From: Shrikanth Hegde <sshegde@linux.ibm.com>
To: linux-kernel@vger.kernel.org, mingo@kernel.org,
peterz@infradead.org, juri.lelli@redhat.com,
vincent.guittot@linaro.org, yury.norov@gmail.com,
kprateek.nayak@amd.com, iii@linux.ibm.com, corbet@lwn.net
Cc: sshegde@linux.ibm.com, tglx@kernel.org,
gregkh@linuxfoundation.org, pbonzini@redhat.com,
seanjc@google.com, vschneid@redhat.com, huschle@linux.ibm.com,
rostedt@goodmis.org, dietmar.eggemann@arm.com,
maddy@linux.ibm.com, srikar@linux.ibm.com, hdanton@sina.com,
chleroy@kernel.org, vineeth@bitbyteword.org, frederic@kernel.org,
arighi@nvidia.com, pauld@redhat.com, christian.loehle@arm.com,
tj@kernel.org, tommaso.cucinotta@gmail.com, maz@kernel.org,
rafael@kernel.org, rdunlap@infradead.org, kernellwp@gmail.com,
linux-doc@vger.kernel.org
Subject: [PATCH v5 04/24] cpumask: Introduce cpu_preferred_mask
Date: Thu, 25 Jun 2026 18:16:28 +0530 [thread overview]
Message-ID: <20260625124648.802832-5-sshegde@linux.ibm.com> (raw)
In-Reply-To: <20260625124648.802832-1-sshegde@linux.ibm.com>
This patch does
- Declare and Define cpu_preferred_mask.
- Get/Set helpers for it.
Values are set/clear by the scheduler by detecting the steal time values.
A CPU is set to preferred when it becomes active. Later it may be
marked as non-preferred depending on steal time values with
steal monitor being enabled.
Always maintain design construct of preferred is subset of active.
i.e. preferred ⊆ active ⊆ online ⊆ present ⊆ possible
Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
---
v4->v5:
- Make it macro instead (Yury Norov)
include/linux/cpumask.h | 21 ++++++++++++++++++++-
kernel/cpu.c | 6 ++++++
kernel/sched/core.c | 5 +++++
3 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 80211900f373..5a643d608ea6 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -120,12 +120,20 @@ extern struct cpumask __cpu_enabled_mask;
extern struct cpumask __cpu_present_mask;
extern struct cpumask __cpu_active_mask;
extern struct cpumask __cpu_dying_mask;
+
+#ifdef CONFIG_PREFERRED_CPU
+extern struct cpumask __cpu_preferred_mask;
+#else
+#define __cpu_preferred_mask __cpu_active_mask
+#endif
+
#define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
#define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask)
#define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask)
#define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask)
#define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask)
#define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask)
+#define cpu_preferred_mask ((const struct cpumask *)&__cpu_preferred_mask)
extern atomic_t __num_online_cpus;
extern unsigned int __num_possible_cpus;
@@ -1161,6 +1169,7 @@ void init_cpu_possible(const struct cpumask *src);
#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present))
#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active))
#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying))
+#define set_cpu_preferred(cpu, preferred) assign_cpu((cpu), &__cpu_preferred_mask, (preferred))
void set_cpu_online(unsigned int cpu, bool online);
void set_cpu_possible(unsigned int cpu, bool possible);
@@ -1256,7 +1265,12 @@ static __always_inline bool cpu_dying(unsigned int cpu)
return cpumask_test_cpu(cpu, cpu_dying_mask);
}
-#else
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+ return cpumask_test_cpu(cpu, cpu_preferred_mask);
+}
+
+#else /* NR_CPUS <= 1 */
#define num_online_cpus() 1U
#define num_possible_cpus() 1U
@@ -1294,6 +1308,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
return false;
}
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+ return cpu == 0;
+}
+
#endif /* NR_CPUS > 1 */
#define cpu_is_offline(cpu) unlikely(!cpu_online(cpu))
diff --git a/kernel/cpu.c b/kernel/cpu.c
index bc4f7a9ba64e..d623a9c5554a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3107,6 +3107,11 @@ EXPORT_SYMBOL(__cpu_dying_mask);
atomic_t __num_online_cpus __read_mostly;
EXPORT_SYMBOL(__num_online_cpus);
+#ifdef CONFIG_PREFERRED_CPU
+struct cpumask __cpu_preferred_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_preferred_mask);
+#endif
+
void init_cpu_present(const struct cpumask *src)
{
cpumask_copy(&__cpu_present_mask, src);
@@ -3164,6 +3169,7 @@ void __init boot_cpu_init(void)
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
set_cpu_online(cpu, true);
set_cpu_active(cpu, true);
+ set_cpu_preferred(cpu, true);
set_cpu_present(cpu, true);
