#ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; EXPORT_PER_CPU_SYMBOL(vm_event_states); static void sum_vm_events(unsigned long *ret) { int cpu; int i; memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); for_each_online_cpu(cpu) { struct vm_event_state *this = &per_cpu(vm_event_states, cpu); for (i = 0; i < NR_VM_EVENT_ITEMS; i++) ret[i] += this->event[i]; } } /* * Accumulate the vm event counters across all CPUs. * The result is unavoidably approximate - it can change * during and after execution of this function. */ void all_vm_events(unsigned long *ret) { cpus_read_lock(); sum_vm_events(ret); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(all_vm_events); /* * Fold the foreign cpu events into our own. * * This is adding to the events on one processor * but keeps the global counts constant. */ void vm_events_fold_cpu(int cpu) { struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu); int i; for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { count_vm_events(i, fold_state->event[i]); fold_state->event[i] = 0; } } #endif /* CONFIG_VM_EVENT_COUNTERS */

#ifdef CONFIG_NUMA int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; /* zero numa counters within a zone */ static void zero_zone_numa_counters(struct zone *zone) { int item, cpu; for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) { atomic_long_set(&zone->vm_numa_event[item], 0); for_each_online_cpu(cpu) { per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item] = 0; } } } /* zero numa counters of all the populated zones */ static void zero_zones_numa_counters(void) { struct zone *zone; for_each_populated_zone(zone) zero_zone_numa_counters(zone); } /* zero global numa counters */ static void zero_global_numa_counters(void) { int item; for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) atomic_long_set(&vm_numa_event[item], 0); } static void invalid_numa_statistics(void) { zero_zones_numa_counters(); zero_global_numa_counters(); } static DEFINE_MUTEX(vm_numa_stat_lock); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret, oldval; mutex_lock(&vm_numa_stat_lock); if (write) oldval = sysctl_vm_numa_stat; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (ret || !write) goto out; if (oldval == sysctl_vm_numa_stat) goto out; else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) { static_branch_enable(&vm_numa_stat_key); pr_info("enable numa statistics\n"); } else { static_branch_disable(&vm_numa_stat_key); invalid_numa_statistics(); pr_info("disable numa statistics, and clear numa counters\n"); } out: mutex_unlock(&vm_numa_stat_lock); return ret; } #endif

if (should_proactive_compact_node(pgdat)) { unsigned int prev_score, score; prev_score = fragmentation_score_node(pgdat); proactive_compact_node(pgdat); score = fragmentation_score_node(pgdat); /* * Defer proactive compaction if the fragmentation * score did not go down i.e. no progress made. */ if (unlikely(score >= prev_score)) timeout = default_timeout << COMPACT_MAX_DEFER_SHIFT; }

#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) static ssize_t compact_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int nid = dev->id; if (nid >= 0 && nid < nr_node_ids && node_online(nid)) { /* Flush pending updates to the LRU lists */ lru_add_drain_all(); compact_node(nid); } return count; } static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { return device_create_file(&node->dev, &dev_attr_compact); } void compaction_unregister_node(struct node *node) { device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */

if (prio > MIN_COMPACT_PRIORITY && compaction_deferred(zone, order)) { rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); continue; } status = compact_zone_order(zone, order, gfp_mask, prio, alloc_flags, ac->highest_zoneidx, capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ if (status == COMPACT_SUCCESS) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller * will repeat this with true if allocation indeed * succeeds in this zone. */ compaction_defer_reset(zone, order, false); break; } if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE || status == COMPACT_PARTIAL_SKIPPED)) /* * We think that allocation won't succeed in this zone * so we defer compaction there. If it ends up * succeeding after all, it will be reset. */ defer_compaction(zone, order); /* * We might have stopped compacting due to need_resched() in * async compaction, or due to a fatal signal detected. In that * case do not try further zones */ if ((prio == COMPACT_PRIO_ASYNC && need_resched()) || fatal_signal_pending(current)) break;

if (cc->nr_freepages > 0) { unsigned long free_pfn = release_freepages(&cc->freepages); cc->nr_freepages = 0; VM_BUG_ON(free_pfn == 0); /* The cached pfn is always the first in a pageblock */ free_pfn = pageblock_start_pfn(free_pfn); /* * Only go back, not forward. The cached pfn might have been * already reset to zone end in compact_finished() */ if (free_pfn > cc->zone->compact_cached_free_pfn) cc->zone->compact_cached_free_pfn = free_pfn; }

if (err) { putback_movable_pages(&cc->migratepages); /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it */ if (err == -ENOMEM && !compact_scanners_met(cc)) { ret = COMPACT_CONTENDED; goto out; } /* * 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 (!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; } }

#ifdef CONFIG_CMA /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ if (migratetype == MIGRATE_MOVABLE && !free_area_empty(area, MIGRATE_CMA)) return COMPACT_SUCCESS; #endif

/* * compaction_suitable: Is this suitable to run compaction on this zone now? */ bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx) { enum compact_result compact_result; bool suitable; suitable = __compaction_suitable(zone, order, highest_zoneidx, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation * * index of -1000 would imply allocations might succeed depending on * watermarks, but we already failed the high-order watermark check * index towards 0 implies failure is due to lack of memory * index towards 1000 implies failure is due to fragmentation * * Only compact if a failure would be due to fragmentation. Also * ignore fragindex for non-costly orders where the alternative to * a successful reclaim/compaction is OOM. Fragindex and the * vm.extfrag_threshold sysctl is meant as a heuristic to prevent * excessive compaction for costly orders, but it should not be at the * expense of system stability. */ 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, compact_result); return suitable; }

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; }

#ifdef CONFIG_SPARSEMEM

#ifdef CONFIG_COMPACTION