page(page, isolate_mode)) + if (isolate_movable_ops_page(page, mode)) { + folio = page_folio(page); goto isolate_success; + } } goto isolate_fail; } /* + * Be careful not to clear PageLRU until after we're + * sure the page is not being freed elsewhere -- the + * page release code relies on it. + */ + folio = folio_get_nontail_page(page); + if (unlikely(!folio)) + goto isolate_fail; + + /* * Migration will fail if an anonymous page is pinned in memory, * so avoid taking lru_lock and isolating it unnecessarily in an * admittedly racy check. */ - if (!page_mapping(page) && - page_count(page) > page_mapcount(page)) - goto isolate_fail; + mapping = folio_mapping(folio); + if (!mapping && (folio_ref_count(folio) - 1) > folio_mapcount(folio)) + goto isolate_fail_put; /* * Only allow to migrate anonymous pages in GFP_NOFS context * because those do not depend on fs locks. */ - if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page)) - goto isolate_fail; + if (!(cc->gfp_mask & __GFP_FS) && mapping) + goto isolate_fail_put; - /* If we already hold the lock, we can skip some rechecking */ - if (!locked) { - locked = compact_trylock_irqsave(zone_lru_lock(zone), - &flags, cc); - if (!locked) - break; + /* Only take pages on LRU: a check now makes later tests safe */ + if (!folio_test_lru(folio)) + goto isolate_fail_put; - /* Recheck PageLRU and PageCompound under lock */ - if (!PageLRU(page)) - goto isolate_fail; + is_unevictable = folio_test_unevictable(folio); + + /* Compaction might skip unevictable pages but CMA takes them */ + if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable) + goto isolate_fail_put; + + /* + * To minimise LRU disruption, the caller can indicate with + * ISOLATE_ASYNC_MIGRATE that it only wants to isolate pages + * it will be able to migrate without blocking - clean pages + * for the most part. PageWriteback would require blocking. + */ + if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio)) + goto isolate_fail_put; + + is_dirty = folio_test_dirty(folio); + + if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) || + (mapping && is_unevictable)) { + bool migrate_dirty = true; + bool is_inaccessible; /* - * Page become compound since the non-locked check, - * 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. + * Only folios without mappings or that have + * a ->migrate_folio callback are possible to migrate + * without blocking. + * + * Folios from inaccessible mappings are not migratable. + * + * However, we can be racing with truncation, which can + * free the mapping that we need to check. Truncation + * holds the folio lock until after the folio is removed + * from the page so holding it ourselves is sufficient. + * + * To avoid locking the folio just to check inaccessible, + * assume every inaccessible folio is also unevictable, + * which is a cheaper test. If our assumption goes + * wrong, it's not a correctness bug, just potentially + * wasted cycles. */ - if (unlikely(PageCompound(page))) { - low_pfn += (1UL << compound_order(page)) - 1; - goto isolate_fail; + if (!folio_trylock(folio)) + goto isolate_fail_put; + + mapping = folio_mapping(folio); + if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) { + migrate_dirty = !mapping || + mapping->a_ops->migrate_folio; } + is_inaccessible = mapping && mapping_inaccessible(mapping); + folio_unlock(folio); + if (!migrate_dirty || is_inaccessible) + goto isolate_fail_put; } - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + /* Try isolate the folio */ + if (!folio_test_clear_lru(folio)) + goto isolate_fail_put; - /* Try isolate the page */ - if (__isolate_lru_page(page, isolate_mode) != 0) - goto isolate_fail; + lruvec = folio_lruvec(folio); + + /* If we already hold the lock, we can skip some rechecking */ + if (lruvec != locked) { + if (locked) + unlock_page_lruvec_irqrestore(locked, flags); + + compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); + locked = lruvec; - VM_BUG_ON_PAGE(PageCompound(page), page); + lruvec_memcg_debug(lruvec, folio); + + /* + * Try get exclusive access under lock. If marked for + * skip, the scan is aborted unless the current context + * is a rescan to reach the end of the pageblock. + */ + if (!skip_updated && valid_page) { + skip_updated = true; + if (test_and_set_skip(cc, valid_page) && + !cc->finish_pageblock) { + low_pfn = end_pfn; + goto isolate_abort; + } + } + + /* + * Check LRU folio order under the lock + */ + if (unlikely(skip_isolation_on_order(folio_order(folio), + cc->order) && + !cc->alloc_contig)) { + low_pfn += folio_nr_pages(folio) - 1; + nr_scanned += folio_nr_pages(folio) - 1; + folio_set_lru(folio); + goto isolate_fail_put; + } + } + + /* The folio is taken off the LRU */ + if (folio_test_large(folio)) + low_pfn += folio_nr_pages(folio) - 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)); + lruvec_del_folio(lruvec, folio); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); isolate_success: - list_add(&page->lru, &cc->migratepages); - cc->nr_migratepages++; - nr_isolated++; + list_add(&folio->lru, &cc->migratepages); +isolate_success_no_list: + cc->nr_migratepages += folio_nr_pages(folio); + nr_isolated += folio_nr_pages(folio); + nr_scanned += folio_nr_pages(folio) - 1; /* - * 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 + * fully scanned (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->finish_pageblock && !cc->contended) { ++low_pfn; break; } continue; + +isolate_fail_put: + /* Avoid potential deadlock in freeing page under lru_lock */ + if (locked) { + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; + } + folio_put(folio); + isolate_fail: - if (!skip_on_failure) + if (!skip_on_failure && ret != -ENOMEM) continue; /* @@ -913,12 +1242,11 @@ isolate_fail: */ if (nr_isolated) { if (locked) { - spin_unlock_irqrestore(zone_lru_lock(zone), flags); - locked = false; + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; } putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; - cc->last_migrated_pfn = 0; nr_isolated = 0; } @@ -930,6 +1258,9 @@ isolate_fail: */ next_skip_pfn += 1UL << cc->order; } + + if (ret == -ENOMEM) + break; } /* @@ -939,24 +1270,41 @@ isolate_fail: if (unlikely(low_pfn > end_pfn)) low_pfn = end_pfn; + folio = NULL; + +isolate_abort: if (locked) - spin_unlock_irqrestore(zone_lru_lock(zone), flags); + unlock_page_lruvec_irqrestore(locked, flags); + if (folio) { + folio_set_lru(folio); + folio_put(folio); + } /* - * Update the pageblock-skip information and cached scanner pfn, - * if the whole pageblock was scanned without isolating any page. + * Update 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->finish_pageblock)) { + if (!cc->no_set_skip_hint && 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); - return low_pfn; + cc->migrate_pfn = low_pfn; + + return ret; } /** @@ -965,15 +1313,15 @@ isolate_fail: * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * - * Returns zero if isolation fails fatally due to e.g. pending signal. - * Otherwise, function returns one-past-the-last PFN of isolated page - * (which may be greater than end_pfn if end fell in a middle of a THP page). + * Returns -EAGAIN when contented, -EINTR in case of a signal pending, -ENOMEM + * in case we could not allocate a page, or 0. */ -unsigned long +int isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn, block_start_pfn, block_end_pfn; + int ret = 0; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; @@ -992,17 +1340,17 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, block_end_pfn, cc->zone)) continue; - pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, - ISOLATE_UNEVICTABLE); + ret = isolate_migratepages_block(cc, pfn, block_end_pfn, + ISOLATE_UNEVICTABLE); - if (!pfn) + if (ret) break; - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } - return pfn; + return ret; } #endif /* CONFIG_COMPACTION || CONFIG_CMA */ @@ -1013,6 +1361,9 @@ static bool suitable_migration_source(struct compact_control *cc, { int block_mt; + if (pageblock_skip_persistent(page)) + return false; + if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) return true; @@ -1030,12 +1381,14 @@ static bool suitable_migration_target(struct compact_control *cc, { /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { + int order = cc->order > 0 ? cc->order : pageblock_order; + /* * We are checking page_order without zone->lock taken. But * 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) >= order) return false; } @@ -1050,6 +1403,14 @@ static bool suitable_migration_target(struct compact_control *cc, 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. @@ -1061,6 +1422,255 @@ static inline bool compact_scanners_met(struct compact_control *cc) } /* + * 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_first(&freepage->buddy_list, freelist)) { + list_cut_before(&sublist, freelist, &freepage->buddy_list); + 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_last(&freepage->buddy_list, freelist)) { + list_cut_position(&sublist, freelist, &freepage->buddy_list); + 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 (start_pfn == end_pfn && !cc->no_set_skip_hint) + set_pageblock_skip(page); +} + +/* 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 void fast_isolate_freepages(struct compact_control *cc) +{ + unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1); + unsigned int nr_scanned = 0, total_isolated = 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; + + /* + * 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, buddy_list) { + 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 maximum candidate 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; + nr_scanned += nr_isolated - 1; + total_isolated += nr_isolated; + cc->nr_freepages += nr_isolated; + list_add_tail(&page->lru, &cc->freepages[order]); + 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); + + /* Skip fast search if enough freepages isolated */ + if (cc->nr_freepages >= cc->nr_migratepages) + break; + + /* + * Smaller scan on next order so the total scan is related + * to freelist_scan_limit. + */ + if (order_scanned >= limit) + limit = max(1U, limit >> 1); + } + + trace_mm_compaction_fast_isolate_freepages(min_pfn, cc->free_pfn, + nr_scanned, total_isolated); + + 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 >= min_pfn) { + 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); + if (page && !suitable_migration_target(cc, page)) + page = NULL; + + 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; + + low_pfn = page_to_pfn(page); + fast_isolate_around(cc, low_pfn); +} + +/* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. */ @@ -1072,7 +1682,12 @@ static void isolate_freepages(struct compact_control *cc) unsigned long isolate_start_pfn; /* exact pfn we start at */ 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 */ + fast_isolate_freepages(cc); + if (cc->nr_freepages) + return; /* * Initialise the free scanner. The starting point is where we last @@ -1081,15 +1696,16 @@ static void isolate_freepages(struct compact_control *cc) * 