Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - A few misc subsystems: kthread, scripts, ntfs, ocfs2, block, and vfs

 - Most the MM patches which precede the patches in Willy's tree: kasan,
   pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
   sparsemem, vmalloc, pagealloc, memory-failure, mlock, hugetlb,
   userfaultfd, vmscan, compaction, mempolicy, oom-kill, migration, thp,
   cma, autonuma, psi, ksm, page-poison, madvise, memory-hotplug, rmap,
   zswap, uaccess, ioremap, highmem, cleanups, kfence, hmm, and damon.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (227 commits)
  mm/damon/sysfs: remove repeat container_of() in damon_sysfs_kdamond_release()
  Docs/ABI/testing: add DAMON sysfs interface ABI document
  Docs/admin-guide/mm/damon/usage: document DAMON sysfs interface
  selftests/damon: add a test for DAMON sysfs interface
  mm/damon/sysfs: support DAMOS stats
  mm/damon/sysfs: support DAMOS watermarks
  mm/damon/sysfs: support schemes prioritization
  mm/damon/sysfs: support DAMOS quotas
  mm/damon/sysfs: support DAMON-based Operation Schemes
  mm/damon/sysfs: support the physical address space monitoring
  mm/damon/sysfs: link DAMON for virtual address spaces monitoring
  mm/damon: implement a minimal stub for sysfs-based DAMON interface
  mm/damon/core: add number of each enum type values
  mm/damon/core: allow non-exclusive DAMON start/stop
  Docs/damon: update outdated term 'regions update interval'
  Docs/vm/damon/design: update DAMON-Idle Page Tracking interference handling
  Docs/vm/damon: call low level monitoring primitives the operations
  mm/damon: remove unnecessary CONFIG_DAMON option
  mm/damon/paddr,vaddr: remove damon_{p,v}a_{target_valid,set_operations}()
  mm/damon/dbgfs-test: fix is_target_id() change
  ...

1 files changed, 54 insertions, 62 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index c7da064b4781..bc9da3fd01aa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -51,6 +51,7 @@
 #include <linux/oom.h>
 #include <linux/memory.h>
 #include <linux/random.h>
+#include <linux/sched/sysctl.h>
 
 #include <asm/tlbflush.h>
 
@@ -107,7 +108,7 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode)
 
 	/* Driver shouldn't use PG_isolated bit of page->flags */
 	WARN_ON_ONCE(PageIsolated(page));
-	__SetPageIsolated(page);
+	SetPageIsolated(page);
 	unlock_page(page);
 
 	return 0;
@@ -126,7 +127,7 @@ static void putback_movable_page(struct page *page)
 
 	mapping = page_mapping(page);
 	mapping->a_ops->putback_page(page);
-	__ClearPageIsolated(page);
+	ClearPageIsolated(page);
 }
 
 /*
@@ -159,7 +160,7 @@ void putback_movable_pages(struct list_head *l)
 			if (PageMovable(page))
 				putback_movable_page(page);
 			else
-				__ClearPageIsolated(page);
+				ClearPageIsolated(page);
 			unlock_page(page);
 			put_page(page);
 		} else {
@@ -883,7 +884,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		VM_BUG_ON_PAGE(!PageIsolated(page), page);
 		if (!PageMovable(page)) {
 			rc = MIGRATEPAGE_SUCCESS;
-			__ClearPageIsolated(page);
+			ClearPageIsolated(page);
 			goto out;
 		}
 
@@ -905,7 +906,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 			 * We clear PG_movable under page_lock so any compactor
 			 * cannot try to migrate this page.
 			 */
-			__ClearPageIsolated(page);
+			ClearPageIsolated(page);
 		}
 
 		/*
@@ -917,8 +918,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 			page->mapping = NULL;
 
 		if (likely(!is_zone_device_page(newpage)))
-			flush_dcache_page(newpage);
-
+			flush_dcache_folio(page_folio(newpage));
 	}
 out:
 	return rc;
@@ -1092,7 +1092,7 @@ static int unmap_and_move(new_page_t get_new_page,
 		if (unlikely(__PageMovable(page))) {
 			lock_page(page);
 			if (!PageMovable(page))
-				__ClearPageIsolated(page);
+				ClearPageIsolated(page);
 			unlock_page(page);
 		}
 		goto out;
@@ -1351,7 +1351,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	bool is_thp = false;
 	struct page *page;
 	struct page *page2;
-	int swapwrite = current->flags & PF_SWAPWRITE;
 	int rc, nr_subpages;
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(thp_split_pages);
@@ -1360,9 +1359,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 
 	trace_mm_migrate_pages_start(mode, reason);
 
-	if (!swapwrite)
-		current->flags |= PF_SWAPWRITE;
-
 thp_subpage_migration:
 	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
@@ -1517,9 +1513,6 @@ out:
 	trace_mm_migrate_pages(nr_succeeded, nr_failed_pages, nr_thp_succeeded,
 			       nr_thp_failed, nr_thp_split, mode, reason);
 
-	if (!swapwrite)
-		current->flags &= ~PF_SWAPWRITE;
-
 	if (ret_succeeded)
 		*ret_succeeded = nr_succeeded;
 
