[PATCH 17/22] mm/vmscan: restrict reclaim to common memory
From: Gregory Price (Meta)
Date: Sat Nov 14 2026 - 02:13:02 EST
Reclaim serves the ordinary allocation domain.
Restrict it to N_MEMORY_COMMON:
- start kswapd only on common nodes, at boot or hotplug.
- walk only common zones in direct reclaim and when throttling it,
so no reclaimer waits on a node that has no kswapd.
- walk common nodes when MGLRU registers an mm and when its debugfs
interface iterates or validates nodes, using first_node_state()
and next_node_state() in place of first_memory_node and
next_memory_node.
The fallback zonelists hold only common memory, and all memory is common
at this point, so behavior is unchanged.
Signed-off-by: Gregory Price (Meta) <gourry@xxxxxxxxxx>
---
mm/memory_hotplug.c | 3 ++-
mm/vmscan.c | 26 +++++++++++++-------------
2 files changed, 15 insertions(+), 14 deletions(-)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 29ff2c46499b3..410a29732bae7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1207,7 +1207,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
/* reinitialise watermarks and update pcp limits */
init_per_zone_wmark_min();
- kswapd_run(nid);
+ if (node_state(nid, N_MEMORY_COMMON))
+ kswapd_run(nid);
kcompactd_run(nid);
if (node_arg.nid >= 0)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 061fbd168d982..bb7b1c50bfb78 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2932,7 +2932,7 @@ void lru_gen_add_mm(struct mm_struct *mm)
#endif
spin_lock(&mm_list->lock);
- for_each_node_state(nid, N_MEMORY) {
+ for_each_node_state(nid, N_MEMORY_COMMON) {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
@@ -5562,7 +5562,7 @@ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos)
do {
int nid;
- for_each_node_state(nid, N_MEMORY) {
+ for_each_node_state(nid, N_MEMORY_COMMON) {
if (!nr_to_skip--)
return mem_cgroup_lruvec(memcg, NODE_DATA(nid));
}
@@ -5587,13 +5587,13 @@ static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos)
++*pos;
- nid = next_memory_node(nid);
+ nid = next_node_state(nid, N_MEMORY_COMMON);
if (nid == MAX_NUMNODES) {
memcg = mem_cgroup_iter(NULL, memcg, NULL);
if (!memcg)
return NULL;
- nid = first_memory_node;
+ nid = first_node_state(N_MEMORY_COMMON);
}
return mem_cgroup_lruvec(memcg, NODE_DATA(nid));
@@ -5665,7 +5665,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
DEFINE_MAX_SEQ(lruvec);
DEFINE_MIN_SEQ(lruvec);
- if (nid == first_memory_node) {
+ if (nid == first_node_state(N_MEMORY_COMMON)) {
const char *path = memcg ? m->private : "";
#ifdef CONFIG_MEMCG
@@ -5765,7 +5765,7 @@ static int run_cmd(char cmd, u64 memcg_id, int nid, unsigned long seq,
int err = -EINVAL;
struct mem_cgroup *memcg = NULL;
- if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY))
+ if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY_COMMON))
return -EINVAL;
if (!mem_cgroup_disabled()) {
@@ -6492,8 +6492,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
sc->reclaim_idx = gfp_zone(sc->gfp_mask);
}
- for_each_zone_zonelist_nodemask(zone, z, zonelist,
- sc->reclaim_idx, sc->nodemask) {
+ for_each_zone_node_state(zone, z, zonelist, sc->reclaim_idx,
+ sc->nodemask, N_MEMORY_COMMON) {
/*
* Take care memory controller reclaiming has small influence
* to global LRU.
@@ -6604,8 +6604,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
} while (--sc->priority >= 0);
last_pgdat = NULL;
- for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx,
- sc->nodemask) {
+ for_each_zone_node_state(zone, z, zonelist, sc->reclaim_idx,
+ sc->nodemask, N_MEMORY_COMMON) {
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
@@ -6756,8 +6756,8 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
* for remote pfmemalloc reserves and processes on different nodes
* should make reasonable progress.
*/
- for_each_zone_zonelist_nodemask(zone, z, zonelist,
- gfp_zone(gfp_mask), nodemask) {
+ for_each_zone_node_state(zone, z, zonelist, gfp_zone(gfp_mask),
+ nodemask, N_MEMORY_COMMON) {
if (zone_idx(zone) > ZONE_NORMAL)
continue;
@@ -7736,7 +7736,7 @@ static int __init kswapd_init(void)
{
int nid;
- for_each_node_state(nid, N_MEMORY)
+ for_each_node_state(nid, N_MEMORY_COMMON)
kswapd_run(nid);
register_sysctl_init("vm", vmscan_sysctl_table);
return 0;
--
2.53.1-Meta