From: Yafang Shao <laoar.shao@gmail.com>
To: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
eddyz87@gmail.com, memxor@gmail.com, mingo@redhat.com,
peterz@infradead.org, juri.lelli@redhat.com,
vincent.guittot@linaro.org, akpm@linux-foundation.org,
david@kernel.org, gourry@gourry.net, tj@kernel.org,
hannes@cmpxchg.org, mkoutny@suse.com, shakeel.butt@linux.dev,
roman.gushchin@linux.dev, yu.c.chen@intel.com,
zhao1.liu@intel.com
Cc: bpf@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org, Yafang Shao <laoar.shao@gmail.com>
Subject: [RFC PATCH v2 1/3] sched: add helpers for numa balancing
Date: Mon, 12 Oct 2026 20:04:36 +0800 [thread overview]
Message-ID: <20261012120438.52849-2-laoar.shao@gmail.com> (raw)
In-Reply-To: <20261012120438.52849-1-laoar.shao@gmail.com>
Two new helpers task_numab_enabled() and numab_mode_tiering() are
introduced to replace the scattered direct accesses to the
sched_numa_balancing static key and the sysctl_numa_balancing_mode
bitmask.
No functional change.
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
include/linux/sched/numa_balancing.h | 31 ++++++++++++++++++++++++++++
kernel/sched/fair.c | 16 +++++++-------
kernel/sched/sched.h | 1 -
mm/memory-tiers.c | 3 ++-
mm/migrate.c | 7 ++++---
mm/vmscan.c | 6 +++---
6 files changed, 48 insertions(+), 16 deletions(-)
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 52b22c5c396d..353772b49c5f 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -8,6 +8,7 @@
*/
#include <linux/sched.h>
+#include <linux/sched/sysctl.h>
#define TNF_MIGRATED 0x01
#define TNF_NO_GROUP 0x02
@@ -32,6 +33,28 @@ extern void set_numabalancing_state(bool enabled);
extern void task_numa_free(struct task_struct *p, bool final);
bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
int src_nid, int dst_cpu);
+
+extern struct static_key_false sched_numa_balancing;
+
+/*
+ * Whether NUMA balancing applies to @p. The @p argument is unused for
+ * now: a later patch will consult a per-cgroup BPF policy with it.
+ */
+static inline bool task_numab_enabled(struct task_struct *p)
+{
+ return static_branch_unlikely(&sched_numa_balancing);
+}
+
+/*
+ * The global sysctl state, for the system-wide tiering machinery: this
+ * reflects kernel.numa_balancing_mode only and takes no task.
+ */
+static inline bool numab_mode_tiering(void)
+{
+ if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
+ return true;
+ return false;
+}
#else
static inline void task_numa_fault(int last_node, int node, int pages,
int flags)
@@ -52,6 +75,14 @@ static inline bool should_numa_migrate_memory(struct task_struct *p,
{
return true;
}
+static inline bool task_numab_enabled(struct task_struct *p)
+{
+ return false;
+}
+static inline bool numab_mode_tiering(void)
+{
+ return false;
+}
#endif
#endif /* _LINUX_SCHED_NUMA_BALANCING_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 57360f5cdde4..45086e6f246c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -39,6 +39,7 @@
#include <linux/sched/cputime.h>
#include <linux/sched/isolation.h>
#include <linux/sched/nohz.h>
+#include <linux/sched/numa_balancing.h>
#include <linux/sched/prio.h>
#include <linux/static_call.h>
@@ -2963,8 +2964,8 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
last_cpupid = folio_xchg_last_cpupid(folio, this_cpupid);
- if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
- !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
+ if (!(numab_mode_tiering()) && !node_is_toptier(src_nid) &&
+ !cpupid_valid(last_cpupid))
return false;
/*
@@ -4194,7 +4195,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
struct numa_group *ng;
int priv;
- if (!static_branch_likely(&sched_numa_balancing))
+ if (!task_numab_enabled(p))
return;
/* for example, ksmd faulting in a user's mm */
@@ -4206,8 +4207,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
* node for memory tiering mode.
