1 files changed, 138 insertions, 69 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4936a88bb26a..bd6637fcd8f9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -54,6 +54,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
+#include <linux/khugepaged.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1020,31 +1021,52 @@ out:
 	return freed;
 }
 
-static void drop_slab_node(int nid)
+static unsigned long drop_slab_node(int nid)
 {
-	unsigned long freed;
-	int shift = 0;
+	unsigned long freed = 0;
+	struct mem_cgroup *memcg = NULL;
 
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
-		struct mem_cgroup *memcg = NULL;
+		freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
 
-		if (fatal_signal_pending(current))
-			return;
+	return freed;
+}
 
+void drop_slab(void)
+{
+	int nid;
+	int shift = 0;
+	unsigned long freed;
+
+	do {
 		freed = 0;
-		memcg = mem_cgroup_iter(NULL, NULL, NULL);
-		do {
-			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
-		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+		for_each_online_node(nid) {
+			if (fatal_signal_pending(current))
+				return;
+
+			freed += drop_slab_node(nid);
+		}
 	} while ((freed >> shift++) > 1);
 }
 
-void drop_slab(void)
+static int reclaimer_offset(void)
 {
-	int nid;
+	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
+			PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
+	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
+			PGSCAN_DIRECT - PGSCAN_KSWAPD);
+	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
+			PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
+	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
+			PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);
 
-	for_each_online_node(nid)
-		drop_slab_node(nid);
+	if (current_is_kswapd())
+		return 0;
+	if (current_is_khugepaged())
+		return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD;
+	return PGSTEAL_DIRECT - PGSTEAL_KSWAPD;
 }
 
 static inline int is_page_cache_freeable(struct folio *folio)
@@ -1346,11 +1368,10 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 	if (folio_test_swapcache(folio)) {
 		swp_entry_t swap = folio_swap_entry(folio);
 
-		/* get a shadow entry before mem_cgroup_swapout() clears folio_memcg() */
 		if (reclaimed && !mapping_exiting(mapping))
 			shadow = workingset_eviction(folio, target_memcg);
-		mem_cgroup_swapout(folio, swap);
 		__delete_from_swap_cache(folio, swap, shadow);
+		mem_cgroup_swapout(folio, swap);
 		xa_unlock_irq(&mapping->i_pages);
 		put_swap_folio(folio, swap);
 	} else {
@@ -1599,10 +1620,7 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
 		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
 		      &nr_succeeded);
 
-	if (current_is_kswapd())
-		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);
-	else
-		__count_vm_events(PGDEMOTE_DIRECT, nr_succeeded);
+	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
 
 	return nr_succeeded;
 }
@@ -2069,10 +2087,29 @@ keep:
 	nr_reclaimed += demote_folio_list(&demote_folios, pgdat);
 	/* Folios that could not be demoted are still in @demote_folios */
 	if (!list_empty(&demote_folios)) {
-		/* Folios which weren't demoted go back on @folio_list for retry: */
+		/* Folios which weren't demoted go back on @folio_list */
 		list_splice_init(&demote_folios, folio_list);
-		do_demote_pass = false;
-		goto retry;
+
+		/*
+		 * goto retry to reclaim the undemoted folios in folio_list if
+		 * desired.
+		 *
+		 * Reclaiming directly from top tier nodes is not often desired
+		 * due to it breaking the LRU ordering: in general memory
+		 * should be reclaimed from lower tier nodes and demoted from
+		 * top tier nodes.
+		 *
+		 * However, disabling reclaim from top tier nodes entirely
+		 * would cause ooms in edge scenarios where lower tier memory
+		 * is unreclaimable for whatever reason, eg memory being
+		 * mlocked or too hot to reclaim. We can disable reclaim
+		 * from top tier nodes in proactive reclaim though as that is
+		 * not real memory pressure.
+		 */
+		if (!sc->proactive) {
+			do_demote_pass = false;
+			goto retry;
+		}
 	}
 
 	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
@@ -2475,7 +2512,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 				     &nr_scanned, sc, lru);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
-	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
+	item = PGSCAN_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_scanned);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
@@ -2492,14 +2529,14 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	move_folios_to_lru(lruvec, &folio_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+	item = PGSTEAL_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
 	spin_unlock_irq(&lruvec->lru_lock);
 
-	lru_note_cost(lruvec, file, stat.nr_pageout);
+	lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed);
 	mem_cgroup_uncharge_list(&folio_list);
 	free_unref_page_list(&folio_list);
 
