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>

2 files changed, 11 insertions, 200 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ebd1e86..3508777 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -204,50 +204,6 @@ struct mem_cgroup_eventfd_list {
 static void mem_cgroup_threshold(struct mem_cgroup *mem);
 static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
 
-enum {
-	SCAN_BY_LIMIT,
-	SCAN_BY_SYSTEM,
-	NR_SCAN_CONTEXT,
-	SCAN_BY_SHRINK,	/* not recorded now */
-};
-
-enum {
-	SCAN,
-	SCAN_ANON,
-	SCAN_FILE,
-	ROTATE,
-	ROTATE_ANON,
-	ROTATE_FILE,
-	FREED,
-	FREED_ANON,
-	FREED_FILE,
-	ELAPSED,
-	NR_SCANSTATS,
-};
-
-struct scanstat {
-	spinlock_t	lock;
-	unsigned long	stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
-	unsigned long	rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
-};
-
-const char *scanstat_string[NR_SCANSTATS] = {
-	"scanned_pages",
-	"scanned_anon_pages",
-	"scanned_file_pages",
-	"rotated_pages",
-	"rotated_anon_pages",
-	"rotated_file_pages",
-	"freed_pages",
-	"freed_anon_pages",
-	"freed_file_pages",
-	"elapsed_ns",
-};
-#define SCANSTAT_WORD_LIMIT	"_by_limit"
-#define SCANSTAT_WORD_SYSTEM	"_by_system"
-#define SCANSTAT_WORD_HIERARCHY	"_under_hierarchy"
-
-
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -313,8 +269,7 @@ struct mem_cgroup {
 
 	/* For oom notifier event fd */
 	struct list_head oom_notify;
-	/* For recording LRU-scan statistics */
-	struct scanstat scanstat;
+
 	/*
 	 * Should we move charges of a task when a task is moved into this
 	 * mem_cgroup ? And what type of charges should we move ?
@@ -1678,44 +1633,6 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
 }
 #endif
 
-static void __mem_cgroup_record_scanstat(unsigned long *stats,
-			   struct memcg_scanrecord *rec)
-{
-
-	stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1];
-	stats[SCAN_ANON] += rec->nr_scanned[0];
-	stats[SCAN_FILE] += rec->nr_scanned[1];
-
-	stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1];
-	stats[ROTATE_ANON] += rec->nr_rotated[0];
-	stats[ROTATE_FILE] += rec->nr_rotated[1];
-
-	stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1];
-	stats[FREED_ANON] += rec->nr_freed[0];
-	stats[FREED_FILE] += rec->nr_freed[1];
-
-	stats[ELAPSED] += rec->elapsed;
-}
-
-static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec)
-{
-	struct mem_cgroup *mem;
-	int context = rec->context;
-
-	if (context >= NR_SCAN_CONTEXT)
-		return;
-
-	mem = rec->mem;
-	spin_lock(&mem->scanstat.lock);
-	__mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec);
-	spin_unlock(&mem->scanstat.lock);
-
-	mem = rec->root;
-	spin_lock(&mem->scanstat.lock);
-	__mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec);
-	spin_unlock(&mem->scanstat.lock);
-}
-
 /*
  * Scan the hierarchy if needed to reclaim memory. We remember the last child
  * we reclaimed from, so that we don't end up penalizing one child extensively
@@ -1740,9 +1657,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
 	bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
 	bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
-	struct memcg_scanrecord rec;
 	unsigned long excess;
-	unsigned long scanned;
+	unsigned long nr_scanned;
 
 	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
 
@@ -1750,15 +1666,6 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	if (!check_soft && !shrink && root_mem->memsw_is_minimum)
 		noswap = true;
 
-	if (shrink)
-		rec.context = SCAN_BY_SHRINK;
-	else if (check_soft)
-		rec.context = SCAN_BY_SYSTEM;
-	else
-		rec.context = SCAN_BY_LIMIT;
-
-	rec.root = root_mem;
-
 	while (1) {
 		victim = mem_cgroup_select_victim(root_mem);
 		if (victim == root_mem) {
@@ -1799,23 +1706,14 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 			css_put(&victim->css);
 			continue;
 		}
-		rec.mem = victim;
-		rec.nr_scanned[0] = 0;
-		rec.nr_scanned[1] = 0;
-		rec.nr_rotated[0] = 0;
-		rec.nr_rotated[1] = 0;
-		rec.nr_freed[0] = 0;
-		rec.nr_freed[1] = 0;
-		rec.elapsed = 0;
 		/* we use swappiness of local cgroup */
 		if (check_soft) {
 			ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
-				noswap, zone, &rec, &scanned);
-			*total_scanned += scanned;
+				noswap, zone, &nr_scanned);
+			*total_scanned += nr_scanned;
 		} else
 			ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
-						noswap, &rec);
-		mem_cgroup_record_scanstat(&rec);
+						noswap);
 		css_put(&victim->css);
 		/*
 		 * At shrinking usage, we can't check we should stop here or
@@ -3854,18 +3752,14 @@ try_to_free:
 	/* try to free all pages in this cgroup */
 	shrink = 1;
 	while (nr_retries && mem->res.usage > 0) {
-		struct memcg_scanrecord rec;
 		int progress;
 
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
 		}
-		rec.context = SCAN_BY_SHRINK;
-		rec.mem = mem;
-		rec.root = mem;
 		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
-						false, &rec);
+						false);
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
@@ -4709,54 +4603,6 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 }
 #endif /* CONFIG_NUMA */
 
-static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp,
-				struct cftype *cft,
-				struct cgroup_map_cb *cb)
-{
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
-	char string[64];
-	int i;
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_LIMIT);
-		cb->fill(cb, string,  mem->scanstat.stats[SCAN_BY_LIMIT][i]);
-	}
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_SYSTEM);
-		cb->fill(cb, string,  mem->scanstat.stats[SCAN_BY_SYSTEM][i]);
-	}
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_LIMIT);
-		strcat(string, SCANSTAT_WORD_HIERARCHY);
-		cb->fill(cb, string,  mem->scanstat.rootstats[SCAN_BY_LIMIT][i]);
-	}
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_SYSTEM);
-		strcat(string, SCANSTAT_WORD_HIERARCHY);
-		cb->fill(cb, string,  mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]);
-	}
-	return 0;
-}
-
-static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp,
-				unsigned int event)
-{
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
-
-	spin_lock(&mem->scanstat.lock);
-	memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats));
-	memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats));
-	spin_unlock(&mem->scanstat.lock);
-	return 0;
-}
-
-
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -4827,11 +4673,6 @@ static struct cftype mem_cgroup_files[] = {
 		.mode = S_IRUGO,
 	},
 #endif
-	{
-		.name = "vmscan_stat",
-		.read_map = mem_cgroup_vmscan_stat_read,
-		.trigger = mem_cgroup_reset_vmscan_stat,
-	},
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
@@ -5095,7 +4936,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	atomic_set(&mem->refcnt, 1);
 	mem->move_charge_at_immigrate = 0;
 	mutex_init(&mem->thresholds_lock);
-	spin_lock_init(&mem->scanstat.lock);
 	return &mem->css;
 free_out:
 	__mem_cgroup_free(mem);
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);