*/
if (!node_is_toptier(mem_node) &&
- (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ||
- !cpupid_valid(last_cpupid)))
+ (numab_mode_tiering() || !cpupid_valid(last_cpupid)))
return;
/* Allocate buffer to track faults on a per-node basis */
@@ -4665,7 +4665,7 @@ static void update_scan_period(struct task_struct *p, int new_cpu)
int src_nid = cpu_to_node(task_cpu(p));
int dst_nid = cpu_to_node(new_cpu);
- if (!static_branch_likely(&sched_numa_balancing))
+ if (!task_numab_enabled(p))
return;
if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING))
@@ -10697,7 +10697,7 @@ static long migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
unsigned long src_weight, dst_weight;
int src_nid, dst_nid, dist;
- if (!static_branch_likely(&sched_numa_balancing))
+ if (!task_numab_enabled(p))
return 0;
if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
@@ -15351,7 +15351,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
if (queued)
return;
- if (static_branch_unlikely(&sched_numa_balancing))
+ if (task_numab_enabled(curr))
task_tick_numa(rq, curr);
task_tick_cache(rq, curr);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e656c7059bf8..38e21c8c57dd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2465,7 +2465,6 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#endif /* !CONFIG_JUMP_LABEL */
-extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
static inline u64 global_rt_period(void)
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 54851d8a195b..ec7b9aadda98 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -7,6 +7,7 @@
#include <linux/memory-tiers.h>
#include <linux/notifier.h>
#include <linux/sched/sysctl.h>
+#include <linux/sched/numa_balancing.h>
#include "internal.h"
@@ -64,7 +65,7 @@ static const struct bus_type memory_tier_subsys = {
*/
bool folio_use_access_time(struct folio *folio)
{
- return (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
+ return numab_mode_tiering() &&
!node_is_toptier(folio_nid(folio));
}
#endif
diff --git a/mm/migrate.c b/mm/migrate.c
index 15b45832bcfa..4d2ba87eaa34 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -41,6 +41,7 @@
#include <linux/ptrace.h>
#include <linux/memory.h>
#include <linux/sched/sysctl.h>
+#include <linux/sched/numa_balancing.h>
#include <linux/memory-tiers.h>
#include <linux/pagewalk.h>
@@ -818,7 +819,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
* memory node, reset cpupid, because that is used to record
* page access time in slow memory node.
*/
- if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) {
+ if (numab_mode_tiering()) {
bool f_toptier = node_is_toptier(folio_nid(folio));
bool t_toptier = node_is_toptier(folio_nid(newfolio));
@@ -2718,7 +2719,7 @@ int migrate_misplaced_folio_prepare(struct folio *folio,
if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
int z;
- if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
+ if (!(numab_mode_tiering()))
return -EAGAIN;
for (z = pgdat->nr_zones - 1; z >= 0; z--) {
if (managed_zone(pgdat->node_zones + z))
@@ -2770,7 +2771,7 @@ int migrate_misplaced_folio(struct folio *folio, int node)
if (nr_succeeded) {
count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
count_memcg_events(memcg, NUMA_PAGE_MIGRATE, nr_succeeded);
- if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
+ if ((numab_mode_tiering())
&& !node_is_toptier(folio_nid(folio))
&& node_is_toptier(node))
mod_lruvec_state(lruvec, PGPROMOTE_SUCCESS, nr_succeeded);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f11491ee9ed5..af46869bb15e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -65,6 +65,7 @@
#include <linux/swapops.h>
#include <linux/sched/sysctl.h>
+#include <linux/sched/numa_balancing.h>
#include "internal.h"
#include "page_alloc.h"
@@ -5029,8 +5030,7 @@ static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
if (!current_is_kswapd() || sc->order)
return false;
- mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
- WMARK_PROMO : WMARK_HIGH;
+ mark = numab_mode_tiering() ? WMARK_PROMO : WMARK_HIGH;
for (i = 0; i <= sc->reclaim_idx; i++) {
struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
@@ -6974,7 +6974,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
enum zone_stat_item item;
unsigned long free_pages;
- if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
+ if (numab_mode_tiering())
mark = promo_wmark_pages(zone);
else
mark = high_wmark_pages(zone);
--
2.52.0
next prev parent reply other threads:[~2026-10-12 12:05 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-12 12:04 [RFC PATCH v2 0/3] BPF-based per-cgroup NUMA balancing mode selection Yafang Shao
2026-10-12 12:04 ` Yafang Shao [this message]
2026-10-12 12:04 ` [RFC PATCH v2 2/3] sched: add per-cgroup NUMA balancing mode selection via BPF Yafang Shao
2026-10-12 12:04 ` [RFC PATCH v2 3/3] selftests/bpf: add tests for the bpf_numab_ops struct_ops Yafang Shao
2026-10-12 17:51 ` [RFC PATCH v2 0/3] BPF-based per-cgroup NUMA balancing mode selection Tejun Heo
2026-10-13 2:16 ` Yafang Shao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261012120438.52849-2-laoar.shao@gmail.com \
--to=laoar.shao@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=david@kernel.org \
--cc=eddyz87@gmail.com \
--cc=gourry@gourry.net \
--cc=hannes@cmpxchg.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=memxor@gmail.com \
--cc=mingo@redhat.com \
--cc=mkoutny@suse.com \
--cc=peterz@infradead.org \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=tj@kernel.org \
--cc=vincent.guittot@linaro.org \
--cc=yu.c.chen@intel.com \
--cc=zhao1.liu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®