linux-kernel - [PATCH V4 3/6] Sched: Tunable to specify duration of time slice extension

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: <20250513214554.4160454-4-prakash.sangappa@oracle.com>
Date: Tue, 13 May 2025 21:45:51 +0000
From: Prakash Sangappa <prakash.sangappa@...cle.com>
To: linux-kernel@...r.kernel.org
Cc: peterz@...radead.org, rostedt@...dmis.org, mathieu.desnoyers@...icios.com,
        tglx@...utronix.de, bigeasy@...utronix.de, kprateek.nayak@....com
Subject: [PATCH V4 3/6] Sched: Tunable to specify duration of time slice extension

Add a tunable to specify duration of scheduler time slice extension.
The default will be set to 30us and the max value that can be specified
is 100us. Setting it to 0, disables scheduler time slice extension.

Signed-off-by: Prakash Sangappa <prakash.sangappa@...cle.com>
---
 include/linux/sched.h     |  3 +++
 include/uapi/linux/rseq.h |  5 +++--
 kernel/rseq.c             |  7 +++++--
 kernel/sched/core.c       | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 71e6c8221c1e..c279232ca6a2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -407,6 +407,9 @@ static inline void sched_domains_mutex_lock(void) { }
 static inline void sched_domains_mutex_unlock(void) { }
 #endif
 
+/* Scheduler time slice extension */
+extern unsigned int sysctl_sched_preempt_delay_us;
+
 struct sched_param {
 	int sched_priority;
 };
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index f4813d931387..015534f064af 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -137,8 +137,9 @@ struct rseq {
 	 *     this thread.
 	 * - RSEQ_CS_FLAG_DELAY_RESCHED
 	 *     Request by user thread to delay preemption. With use
-	 *     of a timer, kernel grants extra cpu time upto 30us for this
-	 *     thread before being rescheduled.
+	 *     of a timer, kernel grants extra cpu time upto the tunable
+	 *     'sched_preempt_delay_us' value for this thread before it gets
+	 *     rescheduled.
 	 * - RSEQ_CS_FLAG_RESCHEDULED
 	 *     Set by kernel if the thread was rescheduled in the extra time
 	 *     granted due to request RSEQ_CS_DELAY_RESCHED. This bit is
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 9355654e9b38..44d0f3ae0cd3 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -456,6 +456,8 @@ bool rseq_delay_resched(void)
 	if (!IS_ENABLED(CONFIG_SCHED_HRTICK))
 		return false;
 
+	if (!sysctl_sched_preempt_delay_us)
+		return false;
 	if (!t->rseq)
 		return false;
 
@@ -489,8 +491,9 @@ void rseq_delay_resched_fini(void)
 	 * If your critical section is longer than 30 us you get to keep the
 	 * pieces.
 	 */
-	if (t->sched_time_delay)
-		hrtick_local_start(30 * NSEC_PER_USEC);
+	if (sysctl_sched_preempt_delay_us && t->sched_time_delay)
+		hrtick_local_start(sysctl_sched_preempt_delay_us *
+				   NSEC_PER_USEC);
 #endif
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 86583fb72914..31928cbcd907 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -148,6 +148,15 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
  */
 __read_mostly unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
 
+/*
+ * Scheduler time slice extension, duration in microsecs.
+ * Max value allowed 100us, default is 30us.
+ * If set to 0, scheduler time slice extension is disabled.
+ */
+#define SCHED_PREEMPT_DELAY_DEFAULT_US	30
+__read_mostly unsigned int sysctl_sched_preempt_delay_us =
+	SCHED_PREEMPT_DELAY_DEFAULT_US;
+
 __read_mostly int scheduler_running;
 
 #ifdef CONFIG_SCHED_CORE
@@ -4664,6 +4673,20 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf
 #endif /* CONFIG_PROC_SYSCTL */
 #endif /* CONFIG_SCHEDSTATS */
 
+static int sysctl_sched_preempt_delay(const struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err;
+
+	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (sysctl_sched_preempt_delay_us > SCHED_PREEMPT_DELAY_DEFAULT_US)
+		pr_warn("Sched preemption delay time set higher then default value %d us\n",
+			SCHED_PREEMPT_DELAY_DEFAULT_US);
+	return err;
+}
+
 #ifdef CONFIG_SYSCTL
 static const struct ctl_table sched_core_sysctls[] = {
 #ifdef CONFIG_SCHEDSTATS
@@ -4711,6 +4734,15 @@ static const struct ctl_table sched_core_sysctls[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
+	{
+		.procname	= "sched_preempt_delay_us",
+		.data		= &sysctl_sched_preempt_delay_us,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sched_preempt_delay,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE_HUNDRED,
+	},
 };
 static int __init sched_core_sysctl_init(void)
 {
-- 
2.43.5