mm/lru: introduce TestClearPageLRU()

Currently lru_lock still guards both lru list and page's lru bit, that's
ok. but if we want to use specific lruvec lock on the page, we need to
pin down the page's lruvec/memcg during locking. Just taking lruvec lock
first may be undermined by the page's memcg charge/migration. To fix this
problem, we will clear the lru bit out of locking and use it as pin down
action to block the page isolation in memcg changing.

So now a standard steps of page isolation is following:
1, get_page(); #pin the page avoid to be free
2, TestClearPageLRU(); #block other isolation like memcg change
3, spin_lock on lru_lock; #serialize lru list access
4, delete page from lru list;

This patch start with the first part: TestClearPageLRU, which combines
PageLRU check and ClearPageLRU into a macro func TestClearPageLRU. This
function will be used as page isolation precondition to prevent other
isolations some where else. Then there are may !PageLRU page on lru list,
need to remove BUG() checking accordingly.

There 2 rules for lru bit now:
1, the lru bit still indicate if a page on lru list, just in some
temporary moment(isolating), the page may have no lru bit when
it's on lru list. but the page still must be on lru list when the
lru bit set.
2, have to remove lru bit before delete it from lru list.

As Andrew Morton mentioned this change would dirty cacheline for a page
which isn't on the LRU. But the loss would be acceptable in Rong Chen
<[e-mail]> report:
https://lore.kernel.org/lkml/20200304090301.GB5972@shao2-debian/

Link: https://lkml.kernel.org/r/[e-mail]
Suggested-by: Johannes Weiner <[e-mail]>
Signed-off-by: Alex Shi <[e-mail]>
Acked-by: Hugh Dickins <[e-mail]>
Acked-by: Johannes Weiner <[e-mail]>
Acked-by: Vlastimil Babka <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Vladimir Davydov <[e-mail]>
Cc: Alexander Duyck <[e-mail]>
Cc: Andrea Arcangeli <[e-mail]>
Cc: Andrey Ryabinin <[e-mail]>
Cc: Daniel Jordan <[e-mail]>
Cc: "Huang, Ying" <[e-mail]>
Cc: Jann Horn <[e-mail]>
Cc: Joonsoo Kim <[e-mail]>
Cc: Kirill A. Shutemov <[e-mail]>
Cc: Kirill A. Shutemov <[e-mail]>
Cc: Konstantin Khlebnikov <[e-mail]>
Cc: Matthew Wilcox (Oracle) <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Mika Penttilä <[e-mail]>
Cc: Minchan Kim <[e-mail]>
Cc: Shakeel Butt <[e-mail]>
Cc: Tejun Heo <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Wei Yang <[e-mail]>
Cc: Yang Shi <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/page-flags.h

···
 PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
 	__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
 PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
+	TESTCLEARFLAG(LRU, lru, PF_HEAD)
 PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
 	TESTCLEARFLAG(Active, active, PF_HEAD)
 PAGEFLAG(Workingset, workingset, PF_HEAD)

mm/mlock.c

···
 			 * We already have pin from follow_page_mask()
 			 * so we can spare the get_page() here.
 			 */
-			if (PageLRU(page)) {
+			if (TestClearPageLRU(page)) {
 				struct lruvec *lruvec;
 
-				ClearPageLRU(page);
 				lruvec = mem_cgroup_page_lruvec(page,
 							page_pgdat(page));
 				del_page_from_lru_list(page, lruvec,

mm/vmscan.c

···
  */
 int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 {
-	int ret = -EINVAL;
+	int ret = -EBUSY;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
···
 	/* Compaction should not handle unevictable pages but CMA can do so */
 	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
 		return ret;
-
-	ret = -EBUSY;
 
 	/*
 	 * To minimise LRU disruption, the caller can indicate that it only
···
 		 * sure the page is not being freed elsewhere -- the
 		 * page release code relies on it.
 		 */
-		ClearPageLRU(page);
-		ret = 0;
+		if (TestClearPageLRU(page))
+			ret = 0;
+		else
+			put_page(page);
 	}
 
 	return ret;
···
 
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
-
-		VM_BUG_ON_PAGE(!PageLRU(page), page);
 
 		nr_pages = compound_nr(page);
 		total_scan += nr_pages;
···
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
-	if (PageLRU(page)) {
+	if (TestClearPageLRU(page)) {
 		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 
-		spin_lock_irq(&pgdat->lru_lock);
+		get_page(page);
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		if (PageLRU(page)) {
-			int lru = page_lru(page);
-			get_page(page);
-			ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, lru);
-			ret = 0;
-		}
+		spin_lock_irq(&pgdat->lru_lock);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
 		spin_unlock_irq(&pgdat->lru_lock);
+		ret = 0;
 	}
+
 	return ret;
 }
 
···
 		nr_pages = thp_nr_pages(page);
 		pgscanned += nr_pages;
 
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
+
 		if (pagepgdat != pgdat) {
 			if (pgdat)
 				spin_unlock_irq(&pgdat->lru_lock);
···
 		}
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
-		if (!PageLRU(page) || !PageUnevictable(page))
-			continue;
-
-		if (page_evictable(page)) {
+		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
 
 			VM_BUG_ON_PAGE(PageActive(page), page);
···
 			add_page_to_lru_list(page, lruvec, lru);
 			pgrescued += nr_pages;
 		}
+		SetPageLRU(page);
 	}
 
 	if (pgdat) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 		spin_unlock_irq(&pgdat->lru_lock);
+	} else if (pgscanned) {
+		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 	}
 }
 EXPORT_SYMBOL_GPL(check_move_unevictable_pages);