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, tim.c.chen@linux.intel.com,
lizhe.67@bytedance.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 v3 bpf-next 3/5] sched: add helpers for numa balancing
Date: Mon, 19 Oct 2026 14:41:55 +0800 [thread overview]
Message-ID: <20261019064157.29885-4-laoar.shao@gmail.com> (raw)
In-Reply-To: <20261019064157.29885-1-laoar.shao@gmail.com>
Three new helpers task_numab_enabled(), numab_in_tiering_mode() and
numab_in_normal_mode() 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>
Cc: David Hildenbrand (Arm) <david@kernel.org>
---
include/linux/sched/numa_balancing.h | 33 ++++++++++++++++++++++++++++
kernel/sched/fair.c | 31 +++++++++++++-------------
kernel/sched/sched.h | 1 -
mm/memory-tiers.c | 3 ++-
mm/mempolicy.c | 3 +--
mm/migrate.c | 7 +++---
mm/vmscan.c | 6 ++---
7 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 52b22c5c396d..36de57f7fb06 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 +33,26 @@ 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. */
+static inline bool task_numab_enabled(struct task_struct *p)
+{
+ return static_branch_likely(&sched_numa_balancing);
+}
+
+/* Whether NUMA balancing is in memory tiering mode. */
+static inline bool numab_in_tiering_mode(void)
+{
+ return sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING;
+}
+
+/* Whether NUMA balancing is in normal mode. */
+static inline bool numab_in_normal_mode(void)
+{
+ return sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL;
+}
#else
static inline void task_numa_fault(int last_node, int node, int pages,
int flags)
@@ -52,6 +73,18 @@ 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_in_tiering_mode(void)
+{
+ return false;
+}
+static inline bool numab_in_normal_mode(void)
+{
+ return false;
+}
#endif
#endif /* _LINUX_SCHED_NUMA_BALANCING_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 71dc47d6114d..066818498c76 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>
@@ -1478,7 +1479,8 @@ static inline int get_sched_cache_scale(int mul)
return (1 + (tol - 1) * mul);
}
-static bool exceed_llc_capacity(struct sched_cache_group *grp, int cpu)
+static bool exceed_llc_capacity(struct sched_cache_group *grp, struct task_struct *p,
+ int cpu)
{
#ifdef CONFIG_NUMA_BALANCING
unsigned long llc, footprint;
@@ -1491,7 +1493,7 @@ static bool exceed_llc_capacity(struct sched_cache_group *grp, int cpu)
if (!sd)
return true;
- if (static_branch_likely(&sched_numa_balancing)) {
+ if (task_numab_enabled(p)) {
/*
* TBD: RDT exclusive LLC ways reserved should be
* excluded.
@@ -1879,7 +1881,7 @@ static int get_pref_llc(struct task_struct *p, struct sched_cache_group *grp)
* than sched_setnuma() at least -- and thus the
* conflict only exists for a short period of time.