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 @@ -1100,19 +1716,26 @@ static void isolate_freepages(struct compact_control *cc) 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 % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) + cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone); - if (!page) + if (!page) { + unsigned long next_pfn; + + next_pfn = skip_offline_sections_reverse(block_start_pfn); + if (next_pfn) + block_start_pfn = max(next_pfn, low_pfn); + continue; + } /* Check the block is suitable for migration */ if (!suitable_migration_target(cc, page)) @@ -1123,15 +1746,16 @@ static void isolate_freepages(struct compact_control *cc) 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, cc->freepages, 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 - + pageblock_nr_pages); + + /* 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 +1772,14 @@ static void isolate_freepages(struct compact_control *cc) */ 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 @@ -1166,29 +1794,57 @@ static void isolate_freepages(struct compact_control *cc) * This is a migrate-callback that "allocates" freepages by taking pages * from the isolated freelists in the block we are migrating to. */ -static struct page *compaction_alloc(struct page *migratepage, - unsigned long data) +static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; + struct folio *dst; + int order = folio_order(src); + bool has_isolated_pages = false; + int start_order; struct page *freepage; + unsigned long size; - /* - * 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); +again: + for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++) + if (!list_empty(&cc->freepages[start_order])) + break; - if (list_empty(&cc->freepages)) + /* no free pages in the list */ + if (start_order == NR_PAGE_ORDERS) { + if (has_isolated_pages) return NULL; + isolate_freepages(cc); + has_isolated_pages = true; + goto again; } - freepage = list_entry(cc->freepages.next, struct page, lru); + freepage = list_first_entry(&cc->freepages[start_order], struct page, + lru); + size = 1 << start_order; + list_del(&freepage->lru); - cc->nr_freepages--; - return freepage; + while (start_order > order) { + start_order--; + size >>= 1; + + list_add(&freepage[size].lru, &cc->freepages[start_order]); + set_page_private(&freepage[size], start_order); + } + dst = (struct folio *)freepage; + + post_alloc_hook(&dst->page, order, __GFP_MOVABLE); + set_page_refcounted(&dst->page); + if (order) + prep_compound_page(&dst->page, order); + cc->nr_freepages -= 1 << order; + cc->nr_migratepages -= 1 << order; + return page_rmappable_folio(&dst->page); +} + +static struct folio *compaction_alloc(struct folio *src, unsigned long data) +{ + return alloc_hooks(compaction_alloc_noprof(src, data)); } /* @@ -1196,12 +1852,22 @@ static struct page *compaction_alloc(struct page *migratepage, * freelist. All pages on the freelist are from the same zone, so there is no * special handling needed for NUMA. */ -static void compaction_free(struct page *page, unsigned long data) +static void compaction_free(struct folio *dst, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; + int order = folio_order(dst); + struct page *page = &dst->page; - list_add(&page->lru, &cc->freepages); - cc->nr_freepages++; + if (folio_put_testzero(dst)) { + free_pages_prepare(page, order); + list_add(&dst->lru, &cc->freepages[order]); + cc->nr_freepages += 1 << order; + } + cc->nr_migratepages += 1 << order; + /* + * someone else has referenced the page, we cannot take it back to our + * free list. + */ } /* possible outcome of isolate_migratepages */ @@ -1215,15 +1881,168 @@ typedef enum { * Allow userspace to control policy on scanning the unevictable LRU for * compactable pages. */ -int sysctl_compact_unevictable_allowed __read_mostly = 1; +static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; +/* + * Tunable for proactive compaction. It determines how + * aggressively the kernel should compact memory in the + * background. It takes values in the range [0, 100]. + */ +static unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +static int sysctl_extfrag_threshold = 500; +static int __read_mostly sysctl_compact_memory; + +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 pageblock should be finished then do not select a different + * pageblock. + */ + if (cc->finish_pageblock) + 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, buddy_list) { + 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; + 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 +2051,24 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, 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() has already ensured the pageblock is not + * set with a skipped flag, so to avoid the isolation_suitable check + * below again, 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); @@ -1250,41 +2078,58 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, * Do not cross the free scanner. */ for (; block_end_pfn <= cc->free_pfn; - low_pfn = block_end_pfn, + fast_find_block = false, + cc->migrate_pfn = low_pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* * 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 % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) + cond_resched(); - page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, - zone); - if (!page) + page = pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone); + if (!page) { + unsigned long next_pfn; + + next_pfn = skip_offline_sections(block_start_pfn); + if (next_pfn) + block_end_pfn = min(next_pfn, cc->free_pfn); 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 ((pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn) && + !