matching the ownership tracking * granularities between memcg and writeback in either direction

if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)) return ep; if (parent_effective > siblings_protected && parent_usage > siblings_protected && usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; unclaimed *= usage - protected; unclaimed /= parent_usage - siblings_protected; ep += unclaimed; } return ep;

if (total >= (excess >> 2) || (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) break;

/* * Don't sleep if the amount of jiffies this memcg owes us is so low * that it's not even worth doing, in an attempt to be nice to those who * go only a small amount over their memory.high value and maybe haven't * been aggressively reclaimed enough yet. */ if (penalty_jiffies <= HZ / 100) goto out;

static inline bool should_continue_reclaim(struct pglist_data *pgdat,

/* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; }

*/ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again;

static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; }

nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan = nr >> priority; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) {

if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; }

if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; }

static void pcpu_balance_workfn(struct work_struct *work)

if (freed_page_start < freed_page_end) {

int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)

if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; }

static void pcpu_balance_populated(void)

if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)

if (!pcpu_check_block_hint(chunk_md, alloc_bits, align))

static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits)

if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; }

if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : "Memory cgroup out of memory");

/* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + mm_pgtables_bytes(p->mm) / PAGE_SIZE; task_unlock(p); /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; points += adj;

if (start != vma->vm_start) { error = split_vma(&vmi, vma, start, 1); if (error) return error; } if (end != vma->vm_end) { error = split_vma(&vmi, vma, end, 0); if (error) return error; }

if (behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); }

if (folio_test_large(folio)) { int err; if (folio_estimated_sharers(folio) != 1) break; if (!folio_trylock(folio)) break; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (err) break; start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; arch_enter_lazy_mmu_mode(); pte--; addr -= PAGE_SIZE; continue; }

if (!pte_present(ptent)) { swp_entry_t entry; entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { nr_swap--; free_swap_and_cache(entry); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; }

pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval);

if (pending != flushed) { arch_flush_tlb_batched_pending(mm);

if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma;

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 (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; } }

/* * 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; }

static bool kcompactd_node_suitable(pg_data_t *pgdat) { int zoneid; struct zone *zone; enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; /* Allocation can already succeed, check other zones */ if (zone_watermark_ok(zone, pgdat->kcompactd_max_order, min_wmark_pages(zone), highest_zoneidx, 0)) continue; if (compaction_suitable(zone, pgdat->kcompactd_max_order, highest_zoneidx)) return true; } return false; }

static int compaction_proactiveness_sysctl_handler(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; }

if (suitable) {

watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, ALLOC_CMA, wmark_target);

static enum compact_result __compact_finished(struct compact_control *cc) { unsigned int order; const int migratetype = cc->migratetype; 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(cc->zone); /* * Mark that the PG_migrate_skip information should be cleared * by kswapd when it goes to sleep. kcompactd does not set the * flag itself as the decision to be clear should be directly * based on an allocation request. */ if (cc->direct_compaction) cc->zone->compact_blockskip_flush = true; if (cc->whole_zone) return COMPACT_COMPLETE; else 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; /* * 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; /* Direct compactor: Is a suitable page free? */ ret = COMPACT_NO_SUITABLE_PAGE; for (order = cc->order; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &cc->zone->free_area[order]; bool can_steal; /* Job done if page is free of the right migratetype */ if (!free_area_empty(area, migratetype)) return COMPACT_SUCCESS;

#ifdef CONFIG_COMPACTION static bool suitable_migration_source(struct compact_control *cc, struct page *page) { int block_mt; if (pageblock_skip_persistent(page)) return false; if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) return true; block_mt = get_pageblock_migratetype(page); if (cc->migratetype == MIGRATE_MOVABLE) return is_migrate_movable(block_mt); else return block_mt == cc->migratetype; }

/* Similar to reclaim, but different enough that they don't share logic */ 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(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; }

/* * 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. */ static bool pageblock_skip_persistent(struct page *page) { if (!PageCompound(page)) return false; page = compound_head(page); if (compound_order(page) >= pageblock_order) return true; return false; }

