linux-kernel - [RFC PATCH 8/9] sched/rt: Remove support for cgroups-v1

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250605071412.139240-9-yurand2000@gmail.com>
Date: Thu,  5 Jun 2025 09:14:11 +0200
From: Yuri Andriaccio <yurand2000@...il.com>
To: Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>
Cc: linux-kernel@...r.kernel.org,
	Luca Abeni <luca.abeni@...tannapisa.it>,
	Yuri Andriaccio <yuri.andriaccio@...tannapisa.it>
Subject: [RFC PATCH 8/9] sched/rt: Remove support for cgroups-v1

Disable control files for cgroups-v1, and allow only cgroups-v2. This should
simplify maintaining the code, also because cgroups-v1 is deprecated.

Set the default rt-cgroups runtime to zero, otherwise a cgroup-v1 kernel will
not be able to start SCHED_DEADLINE tasks.

Allow zeroing the runtime of the root control group. This runtime only affects
the available bandwidth of the rt-cgroup hierarchy but not the SCHED_FIFO /
SCHED_RR tasks on the global runqueue.

Notes:
Disabling the root control group bandwidth should not cause any side effect, as
SCHED_FIFO / SCHED_RR tasks do not depend on it since the introduction of
fair_servers.

Signed-off-by: Yuri Andriaccio <yurand2000@...il.com>
---
 kernel/sched/core.c     | 22 ++--------------------
 kernel/sched/rt.c       | 13 +++++--------
 kernel/sched/syscalls.c |  2 +-
 3 files changed, 8 insertions(+), 29 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cad2963a2..9c8bc9728 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8566,7 +8566,7 @@ void __init sched_init(void)
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_dl_bandwidth(&root_task_group.dl_bandwidth,
-			global_rt_period(), global_rt_runtime());
+			global_rt_period(), 0);
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -9198,7 +9198,7 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 		goto scx_check;
 
 	cgroup_taskset_for_each(task, css, tset) {
-		if (!sched_rt_can_attach(css_tg(css), task))
+		if (rt_task(task) && !sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
 	}
 scx_check:
@@ -9873,20 +9873,6 @@ static struct cftype cpu_legacy_files[] = {
 };
 
 #ifdef CONFIG_RT_GROUP_SCHED
-static struct cftype rt_group_files[] = {
-	{
-		.name = "rt_runtime_us",
-		.read_s64 = cpu_rt_runtime_read,
-		.write_s64 = cpu_rt_runtime_write,
-	},
-	{
-		.name = "rt_period_us",
-		.read_u64 = cpu_rt_period_read_uint,
-		.write_u64 = cpu_rt_period_write_uint,
-	},
-	{ }	/* Terminate */
-};
-
 # ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
 DEFINE_STATIC_KEY_FALSE(rt_group_sched);
 # else
@@ -9912,10 +9898,6 @@ __setup("rt_group_sched=", setup_rt_group_sched);
 
 static int __init cpu_rt_group_init(void)
 {
-	if (!rt_group_sched_enabled())
-		return 0;
-
-	WARN_ON(cgroup_add_legacy_cftypes(&cpu_cgrp_subsys, rt_group_files));
 	return 0;
 }
 subsys_initcall(cpu_rt_group_init);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9d17bda66..ce3320f12 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2197,13 +2197,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 {
 	int i, err = 0;
 
-	/*
-	 * Disallowing the root group RT runtime is BAD, it would disallow the
-	 * kernel creating (and or operating) RT threads.
-	 */
-	if (tg == &root_task_group && rt_runtime == 0)
-		return -EINVAL;
-
 	/* No period doesn't make any sense. */
 	if (rt_period == 0)
 		return -EINVAL;
@@ -2297,8 +2290,12 @@ static int sched_rt_global_constraints(void)
 
 int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 {
+	/* Allow executing in the root cgroup regardless of allowed bandwidth */
+	if (tg == &root_task_group)
+		return 1;
+
 	/* Don't accept real-time tasks when there is no way for them to run */
-	if (rt_group_sched_enabled() && rt_task(tsk) && tg->dl_bandwidth.dl_runtime == 0)
+	if (rt_group_sched_enabled() && tg->dl_bandwidth.dl_runtime == 0)
 		return 0;
 
 	return 1;
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 6c6666b39..45a38fe5e 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -636,7 +636,7 @@ int __sched_setscheduler(struct task_struct *p,
 		 */
 		if (rt_group_sched_enabled() &&
 				dl_bandwidth_enabled() && rt_policy(policy) &&
-				task_group(p)->dl_bandwidth.dl_runtime == 0 &&
+				!sched_rt_can_attach(task_group(p), p) &&
 				!task_group_is_autogroup(task_group(p))) {
 			retval = -EPERM;
 			goto unlock;
-- 
2.49.0