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 direct compaction, only scan the pageblocks of the + * same migratetype without huge pages. Async direct 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 (isolate_migratepages_block(cc, low_pfn, block_end_pfn, + isolate_mode)) return ISOLATE_ABORT; /* @@ -1295,34 +2140,107 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, break; } - /* Record where migration scanner will be restarted. */ - cc->migrate_pfn = low_pfn; - return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } /* - * order == -1 is expected when compacting via - * /proc/sys/vm/compact_memory + * Determine whether kswapd is (or recently was!) running on this node. + * + * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't + * zero it. */ -static inline bool is_via_compact_memory(int order) +static bool kswapd_is_running(pg_data_t *pgdat) { - return order == -1; + bool running; + + pgdat_kswapd_lock(pgdat); + running = pgdat->kswapd && task_is_running(pgdat->kswapd); + pgdat_kswapd_unlock(pgdat); + + return running; } -static enum compact_result __compact_finished(struct zone *zone, - struct compact_control *cc) +/* + * 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]; + if (!populated_zone(zone)) + continue; + score += fragmentation_score_zone_weighted(zone); + } + + return score; +} + +static unsigned int fragmentation_score_wmark(bool low) +{ + unsigned int wmark_low, leeway; + + wmark_low = 100U - sysctl_compaction_proactiveness; + leeway = min(10U, wmark_low / 2); + return low ? wmark_low : min(wmark_low + leeway, 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(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; /* 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 +2249,7 @@ static enum compact_result __compact_finished(struct zone *zone, * 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; @@ -1339,140 +2257,141 @@ static enum compact_result __compact_finished(struct zone *zone, 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(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 (!pageblock_aligned(cc->migrate_pfn)) + return COMPACT_CONTINUE; + + /* + * When defrag_mode is enabled, make kcompactd target + * watermarks in whole pageblocks. Because they can be stolen + * without polluting, no further fallback checks are needed. + */ + if (defrag_mode && !cc->direct_compaction) { + if (__zone_watermark_ok(cc->zone, cc->order, + high_wmark_pages(cc->zone), + cc->highest_zoneidx, cc->alloc_flags, + zone_page_state(cc->zone, + NR_FREE_PAGES_BLOCKS))) + return COMPACT_SUCCESS; + + return COMPACT_CONTINUE; } /* Direct compactor: Is a suitable page free? */ - for (order = cc->order; order < MAX_ORDER; order++) { - struct free_area *area = &zone->free_area[order]; - bool can_steal; + ret = COMPACT_NO_SUITABLE_PAGE; + for (order = cc->order; order < NR_PAGE_ORDERS; order++) { + struct free_area *area = &cc->zone->free_area[order]; /* 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 /* * Job done if allocation would steal freepages from * other migratetype buddy lists. */ - if (find_suitable_fallback(area, order, migratetype, - true, &can_steal) != -1) { - - /* movable pages are OK in any pageblock */ - if (migratetype == MIGRATE_MOVABLE) - return COMPACT_SUCCESS; - + if (find_suitable_fallback(area, order, migratetype, true) >= 0) /* - * We are stealing for a non-movable allocation. Make - * sure we finish compacting the current pageblock - * first so it is as free as possible and we won't - * have to steal another one soon. This only applies - * to sync compaction, as async compaction operates - * on pageblocks of the same migratetype. + * Movable pages are OK in any pageblock. If we are + * stealing for a non-movable allocation, make sure + * we finish compacting the current pageblock first + * (which is assured by the above migrate_pfn align + * check) so it is as free as possible and we won't + * have to steal another one soon. */ - if (cc->mode == MIGRATE_ASYNC || - IS_ALIGNED(cc->migrate_pfn, - pageblock_nr_pages)) { - return COMPACT_SUCCESS; - } - - cc->finishing_block = true; - return COMPACT_CONTINUE; - } + return COMPACT_SUCCESS; } - return COMPACT_NO_SUITABLE_PAGE; +out: + if (cc->contended || fatal_signal_pending(current)) + 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; return ret; } -/* - * compaction_suitable: Is this suitable to run compaction on this zone now? - * Returns - * COMPACT_SKIPPED - If there are too few free pages for compaction - * COMPACT_SUCCESS - If the allocation would succeed without compaction - * COMPACT_CONTINUE - If compaction should run now - */ -static enum compact_result __compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, - int classzone_idx, - unsigned long wmark_target) +static bool __compaction_suitable(struct zone *zone, int order, + unsigned long watermark, int highest_zoneidx, + unsigned long free_pages) { - unsigned long watermark; - - if (is_via_compact_memory(order)) - return COMPACT_CONTINUE; - - 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, - alloc_flags)) - return COMPACT_SUCCESS; - /* * Watermarks for order-0 must be met for compaction to be able to * isolate free pages for migration targets. This means that the - * 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. - * For costly orders, we require