/* Returns true if compaction should be skipped this time */ static bool compaction_deferred(struct zone *zone, int order) { unsigned long defer_limit = 1UL << zone->compact_defer_shift; if (order < zone->compact_order_failed) return false; /* Avoid possible overflow */ if (++zone->compact_considered >= defer_limit) { zone->compact_considered = defer_limit; return false; } trace_mm_compaction_deferred(zone, order); return true; }

batch = min(zone_managed_pages(zone) >> 10, SZ_1M / PAGE_SIZE); batch /= 4; /* We effectively *= 4 below */ if (batch < 1) batch = 1; /* * Clamp the batch to a 2^n - 1 value. Having a power * of 2 value was found to be more likely to have * suboptimal cache aliasing properties in some cases. * * For example if 2 tasks are alternately allocating * batches of pages, one task can end up with a lot * of pages of one half of the possible page colors * and the other with pages of the other colors. */ batch = rounddown_pow_of_two(batch + batch/2) - 1;

if (can_direct_reclaim && can_compact && (costly_order || (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) && !gfp_pfmemalloc_allowed(gfp_mask))

if (!order || order > PAGE_ALLOC_COSTLY_ORDER)

if (!node_isset(node, *used_node_mask)) { node_set(node, *used_node_mask); return node; } for_each_node_state(n, N_MEMORY) { /* Don't want a node to appear more than once */ if (node_isset(n, *used_node_mask)) continue; /* Use the distance array to find the distance */ val = node_distance(node, n); /* Penalize nodes under us ("prefer the next node") */ val += (n < node); /* Give preference to headless and unused nodes */ if (!cpumask_empty(cpumask_of_node(n))) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ val *= MAX_NUMNODES; val += node_load[n]; if (val < min_val) { min_val = val; best_node = n; } } if (best_node >= 0) node_set(best_node, *used_node_mask);

/* * !costly requests are much more important than * __GFP_RETRY_MAYFAIL costly ones because they are de * facto nofail and invoke OOM killer to move on while * costly can fail and users are ready to cope with * that. 1/4 retries is rather arbitrary but we would * need much more detailed feedback from compaction to * make a better decision. */ if (order > PAGE_ALLOC_COSTLY_ORDER) max_retries /= 4; if (++(*compaction_retries) <= max_retries) { ret = true; goto out; }

if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) *no_progress_loops = 0; else (*no_progress_loops)++;

/* * Do not steal pages from freelists belonging to other pageblocks * i.e. orders < pageblock_order. If there are no local zones free, * the zonelists will be reiterated without ALLOC_NOFRAGMENT. */ if (order < pageblock_order && alloc_flags & ALLOC_NOFRAGMENT) min_order = pageblock_order;

/* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); for (i = 0; i < numpages; i++) clear_highpage_kasan_tagged(page + i); kasan_enable_current();

/* * Check tail pages before head page information is cleared to * avoid checking PageCompound for order-0 pages. */ if (unlikely(order)) { bool compound = PageCompound(page); int i; VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); if (compound) page[1].flags &= ~PAGE_FLAGS_SECOND;

if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != pageblock_order); movable = migratetype == MIGRATE_MOVABLE; return NR_LOWORDER_PCP_LISTS + movable; }

/* * Temporary debugging check for pages not lying within a given zone. */ static int __maybe_unused bad_range(struct zone *zone, struct page *page) { if (page_outside_zone_boundaries(zone, page)) return 1; if (zone != page_zone(page)) return 1; return 0; }

if (likely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype);

static inline bool free_page_is_bad(struct page *page) { if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE))) return false; /* Something has gone sideways, find it */ free_page_is_bad_report(page); return true; }

if (unlikely(!order && (alloc_flags & ALLOC_MIN_RESERVE) && z->watermark_boost && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) { mark = z->_watermark[WMARK_MIN]; return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, free_pages); }

bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages) { long min = mark; int o; /* free_pages may go negative - that's OK */ free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags); if (unlikely(alloc_flags & ALLOC_RESERVES)) { /* * __GFP_HIGH allows access to 50% of the min reserve as well * as OOM. */ if (alloc_flags & ALLOC_MIN_RESERVE) { min -= min / 2; /* * Non-blocking allocations (e.g. GFP_ATOMIC) can * access more reserves than just __GFP_HIGH. Other * non-blocking allocations requests such as GFP_NOWAIT * or (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) do not get * access to the min reserve. */ if (alloc_flags & ALLOC_NON_BLOCK) min -= min / 4; } /* * OOM victims can try even harder than the normal reserve * users on the grounds that it's definitely going to be in * the exit path shortly and free memory. Any allocation it * makes during the free path will be small and short-lived. */ if (alloc_flags & ALLOC_OOM) min -= min / 2; } /* * Check watermarks for an order-0 allocation request. If these * are not met, then a high-order request also cannot go ahead * even if a suitable page happened to be free. */ if (free_pages <= min + z->lowmem_reserve[highest_zoneidx]) return false; /* If this is an order-0 request then the watermark is fine */ if (!order) return true; /* For a high-order request, check at least one suitable page is free */ for (o = order; o < NR_PAGE_ORDERS; o++) { struct free_area *area = &z->free_area[o]; int mt; if (!area->nr_free) continue; for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { if (!free_area_empty(area, mt)) return true; } #ifdef CONFIG_CMA if ((alloc_flags & ALLOC_CMA) && !free_area_empty(area, MIGRATE_CMA)) { return true; } #endif if ((alloc_flags & (ALLOC_HIGHATOMIC|ALLOC_OOM)) && !free_area_empty(area, MIGRATE_HIGHATOMIC)) { return true; } } return false; }

if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } else if (unlikely(!si->cluster_nr--)) {

/* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = get_random_u32_inclusive(1, p->highest_bit); }

else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster;

if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL);

/* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base;

/* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ }

node = numa_node_id();

plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);

static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause

if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb);

if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; }

t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));

int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags)

static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed)

static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written)

static void domain_dirty_limits(struct dirty_throttle_control *dtc)

void writeback_set_ratelimit(void)

bool wb_over_bg_thresh(struct bdi_writeback *wb)

static void wb_position_ratio(struct dirty_throttle_control *dtc)

/* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause;

/* * Some pages could be missed by concurrent allocation or free, * because we don't hold the zone lock. */ if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) goto ext_put_continue; /* * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) goto ext_put_continue; page_owner = get_page_owner(page_ext); /* * Don't print "tail" pages of high-order allocations as that * would inflate the stats. */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) goto ext_put_continue;

/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) pfn++;

static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc)

f (lru_gen_enabled()) return lru_gen_eviction(folio);

static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { int ret; bool found_slot = false; struct memory_tier *memtier, *new_memtier; int adistance = memtype->adistance; unsigned int memtier_adistance_chunk_size = MEMTIER_CHUNK_SIZE; lockdep_assert_held_once(&memory_tier_lock); adistance = round_down(adistance, memtier_adistance_chunk_size); /* * If the memtype is already part of a memory tier, * just return that. */ if (!list_empty(&memtype->tier_sibiling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; } WARN_ON(1); return ERR_PTR(-EINVAL); } list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) { goto link_memtype; } else if (adistance < memtier->adistance_start) { found_slot = true; break; } } new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL); if (!new_memtier) return ERR_PTR(-ENOMEM); new_memtier->adistance_start = adistance; INIT_LIST_HEAD(&new_memtier->list); INIT_LIST_HEAD(&new_memtier->memory_types); if (found_slot) list_add_tail(&new_memtier->list, &memtier->list); else list_add_tail(&new_memtier->list, &memory_tiers); new_memtier->dev.id = adistance >> MEMTIER_CHUNK_BITS; new_memtier->dev.bus = &memory_tier_subsys; new_memtier->dev.release = memory_tier_device_release; new_memtier->dev.groups = memtier_dev_groups; ret = device_register(&new_memtier->dev); if (ret) { list_del(&new_memtier->list); put_device(&new_memtier->dev); return ERR_PTR(ret); } memtier = new_memtier; link_memtype: list_add(&memtype->tier_sibiling, &memtier->memory_types); return memtier; }

static void establish_demotion_targets(void) { struct memory_tier *memtier; struct demotion_nodes *nd; int target = NUMA_NO_NODE, node; int distance, best_distance; nodemask_t tier_nodes, lower_tier; lockdep_assert_held_once(&memory_tier_lock); if (!node_demotion) return; disable_all_demotion_targets(); for_each_node_state(node, N_MEMORY) { best_distance = -1; nd = &node_demotion[node]; memtier = __node_get_memory_tier(node); if (!memtier || list_is_last(&memtier->list, &memory_tiers)) continue; /* * Get the lower memtier to find the demotion node list. */ memtier = list_next_entry(memtier, list); tier_nodes = get_memtier_nodemask(memtier); /* * find_next_best_node, use 'used' nodemask as a skip list. * Add all memory nodes except the selected memory tier * nodelist to skip list so that we find the best node from the * memtier nodelist. */ nodes_andnot(tier_nodes, node_states[N_MEMORY], tier_nodes); /* * Find all the nodes in the memory tier node list of same best distance. * add them to the preferred mask. We randomly select between nodes * in the preferred mask when allocating pages during demotion. */ do { target = find_next_best_node(node, &tier_nodes); if (target == NUMA_NO_NODE) break; distance = node_distance(node, target); if (distance == best_distance || best_distance == -1) { best_distance = distance; node_set(target, nd->preferred); } else { break; } } while (1); } /* * Promotion is allowed from a memory tier to higher * memory tier only if the memory tier doesn't include * compute. We want to skip promotion from a memory tier, * if any node that is part of the memory tier have CPUs. * Once we detect such a memory tier, we consider that tier * as top tiper from which promotion is not allowed. */ list_for_each_entry_reverse(memtier, &memory_tiers, list) { tier_nodes = get_memtier_nodemask(memtier); nodes_and(tier_nodes, node_states[N_CPU], tier_nodes); if (!nodes_empty(tier_nodes)) { /* * abstract distance below the max value of this memtier * is considered toptier. */ top_tier_adistance = memtier->adistance_start + MEMTIER_CHUNK_SIZE - 1; break; } } /* * Now build the lower_tier mask for each node collecting node mask from * all memory tier below it. This allows us to fallback demotion page * allocation to a set of nodes that is closer the above selected * perferred node. */ lower_tier = node_states[N_MEMORY]; list_for_each_entry(memtier, &memory_tiers, list) { /* * Keep removing current tier from lower_tier nodes, * This will remove all nodes in current and above * memory tier from the lower_tier mask. */ tier_nodes = get_memtier_nodemask(memtier); nodes_andnot(lower_tier, lower_tier, tier_nodes); memtier->lower_tier_mask = lower_tier; } }

