From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: "Frederic Weisbecker" <frederic@kernel.org>,
"Michal Koutný" <mkoutny@suse.com>,
"Ingo Molnar" <mingo@redhat.com>,
"Johannes Weiner" <hannes@cmpxchg.org>,
"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>,
cgroups@vger.kernel.org
Subject: [PATCH 14/33] cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset
Date: Fri, 29 Aug 2025 17:47:55 +0200 [thread overview]
Message-ID: <20250829154814.47015-15-frederic@kernel.org> (raw)
In-Reply-To: <20250829154814.47015-1-frederic@kernel.org>
Until now, HK_TYPE_DOMAIN used to only include boot defined isolated
CPUs passed through isolcpus= boot option. Users interested in also
knowing the runtime defined isolated CPUs through cpuset must use
different APIs: cpuset_cpu_is_isolated(), cpu_is_isolated(), etc...
There are many drawbacks to that approach:
1) Most interested subsystems want to know about all isolated CPUs, not
just those defined on boot time.
2) cpuset_cpu_is_isolated() / cpu_is_isolated() are not synchronized with
concurrent cpuset changes.
3) Further cpuset modifications are not propagated to subsystems
Solve 1) and 2) and centralize all isolated CPUs within the
HK_TYPE_DOMAIN housekeeping cpumask.
Subsystems can rely on RCU to synchronize against concurrent changes.
The propagation mentioned in 3) will be handled in further patches.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
include/linux/sched/isolation.h | 4 +-
kernel/cgroup/cpuset.c | 2 +
kernel/sched/isolation.c | 65 ++++++++++++++++++++++++++++++---
kernel/sched/sched.h | 1 +
4 files changed, 65 insertions(+), 7 deletions(-)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 9262378760b1..199d0fc4646f 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -36,12 +36,13 @@ extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
static inline bool housekeeping_cpu(int cpu, enum hk_type type)
{
- if (housekeeping_flags & BIT(type))
+ if (READ_ONCE(housekeeping_flags) & BIT(type))
return housekeeping_test_cpu(cpu, type);
else
return true;
}
+extern int housekeeping_update(struct cpumask *mask, enum hk_type type);
extern void __init housekeeping_init(void);
#else
@@ -74,6 +75,7 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type)
return true;
}
+static inline int housekeeping_update(struct cpumask *mask, enum hk_type type) { return 0; }
static inline void housekeeping_init(void) { }
#endif /* CONFIG_CPU_ISOLATION */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2d2fc74bc00c..4f2bc68332a7 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1351,6 +1351,8 @@ static void update_unbound_workqueue_cpumask(bool isolcpus_updated)
ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
WARN_ON_ONCE(ret < 0);
+ ret = housekeeping_update(isolated_cpus, HK_TYPE_DOMAIN);
+ WARN_ON_ONCE(ret < 0);
}
/**
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 5ddb8dc5ca91..48f3b6b20604 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -23,16 +23,39 @@ EXPORT_SYMBOL_GPL(housekeeping_flags);
bool housekeeping_enabled(enum hk_type type)
{
- return !!(housekeeping_flags & BIT(type));
+ return !!(READ_ONCE(housekeeping_flags) & BIT(type));
}
EXPORT_SYMBOL_GPL(housekeeping_enabled);
+static bool housekeeping_dereference_check(enum hk_type type)
+{
+ if (type == HK_TYPE_DOMAIN) {
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_write_held())
+ return true;
+ if (IS_ENABLED(CONFIG_CPUSETS) && lockdep_is_cpuset_held())
+ return true;
+
+ return false;
+ }
+
+ return true;
+}
+
+static inline struct cpumask *__housekeeping_cpumask(enum hk_type type)
+{
+ return rcu_dereference_check(housekeeping_cpumasks[type],
+ housekeeping_dereference_check(type));
+}
+
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;
+ const struct cpumask *mask = NULL;
+
+ if (READ_ONCE(housekeeping_flags) & BIT(type))
+ mask = __housekeeping_cpumask(type);
+ if (!mask)
+ mask = cpu_possible_mask;
+ return mask;
}
EXPORT_SYMBOL_GPL(housekeeping_cpumask);
@@ -70,12 +93,42 @@ EXPORT_SYMBOL_GPL(housekeeping_affine);
bool housekeeping_test_cpu(int cpu, enum hk_type type)
{
- if (housekeeping_flags & BIT(type))
+ if (READ_ONCE(housekeeping_flags) & BIT(type))
return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
return true;
}
EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
+int housekeeping_update(struct cpumask *mask, enum hk_type type)
+{
+ struct cpumask *trial, *old = NULL;
+
+ if (type != HK_TYPE_DOMAIN)
+ return -ENOTSUPP;
+
+ trial = kmalloc(sizeof(*trial), GFP_KERNEL);
+ if (!trial)
+ return -ENOMEM;
+
+ cpumask_andnot(trial, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT), mask);
+ if (!cpumask_intersects(trial, cpu_online_mask)) {
+ kfree(trial);
+ return -EINVAL;
+ }
+
+ if (housekeeping_flags & BIT(type))
+ old = __housekeeping_cpumask(type);
+ else
+ WRITE_ONCE(housekeeping_flags, housekeeping_flags | BIT(type));
+ rcu_assign_pointer(housekeeping_cpumasks[type], trial);
+
+ synchronize_rcu();
+
+ kfree(old);
+
+ return 0;
+}
+
void __init housekeeping_init(void)
{
enum hk_type type;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0b1a233dcabf..d3512138027b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -30,6 +30,7 @@
#include <linux/context_tracking.h>
#include <linux/cpufreq.h>
#include <linux/cpumask_api.h>
+#include <linux/cpuset.h>
#include <linux/ctype.h>
#include <linux/file.h>
#include <linux/fs_api.h>
--
2.51.0
next prev parent reply other threads:[~2025-08-29 15:49 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20250829154814.47015-1-frederic@kernel.org>
2025-08-29 15:47 ` [PATCH 07/33] cpuset: Convert boot_hk_cpus to use HK_TYPE_DOMAIN_BOOT Frederic Weisbecker
2025-08-29 15:47 ` [PATCH 12/33] cpuset: Provide lockdep check for cpuset lock held Frederic Weisbecker
2025-08-29 15:47 ` Frederic Weisbecker [this message]
2025-09-01 0:40 ` [PATCH 14/33] cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset Waiman Long
2025-08-29 15:47 ` [PATCH 15/33] sched/isolation: Flush memcg workqueues on cpuset isolated partition change Frederic Weisbecker
2025-08-29 15:47 ` [PATCH 17/33] cpuset: Propagate cpuset isolation update to workqueue through housekeeping Frederic Weisbecker
2025-09-01 2:51 ` Waiman Long
2025-08-29 15:47 ` [PATCH 18/33] cpuset: Remove cpuset_cpu_is_isolated() Frederic Weisbecker
2025-08-29 15:48 ` [PATCH 26/33] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Frederic Weisbecker
2025-09-02 15:44 ` Waiman Long
2025-08-29 15:48 ` [PATCH 28/33] kthread: Honour kthreads preferred affinity after cpuset changes 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=20250829154814.47015-15-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=hannes@cmpxchg.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=mkoutny@suse.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 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).