@@ -2514,8 +2551,20 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	 * the flushers simply cannot keep up with the allocation
 	 * rate. Nudge the flusher threads in case they are asleep.
 	 */
-	if (stat.nr_unqueued_dirty == nr_taken)
+	if (stat.nr_unqueued_dirty == nr_taken) {
 		wakeup_flusher_threads(WB_REASON_VMSCAN);
+		/*
+		 * For cgroupv1 dirty throttling is achieved by waking up
+		 * the kernel flusher here and later waiting on folios
+		 * which are in writeback to finish (see shrink_folio_list()).
+		 *
+		 * Flusher may not be able to issue writeback quickly
+		 * enough for cgroupv1 writeback throttling to work
+		 * on a large system.
+		 */
+		if (!writeback_throttling_sane(sc))
+			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
+	}
 
 	sc->nr.dirty += stat.nr_dirty;
 	sc->nr.congested += stat.nr_congested;
@@ -2639,6 +2688,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&lruvec->lru_lock);
 
+	if (nr_rotated)
+		lru_note_cost(lruvec, file, 0, nr_rotated);
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
 	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
@@ -3133,7 +3184,7 @@ static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
 	if (memcg) {
 		struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
 
-		/* for hotadd_new_pgdat() */
+		/* see the comment in mem_cgroup_lruvec() */
 		if (!lruvec->pgdat)
 			lruvec->pgdat = pgdat;
 
@@ -3142,7 +3193,7 @@ static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
 #endif
 	VM_WARN_ON_ONCE(!mem_cgroup_disabled());
 
-	return pgdat ? &pgdat->__lruvec : NULL;
+	return &pgdat->__lruvec;
 }
 
 static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
@@ -3206,9 +3257,6 @@ void lru_gen_add_mm(struct mm_struct *mm)
 	for_each_node_state(nid, N_MEMORY) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
 
-		if (!lruvec)
-			continue;
-
 		/* the first addition since the last iteration */
 		if (lruvec->mm_state.tail == &mm_list->fifo)
 			lruvec->mm_state.tail = &mm->lru_gen.list;
@@ -3238,9 +3286,6 @@ void lru_gen_del_mm(struct mm_struct *mm)
 	for_each_node(nid) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
 
-		if (!lruvec)
-			continue;
-
 		/* where the last iteration ended (exclusive) */
 		if (lruvec->mm_state.tail == &mm->lru_gen.list)
 			lruvec->mm_state.tail = lruvec->mm_state.tail->next;
@@ -3975,7 +4020,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
+			if (arch_has_hw_nonleaf_pmd_young() &&
 			    get_cap(LRU_GEN_NONLEAF_YOUNG))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
@@ -4070,14 +4115,14 @@ restart:
 #endif
 		walk->mm_stats[MM_NONLEAF_TOTAL]++;
 
-#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
-		if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
+		if (arch_has_hw_nonleaf_pmd_young() &&
+		    get_cap(LRU_GEN_NONLEAF_YOUNG)) {
 			if (!pmd_young(val))
 				continue;
 
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
 		}
-#endif
+
 		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
 			continue;
 
@@ -4483,7 +4528,7 @@ static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned
 
 	mem_cgroup_calculate_protection(NULL, memcg);
 
-	if (mem_cgroup_below_min(memcg))
+	if (mem_cgroup_below_min(NULL, memcg))
 		return false;
 
 	need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
@@ -4854,7 +4899,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
 			break;
 	}
 
-	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
+	item = PGSCAN_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc)) {
 		__count_vm_events(item, isolated);
 		__count_vm_events(PGREFILL, sorted);
@@ -4968,10 +5013,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	int scanned;
 	int reclaimed;
 	LIST_HEAD(list);
+	LIST_HEAD(clean);
 	struct folio *folio;
+	struct folio *next;
 	enum vm_event_item item;
 	struct reclaim_stat stat;
 	struct lru_gen_mm_walk *walk;
+	bool skip_retry = false;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
@@ -4988,20 +5036,37 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 
 	if (list_empty(&list))
 		return scanned;
-
+retry:
 	reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
+	sc->nr_reclaimed += reclaimed;
 
-	list_for_each_entry(folio, &list, lru) {
-		/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
-		if (folio_test_workingset(folio))
-			folio_set_referenced(folio);
+	list_for_each_entry_safe_reverse(folio, next, &list, lru) {
+		if (!folio_evictable(folio)) {
+			list_del(&folio->lru);
+			folio_putback_lru(folio);
+			continue;
+		}
 