set_cpu_possible(cpu, true);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2f4530eb543f..9e16946c9d62 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8685,6 +8685,9 @@ int sched_cpu_activate(unsigned int cpu)
*/
sched_set_rq_online(rq, cpu);
+ /* preferred is subset of active and follows its state */
+ set_cpu_preferred(cpu, true);
+
return 0;
}
@@ -8698,6 +8701,8 @@ int sched_cpu_deactivate(unsigned int cpu)
if (ret)
return ret;
+ set_cpu_preferred(cpu, false);
+
/*
* Remove CPU from nohz.idle_cpus_mask to prevent participating in
* load balancing when not active
--
2.47.3
next prev parent reply other threads:[~2026-06-25 12:47 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-25 12:46 [PATCH v5 00/24] sched: Introduce cpu_preferred_mask and steal-driven vCPU backoff Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 01/24] sched/debug: Remove unused schedstats Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 02/24] sched/docs: Document cpu_preferred_mask and Preferred CPU concept Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 03/24] kconfig: Provide PREFERRED_CPU option Shrikanth Hegde
2026-06-25 12:46 ` Shrikanth Hegde [this message]
2026-06-25 12:46 ` [PATCH v5 05/24] sysfs: Add preferred CPU file Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 06/24] sched/core: allow only preferred CPUs in is_cpu_allowed Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 07/24] sched/fair: Select preferred CPU at wakeup when possible Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 08/24] sched/fair: load balance only among preferred CPUs Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 09/24] sched/fair: Pull the load on preferred CPU Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 10/24] sched/core: Keep tick on non-preferred CPUs until tasks are out Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 11/24] sched/core: Push current task from non preferred CPU Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 12/24] sched/debug: Add migration stats due to non preferred CPUs Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 13/24] virt/steal_monitor: Add documentation Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 14/24] virt: Introduce steal monitor driver Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 15/24] virt/steal_monitor: Restore to active on module disable Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 16/24] virt/steal_monitor: Define steal_monitor structure Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 17/24] virt/steal_monitor: Add control knobs for handling steal values Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 18/24] virt/steal_monitor: Compute work at regular intervals Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 19/24] virt/steal_monitor: Provide default method to get systemwide steal time Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 20/24] virt/steal_monitor: Provide default method to inc/dec preferred CPUs Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 21/24] virt/steal_monitor: Provide default method to get num of CPUs for steal ratio Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 22/24] virt/steal_monitor: Act on steal values at regular intervals Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 23/24] virt/steal_monitor: Add direction control Shrikanth Hegde
2026-06-25 12:46 ` [PATCH v5 24/24] virt/steal_monitor: Add design check of preferred subset of active Shrikanth Hegde
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=20260625124648.802832-5-sshegde@linux.ibm.com \
--to=sshegde@linux.ibm.com \
--cc=arighi@nvidia.com \
--cc=chleroy@kernel.org \
--cc=christian.loehle@arm.com \
--cc=corbet@lwn.net \
--cc=dietmar.eggemann@arm.com \
--cc=frederic@kernel.org \
--cc=gregkh@linuxfoundation.org \
--cc=hdanton@sina.com \
--cc=huschle@linux.ibm.com \
--cc=iii@linux.ibm.com \
--cc=juri.lelli@redhat.com \
--cc=kernellwp@gmail.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maddy@linux.ibm.com \
--cc=maz@kernel.org \
--cc=mingo@kernel.org \
--cc=pauld@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=rdunlap@infradead.org \
--cc=rostedt@goodmis.org \
--cc=seanjc@google.com \
--cc=srikar@linux.ibm.com \
--cc=tglx@kernel.org \
--cc=tj@kernel.org \
--cc=tommaso.cucinotta@gmail.com \
--cc=vincent.guittot@linaro.org \
--cc=vineeth@bitbyteword.org \
--cc=vschneid@redhat.com \
--cc=yury.norov@gmail.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