From: Waiman Long <longman@redhat.com>
To: Tejun Heo <tj@kernel.org>, Zefan Li <lizefan.x@bytedance.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Frederic Weisbecker <frederic@kernel.org>,
Jonathan Corbet <corbet@lwn.net>,
"Paul E. McKenney" <paulmck@kernel.org>,
Neeraj Upadhyay <quic_neeraju@quicinc.com>,
Joel Fernandes <joel@joelfernandes.org>,
Josh Triplett <josh@joshtriplett.org>,
Boqun Feng <boqun.feng@gmail.com>,
Steven Rostedt <rostedt@goodmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Lai Jiangshan <jiangshanlai@gmail.com>,
Zqiang <qiang.zhang1211@gmail.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Shuah Khan <shuah@kernel.org>
Cc: cgroups@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, rcu@vger.kernel.org,
linux-kselftest@vger.kernel.org, Mrunal Patel <mpatel@redhat.com>,
Ryan Phillips <rphillips@redhat.com>,
Brent Rowsell <browsell@redhat.com>,
Peter Hunt <pehunt@redhat.com>,
Cestmir Kalina <ckalina@redhat.com>,
Nicolas Saenz Julienne <nsaenz@kernel.org>,
Alex Gladkov <agladkov@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Phil Auld <pauld@redhat.com>,
Paul Gortmaker <paul.gortmaker@windriver.com>,
Daniel Bristot de Oliveira <bristot@kernel.org>,
Juri Lelli <juri.lelli@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Costa Shulyupin <cshulyup@redhat.com>,
Waiman Long <longman@redhat.com>
Subject: [RFC PATCH 5/8] cgroup/cpuset: Add cpuset.cpus.isolation_full
Date: Wed, 17 Jan 2024 11:35:08 -0500 [thread overview]
Message-ID: <20240117163511.88173-6-longman@redhat.com> (raw)
In-Reply-To: <20240117163511.88173-1-longman@redhat.com>
This patch adds a new root only cpuset.cpus.isolation_full control file
for enabling or disabling full CPU isolation mode where additional CPU
isolation methods available to be used by cpuset will be turned on or
off for all the isolated CPUs within isolated partitions.
On write, cpuset.cpus.isolation_full accepts any integer. A zero value
will disable full CPU isolation while a non-zero value will enable it.
On read, cpuset.cpus.isolation_full will return either "0" (disabled)
or "1" (enabled) followed by a comma separated list of additional
CPU isolation methods that are enabled. The list of these available
isolation methods will depend on kernel configuration options used as
well as the presence of some pre-conditions for some of them.
This patch only provides the infrastructure code. The various isolation
methods will be added later on.
Signed-off-by: Waiman Long <longman@redhat.com>
---
kernel/cgroup/cpuset.c | 88 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 88 insertions(+)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 0479af76a5dc..d1d4ce213979 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -218,6 +218,30 @@ enum isolated_cpus_modifiers {
*/
static cpumask_var_t isolated_cpus;
+/*
+ * Enable full CPU isolation in isolated partitions, if set.
+ */
+static bool isolation_full;
+
+/*
+ * A flag indicating what cpuset full isolation modes can be enabled.
+ */
+static int isolation_flags;
+
+enum cpuset_isolation_types {
+ ISOL_TYPE_MAX,
+};
+
+static const char * const isolation_type_names[ISOL_TYPE_MAX] = {
+};
+
+/* Detect the cpuset isolation modes that can be enabled */
+static __init int set_isolation_flags(void)
+{
+ return 0;
+}
+late_initcall(set_isolation_flags);
+
/* List of remote partition root children */
static struct list_head remote_children;
@@ -1524,6 +1548,8 @@ static int partition_xcpus_del(int old_prs, struct cpuset *parent,
* state and the whole isolated_cpus is passed. Repeated calls with the same
* isolated_cpus will not cause further action other than a wasted mutex
* lock/unlock.
+ *
+ * The other isolation modes will only be activated when isolation_full is set.