-		/* don't add rejected pages to the oldest generation */
 		if (folio_test_reclaim(folio) &&
-		    (folio_test_dirty(folio) || folio_test_writeback(folio)))
-			folio_clear_active(folio);
-		else
-			folio_set_active(folio);
+		    (folio_test_dirty(folio) || folio_test_writeback(folio))) {
+			/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
+			if (folio_test_workingset(folio))
+				folio_set_referenced(folio);
+			continue;
+		}
+
+		if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) ||
+		    folio_mapped(folio) || folio_test_locked(folio) ||
+		    folio_test_dirty(folio) || folio_test_writeback(folio)) {
+			/* don't add rejected folios to the oldest generation */
+			set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
+				      BIT(PG_active));
+			continue;
+		}
+
+		/* retry folios that may have missed folio_rotate_reclaimable() */
+		list_move(&folio->lru, &clean);
+		sc->nr_scanned -= folio_nr_pages(folio);
 	}
 
 	spin_lock_irq(&lruvec->lru_lock);
@@ -5012,7 +5077,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	if (walk && walk->batched)
 		reset_batch_size(lruvec, walk);
 
-	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+	item = PGSTEAL_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, reclaimed);
 	__count_memcg_events(memcg, item, reclaimed);
@@ -5023,7 +5088,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	mem_cgroup_uncharge_list(&list);
 	free_unref_page_list(&list);
 
-	sc->nr_reclaimed += reclaimed;
+	INIT_LIST_HEAD(&list);
+	list_splice_init(&clean, &list);
+
+	if (!list_empty(&list)) {
+		skip_retry = true;
+		goto retry;
+	}
 
 	if (need_swapping && type == LRU_GEN_ANON)
 		*need_swapping = true;
@@ -5044,8 +5115,9 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
-	if (mem_cgroup_below_min(memcg) ||
-	    (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
+	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg) ||
+	    (mem_cgroup_below_low(sc->target_mem_cgroup, memcg) &&
+	     !sc->memcg_low_reclaim))
 		return 0;
 
 	*need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
@@ -5286,9 +5358,6 @@ static void lru_gen_change_state(bool enabled)
 		for_each_node(nid) {
 			struct lruvec *lruvec = get_lruvec(memcg, nid);
 
-			if (!lruvec)
-				continue;
-
 			spin_lock_irq(&lruvec->lru_lock);
 
 			VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
@@ -5351,10 +5420,10 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
 	if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
 		caps |= BIT(LRU_GEN_MM_WALK);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
+	if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
 		caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
 
-	return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);
+	return sysfs_emit(buf, "0x%04x\n", caps);
 }
 
 /* see Documentation/admin-guide/mm/multigen_lru.rst for details */
@@ -5841,8 +5910,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	enum lru_list lru;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
+	bool proportional_reclaim;
 	struct blk_plug plug;
-	bool scan_adjusted;
 
 	if (lru_gen_enabled()) {
 		lru_gen_shrink_lruvec(lruvec, sc);
@@ -5865,8 +5934,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	 * abort proportional reclaim if either the file or anon lru has already
 	 * dropped to zero at the first pass.
 	 */
-	scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
-			 sc->priority == DEF_PRIORITY);
+	proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
+				sc->priority == DEF_PRIORITY);
 
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -5886,7 +5955,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 
 		cond_resched();
 
-		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
+		if (nr_reclaimed < nr_to_reclaim || proportional_reclaim)
 			continue;
 
 		/*
@@ -5937,8 +6006,6 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		nr_scanned = targets[lru] - nr[lru];
 		nr[lru] = targets[lru] * (100 - percentage) / 100;
 		nr[lru] -= min(nr[lru], nr_scanned);
-
-		scan_adjusted = true;
 	}
 	blk_finish_plug(&plug);
 	sc->nr_reclaimed += nr_reclaimed;
@@ -6045,13 +6112,13 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 
 		mem_cgroup_calculate_protection(target_memcg, memcg);
 
-		if (mem_cgroup_below_min(memcg)) {
+		if (mem_cgroup_below_min(target_memcg, memcg)) {
 			/*
 			 * Hard protection.
 			 * If there is no reclaimable memory, OOM.
 			 */
 			continue;
-		} else if (mem_cgroup_below_low(memcg)) {
+		} else if (mem_cgroup_below_low(target_memcg, memcg)) {
 			/*
 			 * Soft protection.
 			 * Respect the protection only as long as
@@ -6687,7 +6754,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
-					   unsigned int reclaim_options)
+					   unsigned int reclaim_options,
+					   nodemask_t *nodemask)
 {
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
@@ -6702,6 +6770,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
 		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
+		.nodemask = nodemask,
 	};
 	/*
 	 * Traverse the ZONELIST_FALLBACK zonelist of the current node to put