From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Marco Crivellari <marco.crivellari@suse.com>,
Michal Hocko <mhocko@suse.com>,
Peter Zijlstra <peterz@infradead.org>, Tejun Heo <tj@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Vlastimil Babka <vbabka@suse.cz>,
Waiman Long <longman@redhat.com>
Subject: [PATCH 14/27] sched/isolation: Convert housekeeping cpumasks to rcu pointers
Date: Fri, 20 Jun 2025 17:22:55 +0200 [thread overview]
Message-ID: <20250620152308.27492-15-frederic@kernel.org> (raw)
In-Reply-To: <20250620152308.27492-1-frederic@kernel.org>
HK_TYPE_DOMAIN's cpumask will soon be made modifyable by cpuset.
Sleepable users of housekeeping can synchronize against cpumask
modifications using the housekeeping rwsem. Other callsites need an
alternative.
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 | 52 ++++++++++++++++++++++++++--------------
kernel/sched/sched.h | 1 +
2 files changed, 35 insertions(+), 18 deletions(-)
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9ecf53c5328b..75505668dcb9 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -15,7 +15,7 @@ enum hk_flags {
HK_FLAG_KERNEL_NOISE = BIT(HK_TYPE_KERNEL_NOISE),
};
-static cpumask_var_t housekeeping_cpumasks[HK_TYPE_MAX];
+static struct cpumask __rcu *housekeeping_cpumasks[HK_TYPE_MAX];
unsigned long housekeeping_flags;
EXPORT_SYMBOL_GPL(housekeeping_flags);
@@ -37,16 +37,25 @@ void housekeeping_unlock(void)
percpu_up_read(&housekeeping_pcpu_lock);
}
+const struct cpumask *housekeeping_cpumask(enum hk_type type)
+{
+ 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 (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;
/*
@@ -62,25 +71,17 @@ int housekeeping_any_cpu(enum hk_type type)
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
-const struct cpumask *housekeeping_cpumask(enum hk_type type)
-{
- 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 (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 (housekeeping_flags & BIT(type))
- return cpumask_test_cpu(cpu, housekeeping_cpumasks[type]);
+ return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
return true;
}
EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
@@ -95,9 +96,23 @@ 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());
}
}
@@ -105,9 +120,10 @@ static void __init housekeeping_setup_type(enum hk_type type,
cpumask_var_t housekeeping_staging)
{
- alloc_bootmem_cpumask_var(&housekeeping_cpumasks[type]);
- cpumask_copy(housekeeping_cpumasks[type],
- housekeeping_staging);
+ struct cpumask *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
+
+ cpumask_copy(mask, housekeeping_staging);
+ RCU_INIT_POINTER(housekeeping_cpumasks[type], mask);
}
static int __init housekeeping_setup(char *str, unsigned long flags)
@@ -160,7 +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 0cdb560ef2f3..407e7f5ad929 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>
--
2.48.1
next prev parent reply other threads:[~2025-06-20 15:23 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-20 15:22 [PATCH 00/27] cpuset/isolation: Honour kthreads preferred affinity Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 01/27] sched/isolation: Remove housekeeping static key Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 02/27] sched/isolation: Introduce housekeeping per-cpu rwsem Frederic Weisbecker
2025-06-23 17:34 ` Waiman Long
2025-06-23 17:39 ` Tejun Heo
2025-06-23 17:57 ` Waiman Long
2025-06-23 18:03 ` Tejun Heo
2025-06-25 14:30 ` Frederic Weisbecker
2025-06-25 12:18 ` Phil Auld
2025-06-25 14:34 ` Frederic Weisbecker
2025-06-25 15:50 ` Phil Auld
2025-06-27 0:11 ` Waiman Long
2025-06-27 0:48 ` Phil Auld
2025-06-30 12:59 ` Thomas Gleixner
2025-06-25 14:18 ` Frederic Weisbecker
2025-06-26 23:58 ` Waiman Long
2025-06-20 15:22 ` [PATCH 03/27] PCI: Protect against concurrent change of housekeeping cpumask Frederic Weisbecker
2025-06-20 16:17 ` Bjorn Helgaas
2025-06-26 14:51 ` Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 04/27] cpu: Protect against concurrent isolated cpuset change Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 05/27] memcg: Prepare to protect " Frederic Weisbecker
2025-06-20 19:19 ` Shakeel Butt
2025-06-20 15:22 ` [PATCH 06/27] mm: vmstat: " Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 07/27] sched/isolation: Save boot defined domain flags Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 08/27] cpuset: Convert boot_hk_cpus to use HK_TYPE_DOMAIN_BOOT Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 09/27] driver core: cpu: Convert /sys/devices/system/cpu/isolated " Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 10/27] net: Keep ignoring isolated cpuset change Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 11/27] block: Protect against concurrent " Frederic Weisbecker
2025-06-20 15:59 ` Bart Van Assche
2025-06-26 15:03 ` Frederic Weisbecker
2025-06-23 5:46 ` Christoph Hellwig
2025-06-26 15:33 ` Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 12/27] cpu: Provide lockdep check for CPU hotplug lock write-held Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 13/27] cpuset: Provide lockdep check for cpuset lock held Frederic Weisbecker
2025-06-20 15:22 ` Frederic Weisbecker [this message]
2025-06-20 15:22 ` [PATCH 15/27] cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 16/27] sched/isolation: Flush memcg workqueues on cpuset isolated partition change Frederic Weisbecker
2025-06-20 19:30 ` Shakeel Butt
2025-06-20 15:22 ` [PATCH 17/27] sched/isolation: Flush vmstat " Frederic Weisbecker
2025-06-20 15:22 ` [PATCH 18/27] cpuset: Propagate cpuset isolation update to workqueue through housekeeping Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 19/27] cpuset: Remove cpuset_cpu_is_isolated() Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 20/27] sched/isolation: Remove HK_TYPE_TICK test from cpu_is_isolated() Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 21/27] kthread: Refine naming of affinity related fields Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 22/27] kthread: Include unbound kthreads in the managed affinity list Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 23/27] kthread: Include kthreadd to " Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 24/27] kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 25/27] sched: Switch the fallback task allowed cpumask to HK_TYPE_DOMAIN Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 26/27] kthread: Honour kthreads preferred affinity after cpuset changes Frederic Weisbecker
2025-06-20 15:23 ` [PATCH 27/27] kthread: Comment on the purpose and placement of kthread_affine_node() call Frederic Weisbecker
2025-06-20 16:08 ` [PATCH 00/27] cpuset/isolation: Honour kthreads preferred affinity Bjorn Helgaas
2025-06-26 14:57 ` 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=20250620152308.27492-15-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=marco.crivellari@suse.com \
--cc=mhocko@suse.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.