From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: "Frederic Weisbecker" <frederic@kernel.org>,
"Michal Koutný" <mkoutny@suse.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Catalin Marinas" <catalin.marinas@arm.com>,
"Danilo Krummrich" <dakr@kernel.org>,
"David S . Miller" <davem@davemloft.net>,
"Eric Dumazet" <edumazet@google.com>,
"Gabriele Monaco" <gmonaco@redhat.com>,
"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
"Ingo Molnar" <mingo@redhat.com>,
"Jakub Kicinski" <kuba@kernel.org>,
"Jens Axboe" <axboe@kernel.dk>,
"Johannes Weiner" <hannes@cmpxchg.org>,
"Lai Jiangshan" <jiangshanlai@gmail.com>,
"Marco Crivellari" <marco.crivellari@suse.com>,
"Michal Hocko" <mhocko@suse.com>,
"Muchun Song" <muchun.song@linux.dev>,
"Paolo Abeni" <pabeni@redhat.com>,
"Peter Zijlstra" <peterz@infradead.org>,
"Phil Auld" <pauld@redhat.com>,
"Rafael J . Wysocki" <rafael@kernel.org>,
"Roman Gushchin" <roman.gushchin@linux.dev>,
"Shakeel Butt" <shakeel.butt@linux.dev>,
"Simon Horman" <horms@kernel.org>, "Tejun Heo" <tj@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Vlastimil Babka" <vbabka@suse.cz>,
"Waiman Long" <longman@redhat.com>,
"Will Deacon" <will@kernel.org>,
cgroups@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
linux-block@vger.kernel.org, linux-mm@kvack.org,
linux-pci@vger.kernel.org, netdev@vger.kernel.org
Subject: [PATCH 12/31] sched/isolation: Convert housekeeping cpumasks to rcu pointers
Date: Wed, 5 Nov 2025 22:03:28 +0100 [thread overview]
Message-ID: <20251105210348.35256-13-frederic@kernel.org> (raw)
In-Reply-To: <20251105210348.35256-1-frederic@kernel.org>
HK_TYPE_DOMAIN's cpumask will soon be made modifiable by cpuset.
A synchronization mechanism is then needed to synchronize the updates
with the housekeeping cpumask readers.
Turn the housekeeping cpumasks into RCU pointers. Once a housekeeping
cpumask will be modified, the update side will wait for an RCU grace
period and propagate the change to interested subsystem when deemed
necessary.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
kernel/sched/isolation.c | 58 +++++++++++++++++++++++++---------------
kernel/sched/sched.h | 1 +
2 files changed, 37 insertions(+), 22 deletions(-)
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 8690fb705089..bee6c04be103 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -21,7 +21,7 @@ DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
EXPORT_SYMBOL_GPL(housekeeping_overridden);
struct housekeeping {
- cpumask_var_t cpumasks[HK_TYPE_MAX];
+ struct cpumask __rcu *cpumasks[HK_TYPE_MAX];
unsigned long flags;
};
@@ -33,17 +33,28 @@ bool housekeeping_enabled(enum hk_type type)
}
EXPORT_SYMBOL_GPL(housekeeping_enabled);
+const struct cpumask *housekeeping_cpumask(enum hk_type type)
+{
+ if (static_branch_unlikely(&housekeeping_overridden)) {
+ if (housekeeping.flags & BIT(type)) {
+ return rcu_dereference_check(housekeeping.cpumasks[type], 1);
+ }
+ }
+ return cpu_possible_mask;
+}
+EXPORT_SYMBOL_GPL(housekeeping_cpumask);
+
int housekeeping_any_cpu(enum hk_type type)
{
int cpu;
if (static_branch_unlikely(&housekeeping_overridden)) {
if (housekeeping.flags & BIT(type)) {
- cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id());
+ cpu = sched_numa_find_closest(housekeeping_cpumask(type), smp_processor_id());
if (cpu < nr_cpu_ids)
return cpu;
- cpu = cpumask_any_and_distribute(housekeeping.cpumasks[type], cpu_online_mask);
+ cpu = cpumask_any_and_distribute(housekeeping_cpumask(type), cpu_online_mask);
if (likely(cpu < nr_cpu_ids))
return cpu;
/*
@@ -59,28 +70,18 @@ int housekeeping_any_cpu(enum hk_type type)
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
-const struct cpumask *housekeeping_cpumask(enum hk_type type)
-{
- if (static_branch_unlikely(&housekeeping_overridden))
- if (housekeeping.flags & BIT(type))
- return housekeeping.cpumasks[type];
- return cpu_possible_mask;
-}
-EXPORT_SYMBOL_GPL(housekeeping_cpumask);
-
void housekeeping_affine(struct task_struct *t, enum hk_type type)
{
if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping.flags & BIT(type))
- set_cpus_allowed_ptr(t, housekeeping.cpumasks[type]);
+ set_cpus_allowed_ptr(t, housekeeping_cpumask(type));
}
EXPORT_SYMBOL_GPL(housekeeping_affine);
bool housekeeping_test_cpu(int cpu, enum hk_type type)
{
- if (static_branch_unlikely(&housekeeping_overridden))
- if (housekeeping.flags & BIT(type))
- return cpumask_test_cpu(cpu, housekeeping.cpumasks[type]);
+ if (static_branch_unlikely(&housekeeping_overridden) && housekeeping.flags & BIT(type))
+ return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
return true;
}
EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
@@ -96,20 +97,33 @@ void __init housekeeping_init(void)
if (housekeeping.flags & HK_FLAG_KERNEL_NOISE)
sched_tick_offload_init();
-
+ /*
+ * Realloc with a proper allocator so that any cpumask update
+ * can indifferently free the old version with kfree().
