Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

1 files changed, 138 insertions, 16 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 71f178f85f5b..ef4a6dc7f000 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1021,6 +1021,91 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
+void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
+{
+	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
+	long timeout, ret;
+	DEFINE_WAIT(wait);
+
+	/*
+	 * Do not throttle IO workers, kthreads other than kswapd or
+	 * workqueues. They may be required for reclaim to make
+	 * forward progress (e.g. journalling workqueues or kthreads).
+	 */
+	if (!current_is_kswapd() &&
+	    current->flags & (PF_IO_WORKER|PF_KTHREAD))
+		return;
+
+	/*
+	 * These figures are pulled out of thin air.
+	 * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
+	 * parallel reclaimers which is a short-lived event so the timeout is
+	 * short. Failing to make progress or waiting on writeback are
+	 * potentially long-lived events so use a longer timeout. This is shaky
+	 * logic as a failure to make progress could be due to anything from
+	 * writeback to a slow device to excessive references pages at the tail
+	 * of the inactive LRU.
+	 */
+	switch(reason) {
+	case VMSCAN_THROTTLE_WRITEBACK:
+		timeout = HZ/10;
+
+		if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
+			WRITE_ONCE(pgdat->nr_reclaim_start,
+				node_page_state(pgdat, NR_THROTTLED_WRITTEN));
+		}
+
+		break;
+	case VMSCAN_THROTTLE_NOPROGRESS:
+		timeout = HZ/2;
+		break;
+	case VMSCAN_THROTTLE_ISOLATED:
+		timeout = HZ/50;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		timeout = HZ;
+		break;
+	}
+
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+	if (reason == VMSCAN_THROTTLE_WRITEBACK)
+		atomic_dec(&pgdat->nr_writeback_throttled);
+
+	trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
+				jiffies_to_usecs(timeout - ret),
+				reason);
+}
+
+/*
+ * Account for pages written if tasks are throttled waiting on dirty
+ * pages to clean. If enough pages have been cleaned since throttling
+ * started then wakeup the throttled tasks.
+ */
+void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
+							int nr_throttled)
+{
+	unsigned long nr_written;
+
+	node_stat_add_folio(folio, NR_THROTTLED_WRITTEN);
+
+	/*
+	 * This is an inaccurate read as the per-cpu deltas may not
+	 * be synchronised. However, given that the system is
+	 * writeback throttled, it is not worth taking the penalty
+	 * of getting an accurate count. At worst, the throttle
+	 * timeout guarantees forward progress.
+	 */
+	nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) -
+		READ_ONCE(pgdat->nr_reclaim_start);
+
+	if (nr_written > SWAP_CLUSTER_MAX * nr_throttled)
+		wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]);
+}
+
 /* possible outcome of pageout() */
 typedef enum {
 	/* failed to write page out, page is locked */
@@ -1352,7 +1437,6 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 {
 	int target_nid = next_demotion_node(pgdat->node_id);
 	unsigned int nr_succeeded;
-	int err;
 
 	if (list_empty(demote_pages))
 		return 0;
@@ -1361,7 +1445,7 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 		return 0;
 
 	/* Demotion ignores all cpuset and mempolicy settings */
-	err = migrate_pages(demote_pages, alloc_demote_page, NULL,
+	migrate_pages(demote_pages, alloc_demote_page, NULL,
 			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
 			    &nr_succeeded);
 
@@ -1427,9 +1511,8 @@ retry:
 
 		/*
 		 * The number of dirty pages determines if a node is marked
-		 * reclaim_congested which affects wait_iff_congested. kswapd
-		 * will stall and start writing pages if the tail of the LRU
-		 * is all dirty unqueued pages.
+		 * reclaim_congested. kswapd will stall and start writing
+		 * pages if the tail of the LRU is all dirty unqueued pages.
 		 */
 		page_check_dirty_writeback(page, &dirty, &writeback);
 		if (dirty || writeback)
@@ -2135,6 +2218,7 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 		struct scan_control *sc)
 {
 	unsigned long inactive, isolated;
+	bool too_many;
 
 	if (current_is_kswapd())
 		return 0;
@@ -2158,7 +2242,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 	if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
 		inactive >>= 3;
 
