[RFC PATCH 2/2] sched: sysctl: Panic on scheduling while atomic

[Daniel Bristot de Oliveira]

Currently, a schedule while atomic error prints the stack trace to the
kernel log and the system continue running.

Although it is possible to collect the kernel log messages and analyse
it, often more information are needed. Furthermore, keep the system
running is not always the best choice. For example, when the preempt
count underflows the system will not stop to complain about scheduling
while atomic, so the kernel log can wraparound overwriting the first
stack trace, tuning the analysis even more difficult.

This patch implements the kernel.panic_on_sched_in_atomic sysctl to
help out on these more complex situations.

When kernel.panic_on_sched_in_atomic is set to 1, the kernel will
panic() in the schedule while atomic detection.

The default value for the sysctl is 0, maintaining the current behavior.

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Reviewed-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Signed-off-by: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
---
 Documentation/sysctl/kernel.txt | 13 +++++++++++++
 include/linux/kernel.h          |  1 +
 kernel/sched/core.c             |  7 +++++++
 kernel/sysctl.c                 |  9 +++++++++
 4 files changed, 30 insertions(+)

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 29ec4bb..0b176bb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -59,6 +59,7 @@ show up in /proc/sys/kernel:
 - panic_on_unrecovered_nmi
 - panic_on_warn
 - panic_on_rcu_stall
+- panic_on_sched_in_atomic
 - perf_cpu_time_max_percent
 - perf_event_paranoid
 - perf_event_max_stack
@@ -630,6 +631,18 @@ is useful to define the root cause of RCU stalls using kdump.
 
 ==============================================================
 
+panic_on_sched_in_atomic:
+
+When set to 1, calls panic() in the schedule while in atomic detection.
+This is useful get a vmcore to inspect the root cause of a schedule()
+call in the atomic context.
+
+0: do not panic() on scheduling while in atomic, default behavior.
+
+1: panic() after printing schedule while in atomic messages.
+
+==============================================================
+
 perf_cpu_time_max_percent:
 
 Hints to the kernel how much CPU time it should be allowed to
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c420821..e4d9804 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -452,6 +452,7 @@ extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
 extern int panic_on_warn;
 extern int sysctl_panic_on_rcu_stall;
+extern int sysctl_panic_on_sched_in_atomic;
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4..602f978 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -152,6 +152,11 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+/*
+ * panic on scheduling while atomic
+ */
+__read_mostly int sysctl_panic_on_sched_in_atomic = 0;
+
 /* cpus with isolated domains */
 cpumask_var_t cpu_isolated_map;
 
@@ -3146,6 +3151,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
 		pr_cont("\n");
 	}
 #endif
+	if (sysctl_panic_on_sched_in_atomic)
+		panic("scheduling while atomic\n");
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d3b93aa..f0a984c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1216,6 +1216,15 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &one,
 	},
 #endif
+	{
+		.procname	= "panic_on_sched_in_atomic",
+		.data		= &sysctl_panic_on_sched_in_atomic,
+		.maxlen		= sizeof(sysctl_panic_on_sched_in_atomic),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
-- 
2.5.5