if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; }

static inline bool should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, enum compact_result compact_result, enum compact_priority *compact_priority, int *compaction_retries) { int max_retries = MAX_COMPACT_RETRIES; int min_priority; bool ret = false; int retries = *compaction_retries; enum compact_priority priority = *compact_priority; if (!order) return false; if (fatal_signal_pending(current)) return false; /* * Compaction was skipped due to a lack of free order-0 * migration targets. Continue if reclaim can help. */ if (compact_result == COMPACT_SKIPPED) { ret = compaction_zonelist_suitable(ac, order, alloc_flags); goto out; } /* * Compaction managed to coalesce some page blocks, but the * allocation failed presumably due to a race. Retry some. */ if (compact_result == COMPACT_SUCCESS) { /* * !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; } } /* * Compaction failed. Retry with increasing priority. */ min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ? MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY; if (*compact_priority > min_priority) { (*compact_priority)--; *compaction_retries = 0; ret = true; } out: trace_compact_retry(order, priority, compact_result, retries, max_retries, ret); return ret; }

/* * A fragmentation index only makes sense if an allocation of a requested * size would fail. If that is true, the fragmentation index indicates * whether external fragmentation or a lack of memory was the problem. * The value can be used to determine if page reclaim or compaction * should be used */ static int __fragmentation_index(unsigned int order, struct contig_page_info *info) { unsigned long requested = 1UL << order; if (WARN_ON_ONCE(order > MAX_ORDER)) return 0; if (!info->free_blocks_total) return 0; /* Fragmentation index only makes sense when a request would fail */ if (info->free_blocks_suitable) return -1000; /* * Index is between 0 and 1 so return within 3 decimal places * * 0 => allocation would fail due to lack of memory * 1 => allocation would fail due to fragmentation */ return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total); }

.mode = (prio == COMPACT_PRIO_ASYNC) ? MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT,

/* 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; }

enum compact_priority { COMPACT_PRIO_SYNC_FULL, MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL, COMPACT_PRIO_SYNC_LIGHT, MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, COMPACT_PRIO_ASYNC, INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC };

for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } if (page_mapcount(page) > 1) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } page = compound_head(page); /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = page_to_nid(page); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (PageLocked(page)) { result = SCAN_PAGE_LOCK; goto out_unmap; } if (!PageAnon(page)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see total_mapcount > refcount in some cases? * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(page)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; }

xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) { ++swap; if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } /* * TODO: khugepaged should compact smaller compound pages * into a PMD sized page */ if (PageTransCompound(page)) { struct page *head = compound_head(page); result = compound_order(head) == HPAGE_PMD_ORDER && head->index == start /* Maybe PMD-mapped */ ? SCAN_PTE_MAPPED_HUGEPAGE : SCAN_PAGE_COMPOUND; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = page_to_nid(page); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; break; } if (page_count(page) != 1 + page_mapcount(page) + page_has_private(page)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the page is referenced here, but * nobody would transfer pte_young() to PageReferenced() for us. * And rmap walk here is just too costly... */ present++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } }