memcg: Revert "memcg: add memory.vmscan_stat"

Revert the post-3.0 commit 82f9d486e59f5 ("memcg: add
memory.vmscan_stat").

The implementation of per-memcg reclaim statistics violates how memcg
hierarchies usually behave: hierarchically.

The reclaim statistics are accounted to child memcgs and the parent
hitting the limit, but not to hierarchy levels in between.  Usually,
hierarchical statistics are perfectly recursive, with each level
representing the sum of itself and all its children.

Since this exports statistics to userspace, this may lead to confusion
and problems with changing things after the release, so revert it now,
we can try again later.

Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 34 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index e49bcb6..b55699c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -105,7 +105,6 @@ struct scan_control {
 
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
-	struct memcg_scanrecord *memcg_record;
 
 	/*
 	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
@@ -1349,8 +1348,6 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc,
 			int file = is_file_lru(lru);
 			int numpages = hpage_nr_pages(page);
 			reclaim_stat->recent_rotated[file] += numpages;
-			if (!scanning_global_lru(sc))
-				sc->memcg_record->nr_rotated[file] += numpages;
 		}
 		if (!pagevec_add(&pvec, page)) {
 			spin_unlock_irq(&zone->lru_lock);
@@ -1394,10 +1391,6 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone,
 
 	reclaim_stat->recent_scanned[0] += *nr_anon;
 	reclaim_stat->recent_scanned[1] += *nr_file;
-	if (!scanning_global_lru(sc)) {
-		sc->memcg_record->nr_scanned[0] += *nr_anon;
-		sc->memcg_record->nr_scanned[1] += *nr_file;
-	}
 }
 
 /*
@@ -1511,9 +1504,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 		nr_reclaimed += shrink_page_list(&page_list, zone, sc);
 	}
 
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_freed[file] += nr_reclaimed;
-
 	local_irq_disable();
 	if (current_is_kswapd())
 		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
@@ -1613,8 +1603,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	}
 
 	reclaim_stat->recent_scanned[file] += nr_taken;
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_scanned[file] += nr_taken;
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	if (file)
@@ -1666,8 +1654,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * get_scan_ratio.
 	 */
 	reclaim_stat->recent_rotated[file] += nr_rotated;
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_rotated[file] += nr_rotated;
 
 	move_active_pages_to_lru(zone, &l_active,
 						LRU_ACTIVE + file * LRU_FILE);
@@ -2265,10 +2251,9 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
-					gfp_t gfp_mask, bool noswap,
-					struct zone *zone,
-					struct memcg_scanrecord *rec,
-					unsigned long *scanned)
+						gfp_t gfp_mask, bool noswap,
+						struct zone *zone,
+						unsigned long *nr_scanned)
 {
 	struct scan_control sc = {
 		.nr_scanned = 0,
@@ -2278,9 +2263,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.may_swap = !noswap,
 		.order = 0,
 		.mem_cgroup = mem,
-		.memcg_record = rec,
 	};
-	ktime_t start, end;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2289,7 +2272,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						      sc.may_writepage,
 						      sc.gfp_mask);
 
-	start = ktime_get();
 	/*
 	 * NOTE: Although we can get the priority field, using it
 	 * here is not a good idea, since it limits the pages we can scan.
@@ -2298,25 +2280,19 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 	 * the priority and make it zero.
 	 */
 	shrink_zone(0, zone, &sc);
-	end = ktime_get();
-
-	if (rec)
-		rec->elapsed += ktime_to_ns(ktime_sub(end, start));
-	*scanned = sc.nr_scanned;
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
+	*nr_scanned = sc.nr_scanned;
 	return sc.nr_reclaimed;
 }
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					   gfp_t gfp_mask,
-					   bool noswap,
-					   struct memcg_scanrecord *rec)
+					   bool noswap)
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
-	ktime_t start, end;
 	int nid;
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
@@ -2325,7 +2301,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.order = 0,
 		.mem_cgroup = mem_cont,
-		.memcg_record = rec,
 		.nodemask = NULL, /* we don't care the placement */
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
@@ -2334,7 +2309,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.gfp_mask = sc.gfp_mask,
 	};
 
-	start = ktime_get();
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
 	 * take care of from where we get pages. So the node where we start the
@@ -2349,9 +2323,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					    sc.gfp_mask);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
-	end = ktime_get();
-	if (rec)
-		rec->elapsed += ktime_to_ns(ktime_sub(end, start));
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);