*/
- if (static_branch_likely(&sched_numa_balancing) &&
+ if (task_numab_enabled(p) &&
p->numa_preferred_nid >= 0 &&
cpu_to_node(mm_sched_cpu) != p->numa_preferred_nid)
mm_sched_llc = -1;
@@ -1932,7 +1934,7 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
*/
if ((long)(epoch - READ_ONCE(grp->epoch)) > llc_epoch_affinity_timeout ||
invalid_llc_nr(grp, p, cpu_of(rq)) ||
- exceed_llc_capacity(grp, cpu_of(rq))) {
+ exceed_llc_capacity(grp, p, cpu_of(rq))) {
if (READ_ONCE(grp->cpu) != -1)
WRITE_ONCE(grp->cpu, -1);
}
@@ -1980,7 +1982,7 @@ static void get_scan_cpumasks(cpumask_var_t cpus, struct task_struct *p,
#ifdef CONFIG_NUMA_BALANCING
int cpu, curr_cpu, nid, pref_nid;
- if (!static_branch_likely(&sched_numa_balancing))
+ if (!task_numab_enabled(p))
goto out;
cpu = READ_ONCE(grp->cpu);
@@ -2076,7 +2078,7 @@ static void task_cache_work(struct callback_head *work)
curr_cpu = task_cpu(p);
if (invalid_llc_nr(grp, p, curr_cpu) ||
- exceed_llc_capacity(grp, curr_cpu)) {
+ exceed_llc_capacity(grp, p, curr_cpu)) {
if (READ_ONCE(grp->cpu) != -1)
WRITE_ONCE(grp->cpu, -1);
@@ -2963,8 +2965,8 @@ 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_in_tiering_mode()) && !node_is_toptier(src_nid) &&
+ !cpupid_valid(last_cpupid))
return false;
/*
@@ -4194,7 +4196,7 @@ 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 +4208,7 @@ 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_in_tiering_mode() || !cpupid_valid(last_cpupid)))
return;
/* Allocate buffer to track faults on a per-node basis */
@@ -4665,7 +4666,7 @@ 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 +10698,7 @@ 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))
@@ -10960,7 +10961,7 @@ static enum llc_mig can_migrate_llc_task(struct lb_env *env,
/* skip cache aware load balance for too many threads */
if (invalid_llc_nr(grp, p, dst_cpu) ||
- exceed_llc_capacity(grp, dst_cpu)) {
+ exceed_llc_capacity(grp, p, dst_cpu)) {
if (READ_ONCE(grp->cpu) != -1)
WRITE_ONCE(grp->cpu, -1);
return mig_unrestricted;
@@ -15351,7 +15352,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
if (queued)
return;
- if (static_branch_likely(&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..9009b164edc2 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -6,6 +6,7 @@
#include <linux/memory.h>
#include <linux/memory-tiers.h>
#include <linux/notifier.h>
+#include <linux/sched/numa_balancing.h>
#include <linux/sched/sysctl.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_in_tiering_mode() &&
!node_is_toptier(folio_nid(folio));
}
#endif
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 79053ece02cd..442c93079fb0 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -871,8 +871,7 @@ bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma,
* Skip scanning top tier node if normal numa
* balancing is disabled
*/
- if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
- node_is_toptier(nid))
+ if (!numab_in_normal_mode() && node_is_toptier(nid))
return false;
if (folio_use_access_time(folio))
diff --git a/mm/migrate.c b/mm/migrate.c
index 15b45832bcfa..a622df9a9b42 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_in_tiering_mode()) {
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_in_tiering_mode())
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_in_tiering_mode())
&& !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..17455255fc30 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_in_tiering_mode() ? 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_in_tiering_mode())
mark = promo_wmark_pages(zone);
else
mark = high_wmark_pages(zone);
--
2.52.0
next prev parent reply other threads:[~2026-10-19 6:42 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-19 6:41 [RFC PATCH v3 bpf-next 0/5] BPF-based per-cgroup NUMA balancing mode selection Yafang Shao
2026-10-19 6:41 ` [RFC PATCH v3 bpf-next 1/5] sched: fix stale get_pref_llc() stub for !CONFIG_SCHED_CACHE Yafang Shao
2026-10-19 6:41 ` [RFC PATCH v3 bpf-next 2/5] sched: use static_branch_likely() for the NUMA balancing tick check Yafang Shao
2026-10-19 6:41 ` Yafang Shao [this message]
2026-10-19 7:14 ` [RFC PATCH v3 bpf-next 3/5] sched: add helpers for numa balancing bot+bpf-ci
2026-10-19 6:41 ` [RFC PATCH v3 bpf-next 4/5] sched: add BPF-based per-cgroup NUMA balancing mode selection Yafang Shao
2026-10-19 7:24 ` bot+bpf-ci
2026-10-19 6:41 ` [RFC PATCH v3 bpf-next 5/5] selftests/bpf: add tests for the numab kfuncs Yafang Shao
2026-10-20 16:54 ` [RFC PATCH v3 bpf-next 0/5] BPF-based per-cgroup NUMA balancing mode selection Tejun Heo
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=20261019064157.29885-4-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=lizhe.67@bytedance.com \
--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=tim.c.chen@linux.intel.com \
--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