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, 36 insertions, 20 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 50938e66083c..e5acb9714436 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -804,7 +804,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
-	bool locked = false;
+	struct lruvec *locked = NULL;
 	struct page *page = NULL, *valid_page = NULL;
 	unsigned long start_pfn = low_pfn;
 	bool skip_on_failure = false;
@@ -868,11 +868,20 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * contention, to give chance to IRQs. Abort completely if
 		 * a fatal signal is pending.
 		 */
-		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(&pgdat->lru_lock,
-					    flags, &locked, cc)) {
-			low_pfn = 0;
-			goto fatal_pending;
+		if (!(low_pfn % SWAP_CLUSTER_MAX)) {
+			if (locked) {
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
+			}
+
+			if (fatal_signal_pending(current)) {
+				cc->contended = true;
+
+				low_pfn = 0;
+				goto fatal_pending;
+			}
+
+			cond_resched();
 		}
 
 		if (!pfn_valid_within(low_pfn))
@@ -944,9 +953,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(&pgdat->lru_lock,
-									flags);
-					locked = false;
+					unlock_page_lruvec_irqrestore(locked, flags);
+					locked = NULL;
 				}
 
 				if (!isolate_movable_page(page, isolate_mode))
@@ -987,10 +995,19 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!TestClearPageLRU(page))
 			goto isolate_fail_put;
 
+		rcu_read_lock();
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+
 		/* If we already hold the lock, we can skip some rechecking */
-		if (!locked) {
-			locked = compact_lock_irqsave(&pgdat->lru_lock,
-								&flags, cc);
+		if (lruvec != locked) {
+			if (locked)
+				unlock_page_lruvec_irqrestore(locked, flags);
+
+			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
+			locked = lruvec;
+			rcu_read_unlock();
+
+			lruvec_memcg_debug(lruvec, page);
 
 			/* Try get exclusive access under lock */
 			if (!skip_updated) {
@@ -1009,9 +1026,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				SetPageLRU(page);
 				goto isolate_fail_put;
 			}
-		}
-
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		} else
+			rcu_read_unlock();
 
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
@@ -1045,8 +1061,8 @@ isolate_success:
 isolate_fail_put:
 		/* Avoid potential deadlock in freeing page under lru_lock */
 		if (locked) {
-			spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			locked = false;
+			unlock_page_lruvec_irqrestore(locked, flags);
+			locked = NULL;
 		}
 		put_page(page);
 
@@ -1061,8 +1077,8 @@ isolate_fail:
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-				locked = false;
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
 			}
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
@@ -1090,7 +1106,7 @@ isolate_fail:
 
 isolate_abort:
 	if (locked)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(locked, flags);
 	if (page) {
 		SetPageLRU(page);
 		put_page(page);