low watermark instead of min for - * compaction to proceed to increase its chances. + * watermark have to match, or be more pessimistic than the check in + * __isolate_free_page(). + * + * For costly orders, we require a higher watermark for compaction to + * proceed to increase its chances. + * + * We use the direct compactor's highest_zoneidx to skip over zones + * where lowmem reserves would prevent allocation even if compaction + * succeeds. + * * ALLOC_CMA is used, as pages in CMA pageblocks are considered - * suitable migration targets + * suitable migration targets. */ - 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, - ALLOC_CMA, wmark_target)) - return COMPACT_SKIPPED; - - return COMPACT_CONTINUE; + if (order > PAGE_ALLOC_COSTLY_ORDER) + watermark += low_wmark_pages(zone) - min_wmark_pages(zone); + return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, + ALLOC_CMA, free_pages); } -enum compact_result compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, - int classzone_idx) +/* + * compaction_suitable: Is this suitable to run compaction on this zone now? + */ +bool compaction_suitable(struct zone *zone, int order, unsigned long watermark, + int highest_zoneidx) { - enum compact_result ret; - int fragindex; + enum compact_result compact_result; + bool suitable; - ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx, - zone_page_state(zone, NR_FREE_PAGES)); + suitable = __compaction_suitable(zone, order, watermark, highest_zoneidx, + zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation @@ -1489,19 +2408,27 @@ enum compact_result compaction_suitable(struct zone *zone, int order, * excessive compaction for costly orders, but it should not be at the * expense of system stability. */ - if (ret == COMPACT_CONTINUE && (order > PAGE_ALLOC_COSTLY_ORDER)) { - fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - ret = COMPACT_NOT_SUITABLE_ZONE; + if (suitable) { + compact_result = COMPACT_CONTINUE; + if (order > PAGE_ALLOC_COSTLY_ORDER) { + int fragindex = fragmentation_index(zone, order); + + if (fragindex >= 0 && + fragindex <= sysctl_extfrag_threshold) { + suitable = false; + compact_result = COMPACT_NOT_SUITABLE_ZONE; + } + } + } else { + compact_result = COMPACT_SKIPPED; } - trace_mm_compaction_suitable(zone, order, ret); - if (ret == COMPACT_NOT_SUITABLE_ZONE) - ret = COMPACT_SKIPPED; + trace_mm_compaction_suitable(zone, order, compact_result); - return ret; + return suitable; } +/* Used by direct reclaimers */ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags) { @@ -1512,10 +2439,9 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, * 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; /* * Do not consider all the reclaimable memory because we do not @@ -1525,38 +2451,104 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, */ 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); - if (compact_result != COMPACT_SKIPPED) + if (__compaction_suitable(zone, order, min_wmark_pages(zone), + ac->highest_zoneidx, available)) return true; } return false; } -static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc) +/* + * Should we do compaction for target allocation order. + * Return COMPACT_SUCCESS if allocation for target order can be already + * satisfied + * Return COMPACT_SKIPPED if compaction for target order is likely to fail + * Return COMPACT_CONTINUE if compaction for target order should be ran + */ +static enum compact_result +compaction_suit_allocation_order(struct zone *zone, unsigned int order, + int highest_zoneidx, unsigned int alloc_flags, + bool async, bool kcompactd) +{ + unsigned long free_pages; + unsigned long watermark; + + if (kcompactd && defrag_mode) + free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS); + else + free_pages = zone_page_state(zone, NR_FREE_PAGES); + + watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + if (__zone_watermark_ok(zone, order, watermark, highest_zoneidx, + alloc_flags, free_pages)) + return COMPACT_SUCCESS; + + /* + * For unmovable allocations (without ALLOC_CMA), check if there is enough + * free memory in the non-CMA pageblocks. Otherwise compaction could form + * the high-order page in CMA pageblocks, which would not help the + * allocation to succeed. However, limit the check to costly order async + * compaction (such as opportunistic THP attempts) because there is the + * possibility that compaction would migrate pages from non-CMA to CMA + * pageblock. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && async && + !(alloc_flags & ALLOC_CMA)) { + if (!__zone_watermark_ok(zone, 0, watermark + compact_gap(order), + highest_zoneidx, 0, + zone_page_state(zone, NR_FREE_PAGES))) + return COMPACT_SKIPPED; + } + + if (!compaction_suitable(zone, order, watermark, highest_zoneidx)) + return COMPACT_SKIPPED; + + return COMPACT_CONTINUE; +} + +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; + unsigned int nr_succeeded = 0, nr_migratepages; + int order; - cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask); - ret = compaction_suitable(zone, cc->order, cc->alloc_flags, - cc->classzone_idx); - /* Compaction is likely to fail */ - if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED) - return ret; - - /* huh, compaction_suitable is returning something unexpected */ - VM_BUG_ON(ret != COMPACT_CONTINUE); + /* + * These counters track activities during zone compaction. Initialize + * them before compacting a new zone. + */ + cc->total_migrate_scanned = 0; + cc->total_free_scanned = 0; + cc->nr_migratepages = 0; + cc->nr_freepages = 0; + for (order = 0; order < NR_PAGE_ORDERS; order++) + INIT_LIST_HEAD(&cc->freepages[order]); + INIT_LIST_HEAD(&cc->migratepages); + + cc->migratetype = gfp_migratetype(cc->gfp_mask); + + if (!is_via_compact_memory(cc->order)) { + ret = compaction_suit_allocation_order(cc->zone, cc->order, + cc->highest_zoneidx, + cc->alloc_flags, + cc->mode == MIGRATE_ASYNC, + !cc->direct_compaction); + if (ret != COMPACT_CONTINUE) + return ret; + } /* * 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 @@ -1564,43 +2556,76 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro * 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); + trace_mm_compaction_begin(cc, start_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 iteration_start_pfn = cc->migrate_pfn; - switch (isolate_migratepages(zone, cc)) { + /* + * Avoid multiple rescans of the same pageblock 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->finish_pageblock = false; + if (pageblock_start_pfn(last_migrated_pfn) == + pageblock_start_pfn(iteration_start_pfn)) { + cc->finish_pageblock = true; + } + +rescan: + 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 @@ -1608,15 +2633,22 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro */ goto check_drain; case ISOLATE_SUCCESS: - ; + update_cached = false; + last_migrated_pfn = max(cc->zone->zone_start_pfn, + pageblock_start_pfn(cc->migrate_pfn - 1)); } + /* + * Record the number of pages to migrate since the + * compaction_alloc/free() will update cc->nr_migratepages + * properly. + */ + nr_migratepages = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, compaction_free, (unsigned long)cc, cc->mode, - MR_COMPACTION); + MR_COMPACTION, &nr_succeeded); - trace_mm_compaction_migratepages(cc->nr_migratepages, err, - &cc->migratepages); + trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded); /* All pages were either migrated or will be released */ cc->nr_migratepages = 0; @@ -1631,19 +2663,39 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro goto out; } /* - * We failed to migrate at least one page in the current - * order-aligned block, so skip the rest of it. + * If an ASYNC or SYNC_LIGHT fails to migrate a page + * within the pageblock_order-aligned block and + * fast_find_migrateblock may be used then scan the + * remainder of the pageblock. This will mark the + * pageblock "skip" to avoid rescanning in the near + * future. This will isolate more pages than necessary + * for the request but avoid loops due to + * fast_find_migrateblock revisiting blocks that were + * recently partially scanned. */ - if (cc->direct_compaction && - (cc->mode == MIGRATE_ASYNC)) { - cc->migrate_pfn = block_end_pfn( - cc->migrate_pfn - 1, cc->order); - /* Draining pcplists is useless in this case */ - cc->last_migrated_pfn = 0; + if (!pageblock_aligned(cc->migrate_pfn) && + !cc->ignore_skip_hint && !cc->finish_pageblock && + (cc->mode < MIGRATE_SYNC)) { + cc->finish_pageblock = true; + /* + * Draining pcplists does not help THP if + * any page failed to migrate. Even after + * drain, the pageblock will not be free. + */ + if (cc->order == COMPACTION_HPAGE_ORDER) + last_migrated_pfn = 0; + + goto rescan; } } + /* Stop if a page has been captured */ + if (capc && capc->page) { + ret = COMPACT_SUCCESS; + break; + } + check_drain: /* * Has the migration scanner moved away from the previous @@ -1652,21 +2704,16 @@ check_drain: * 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; } } - } out: @@ -1675,7 +2722,7 @@ out: * so we don't leave any returned pages behind in the next attempt. */ if (cc->nr_freepages > 0) { - unsigned long free_pfn = release_freepages(&cc->freepages); + unsigned long free_pfn = release_free_list(cc->freepages); cc->nr_freepages = 0; VM_BUG_ON(free_pfn == 0); @@ -1685,54 +2732,74 @@ out: * 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); count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned); - trace_mm_compaction_end(start_pfn, cc->migrate_pfn, - cc->free_pfn, end_pfn, sync, ret); + trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret); + + VM_BUG_ON(!list_empty(&cc->migratepages)); return ret; } 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 = { - .nr_freepages = 0, - .nr_migratepages = 0, - .total_migrate_scanned = 0, - .total_free_scanned = 0, .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) }; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); + struct capture_control capc = { + .cc = &cc, + .page = NULL, + }; + + /* + * 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(zone, &cc); + 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); + /* + * Technically, it is also possible that compaction is skipped but + * the page is still captured out of luck(IRQ came and freed the page). + * Returning COMPACT_SUCCESS in such cases helps in properly accounting + * the COMPACT[STALL|FAIL] when compaction is skipped. + */ + if (*capture) + ret = COMPACT_SUCCESS; return ret; } -int sysctl_extfrag_threshold = 500; - /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation @@ -1740,32 +2807,33 @@ int sysctl_extfrag_threshold = 500; * @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; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; - /* - * Check if the GFP flags allow compaction - GFP_NOIO is really - * tricky context because the migration might require IO - */ - if (!may_perform_io) + if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; 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 (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp_mask)) + continue; + if (prio > MIN_COMPACT_PRIORITY && compaction_deferred(zone, order)) { rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); @@ -1773,7 +2841,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, } 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 */ @@ -1811,83 +2879,122 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, return rc; } - -/* Compact all zones within a node */ -static void compact_node(int nid) +/* + * compact_node() - compact all zones within a node + * @pgdat: The node page data + * @proactive: Whether the compaction is proactive + * + * For proactive compaction, compact 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 int compact_node(pg_data_t *pgdat, bool proactive) { - pg_data_t *pgdat = NODE_DATA(nid); int zoneid; struct zone *zone; struct compact_control cc = { .order = -1, - .total_migrate_scanned = 0, - .total_free_scanned = 0, - .mode = MIGRATE_SYNC, + .mode = proactive ? MIGRATE_SYNC_LIGHT : MIGRATE_SYNC, .ignore_skip_hint = true, .whole_zone = true, .gfp_mask = GFP_KERNEL, + .proactive_compaction = proactive, }; - for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { - zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; - cc.nr_freepages = 0; - cc.nr_migratepages = 0; + if (fatal_signal_pending(current)) + return -EINTR; + cc.zone = zone; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); - compact_zone(zone, &cc); + compact_zone(&cc, NULL); - VM_BUG_ON(!list_empty(&cc.freepages)); - VM_BUG_ON(!list_empty(&cc.migratepages)); + if (proactive) { + count_compact_events(KCOMPACTD_MIGRATE_SCANNED, + cc.total_migrate_scanned); + count_compact_events(KCOMPACTD_FREE_SCANNED, + cc.total_free_scanned); + } } + + return 0; } -/* Compact all nodes in the system */ -static void compact_nodes(void) +/* Compact all zones of all nodes in the system */ +static int compact_nodes(void) { - int nid; + int ret, nid; /* Flush pending updates to the LRU lists */ lru_add_drain_all(); - for_each_online_node(nid) - compact_node(nid); + for_each_online_node(nid) { + ret = compact_node(NODE_DATA(nid), false); + if (ret) + return ret; + } + + return 0; } -/* The written value is actually unused, all memory is compacted */ -int sysctl_compact_memory; +static int compaction_proactiveness_sysctl_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + 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; + trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, -1, + pgdat->nr_zones - 1); + wake_up_interruptible(&pgdat->kcompactd_wait); + } + } + + return 0; +} /* * 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 __user *buffer, size_t *length, loff_t *ppos) +static int sysctl_compaction_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) { - if (write) - compact_nodes(); + int ret; - return 0; -} + ret = proc_dointvec(table, write, buffer, length, ppos); + if (ret) + return ret; -int sysctl_extfrag_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - proc_dointvec_minmax(table, write, buffer, length, ppos); + if (sysctl_compact_memory != 1) + return -EINVAL; - return 0; + if (write) + ret = compact_nodes(); + + return ret; } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -static ssize_t sysfs_compact_node(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t compact_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { int nid = dev->id; @@ -1895,12 +3002,12 @@ static ssize_t sysfs_compact_node(struct device *dev, /* Flush pending updates to the LRU lists */ lru_add_drain_all(); - compact_node(nid); + compact_node(NODE_DATA(nid), false); } return count; } -static DEVICE_ATTR(compact, 0200, NULL, sysfs_compact_node); +static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { @@ -1909,29 +3016,36 @@ int compaction_register_node(struct node *node) void compaction_unregister_node(struct node *node) { - return device_remove_file(&node->dev, &dev_attr_compact); + device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ 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; + enum compact_result ret; + unsigned int alloc_flags = defrag_mode ? + ALLOC_WMARK_HIGH : ALLOC_WMARK_MIN; - 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) + ret = compaction_suit_allocation_order(zone, + pgdat->kcompactd_max_order, + highest_zoneidx, alloc_flags, + false, true); + if (ret == COMPACT_CONTINUE) return true; } @@ -1948,18 +3062,20 @@ static void kcompactd_do_work(pg_data_t *pgdat) struct zone *zone; struct compact_control cc = { .order = pgdat->kcompactd_max_order, - .total_migrate_scanned = 0, - .total_free_scanned = 0, - .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, + .alloc_flags = defrag_mode ? ALLOC_WMARK_HIGH : ALLOC_WMARK_MIN, }; + enum compact_result ret; + 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]; @@ -1969,21 +3085,17 @@ static void kcompactd_do_work(pg_data_t *pgdat) if (compaction_deferred(zone, cc.order)) continue; - if (compaction_suitable(zone, cc.order, 0, zoneid) != - COMPACT_CONTINUE) + ret = compaction_suit_allocation_order(zone, + cc.order, zoneid, cc.alloc_flags, + false, true); + if (ret != COMPACT_CONTINUE) continue; - cc.nr_freepages = 0; - cc.nr_migratepages = 0; - cc.total_migrate_scanned = 0; - cc.total_free_scanned = 0; - cc.zone = zone; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); - if (kthread_should_stop()) return; - status = compact_zone(zone, &cc); + + cc.zone = zone; + status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); @@ -2007,23 +3119,20 @@ static void