Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 10 May 2021 14:05:13 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     tglx@linutronix.de, mingo@kernel.org, juri.lelli@redhat.com,
        vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
        rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
        bristot@redhat.com, bsingharora@gmail.com, pbonzini@redhat.com,
        maz@kernel.org
Cc:     linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
        riel@surriel.com, hannes@cmpxchg.org
Subject: [PATCH 7/6] delayacct: Add sysctl to enable at runtime
Message-ID: <YJkhebGJAywaZowX@hirez.programming.kicks-ass.net>
References: <20210505105940.190490250@infradead.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210505105940.190490250@infradead.org>
Precedence: bulk


Just like sched_schedstats, allow runtime enabling (and disabling) of
delayacct. This is useful if one forgot to add the delayacct boot time
option.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 Documentation/accounting/delay-accounting.rst |    6 ++--
 kernel/delayacct.c                            |   36 ++++++++++++++++++++++++--
 kernel/sysctl.c                               |   12 ++++++++
 3 files changed, 50 insertions(+), 4 deletions(-)

--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -74,8 +74,10 @@ Delay accounting is disabled by default
 
    delayacct
 
-to the kernel boot options. The rest of the instructions
-below assume this has been done.
+to the kernel boot options. The rest of the instructions below assume this has
+been done. Alternatively, use sysctl kernel.sched_delayacct to switch the state
+at runtime. Note however that only tasks started after enabling it will have
+delayacct information.
 
 After the system has booted up, use a utility
 similar to  getdelays.c to access the delays
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -18,6 +18,17 @@ DEFINE_STATIC_KEY_FALSE(delayacct_key);
 int delayacct_on __read_mostly;	/* Delay accounting turned on/off */
 struct kmem_cache *delayacct_cache;
 
+static void set_delayacct(bool enabled)
+{
+	if (enabled) {
+		static_branch_enable(&delayacct_key);
+		delayacct_on = 1;
+	} else {
+		delayacct_on = 0;
+		static_branch_disable(&delayacct_key);
+	}
+}
+
 static int __init delayacct_setup_enable(char *str)
 {
 	delayacct_on = 1;
@@ -29,9 +40,30 @@ void delayacct_init(void)
 {
 	delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT);
 	delayacct_tsk_init(&init_task);
-	if (delayacct_on)
-		static_branch_enable(&delayacct_key);
+	set_delayacct(delayacct_on);
+}
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
+		     size_t *lenp, loff_t *ppos)
+{
+	int state = delayacct_on;
+	struct ctl_table t;
+	int err;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_delayacct(state);
+	return err;
 }
+#endif
 
 void __delayacct_tsk_init(struct task_struct *tsk)
 {
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -71,6 +71,7 @@
 #include <linux/coredump.h>
 #include <linux/latencytop.h>
 #include <linux/pid.h>
+#include <linux/delayacct.h>
 
 #include "../lib/kstrtox.h"
 
@@ -1727,6 +1728,17 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_TASK_DELAY_ACCT
+	{
+		.procname	= "sched_delayacct",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_delayacct,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_TASK_DELAY_ACCT */
 #ifdef CONFIG_NUMA_BALANCING
 	{
 		.procname	= "numa_balancing",