@@ -1612,7 +1605,6 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 {
 	struct vm_area_struct *vma;
 	struct page *page;
-	unsigned int follflags;
 	int err;
 
 	mmap_read_lock(mm);
@@ -1622,8 +1614,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		goto out;
 
 	/* FOLL_DUMP to ignore special (like zero) pages */
-	follflags = FOLL_GET | FOLL_DUMP;
-	page = follow_page(vma, addr, follflags);
+	page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
 
 	err = PTR_ERR(page);
 	if (IS_ERR(page))
@@ -1762,6 +1753,13 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		}
 
 		/*
+		 * The move_pages() man page does not have an -EEXIST choice, so
+		 * use -EFAULT instead.
+		 */
+		if (err == -EEXIST)
+			err = -EFAULT;
+
+		/*
 		 * If the page is already on the target node (!err), store the
 		 * node, otherwise, store the err.
 		 */
@@ -2034,16 +2032,27 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
 	int page_lru;
 	int nr_pages = thp_nr_pages(page);
+	int order = compound_order(page);
 
-	VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);
+	VM_BUG_ON_PAGE(order && !PageTransHuge(page), page);
 
 	/* Do not migrate THP mapped by multiple processes */
 	if (PageTransHuge(page) && total_mapcount(page) > 1)
 		return 0;
 
 	/* Avoid migrating to a node that is nearly full */
-	if (!migrate_balanced_pgdat(pgdat, nr_pages))
+	if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
+		int z;
+
+		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
+			return 0;
+		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+			if (populated_zone(pgdat->node_zones + z))
+				break;
+		}
+		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
 		return 0;
+	}
 
 	if (isolate_lru_page(page))
 		return 0;
@@ -2072,6 +2081,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated;
 	int nr_remaining;
+	unsigned int nr_succeeded;
 	LIST_HEAD(migratepages);
 	new_page_t *new;
 	bool compound;
@@ -2110,7 +2120,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 
 	list_add(&page->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
-				     MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL);
+				     MIGRATE_ASYNC, MR_NUMA_MISPLACED,
+				     &nr_succeeded);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
@@ -2119,8 +2130,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 			putback_lru_page(page);
 		}
 		isolated = 0;
-	} else
-		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
+	}
+	if (nr_succeeded) {
+		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
+		if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node))
+			mod_node_page_state(pgdat, PGPROMOTE_SUCCESS,
+					    nr_succeeded);
+	}
 	BUG_ON(!list_empty(&migratepages));
 	return isolated;
 
@@ -3082,18 +3098,21 @@ static int establish_migrate_target(int node, nodemask_t *used,
 	if (best_distance != -1) {
 		val = node_distance(node, migration_target);
 		if (val > best_distance)
-			return NUMA_NO_NODE;
+			goto out_clear;
 	}
 
 	index = nd->nr;
 	if (WARN_ONCE(index >= DEMOTION_TARGET_NODES,
 		      "Exceeds maximum demotion target nodes\n"))
-		return NUMA_NO_NODE;
+		goto out_clear;
 
 	nd->nodes[index] = migration_target;
 	nd->nr++;
 
 	return migration_target;
+out_clear:
+	node_clear(migration_target, *used);
+	return NUMA_NO_NODE;
 }
 
 /*
@@ -3190,7 +3209,7 @@ again:
 /*
  * For callers that do not hold get_online_mems() already.
  */
-static void set_migration_target_nodes(void)
+void set_migration_target_nodes(void)
 {
 	get_online_mems();
 	__set_migration_target_nodes();
@@ -3254,51 +3273,24 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 	return notifier_from_errno(0);
 }
 
-/*
- * React to hotplug events that might affect the migration targets
- * like events that online or offline NUMA nodes.
- *
- * The ordering is also currently dependent on which nodes have
- * CPUs.  That means we need CPU on/offline notification too.
- */
-static int migration_online_cpu(unsigned int cpu)
-{
-	set_migration_target_nodes();
-	return 0;
-}
-
-static int migration_offline_cpu(unsigned int cpu)
-{
-	set_migration_target_nodes();
-	return 0;
-}
-
-static int __init migrate_on_reclaim_init(void)
+void __init migrate_on_reclaim_init(void)
 {
-	int ret;
-
 	node_demotion = kmalloc_array(nr_node_ids,
 				      sizeof(struct demotion_nodes),
 				      GFP_KERNEL);
 	WARN_ON(!node_demotion);
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline",
-					NULL, migration_offline_cpu);
+	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
 	/*
-	 * In the unlikely case that this fails, the automatic
-	 * migration targets may become suboptimal for nodes
-	 * where N_CPU changes.  With such a small impact in a
-	 * rare case, do not bother trying to do anything special.
+	 * At this point, all numa nodes with memory/CPus have their state
+	 * properly set, so we can build the demotion order now.
+	 * Let us hold the cpu_hotplug lock just, as we could possibily have
+	 * CPU hotplug events during boot.
 	 */
-	WARN_ON(ret < 0);
-	ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
-				migration_online_cpu, NULL);
-	WARN_ON(ret < 0);
-
-	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
-	return 0;
+	cpus_read_lock();
+	set_migration_target_nodes();
+	cpus_read_unlock();
 }
-late_initcall(migrate_on_reclaim_init);
 #endif /* CONFIG_HOTPLUG_CPU */
 
 bool numa_demotion_enabled = false;