mm: memcg: move soft limit reclaim code to memcontrol-v1.c

Soft limits are cgroup v1-specific and are not supported by cgroup v2, so
let's move the corresponding code into memcontrol-v1.c.

Aside from simple moving the code, this commits introduces a trivial
memcg1_soft_limit_reset() function to reset soft limits and also moves the
global soft limit tree initialization code into a new memcg1_init()
function.

It also moves corresponding declarations shared between memcontrol.c and
memcontrol-v1.c into mm/memcontrol-v1.h.

Link: https://lkml.kernel.org/r/20240625005906.106920-3-roman.gushchin@linux.devSigned-off-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/memcontrol-v1.c

 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/memcontrol.h>
+#include <linux/swap.h>
+#include <linux/mm_inline.h>
+
 #include "memcontrol-v1.h"
+
+/*
+ * Cgroups above their limits are maintained in a RB-Tree, independent of
+ * their hierarchy representation
+ */
+
+struct mem_cgroup_tree_per_node {
+	struct rb_root rb_root;
+	struct rb_node *rb_rightmost;
+	spinlock_t lock;
+};
+
+struct mem_cgroup_tree {
+	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
+};
+
+static struct mem_cgroup_tree soft_limit_tree __read_mostly;
+
+/*
+ * Maximum loops in mem_cgroup_soft_reclaim(), used for soft
+ * limit reclaim to prevent infinite loops, if they ever occur.
+ */
+#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
+#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2
+
+static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz,
+					 unsigned long new_usage_in_excess)
+{
+	struct rb_node **p = &mctz->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct mem_cgroup_per_node *mz_node;
+	bool rightmost = true;
+
+	if (mz->on_tree)
+		return;
+
+	mz->usage_in_excess = new_usage_in_excess;
+	if (!mz->usage_in_excess)
+		return;
+	while (*p) {
+		parent = *p;
+		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
+					tree_node);
+		if (mz->usage_in_excess < mz_node->usage_in_excess) {
+			p = &(*p)->rb_left;
+			rightmost = false;
+		} else {
+			p = &(*p)->rb_right;
+		}
+	}
+
+	if (rightmost)
+		mctz->rb_rightmost = &mz->tree_node;
+
+	rb_link_node(&mz->tree_node, parent, p);
+	rb_insert_color(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = true;
+}
+
+static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz)
+{
+	if (!mz->on_tree)
+		return;
+
+	if (&mz->tree_node == mctz->rb_rightmost)
+		mctz->rb_rightmost = rb_prev(&mz->tree_node);
+
+	rb_erase(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = false;
+}
+
+static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+				       struct mem_cgroup_tree_per_node *mctz)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mctz->lock, flags);
+	__mem_cgroup_remove_exceeded(mz, mctz);
+	spin_unlock_irqrestore(&mctz->lock, flags);
+}
+
+static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
+{
+	unsigned long nr_pages = page_counter_read(&memcg->memory);
+	unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
+	unsigned long excess = 0;
+
+	if (nr_pages > soft_limit)
+		excess = nr_pages - soft_limit;
+
+	return excess;
+}
+
+void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
+{
+	unsigned long excess;
+	struct mem_cgroup_per_node *mz;
+	struct mem_cgroup_tree_per_node *mctz;
+
+	if (lru_gen_enabled()) {
+		if (soft_limit_excess(memcg))
+			lru_gen_soft_reclaim(memcg, nid);
+		return;
+	}
+
+	mctz = soft_limit_tree.rb_tree_per_node[nid];
+	if (!mctz)
+		return;
+	/*
+	 * Necessary to update all ancestors when hierarchy is used.
+	 * because their event counter is not touched.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		mz = memcg->nodeinfo[nid];
+		excess = soft_limit_excess(memcg);
+		/*
+		 * We have to update the tree if mz is on RB-tree or
+		 * mem is over its softlimit.
+		 */
+		if (excess || mz->on_tree) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&mctz->lock, flags);
+			/* if on-tree, remove it */
+			if (mz->on_tree)
+				__mem_cgroup_remove_exceeded(mz, mctz);
+			/*
+			 * Insert again. mz->usage_in_excess will be updated.
+			 * If excess is 0, no tree ops.
+			 */
+			__mem_cgroup_insert_exceeded(mz, mctz, excess);
+			spin_unlock_irqrestore(&mctz->lock, flags);
+		}
+	}
+}
+
+void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_tree_per_node *mctz;
+	struct mem_cgroup_per_node *mz;
+	int nid;
+
+	for_each_node(nid) {
+		mz = memcg->nodeinfo[nid];
+		mctz = soft_limit_tree.rb_tree_per_node[nid];
+		if (mctz)
+			mem_cgroup_remove_exceeded(mz, mctz);
+	}
+}
+
+static struct mem_cgroup_per_node *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
+{
+	struct mem_cgroup_per_node *mz;
+
+retry:
+	mz = NULL;
+	if (!mctz->rb_rightmost)
+		goto done;		/* Nothing to reclaim from */
+
+	mz = rb_entry(mctz->rb_rightmost,
