From 898b53827b69340d1dcb976be6fe5e2b8745f870 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Sat, 30 Nov 2019 17:55:49 -0800
Subject: [PATCH] mm: vmscan: split shrink_node() into node part and memcgs
 part

References: bnc#1155780 (VM/FS functional and performance backports)
Patch-mainline: v5.5-rc1
Git-commit: 0f6a5cff43d3bcd6aa54c9af267737249d02aa21

This function is getting long and unwieldy, split out the memcg bits.

The updated shrink_node() handles the generic (node) reclaim aspects:
  - global vmpressure notifications
  - writeback and congestion throttling
  - reclaim/compaction management
  - kswapd giving up on unreclaimable nodes

It then calls a new shrink_node_memcgs() which handles cgroup specifics:
  - the cgroup tree traversal
  - memory.low considerations
  - per-cgroup slab shrinking callbacks
  - per-cgroup vmpressure notifications

[hannes@cmpxchg.org: rename "root" to "target_memcg", per Roman]
  Link: http://lkml.kernel.org/r/20191025143640.GA386981@cmpxchg.org
Link: http://lkml.kernel.org/r/20191022144803.302233-8-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 41 +++++++++++++++++++++++++----------------
 1 file changed, 25 insertions(+), 16 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index addd1bec50c7..2869940b1ebe 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2669,26 +2669,18 @@ static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
 		(memcg && memcg_congested(pgdat, memcg));
 }
 
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 {
-	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	unsigned long nr_reclaimed, nr_scanned;
-	bool reclaimable = false;
+	struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
 	struct mem_cgroup *memcg;
-again:
-	memset(&sc->nr, 0, sizeof(sc->nr));
 
-	nr_reclaimed = sc->nr_reclaimed;
-	nr_scanned = sc->nr_scanned;
-
-	memcg = mem_cgroup_iter(root, NULL, NULL);
+	memcg = mem_cgroup_iter(target_memcg, NULL, NULL);
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 		unsigned long reclaimed;
 		unsigned long scanned;
 
-		switch (mem_cgroup_protected(root, memcg)) {
+		switch (mem_cgroup_protected(target_memcg, memcg)) {
 		case MEMCG_PROT_MIN:
 			/*
 			 * Hard protection.
@@ -2732,7 +2724,23 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			   sc->nr_scanned - scanned,
 			   sc->nr_reclaimed - reclaimed);
 
-	} while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
+	} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
+}
+
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+{
+	struct reclaim_state *reclaim_state = current->reclaim_state;
+	struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
+	unsigned long nr_reclaimed, nr_scanned;
+	bool reclaimable = false;
+
+again:
+	memset(&sc->nr, 0, sizeof(sc->nr));
+
+	nr_reclaimed = sc->nr_reclaimed;
+	nr_scanned = sc->nr_scanned;
+
+	shrink_node_memcgs(pgdat, sc);
 
 	if (reclaim_state) {
 		sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -2740,7 +2748,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	}
 
 	/* Record the subtree's reclaim efficiency */
-	vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+	vmpressure(sc->gfp_mask, target_memcg, true,
 		   sc->nr_scanned - nr_scanned,
 		   sc->nr_reclaimed - nr_reclaimed);
 
@@ -2796,7 +2804,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	 */
 	if (cgroup_reclaim(sc) && writeback_throttling_sane(sc) &&
 	    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
-		set_memcg_congestion(pgdat, root, true);
+		set_memcg_congestion(pgdat, target_memcg, true);
 
 	/*
 	 * Stall direct reclaim for IO completions if underlying BDIs
@@ -2805,7 +2813,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	 * the LRU too quickly.
 	 */
 	if (!sc->hibernation_mode && !current_is_kswapd() &&
-	    current_may_throttle() && pgdat_memcg_congested(pgdat, root))
+	    current_may_throttle() &&
+	    pgdat_memcg_congested(pgdat, target_memcg))
 		wait_iff_congested(BLK_RW_ASYNC, HZ/10);
 
 	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,