+ */
for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
+ struct cpumask *omask, *nmask = kmalloc(cpumask_size(), GFP_KERNEL);
+
+ if (WARN_ON_ONCE(!nmask))
+ return;
+
+ omask = rcu_dereference(housekeeping.cpumasks[type]);
+
/* We need at least one CPU to handle housekeeping work */
- WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type]));
+ WARN_ON_ONCE(cpumask_empty(omask));
+ cpumask_copy(nmask, omask);
+ RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
+ memblock_free(omask, cpumask_size());
}
}
static void __init housekeeping_setup_type(enum hk_type type,
cpumask_var_t housekeeping_staging)
{
+ struct cpumask *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
- alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]);
- cpumask_copy(housekeeping.cpumasks[type],
- housekeeping_staging);
+ cpumask_copy(mask, housekeeping_staging);
+ RCU_INIT_POINTER(housekeeping.cpumasks[type], mask);
}
static int __init housekeeping_setup(char *str, unsigned long flags)
@@ -162,7 +176,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) {
if (!cpumask_equal(housekeeping_staging,
- housekeeping.cpumasks[type])) {
+ housekeeping_cpumask(type))) {
pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
goto free_housekeeping_staging;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index adfb6e3409d7..2fc1ddde3120 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -42,6 +42,7 @@
#include <linux/ktime_api.h>
#include <linux/lockdep_api.h>
#include <linux/lockdep.h>
+#include <linux/memblock.h>
#include <linux/minmax.h>
#include <linux/mm.h>
#include <linux/module.h>
--
2.51.0
next prev parent reply other threads:[~2025-11-05 21:05 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-05 21:03 [PATCH 00/31 v4] cpuset/isolation: Honour kthreads preferred affinity Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 01/31] PCI: Prepare to protect against concurrent isolated cpuset change Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 02/31] cpu: Revert "cpu/hotplug: Prevent self deadlock on CPU hot-unplug" Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 03/31] memcg: Prepare to protect against concurrent isolated cpuset change Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 04/31] mm: vmstat: " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 05/31] sched/isolation: Save boot defined domain flags Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 06/31] cpuset: Convert boot_hk_cpus to use HK_TYPE_DOMAIN_BOOT Frederic Weisbecker
2025-11-06 1:20 ` Chen Ridong
2025-11-05 21:03 ` [PATCH 07/31] driver core: cpu: Convert /sys/devices/system/cpu/isolated " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 08/31] net: Keep ignoring isolated cpuset change Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 09/31] block: Protect against concurrent " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 10/31] cpu: Provide lockdep check for CPU hotplug lock write-held Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 11/31] cpuset: Provide lockdep check for cpuset lock held Frederic Weisbecker
2025-11-05 21:03 ` Frederic Weisbecker [this message]
2025-11-05 21:03 ` [PATCH 13/31] cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset Frederic Weisbecker
2025-11-08 9:05 ` Chen Ridong
2025-11-05 21:03 ` [PATCH 14/31] sched/isolation: Flush memcg workqueues on cpuset isolated partition change Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 15/31] sched/isolation: Flush vmstat " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 16/31] PCI: Flush PCI probe workqueue " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 17/31] cpuset: Propagate cpuset isolation update to workqueue through housekeeping Frederic Weisbecker
2025-11-06 0:55 ` Chen Ridong
2025-11-05 21:03 ` [PATCH 18/31] cpuset: Remove cpuset_cpu_is_isolated() Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 19/31] sched/isolation: Remove HK_TYPE_TICK test from cpu_is_isolated() Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 20/31] PCI: Remove superfluous HK_TYPE_WQ check Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 21/31] kthread: Refine naming of affinity related fields Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 22/31] kthread: Include unbound kthreads in the managed affinity list Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 23/31] kthread: Include kthreadd to " Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 24/31] kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 25/31] sched: Switch the fallback task allowed cpumask to HK_TYPE_DOMAIN Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 26/31] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 27/31] sched/arm64: Move fallback task cpumask to HK_TYPE_DOMAIN Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 28/31] kthread: Honour kthreads preferred affinity after cpuset changes Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 29/31] kthread: Comment on the purpose and placement of kthread_affine_node() call Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 30/31] kthread: Document kthread_affine_preferred() Frederic Weisbecker
2025-11-05 21:03 ` [PATCH 31/31] doc: Add housekeeping documentation Frederic Weisbecker
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=20251105210348.35256-13-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=catalin.marinas@arm.com \
--cc=cgroups@vger.kernel.org \
--cc=dakr@kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gmonaco@redhat.com \
--cc=gregkh@linuxfoundation.org \
--cc=hannes@cmpxchg.org \
--cc=horms@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-pci@vger.kernel.org \
--cc=longman@redhat.com \
--cc=marco.crivellari@suse.com \
--cc=mhocko@suse.com \
--cc=mingo@redhat.com \
--cc=mkoutny@suse.com \
--cc=muchun.song@linux.dev \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).