static struct page *get_ksm_page(struct ksm_stable_node *stable_node, enum get_ksm_page_flags flags) { struct page *page; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ page = pfn_to_page(kpfn); if (READ_ONCE(page->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * the same is in reuse_ksm_page() case; but if page is swapcache * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ while (!get_page_unless_zero(page)) { /* * Another check for page->mapping != expected_mapping would * work here too. We have chosen the !PageSwapCache test to * optimize the common case, when the page is or is about to * be freed: PageSwapCache is cleared (under spin_lock_irq) * in the ref_freeze section of __remove_mapping(); but Anon * page->mapping reset to NULL later, in free_pages_prepare(). */ if (!PageSwapCache(page)) goto stale; cpu_relax(); } if (READ_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } if (flags == GET_KSM_PAGE_TRYLOCK) { if (!trylock_page(page)) { put_page(page); return ERR_PTR(-EBUSY); } } else if (flags == GET_KSM_PAGE_LOCK) lock_page(page); if (flags != GET_KSM_PAGE_NOLOCK) { if (READ_ONCE(page->mapping) != expected_mapping) { unlock_page(page); put_page(page); goto stale; } } return page; stale: /* * We come here from above when page->mapping or !PageSwapCache * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; }

struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct folio *folio = page_folio(page); struct anon_vma *anon_vma = folio_anon_vma(folio); struct page *new_page; if (PageKsm(page)) { if (page_stable_node(page) && !(ksm_run & KSM_RUN_UNMERGE)) return page; /* no need to copy it */ } else if (!anon_vma) { return page; /* no need to copy it */ } else if (page->index == linear_page_index(vma, address) && anon_vma->root == vma->anon_vma->root) { return page; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); if (!PageUptodate(page)) return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page && mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { put_page(new_page); new_page = NULL; } if (new_page) { if (copy_mc_user_highpage(new_page, page, address, vma)) { put_page(new_page); memory_failure_queue(page_to_pfn(page), 0); return ERR_PTR(-EHWPOISON); } SetPageDirty(new_page); __SetPageUptodate(new_page); __SetPageLocked(new_page); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } return new_page; }

static struct page *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) { err = try_to_merge_with_ksm_page(tree_rmap_item, tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it. */ if (err) break_cow(rmap_item); } return err ? NULL : page; }

static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), rmap_item, mm, err); return err; }

if (TestSetPageHWPoison(p)) { pr_err("%#lx: already hardware poisoned\n", pfn); res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); if (flags & MF_COUNT_INCREASED) put_page(p); goto unlock_mutex; }

static bool __meminit defer_init(int nid, unsigned long pfn, unsigned long end_pfn) { static unsigned long prev_end_pfn, nr_initialised; if (early_page_ext_enabled()) return false; /* * prev_end_pfn static that contains the end of previous zone * No need to protect because called very early in boot before smp_init. */ if (prev_end_pfn != end_pfn) { prev_end_pfn = end_pfn; nr_initialised = 0; } /* Always populate low zones for address-constrained allocations */ if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) return false; if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) return true; /* * We start only with one section of pages, more pages are added as * needed until the rest of deferred pages are initialized. */ nr_initialised++; if ((nr_initialised > PAGES_PER_SECTION) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { NODE_DATA(nid)->first_deferred_pfn = pfn; return true; } return false; }

if (prev_class) { if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) { pool->size_class[i] = prev_class; continue; } }

zspage = find_get_zspage(class); if (likely(zspage)) { obj = obj_malloc(pool, zspage, handle); /* Now move the zspage to another fullness group, if required */ fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); goto out; }

if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL);

if (!order) {

if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; }

if (!(force_purge

size = count_history_pages(mapping, index, max);