+		      struct mem_cgroup_per_node, tree_node);
+	/*
+	 * Remove the node now but someone else can add it back,
+	 * we will to add it back at the end of reclaim to its correct
+	 * position in the tree.
+	 */
+	__mem_cgroup_remove_exceeded(mz, mctz);
+	if (!soft_limit_excess(mz->memcg) ||
+	    !css_tryget(&mz->memcg->css))
+		goto retry;
+done:
+	return mz;
+}
+
+static struct mem_cgroup_per_node *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
+{
+	struct mem_cgroup_per_node *mz;
+
+	spin_lock_irq(&mctz->lock);
+	mz = __mem_cgroup_largest_soft_limit_node(mctz);
+	spin_unlock_irq(&mctz->lock);
+	return mz;
+}
+
+static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+				   pg_data_t *pgdat,
+				   gfp_t gfp_mask,
+				   unsigned long *total_scanned)
+{
+	struct mem_cgroup *victim = NULL;
+	int total = 0;
+	int loop = 0;
+	unsigned long excess;
+	unsigned long nr_scanned;
+	struct mem_cgroup_reclaim_cookie reclaim = {
+		.pgdat = pgdat,
+	};
+
+	excess = soft_limit_excess(root_memcg);
+
+	while (1) {
+		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
+		if (!victim) {
+			loop++;
+			if (loop >= 2) {
+				/*
+				 * If we have not been able to reclaim
+				 * anything, it might because there are
+				 * no reclaimable pages under this hierarchy
+				 */
+				if (!total)
+					break;
+				/*
+				 * We want to do more targeted reclaim.
+				 * excess >> 2 is not to excessive so as to
+				 * reclaim too much, nor too less that we keep
+				 * coming back to reclaim from this cgroup
+				 */
+				if (total >= (excess >> 2) ||
+					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
+					break;
+			}
+			continue;
+		}
+		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
+					pgdat, &nr_scanned);
+		*total_scanned += nr_scanned;
+		if (!soft_limit_excess(root_memcg))
+			break;
+	}
+	mem_cgroup_iter_break(root_memcg, victim);
+	return total;
+}
+
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
+{
+	unsigned long nr_reclaimed = 0;
+	struct mem_cgroup_per_node *mz, *next_mz = NULL;
+	unsigned long reclaimed;
+	int loop = 0;
+	struct mem_cgroup_tree_per_node *mctz;
+	unsigned long excess;
+
+	if (lru_gen_enabled())
+		return 0;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
+
+	/*
+	 * Do not even bother to check the largest node if the root
+	 * is empty. Do it lockless to prevent lock bouncing. Races
+	 * are acceptable as soft limit is best effort anyway.
+	 */
+	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
+		return 0;
+
+	/*
+	 * This loop can run a while, specially if mem_cgroup's continuously
+	 * keep exceeding their soft limit and putting the system under
+	 * pressure
+	 */
+	do {
+		if (next_mz)
+			mz = next_mz;
+		else
+			mz = mem_cgroup_largest_soft_limit_node(mctz);
+		if (!mz)
+			break;
+
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
+						    gfp_mask, total_scanned);
+		nr_reclaimed += reclaimed;
+		spin_lock_irq(&mctz->lock);
+
+		/*
+		 * If we failed to reclaim anything from this memory cgroup
+		 * it is time to move on to the next cgroup
+		 */
+		next_mz = NULL;
+		if (!reclaimed)
+			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);
+
+		excess = soft_limit_excess(mz->memcg);
+		/*
+		 * One school of thought says that we should not add
+		 * back the node to the tree if reclaim returns 0.
+		 * But our reclaim could return 0, simply because due
+		 * to priority we are exposing a smaller subset of
+		 * memory to reclaim from. Consider this as a longer
+		 * term TODO.
+		 */
+		/* If excess == 0, no tree ops */
+		__mem_cgroup_insert_exceeded(mz, mctz, excess);
+		spin_unlock_irq(&mctz->lock);
+		css_put(&mz->memcg->css);
+		loop++;
+		/*
+		 * Could not reclaim anything and there are no more
+		 * mem cgroups to try or we seem to be looping without
+		 * reclaiming anything.
+		 */
+		if (!nr_reclaimed &&
+			(next_mz == NULL ||
+			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
+			break;
+	} while (!nr_reclaimed);
+	if (next_mz)
+		css_put(&next_mz->memcg->css);
+	return nr_reclaimed;
+}
+
+static int __init memcg1_init(void)
+{
+	int node;
+
+	for_each_node(node) {
+		struct mem_cgroup_tree_per_node *rtpn;
+
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node);
+
+		rtpn->rb_root = RB_ROOT;
+		rtpn->rb_rightmost = NULL;
+		spin_lock_init(&rtpn->lock);
+		soft_limit_tree.rb_tree_per_node[node] = rtpn;
+	}
+
+	return 0;
+}
+subsys_initcall(memcg1_init);

mm/memcontrol-v1.h

@@ -3,5 +3,12 @@
 #ifndef __MM_MEMCONTROL_V1_H
 #define __MM_MEMCONTROL_V1_H
 
+void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid);
+void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg);
+
+static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg)
+{
+	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
+}
 
 #endif	/* __MM_MEMCONTROL_V1_H */