[RFC PATCH 04/18] mm: count the pages waiting for a grace period

[Kiryl Shutsemau (Meta)]

Deferred folios have refcount 0 and are not on the free lists, so no
counter shows them.  Memory that waits for a grace period is missing
from the free count and from every LRU count.

Count it per zone in NR_FREE_RCU_PAGES: nr_free_rcu in /proc/vmstat,
free_rcu in show_free_areas().  Preparation for freeing the waiting
pages sooner when they hold back memory that is needed.

Assisted-by: LLM
Signed-off-by: Kiryl Shutsemau (Meta) <kas@xxxxxxxxxx>
---
 include/linux/mmzone.h | 1 +
 mm/page_alloc.c        | 4 ++++
 mm/show_mem.c          | 9 ++++++---
 mm/vmstat.c            | 2 ++
 4 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 94f9c3ff5416..3336b9e5ee99 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -228,6 +228,7 @@ enum zone_stat_item {
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
 	NR_FREE_CMA_PAGES,
+	NR_FREE_RCU_PAGES,	/* freed, waiting for an RCU grace period */
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	NR_UNACCEPTED,
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a371e92da273..15bb66e36304 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1348,6 +1348,8 @@ static void rcu_free_pages(struct list_head *list)
 
 	folio_batch_init(&fbatch);
 	list_for_each_entry_safe(folio, next, list, lru) {
+		mod_zone_page_state(folio_zone(folio), NR_FREE_RCU_PAGES,
+				    -folio_nr_pages(folio));
 		if (!folio_batch_add(&fbatch, folio)) {
 			free_unref_folios(&fbatch);
 			cond_resched_tasks_rcu_qs();
@@ -1375,9 +1377,11 @@ static void rcu_free_workfn(struct work_struct *work)
 static void rcu_free_defer(struct folio *folio)
 {
 	struct rcu_free_pcpu *r = raw_cpu_ptr(&rcu_free_pcpu);
+	struct zone *zone = folio_zone(folio);
 	unsigned long flags;
 
 	spin_lock_irqsave(&r->lock, flags);
+	__mod_zone_page_state(zone, NR_FREE_RCU_PAGES, folio_nr_pages(folio));
 	list_add_tail(&folio->lru, &r->pending);
 	rcu_free_start(r);
 	spin_unlock_irqrestore(&r->lock, flags);
diff --git a/mm/show_mem.c b/mm/show_mem.c
index b938cbcd774a..0d3bddbda108 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -204,7 +204,7 @@ static void show_free_areas(unsigned int filter, const nodemask_t *nodemask,
 		" mapped:%lu shmem:%lu pagetables:%lu\n"
 		" sec_pagetables:%lu bounce:%lu\n"
 		" kernel_misc_reclaimable:%lu\n"
-		" free:%lu free_pcp:%lu free_cma:%lu\n",
+		" free:%lu free_pcp:%lu free_cma:%lu free_rcu:%lu\n",
 		global_node_page_state(NR_ACTIVE_ANON),
 		global_node_page_state(NR_INACTIVE_ANON),
 		global_node_page_state(NR_ISOLATED_ANON),
@@ -224,7 +224,8 @@ static void show_free_areas(unsigned int filter, const nodemask_t *nodemask,
 		global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE),
 		global_zone_page_state(NR_FREE_PAGES),
 		free_pcp,
-		global_zone_page_state(NR_FREE_CMA_PAGES));
+		global_zone_page_state(NR_FREE_CMA_PAGES),
+		global_zone_page_state(NR_FREE_RCU_PAGES));
 
 	for_each_online_pgdat(pgdat) {
 		if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
@@ -325,6 +326,7 @@ static void show_free_areas(unsigned int filter, const nodemask_t *nodemask,
 			" free_pcp:%lukB"
 			" local_pcp:%lukB"
 			" free_cma:%lukB"
+			" free_rcu:%lukB"
 			"\n",
 			zone->name,
 			K(zone_page_state(zone, NR_FREE_PAGES)),
@@ -351,7 +353,8 @@ static void show_free_areas(unsigned int filter, const nodemask_t *nodemask,
 			0UL,
 			K(free_pcp),
 			K((unsigned long)this_cpu_read(zone->per_cpu_pageset->count)),
-			K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
+			K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
+			K(zone_page_state(zone, NR_FREE_RCU_PAGES)));
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
 			printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 66ed017bde46..64068d73d6d2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1212,6 +1212,7 @@ const char * const vmstat_text[] = {
 	[I(NR_ZSPAGES)]				= "nr_zspages",
 #endif
 	[I(NR_FREE_CMA_PAGES)]			= "nr_free_cma",
+	[I(NR_FREE_RCU_PAGES)]			= "nr_free_rcu",
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	[I(NR_UNACCEPTED)]			= "nr_unaccepted",
 #endif
@@ -2023,6 +2024,7 @@ static int vmstat_refresh(const struct ctl_table *table, int write,
 		switch (i) {
 		case NR_ZONE_WRITE_PENDING:
 		case NR_FREE_CMA_PAGES:
+		case NR_FREE_RCU_PAGES:
 			continue;
 		}
 		val = atomic_long_read(&vm_zone_stat[i]);
-- 
2.54.0