diff options
Diffstat (limited to 'mm/vmscan.c')
| -rw-r--r-- | mm/vmscan.c | 184 |
1 files changed, 184 insertions, 0 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index 674d336dfe00..986916c15bec 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1635,6 +1635,11 @@ retry: if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; + /* folio_update_gen() tried to promote this page? */ + if (lru_gen_enabled() && !ignore_references && + folio_mapped(folio) && folio_test_referenced(folio)) + goto keep_locked; + /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing @@ -3219,6 +3224,29 @@ static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) * the aging ******************************************************************************/ +/* promote pages accessed through page tables */ +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? */ + if (!(old_flags & LRU_GEN_MASK)) { + /* for shrink_page_list() */ + new_flags = old_flags | BIT(PG_referenced); + continue; + } + + new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); + new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; + } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); + + return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { @@ -3230,6 +3258,11 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { + new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; + /* folio_update_gen() has promoted this page? */ + if (new_gen >= 0 && new_gen != old_gen) + return new_gen; + new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); @@ -3244,6 +3277,43 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai return new_gen; } +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long pfn = pte_pfn(pte); + + VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); + + if (!pte_present(pte) || is_zero_pfn(pfn)) + return -1; + + if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) + return -1; + + if (WARN_ON_ONCE(!pfn_valid(pfn))) + return -1; + + return pfn; +} + +static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, + struct pglist_data *pgdat) +{ + struct folio *folio; + + /* try to avoid unnecessary memory loads */ + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return NULL; + + folio = pfn_folio(pfn); + if (folio_nid(folio) != pgdat->node_id) + return NULL; + + if (folio_memcg_rcu(folio) != memcg) + return NULL; + + return folio; +} + static void inc_min_seq(struct lruvec *lruvec, int type) { struct lru_gen_struct *lrugen = &lruvec->lrugen; @@ -3443,6 +3513,114 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); } +/* + * This function exploits spatial locality when shrink_page_list() walks the + * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. + */ +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ + int i; + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long addr; + unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {}; + struct folio *folio = pfn_folio(pvmw->pfn); + struct mem_cgroup *memcg = folio_memcg(folio); + struct pglist_data *pgdat = folio_pgdat(folio); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + DEFINE_MAX_SEQ(lruvec); + int old_gen, new_gen = lru_gen_from_seq(max_seq); + + lockdep_assert_held(pvmw->ptl); + VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + + if (spin_is_contended(pvmw->ptl)) + return; + + start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start); + end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1; + + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { + if (pvmw->address - start < MIN_LRU_BATCH * PAGE_SIZE / 2) + end = start + MIN_LRU_BATCH * PAGE_SIZE; + else if (end - pvmw->address < MIN_LRU_BATCH * PAGE_SIZE / 2) + start = end - MIN_LRU_BATCH * PAGE_SIZE; + else { + start = pvmw->address - MIN_LRU_BATCH * PAGE_SIZE / 2; + end = pvmw->address + MIN_LRU_BATCH * PAGE_SIZE / 2; + } + } + + pte = pvmw->pte - (pvmw->address - start) / PAGE_SIZE; + + rcu_read_lock(); + arch_enter_lazy_mmu_mode(); + + for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { + unsigned long pfn; + + pfn = get_pte_pfn(pte[i], pvmw->vma, addr); + if (pfn == -1) + continue; + + if (!pte_young(pte[i])) + continue; + + folio = get_pfn_folio(pfn, memcg, pgdat); + if (!folio) + continue; + + if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i)) + VM_WARN_ON_ONCE(true); + + if (pte_dirty(pte[i]) && !folio_test_dirty(folio) && + !(folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio))) + folio_mark_dirty(folio); + + old_gen = folio_lru_gen(folio); + if (old_gen < 0) + folio_set_referenced(folio); + else if (old_gen != new_gen) + __set_bit(i, bitmap); + } + + arch_leave_lazy_mmu_mode(); + rcu_read_unlock(); + + if (bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) { + for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { + folio = pfn_folio(pte_pfn(pte[i])); + folio_activate(folio); + } + return; + } + + /* folio_update_gen() requires stable folio_memcg() */ + if (!mem_cgroup_trylock_pages(memcg)) + return; + + spin_lock_irq(&lruvec->lru_lock); + new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq); + + for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { + folio = pfn_folio(pte_pfn(pte[i])); + if (folio_memcg_rcu(folio) != memcg) + continue; + + old_gen = folio_update_gen(folio, new_gen); + if (old_gen < 0 || old_gen == new_gen) + continue; + + lru_gen_update_size(lruvec, folio, old_gen, new_gen); + } + + spin_unlock_irq(&lruvec->lru_lock); + + mem_cgroup_unlock_pages(); +} + /****************************************************************************** * the eviction ******************************************************************************/ @@ -3479,6 +3657,12 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) return true; } + /* promoted */ + if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { + list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + return true; + } + /* protected */ if (tier > tier_idx) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); |