lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 15 May 2019 12:55:35 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Johannes Weiner <hannes@...xchg.org>,
        Shakeel Butt <shakeelb@...gle.com>,
        Roman Gushchin <guro@...com>, Michal Hocko <mhocko@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 4.19 044/113] mm: fix inactive list balancing between NUMA nodes and cgroups

[ Upstream commit 3b991208b897f52507168374033771a984b947b1 ]

During !CONFIG_CGROUP reclaim, we expand the inactive list size if it's
thrashing on the node that is about to be reclaimed.  But when cgroups
are enabled, we suddenly ignore the node scope and use the cgroup scope
only.  The result is that pressure bleeds between NUMA nodes depending
on whether cgroups are merely compiled into Linux.  This behavioral
difference is unexpected and undesirable.

When the refault adaptivity of the inactive list was first introduced,
there were no statistics at the lruvec level - the intersection of node
and memcg - so it was better than nothing.

But now that we have that infrastructure, use lruvec_page_state() to
make the list balancing decision always NUMA aware.

[hannes@...xchg.org: fix bisection hole]
  Link: http://lkml.kernel.org/r/20190417155241.GB23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412144438.2645-1-hannes@cmpxchg.org
Fixes: 2a2e48854d70 ("mm: vmscan: fix IO/refault regression in cache workingset transition")
Signed-off-by: Johannes Weiner <hannes@...xchg.org>
Reviewed-by: Shakeel Butt <shakeelb@...gle.com>
Cc: Roman Gushchin <guro@...com>
Cc: Michal Hocko <mhocko@...nel.org>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 mm/vmscan.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3830066018c15..ee545d1e9894d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2190,7 +2190,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-				 struct mem_cgroup *memcg,
 				 struct scan_control *sc, bool actual_reclaim)
 {
 	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
@@ -2211,16 +2210,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
 	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
-	if (memcg)
-		refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-	else
-		refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 	/*
 	 * When refaults are being observed, it means a new workingset
 	 * is being established. Disable active list protection to get
 	 * rid of the stale workingset quickly.
 	 */
+	refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 	if (file && actual_reclaim && lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
@@ -2241,12 +2236,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 }
 
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
-				 struct lruvec *lruvec, struct mem_cgroup *memcg,
-				 struct scan_control *sc)
+				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru),
-					 memcg, sc, true))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2346,7 +2339,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			 * anonymous pages on the LRU in eligible zones.
 			 * Otherwise, the small LRU gets thrashed.
 			 */
-			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+			if (!inactive_list_is_low(lruvec, false, sc, false) &&
 			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
 					>> sc->priority) {
 				scan_balance = SCAN_ANON;
@@ -2364,7 +2357,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
 	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
@@ -2517,7 +2510,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 				nr[lru] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(lru, nr_to_scan,
-							    lruvec, memcg, sc);
+							    lruvec, sc);
 			}
 		}
 
@@ -2584,7 +2577,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2982,12 +2975,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
 		unsigned long refaults;
 		struct lruvec *lruvec;
 
-		if (memcg)
-			refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-		else
-			refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 		lruvec->refaults = refaults;
 	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
 }
@@ -3344,7 +3333,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
-- 
2.20.1



Powered by blists - more mailing lists