1 files changed, 98 insertions, 78 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 749cdc110c74..76378bc257e3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -56,6 +56,7 @@
 #include <linux/khugepaged.h>
 #include <linux/rculist_nulls.h>
 #include <linux/random.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1257,8 +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;
 				}
@@ -1475,7 +1476,7 @@ free_it:
 		 */
 		nr_reclaimed += nr_pages;
 
-		folio_undo_large_rmappable(folio);
+		folio_unqueue_deferred_split(folio);
 		if (folio_batch_add(&free_folios, folio) == 0) {
 			mem_cgroup_uncharge_folios(&free_folios);
 			try_to_unmap_flush();
@@ -1863,7 +1864,7 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
 		if (unlikely(folio_put_testzero(folio))) {
 			__folio_clear_lru_flags(folio);
 
-			folio_undo_large_rmappable(folio);
+			folio_unqueue_deferred_split(folio);
 			if (folio_batch_add(&free_folios, folio) == 0) {
 				spin_unlock_irq(&lruvec->lru_lock);
 				mem_cgroup_uncharge_folios(&free_folios);
@@ -2128,7 +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 = {
@@ -2139,12 +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;
 }
@@ -2601,8 +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)
 
@@ -3137,7 +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? */
@@ -3294,7 +3293,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk
 	return false;
 }
 
-static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -3306,13 +3306,20 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
 		return -1;
 
+	if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
-static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pmd_pfn(pmd);
 
@@ -3324,9 +3331,15 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pmd_devmap(pmd)))
 		return -1;
 
+	if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
@@ -3335,15 +3348,11 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
 {
 	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)
+	if (folio_memcg(folio) != memcg)
 		return NULL;
 
 	/* file VMAs can contain anon pages from COW */
@@ -3375,8 +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)) {
@@ -3384,6 +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) {
@@ -3394,21 +3410,16 @@ restart:
 		total++;
 		walk->mm_stats[MM_LEAF_TOTAL]++;
 
-		pfn = get_pte_pfn(ptent, args->vma, addr);
+		pfn = get_pte_pfn(ptent, args->vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent)) {
-			walk->mm_stats[MM_LEAF_OLD]++;
-			continue;
-		}
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
+			continue;
 
 		young++;
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3474,21 +3485,25 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		/* don't round down the first address */
 		addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
 
-		pfn = get_pmd_pfn(pmd[i], vma, addr);
-		if (pfn == -1)
+		if (!pmd_present(pmd[i]))
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (!walk->force_scan && should_clear_pmd_young())
+			if (!walk->force_scan && should_clear_pmd_young() &&
+			    !mm_has_notifiers(args->mm))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
 		}
 
+		pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat);
+		if (pfn == -1)
+			goto next;
+
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			goto next;
 
-		if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
+		if (!pmdp_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3546,27 +3561,18 @@ restart:
 		}
 
 		if (pmd_trans_huge(val)) {
-			unsigned long pfn = pmd_pfn(val);
 			struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+			unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat);
 
 			walk->mm_stats[MM_LEAF_TOTAL]++;
 
-			if (!pmd_young(val)) {
-				walk->mm_stats[MM_LEAF_OLD]++;
-				continue;
-			}
-
-			/* try to avoid unnecessary memory loads */
-			if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-				continue;
-
-			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
+			if (pfn != -1)
+				walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 			continue;
 		}
 
-		walk->mm_stats[MM_NONLEAF_TOTAL]++;
-
-		if (!walk->force_scan && should_clear_pmd_young()) {
+		if (!walk->force_scan && should_clear_pmd_young() &&
+		    !mm_has_notifiers(args->mm)) {
 			if (!pmd_young(val))
 				continue;
 
@@ -3642,10 +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;
 
@@ -3658,10 +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);
@@ -3669,8 +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);
@@ -4040,13 +4038,13 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
  * the PTE table to the Bloom filter. This forms a feedback loop between the
  * eviction and the aging.
  */
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 	int i;
 	unsigned long start;
 	unsigned long end;
 	struct lru_gen_mm_walk *walk;
-	int young = 0;
+	int young = 1;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
@@ -4062,12 +4060,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
 
+	if (!ptep_clear_young_notify(vma, addr, pte))
+		return false;
+
 	if (spin_is_contended(pvmw->ptl))
-		return;
+		return true;
 
 	/* exclude special VMAs containing anon pages from COW */
 	if (vma->vm_flags & VM_SPECIAL)
-		return;
+		return true;
 
 	/* avoid taking the LRU lock under the PTL when possible */
 	walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
@@ -4075,6 +4076,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	start = max(addr & PMD_MASK, vma->vm_start);
 	end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
 
+	if (end - start == PAGE_SIZE)
+		return true;
+
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
 			end = start + MIN_LRU_BATCH * PAGE_SIZE;
@@ -4086,10 +4090,6 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		}
 	}
 
-	/* folio_update_gen() requires stable folio_memcg() */
-	if (!mem_cgroup_trylock_pages(memcg))
-		return;
-
 	arch_enter_lazy_mmu_mode();
 
 	pte -= (addr - start) / PAGE_SIZE;
@@ -4098,19 +4098,16 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		unsigned long pfn;
 		pte_t ptent = ptep_get(pte + i);
 
-		pfn = get_pte_pfn(ptent, vma, addr);
+		pfn = get_pte_pfn(ptent, vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent))
-			continue;
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(vma, addr, pte + i))
+			continue;
 
 		young++;
 
@@ -4130,16 +4127,19 @@ void 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))
 		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
+
+	return true;
 }
 
 /******************************************************************************
@@ -4284,6 +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);
@@ -4329,9 +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;
@@ -4362,7 +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);
@@ -4447,7 +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.
@@ -4581,6 +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,
@@ -4789,6 +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;
 }
@@ -4963,8 +4981,8 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *
 
 	blk_finish_plug(&plug);
 done:
-	/* kswapd should never fail */
-	pgdat->kswapd_failures = 0;
+	if (sc->nr_reclaimed > reclaimed)
+		pgdat->kswapd_failures = 0;
 }
 
 /******************************************************************************
@@ -5254,11 +5272,11 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 	for (tier = 0; tier < MAX_NR_TIERS; tier++) {
 		seq_printf(m, "            %10d", tier);
 		for (type = 0; type < ANON_AND_FILE; type++) {
-			const char *s = "   ";
+			const char *s = "xxx";
 			unsigned long n[3] = {};
 
 			if (seq == max_seq) {
-				s = "RT ";
+				s = "RTx";
 				n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
 				n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
 			} else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
@@ -5280,14 +5298,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 
 	seq_puts(m, "                      ");
 	for (i = 0; i < NR_MM_STATS; i++) {
-		const char *s = "      ";
+		const char *s = "xxxx";
 		unsigned long n = 0;
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
-			s = "LOYNFA";
+			s = "TYFA";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
-			s = "loynfa";
+			s = "tyfa";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
@@ -5934,6 +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;
 	}
@@ -5984,7 +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);
 
 		/*