1 files changed, 28 insertions, 110 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 59b14e0d696c..499fa86e754a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -56,6 +56,7 @@
 
 #include <linux/swapops.h>
 #include <linux/balloon_compaction.h>
+#include <linux/sched/sysctl.h>
 
 #include "internal.h"
 
@@ -989,17 +990,6 @@ static inline int is_page_cache_freeable(struct page *page)
 	return page_count(page) - page_has_private(page) == 1 + page_cache_pins;
 }
 
-static int may_write_to_inode(struct inode *inode)
-{
-	if (current->flags & PF_SWAPWRITE)
-		return 1;
-	if (!inode_write_congested(inode))
-		return 1;
-	if (inode_to_bdi(inode) == current->backing_dev_info)
-		return 1;
-	return 0;
-}
-
 /*
  * We detected a synchronous write error writing a page out.  Probably
  * -ENOSPC.  We need to propagate that into the address_space for a subsequent
@@ -1201,8 +1191,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_inode(mapping->host))
-		return PAGE_KEEP;
 
 	if (clear_page_dirty_for_io(page)) {
 		int res;
@@ -1398,7 +1386,7 @@ static enum page_references page_check_references(struct page *page,
 		/*
 		 * All mapped pages start out with page table
 		 * references from the instantiating fault, so we need
-		 * to look twice if a mapped file page is used more
+		 * to look twice if a mapped file/anon page is used more
 		 * than once.
 		 *
 		 * Mark it and spare it for another trip around the
@@ -1578,9 +1566,7 @@ retry:
 		 * end of the LRU a second time.
 		 */
 		mapping = page_mapping(page);
-		if (((dirty || writeback) && mapping &&
-		     inode_write_congested(mapping->host)) ||
-		    (writeback && PageReclaim(page)))
+		if (writeback && PageReclaim(page))
 			stat->nr_congested++;
 
 		/*
@@ -2014,69 +2000,6 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 }
 
 /*
- * Attempt to remove the specified page from its LRU.  Only take this page
- * if it is of the appropriate PageActive status.  Pages which are being
- * freed elsewhere are also ignored.
- *
- * page:	page to consider
- * mode:	one of the LRU isolation modes defined above
- *
- * returns true on success, false on failure.
- */
-bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
-{
-	/* Only take pages on the LRU. */
-	if (!PageLRU(page))
-		return false;
-
-	/* Compaction should not handle unevictable pages but CMA can do so */
-	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
-		return false;
-
-	/*
-	 * To minimise LRU disruption, the caller can indicate that it only
-	 * wants to isolate pages it will be able to operate on without
-	 * blocking - clean pages for the most part.
-	 *
-	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
-	 * that it is possible to migrate without blocking
-	 */
-	if (mode & ISOLATE_ASYNC_MIGRATE) {
-		/* All the caller can do on PageWriteback is block */
-		if (PageWriteback(page))
-			return false;
-
-		if (PageDirty(page)) {
-			struct address_space *mapping;
-			bool migrate_dirty;
-
-			/*
-			 * Only pages without mappings or that have a
-			 * ->migratepage callback are possible to migrate
-			 * without blocking. However, we can be racing with
-			 * truncation so it's necessary to lock the page
-			 * to stabilise the mapping as truncation holds
-			 * the page lock until after the page is removed
-			 * from the page cache.
-			 */
-			if (!trylock_page(page))
-				return false;
-
-			mapping = page_mapping(page);
-			migrate_dirty = !mapping || mapping->a_ops->migratepage;
-			unlock_page(page);
-			if (!migrate_dirty)
-				return false;
-		}
-	}
-
-	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
-		return false;
-
-	return true;
-}
-
-/*
  * Update LRU sizes after isolating pages. The LRU size updates must
  * be complete before mem_cgroup_update_lru_size due to a sanity check.
  */
@@ -2127,11 +2050,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long skipped = 0;
 	unsigned long scan, total_scan, nr_pages;
 	LIST_HEAD(pages_skipped);
-	isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED);
 
 	total_scan = 0;
 	scan = 0;
 	while (scan < nr_to_scan && !list_empty(src)) {
+		struct list_head *move_to = src;
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -2141,9 +2064,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		total_scan += nr_pages;
 
 		if (page_zonenum(page) > sc->reclaim_idx) {
-			list_move(&page->lru, &pages_skipped);
 			nr_skipped[page_zonenum(page)] += nr_pages;
-			continue;
+			move_to = &pages_skipped;
+			goto move;
 		}
 