-	return isolated > inactive;
+	too_many = isolated > inactive;
+
+	/* Wake up tasks throttled due to too_many_isolated. */
+	if (!too_many)
+		wake_throttle_isolated(pgdat);
+
+	return too_many;
 }
 
 /*
@@ -2267,8 +2357,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 			return 0;
 
 		/* wait a bit for the reclaimer. */
-		msleep(100);
 		stalled = true;
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);
 
 		/* We are about to die and free our memory. Return now. */
 		if (fatal_signal_pending(current))
@@ -3196,19 +3286,19 @@ again:
 		 * If kswapd scans pages marked for immediate
 		 * reclaim and under writeback (nr_immediate), it
 		 * implies that pages are cycling through the LRU
-		 * faster than they are written so also forcibly stall.
+		 * faster than they are written so forcibly stall
+		 * until some pages complete writeback.
 		 */
 		if (sc->nr.immediate)
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
 	}
 
 	/*
-	 * Tag a node/memcg as congested if all the dirty pages
-	 * scanned were backed by a congested BDI and
-	 * wait_iff_congested will stall.
+	 * Tag a node/memcg as congested if all the dirty pages were marked
+	 * for writeback and immediate reclaim (counted in nr.congested).
 	 *
 	 * Legacy memcg will stall in page writeback so avoid forcibly
-	 * stalling in wait_iff_congested().
+	 * stalling in reclaim_throttle().
 	 */
 	if ((current_is_kswapd() ||
 	     (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) &&
@@ -3216,15 +3306,15 @@ again:
 		set_bit(LRUVEC_CONGESTED, &target_lruvec->flags);
 
 	/*
-	 * Stall direct reclaim for IO completions if underlying BDIs
-	 * and node is congested. Allow kswapd to continue until it
+	 * Stall direct reclaim for IO completions if the lruvec is
+	 * node is congested. Allow kswapd to continue until it
 	 * starts encountering unqueued dirty pages or cycling through
 	 * the LRU too quickly.
 	 */
 	if (!current_is_kswapd() && current_may_throttle() &&
 	    !sc->hibernation_mode &&
 	    test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
-		wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
 
 	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 				    sc))
@@ -3272,6 +3362,36 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
 }
 
+static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
+{
+	/*
+	 * If reclaim is making progress greater than 12% efficiency then
+	 * wake all the NOPROGRESS throttled tasks.
+	 */
+	if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) {
+		wait_queue_head_t *wqh;
+
+		wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS];
+		if (waitqueue_active(wqh))
+			wake_up(wqh);
+
+		return;
+	}
+
+	/*
+	 * Do not throttle kswapd on NOPROGRESS as it will throttle on
+	 * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under
+	 * writeback and marked for immediate reclaim at the tail of
+	 * the LRU.
+	 */
+	if (current_is_kswapd())
+		return;
+
+	/* Throttle if making no progress at high prioities. */
+	if (sc->priority < DEF_PRIORITY - 2)
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
+}
+
 /*
  * This is the direct reclaim path, for page-allocating processes.  We only
  * try to reclaim pages from zones which will satisfy the caller's allocation
@@ -3356,6 +3476,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			continue;
 		last_pgdat = zone->zone_pgdat;
 		shrink_node(zone->zone_pgdat, sc);
+		consider_reclaim_throttle(zone->zone_pgdat, sc);
 	}
 
 	/*
@@ -4302,6 +4423,7 @@ static int kswapd(void *p)
 
 	WRITE_ONCE(pgdat->kswapd_order, 0);
 	WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
+	atomic_set(&pgdat->nr_writeback_throttled, 0);
 	for ( ; ; ) {
 		bool ret;