kcompactd_do_work(pg_data_t *pgdat) cc.total_migrate_scanned); count_compact_events(KCOMPACTD_FREE_SCANNED, cc.total_free_scanned); - - VM_BUG_ON(!list_empty(&cc.freepages)); - VM_BUG_ON(!list_empty(&cc.migratepages)); } /* * 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; @@ -2031,8 +3140,8 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) 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() @@ -2045,7 +3154,7 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) return; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order, - classzone_idx); + highest_zoneidx); wake_up_interruptible(&pgdat->kcompactd_wait); } @@ -2055,31 +3164,69 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) */ static int kcompactd(void *p) { - 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); + pg_data_t *pgdat = (pg_data_t *)p; + long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); + long timeout = default_timeout; + current->flags |= PF_KCOMPACTD; 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; + /* + * Avoid the unnecessary wakeup for proactive compaction + * when it is disabled. + */ + if (!sysctl_compaction_proactiveness) + timeout = 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); + /* + * Reset the timeout value. The defer timeout from + * proactive compaction is lost here but that is fine + * as the condition of the zone changing substantionally + * then carrying on with the previous defer interval is + * not useful. + */ + timeout = default_timeout; + continue; + } - psi_memstall_enter(&pflags); - kcompactd_do_work(pgdat); - psi_memstall_leave(&pflags); + /* + * Start the proactive work with default timeout. Based + * on the fragmentation score, this timeout is updated. + */ + timeout = default_timeout; + if (should_proactive_compact_node(pgdat)) { + unsigned int prev_score, score; + + prev_score = fragmentation_score_node(pgdat); + compact_node(pgdat, true); + score = fragmentation_score_node(pgdat); + /* + * Defer proactive compaction if the fragmentation + * score did not go down i.e. no progress made. + */ + if (unlikely(score >= prev_score)) + timeout = + default_timeout << COMPACT_MAX_DEFER_SHIFT; + } + if (unlikely(pgdat->proactive_compact_trigger)) + pgdat->proactive_compact_trigger = false; } + current->flags &= ~PF_KCOMPACTD; + return 0; } @@ -2087,28 +3234,27 @@ static int kcompactd(void *p) * This kcompactd start function will be called by init and node-hot-add. * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added. */ -int kcompactd_run(int nid) +void __meminit kcompactd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - int ret = 0; if (pgdat->kcompactd) - return 0; + return; - pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid); + pgdat->kcompactd = kthread_create_on_node(kcompactd, pgdat, nid, "kcompactd%d", nid); if (IS_ERR(pgdat->kcompactd)) { pr_err("Failed to start kcompactd on node %d\n", nid); - ret = PTR_ERR(pgdat->kcompactd); pgdat->kcompactd = NULL; + } else { + wake_up_process(pgdat->kcompactd); } - return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold mem_hotplug_begin/end(). + * be holding mem_hotplug_begin/done(). */ -void kcompactd_stop(int nid) +void __meminit kcompactd_stop(int nid) { struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd; @@ -2118,44 +3264,69 @@ void kcompactd_stop(int nid) } } -/* - * It's optimal to keep kcompactd on the same CPUs as their memory, but - * not required for correctness. So if the last cpu in a node goes - * away, we get changed to run anywhere: as the first one comes back, - * restore their cpu bindings. - */ -static int kcompactd_cpu_online(unsigned int cpu) +static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, + int write, void *buffer, size_t *lenp, loff_t *ppos) { - int nid; - - for_each_node_state(nid, N_MEMORY) { - pg_data_t *pgdat = NODE_DATA(nid); - const struct cpumask *mask; + int ret, old; - mask = cpumask_of_node(pgdat->node_id); + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) - /* One of our CPUs online: restore mask */ - set_cpus_allowed_ptr(pgdat->kcompactd, mask); - } - return 0; + old = *(int *)table->data; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret) + return ret; + if (old != *(int *)table->data) + pr_warn_once("sysctl attribute %s changed by %s[%d]\n", + table->procname, current->comm, + task_pid_nr(current)); + return ret; } +static const struct ctl_table vm_compaction[] = { + { + .procname = "compact_memory", + .data = &sysctl_compact_memory, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, + { + .procname = "compaction_proactiveness", + .data = &sysctl_compaction_proactiveness, + .maxlen = sizeof(sysctl_compaction_proactiveness), + .mode = 0644, + .proc_handler = compaction_proactiveness_sysctl_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, + }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_THOUSAND, + }, + { + .procname = "compact_unevictable_allowed", + .data = &sysctl_compact_unevictable_allowed, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_warn_RT_change, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +}; + static int __init kcompactd_init(void) { int nid; - int ret; - - ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "mm/compaction:online", - kcompactd_cpu_online, NULL); - if (ret < 0) { - pr_err("kcompactd: failed to register hotplug callbacks.\n"); - return ret; - } for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); + register_sysctl_init("vm", vm_compaction); return 0; } subsys_initcall(kcompactd_init) |