*/
static int update_isolation_cpumasks(struct cpumask *mask, int modifier)
{
@@ -1536,6 +1562,13 @@ static int update_isolation_cpumasks(struct cpumask *mask, int modifier)
err = workqueue_unbound_exclude_cpumask(isolated_cpus);
WARN_ON_ONCE(err);
+
+ if (!isolation_flags || !isolation_full)
+ return err;
+
+ if (WARN_ON_ONCE(cpumask_empty(mask)))
+ return -EINVAL;
+
return err;
}
@@ -3514,6 +3547,7 @@ typedef enum {
FILE_EXCLUSIVE_CPULIST,
FILE_EFFECTIVE_XCPULIST,
FILE_ISOLATED_CPULIST,
+ FILE_ISOLATION_FULL,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_MEM_HARDWALL,
@@ -3713,6 +3747,25 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
case FILE_ISOLATED_CPULIST:
seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus));
break;
+ case FILE_ISOLATION_FULL:
+ if (isolation_full) {
+ int i, cnt;
+
+ /* Also print the isolation modes that are enabled */
+ seq_puts(sf, "1");
+ for (i = cnt = 0; i < ISOL_TYPE_MAX; i++) {
+ if (!(isolation_flags & BIT(i)))
+ continue;
+
+ seq_printf(sf, "%c%s", cnt ? ',' : ' ',
+ isolation_type_names[i]);
+ cnt++;
+ }
+ seq_puts(sf, "\n");
+ } else {
+ seq_puts(sf, "0\n");
+ }
+ break;
default:
ret = -EINVAL;
}
@@ -3833,6 +3886,33 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
return retval ?: nbytes;
}
+/*
+ * cpuset_write_isolfull - enable/disable cpuset isolation full mode
+ */
+static int cpuset_write_isolfull(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
+{
+ struct cpuset *cs = css_cs(css);
+ int retval = 0;
+
+ cpus_read_lock();
+ mutex_lock(&cpuset_mutex);
+ if (!is_cpuset_online(cs)) {
+ retval = -ENODEV;
+ } else if (isolation_full != !!val) {
+ isolation_full = !!val;
+ if (!cpumask_empty(isolated_cpus)) {
+ int mod = isolation_full
+ ? ISOL_CPUS_ADD : ISOL_CPUS_DELETE;
+
+ retval = update_isolation_cpumasks(isolated_cpus, mod);
+ }
+ }
+ mutex_unlock(&cpuset_mutex);
+ cpus_read_unlock();
+ return retval;
+}
+
/*
* for the common functions, 'private' gives the type of file
*/
@@ -4013,6 +4093,14 @@ static struct cftype dfl_files[] = {
.flags = CFTYPE_ONLY_ON_ROOT,
},
+ {
+ .name = "cpus.isolation_full",
+ .seq_show = cpuset_common_seq_show,
+ .write_u64 = cpuset_write_isolfull,
+ .private = FILE_ISOLATION_FULL,
+ .flags = CFTYPE_ONLY_ON_ROOT,
+ },
+
{ } /* terminate */
};
--
2.39.3
next prev parent reply other threads:[~2024-01-17 16:36 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-17 16:35 [RFC PATCH 0/8] cgroup/cpuset: Support RCU_NOCB on isolated partitions Waiman Long
2024-01-17 16:35 ` [RFC PATCH 1/8] rcu/nocb: Pass a cpumask instead of a single CPU to offload/deoffload Waiman Long
2024-01-17 16:35 ` [RFC PATCH 2/8] rcu/nocb: Prepare to change nocb cpumask from CPU-hotplug protected cpuset caller Waiman Long
2024-01-17 16:35 ` [RFC PATCH 3/8] rcu/no_cb: Add rcu_nocb_enabled() to expose the rcu_nocb state Waiman Long
2024-01-17 16:35 ` [RFC PATCH 4/8] cgroup/cpuset: Better tracking of addition/deletion of isolated CPUs Waiman Long
2024-01-17 16:35 ` Waiman Long [this message]
2024-01-17 16:35 ` [RFC PATCH 6/8] cgroup/cpuset: Enable dynamic rcu_nocb mode on " Waiman Long
2024-01-17 16:35 ` [RFC PATCH 7/8] cgroup/cpuset: Document the new cpuset.cpus.isolation_full control file Waiman Long
2024-01-17 16:35 ` [RFC PATCH 8/8] cgroup/cpuset: Update test_cpuset_prs.sh to handle cpuset.cpus.isolation_full Waiman Long
2024-01-17 17:07 ` [RFC PATCH 0/8] cgroup/cpuset: Support RCU_NOCB on isolated partitions Tejun Heo
2024-01-17 17:15 ` Waiman Long
2024-02-06 12:56 ` Frederic Weisbecker
2024-02-06 19:15 ` Marcelo Tosatti
2024-02-07 14:47 ` Frederic Weisbecker
2024-02-07 14:59 ` Marcelo Tosatti
2024-02-10 4:19 ` Waiman Long
2024-01-19 10:24 ` Paul E. McKenney
2024-02-11 1:46 ` Waiman Long
2024-01-22 15:07 ` Michal Koutný
2024-01-23 5:50 ` Waiman Long
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=20240117163511.88173-6-longman@redhat.com \
--to=longman@redhat.com \
--cc=agladkov@redhat.com \
--cc=boqun.feng@gmail.com \
--cc=bristot@kernel.org \
--cc=browsell@redhat.com \
--cc=cgroups@vger.kernel.org \
--cc=ckalina@redhat.com \
--cc=corbet@lwn.net \
--cc=cshulyup@redhat.com \
--cc=dave@stgolabs.net \
--cc=frederic@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=juri.lelli@redhat.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=lizefan.x@bytedance.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=mpatel@redhat.com \
--cc=mtosatti@redhat.com \
--cc=nsaenz@kernel.org \
--cc=paul.gortmaker@windriver.com \
--cc=pauld@redhat.com \
--cc=paulmck@kernel.org \
--cc=pehunt@redhat.com \
--cc=peterz@infradead.org \
--cc=qiang.zhang1211@gmail.com \
--cc=quic_neeraju@quicinc.com \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=rphillips@redhat.com \
--cc=shuah@kernel.org \
--cc=tj@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).