Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ee4eecc..de94881 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -89,9 +89,12 @@
 	unsigned int may_swap:1;
 
 	/*
-	 * Cgroups are not reclaimed below their configured memory.low,
-	 * unless we threaten to OOM. If any cgroups are skipped due to
-	 * memory.low and nothing was reclaimed, go back for memory.low.
+	 * Cgroup memory below memory.low is protected as long as we
+	 * don't threaten to OOM. If any cgroup is reclaimed at
+	 * reduced force or passed over entirely due to its memory.low
+	 * setting (memcg_low_skipped), and nothing is reclaimed as a
+	 * result, then go back for one more cycle that reclaims the protected
+	 * memory (memcg_low_reclaim) to avert OOM.
 	 */
 	unsigned int memcg_low_reclaim:1;
 	unsigned int memcg_low_skipped:1;
@@ -422,7 +425,7 @@
 {
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
 		idr_replace(&shrinker_idr, shrinker, shrinker->id);
 #endif
@@ -2458,14 +2461,14 @@
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
 		unsigned long lruvec_size;
+		unsigned long low, min;
 		unsigned long scan;
-		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(memcg,
-						   sc->memcg_low_reclaim);
+		mem_cgroup_protection(sc->target_mem_cgroup, memcg,
+				      &min, &low);
 
-		if (protection) {
+		if (min || low) {
 			/*
 			 * Scale a cgroup's reclaim pressure by proportioning
 			 * its current usage to its memory.low or memory.min
@@ -2496,12 +2499,21 @@
 			 * hard protection.
 			 */
 			unsigned long cgroup_size = mem_cgroup_size(memcg);
+			unsigned long protection;
+
+			/* memory.low scaling, make sure we retry before OOM */
+			if (!sc->memcg_low_reclaim && low > min) {
+				protection = low;
+				sc->memcg_low_skipped = 1;
+			} else {
+				protection = min;
+			}
 
 			/* Avoid TOCTOU with earlier protection check */
 			cgroup_size = max(cgroup_size, protection);
 
 			scan = lruvec_size - lruvec_size * protection /
-				cgroup_size;
+				(cgroup_size + 1);
 
 			/*
 			 * Minimally target SWAP_CLUSTER_MAX pages to keep
@@ -2530,10 +2542,13 @@
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:
@@ -2772,6 +2787,14 @@
 			unsigned long reclaimed;
 			unsigned long scanned;
 
+			/*
+			 * This loop can become CPU-bound when target memcgs
+			 * aren't eligible for reclaim - either because they
+			 * don't have any reclaimable pages, or because their
+			 * memory is explicitly protected. Avoid soft lockups.
+			 */
+			cond_resched();
+
 			switch (mem_cgroup_protected(root, memcg)) {
 			case MEMCG_PROT_MIN:
 				/*
@@ -3157,8 +3180,9 @@
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
-						(enum zone_type)ZONE_NORMAL);
+		if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+			WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
 
@@ -3790,9 +3814,9 @@
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
 					   enum zone_type prev_classzone_idx)
 {
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return prev_classzone_idx;
-	return pgdat->kswapd_classzone_idx;
+	enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3836,8 +3860,11 @@
 		 * the previous request that slept prematurely.
 		 */
 		if (remaining) {
-			pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+			WRITE_ONCE(pgdat->kswapd_classzone_idx,
+				   kswapd_classzone_idx(pgdat, classzone_idx));
+
+			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
+				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
 		}
 
 		finish_wait(&pgdat->kswapd_wait, &wait);
@@ -3914,12 +3941,12 @@
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	pgdat->kswapd_order = 0;
-	pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+	WRITE_ONCE(pgdat->kswapd_order, 0);
+	WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 	for ( ; ; ) {
 		bool ret;
 
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 
 kswapd_try_sleep:
@@ -3927,10 +3954,10 @@
 					classzone_idx);
 
 		/* Read the new order and classzone_idx */
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-		pgdat->kswapd_order = 0;
-		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+		WRITE_ONCE(pgdat->kswapd_order, 0);
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3974,20 +4001,23 @@
 		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	enum zone_type curr_idx;
 
 	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
-	pgdat = zone->zone_pgdat;
 
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		pgdat->kswapd_classzone_idx = classzone_idx;
-	else
-		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
-						  classzone_idx);
-	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
+	pgdat = zone->zone_pgdat;
+	curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+	if (READ_ONCE(pgdat->kswapd_order) < order)
+		WRITE_ONCE(pgdat->kswapd_order, order);
+
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;