mm/lru: replace pgdat lru_lock with lruvec lock

This patch moves per node lru_lock into lruvec, thus bring a lru_lock for
each of memcg per node.  So on a large machine, each of memcg don't have
to suffer from per node pgdat->lru_lock competition.  They could go fast
with their self lru_lock.

After move memcg charge before lru inserting, page isolation could
serialize page's memcg, then per memcg lruvec lock is stable and could
replace per node lru lock.

In isolate_migratepages_block(), compact_unlock_should_abort and
lock_page_lruvec_irqsave are open coded to work with compact_control.
Also add a debug func in locking which may give some clues if there are
sth out of hands.

Daniel Jordan's testing show 62% improvement on modified readtwice case on
his 2P * 10 core * 2 HT broadwell box.
https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/

Hugh Dickins helped on the patch polish, thanks!

[alex.shi@linux.alibaba.com: fix comment typo]
  Link: https://lkml.kernel.org/r/5b085715-292a-4b43-50b3-d73dc90d1de5@linux.alibaba.com
[alex.shi@linux.alibaba.com: use page_memcg()]
  Link: https://lkml.kernel.org/r/5a4c2b72-7ee8-2478-fc0e-85eb83aafec4@linux.alibaba.com

Link: https://lkml.kernel.org/r/1604566549-62481-18-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rong Chen <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 25 insertions, 30 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index cf99e66e7f33..b27b5dba3fdd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1764,14 +1764,12 @@ int isolate_lru_page(struct page *page)
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
 	if (TestClearPageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 
 		get_page(page);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		spin_lock_irq(&pgdat->lru_lock);
+		lruvec = lock_page_lruvec_irq(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
-		spin_unlock_irq(&pgdat->lru_lock);
+		unlock_page_lruvec_irq(lruvec);
 		ret = 0;
 	}
 
@@ -1838,7 +1836,6 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 						     struct list_head *list)
 {
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
 	struct page *page;
@@ -1849,9 +1846,9 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&pgdat->lru_lock);
+			spin_unlock_irq(&lruvec->lru_lock);
 			putback_lru_page(page);
-			spin_lock_irq(&pgdat->lru_lock);
+			spin_lock_irq(&lruvec->lru_lock);
 			continue;
 		}
 
@@ -1873,9 +1870,9 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 			__ClearPageActive(page);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&pgdat->lru_lock);
+				spin_unlock_irq(&lruvec->lru_lock);
 				destroy_compound_page(page);
-				spin_lock_irq(&pgdat->lru_lock);
+				spin_lock_irq(&lruvec->lru_lock);
 			} else
 				list_add(&page->lru, &pages_to_free);
 
@@ -1952,7 +1949,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
 				     &nr_scanned, sc, lru);
@@ -1964,14 +1961,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
 	__count_vm_events(PGSCAN_ANON + file, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	if (nr_taken == 0)
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 	move_pages_to_lru(lruvec, &page_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
@@ -1980,7 +1977,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		__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(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
@@ -2033,7 +2030,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, lru);
@@ -2044,7 +2041,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		__count_vm_events(PGREFILL, nr_scanned);
 	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
@@ -2090,7 +2087,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_activate = move_pages_to_lru(lruvec, &l_active);
 	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
@@ -2101,7 +2098,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
@@ -2689,10 +2686,10 @@ again:
 	/*
 	 * Determine the scan balance between anon and file LRUs.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&target_lruvec->lru_lock);
 	sc->anon_cost = target_lruvec->anon_cost;
 	sc->file_cost = target_lruvec->file_cost;
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&target_lruvec->lru_lock);
 
 	/*
 	 * Target desirable inactive:active list ratios for the anon
@@ -4268,16 +4265,15 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
  */
 void check_move_unevictable_pages(struct pagevec *pvec)
 {
-	struct lruvec *lruvec;
-	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec = NULL;
 	int pgscanned = 0;
 	int pgrescued = 0;
 	int i;
 
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
 		int nr_pages;
+		struct lruvec *new_lruvec;
 
 		if (PageTransTail(page))
 			continue;
@@ -4289,13 +4285,12 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		if (!TestClearPageLRU(page))
 			continue;
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irq(&pgdat->lru_lock);
-			pgdat = pagepgdat;
-			spin_lock_irq(&pgdat->lru_lock);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irq(lruvec);
+			lruvec = lock_page_lruvec_irq(page);
 		}
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
@@ -4309,10 +4304,10 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		SetPageLRU(page);
 	}
 
-	if (pgdat) {
+	if (lruvec) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
-		spin_unlock_irq(&pgdat->lru_lock);
+		unlock_page_lruvec_irq(lruvec);
 	} else if (pgscanned) {
 		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 	}