openwrt/target/linux/generic/backport-6.1/020-v6.3-03-UPSTREAM-mm-multi-gen-LRU-remove-eviction-fairness-s.patch

From 14f9a7a15f3d1af351f30e0438fd747b7ac253b0 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Wed, 21 Dec 2022 21:19:01 -0700
Subject: [PATCH 03/19] UPSTREAM: mm: multi-gen LRU: remove eviction fairness
 safeguard

Recall that the eviction consumes the oldest generation: first it
bucket-sorts folios whose gen counters were updated by the aging and
reclaims the rest; then it increments lrugen->min_seq.

The current eviction fairness safeguard for global reclaim has a
dilemma: when there are multiple eligible memcgs, should it continue
or stop upon meeting the reclaim goal? If it continues, it overshoots
and increases direct reclaim latency; if it stops, it loses fairness
between memcgs it has taken memory away from and those it has yet to.

With memcg LRU, the eviction, while ensuring eventual fairness, will
stop upon meeting its goal. Therefore the current eviction fairness
safeguard for global reclaim will not be needed.

Note that memcg LRU only applies to global reclaim. For memcg reclaim,
the eviction will continue, even if it is overshooting. This becomes
unconditional due to code simplification.

Link: https://lkml.kernel.org/r/20221222041905.2431096-4-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Bug: 274865848
(cherry picked from commit a579086c99ed70cc4bfc104348dbe3dd8f2787e6)
Change-Id: I08ac1b3c90e29cafd0566785aaa4bcdb5db7d22c
Signed-off-by: T.J. Mercier <tjmercier@google.com>
---
 mm/vmscan.c | 81 +++++++++++++++--------------------------------------
 1 file changed, 23 insertions(+), 58 deletions(-)

--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -448,6 +448,11 @@ static bool cgroup_reclaim(struct scan_c
 	return sc->target_mem_cgroup;
 }
 
+static bool global_reclaim(struct scan_control *sc)
+{
+	return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup);
+}
+
 /**
  * writeback_throttling_sane - is the usual dirty throttling mechanism available?
  * @sc: scan_control in question
@@ -498,6 +503,11 @@ static bool cgroup_reclaim(struct scan_c
 	return false;
 }
 
+static bool global_reclaim(struct scan_control *sc)
+{
+	return true;
+}
+
 static bool writeback_throttling_sane(struct scan_control *sc)
 {
 	return true;
@@ -4993,8 +5003,7 @@ static int isolate_folios(struct lruvec
 	return scanned;
 }
 
-static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-			bool *need_swapping)
+static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
 {
 	int type;
 	int scanned;
@@ -5083,9 +5092,6 @@ retry:
 		goto retry;
 	}
 
-	if (need_swapping && type == LRU_GEN_ANON)
-		*need_swapping = true;
-
 	return scanned;
 }
 
@@ -5124,67 +5130,26 @@ done:
 	return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
 }
 
-static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq,
-			      struct scan_control *sc, bool need_swapping)
+static unsigned long get_nr_to_reclaim(struct scan_control *sc)
 {
-	int i;
-	DEFINE_MAX_SEQ(lruvec);
-
-	if (!current_is_kswapd()) {
-		/* age each memcg at most once to ensure fairness */
-		if (max_seq - seq > 1)
-			return true;
-
-		/* over-swapping can increase allocation latency */
-		if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping)
-			return true;
-
-		/* give this thread a chance to exit and free its memory */
-		if (fatal_signal_pending(current)) {
-			sc->nr_reclaimed += MIN_LRU_BATCH;
-			return true;
-		}
-
-		if (cgroup_reclaim(sc))
-			return false;
-	} else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim)
-		return false;
-
-	/* keep scanning at low priorities to ensure fairness */
-	if (sc->priority > DEF_PRIORITY - 2)
-		return false;
-
-	/*
-	 * A minimum amount of work was done under global memory pressure. For
-	 * kswapd, it may be overshooting. For direct reclaim, the allocation
-	 * may succeed if all suitable zones are somewhat safe. In either case,
-	 * it's better to stop now, and restart later if necessary.
-	 */
-	for (i = 0; i <= sc->reclaim_idx; i++) {
-		unsigned long wmark;
-		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
-
-		if (!managed_zone(zone))
-			continue;
-
-		wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone);
-		if (wmark > zone_page_state(zone, NR_FREE_PAGES))
-			return false;
-	}
+	/* don't abort memcg reclaim to ensure fairness */
+	if (!global_reclaim(sc))
+		return -1;
 
-	sc->nr_reclaimed += MIN_LRU_BATCH;
+	/* discount the previous progress for kswapd */
+	if (current_is_kswapd())
+		return sc->nr_to_reclaim + sc->last_reclaimed;
 
-	return true;
+	return max(sc->nr_to_reclaim, compact_gap(sc->order));
 }
 
 static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	struct blk_plug plug;
 	bool need_aging = false;
-	bool need_swapping = false;
 	unsigned long scanned = 0;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	DEFINE_MAX_SEQ(lruvec);
+	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
 
 	lru_add_drain();
 
@@ -5208,7 +5173,7 @@ static void lru_gen_shrink_lruvec(struct
 		if (!nr_to_scan)
 			goto done;
 
-		delta = evict_folios(lruvec, sc, swappiness, &need_swapping);
+		delta = evict_folios(lruvec, sc, swappiness);
 		if (!delta)
 			goto done;
 
@@ -5216,7 +5181,7 @@ static void lru_gen_shrink_lruvec(struct
 		if (scanned >= nr_to_scan)
 			break;
 
-		if (should_abort_scan(lruvec, max_seq, sc, need_swapping))
+		if (sc->nr_reclaimed >= nr_to_reclaim)
 			break;
 
 		cond_resched();
@@ -5666,7 +5631,7 @@ static int run_eviction(struct lruvec *l
 		if (sc->nr_reclaimed >= nr_to_reclaim)
 			return 0;
 
-		if (!evict_folios(lruvec, sc, swappiness, NULL))
+		if (!evict_folios(lruvec, sc, swappiness))
 			return 0;
 
 		cond_resched();