diff options
Diffstat (limited to 'mm/vmscan.c')
| -rw-r--r-- | mm/vmscan.c | 68 |
1 files changed, 41 insertions, 27 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index 28ba2b06fc7d..76378bc257e3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1258,8 +1258,8 @@ retry: THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } - count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif + count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); if (!add_to_swap(folio)) goto activate_locked_split; } @@ -2129,7 +2129,7 @@ static void shrink_active_list(unsigned long nr_to_scan, static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { - struct reclaim_stat dummy_stat; + struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { @@ -2140,12 +2140,13 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list, .no_demotion = 1, }; - nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true); + nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } + trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat); return nr_reclaimed; } @@ -2602,8 +2603,6 @@ static bool should_clear_pmd_young(void) * shorthand helpers ******************************************************************************/ -#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) - #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) @@ -3138,7 +3137,6 @@ static int folio_update_gen(struct folio *folio, int gen) unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); - VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ @@ -3354,7 +3352,7 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, if (folio_nid(folio) != pgdat->node_id) return NULL; - if (folio_memcg_rcu(folio) != memcg) + if (folio_memcg(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ @@ -3386,8 +3384,10 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); + pmd_t pmdval; - pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl); + pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, + &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { @@ -3395,6 +3395,11 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, return false; } + if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { + pte_unmap_unlock(pte, ptl); + return false; + } + arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { @@ -3643,10 +3648,8 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; - int err; struct lruvec *lruvec = walk->lruvec; - struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; @@ -3659,10 +3662,6 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) if (walk->seq != max_seq) break; - /* folio_update_gen() requires stable folio_memcg() */ - if (!mem_cgroup_trylock_pages(memcg)) - break; - /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); @@ -3670,8 +3669,6 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) mmap_read_unlock(mm); } - mem_cgroup_unlock_pages(); - if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); @@ -4093,10 +4090,6 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) } } - /* folio_update_gen() requires stable folio_memcg() */ - if (!mem_cgroup_trylock_pages(memcg)) - return true; - arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; @@ -4134,12 +4127,13 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); - else if (old_gen != new_gen) + else if (old_gen != new_gen) { + folio_clear_lru_refs(folio); folio_activate(folio); + } } arch_leave_lazy_mmu_mode(); - mem_cgroup_unlock_pages(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) @@ -4290,6 +4284,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c int tier_idx) { bool success; + bool dirty, writeback; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -4335,9 +4330,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c return true; } + dirty = folio_test_dirty(folio); + writeback = folio_test_writeback(folio); + if (type == LRU_GEN_FILE && dirty) { + sc->nr.file_taken += delta; + if (!writeback) + sc->nr.unqueued_dirty += delta; + } + /* waiting for writeback */ - if (folio_test_locked(folio) || folio_test_writeback(folio) || - (type == LRU_GEN_FILE && folio_test_dirty(folio))) { + if (folio_test_locked(folio) || writeback || + (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; @@ -4368,7 +4371,7 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) - set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); + folio_clear_lru_refs(folio); /* for shrink_folio_list() */ folio_clear_reclaim(folio); @@ -4453,7 +4456,8 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); - + if (type == LRU_GEN_FILE) + sc->nr.file_taken += isolated; /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. @@ -4587,6 +4591,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); + sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, @@ -4795,6 +4800,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); } + /* + * If too many file cache in the coldest generation can't be evicted + * due to being dirty, wake up the flusher. + */ + if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) + wakeup_flusher_threads(WB_REASON_VMSCAN); + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -5940,6 +5952,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { + memset(&sc->nr, 0, sizeof(sc->nr)); lru_gen_shrink_node(pgdat, sc); return; } @@ -5990,7 +6003,8 @@ again: set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ - if (sc->nr.unqueued_dirty == sc->nr.file_taken) + if (sc->nr.unqueued_dirty && + sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* |