 		/*
@@ -2151,37 +2074,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * return with no isolated pages if the LRU mostly contains
 		 * ineligible pages.  This causes the VM to not reclaim any
 		 * pages, triggering a premature OOM.
-		 *
-		 * Account all tail pages of THP.  This would not cause
-		 * premature OOM since __isolate_lru_page() returns -EBUSY
-		 * only when the page is being freed somewhere else.
+		 * Account all tail pages of THP.
 		 */
 		scan += nr_pages;
-		if (!__isolate_lru_page_prepare(page, mode)) {
-			/* It is being freed elsewhere */
-			list_move(&page->lru, src);
-			continue;
-		}
+
+		if (!PageLRU(page))
+			goto move;
+		if (!sc->may_unmap && page_mapped(page))
+			goto move;
+
 		/*
 		 * Be careful not to clear PageLRU until after we're
 		 * sure the page is not being freed elsewhere -- the
 		 * page release code relies on it.
 		 */
-		if (unlikely(!get_page_unless_zero(page))) {
-			list_move(&page->lru, src);
-			continue;
-		}
+		if (unlikely(!get_page_unless_zero(page)))
+			goto move;
 
 		if (!TestClearPageLRU(page)) {
 			/* Another thread is already isolating this page */
 			put_page(page);
-			list_move(&page->lru, src);
-			continue;
+			goto move;
 		}
 
 		nr_taken += nr_pages;
 		nr_zone_taken[page_zonenum(page)] += nr_pages;
-		list_move(&page->lru, dst);
+		move_to = dst;
+move:
+		list_move(&page->lru, move_to);
 	}
 
 	/*
@@ -2205,7 +2125,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	}
 	*nr_scanned = total_scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
-				    total_scan, skipped, nr_taken, mode, lru);
+				    total_scan, skipped, nr_taken,
+				    sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru);
 	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }
@@ -2379,9 +2300,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
  */
 static int current_may_throttle(void)
 {
-	return !(current->flags & PF_LOCAL_THROTTLE) ||
-		current->backing_dev_info == NULL ||
-		bdi_write_congested(current->backing_dev_info);
+	return !(current->flags & PF_LOCAL_THROTTLE);
 }
 
 /*
@@ -3977,7 +3896,10 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 		if (!managed_zone(zone))
 			continue;
 
-		mark = high_wmark_pages(zone);
+		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
+			mark = wmark_pages(zone, WMARK_PROMO);
+		else
+			mark = high_wmark_pages(zone);
 		if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx))
 			return true;
 	}
@@ -4474,7 +4396,7 @@ static int kswapd(void *p)
 	 * us from recursively trying to free more memory as we're
 	 * trying to free the first piece of memory in the first place).
 	 */
-	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+	tsk->flags |= PF_MEMALLOC | PF_KSWAPD;
 	set_freezable();
 
 	WRITE_ONCE(pgdat->kswapd_order, 0);
@@ -4525,7 +4447,7 @@ kswapd_try_sleep:
 			goto kswapd_try_sleep;
 	}
 
-	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
+	tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);
 
 	return 0;
 }
@@ -4766,11 +4688,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	fs_reclaim_acquire(sc.gfp_mask);
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
-	 * and we also need to be able to write out pages for RECLAIM_WRITE
-	 * and RECLAIM_UNMAP.
 	 */
 	noreclaim_flag = memalloc_noreclaim_save();
-	p->flags |= PF_SWAPWRITE;
 	set_task_reclaim_state(p, &sc.reclaim_state);
 
 	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
@@ -4784,7 +4703,6 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	}
 
 	set_task_reclaim_state(p, NULL);
-	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);
 	psi_memstall_leave(&pflags);