kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected

mainline inclusion
from mainline-v5.8-rc1
commit 0ec9dc9b
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I48GW3
CVE: NA

---------------------------

Commit 401c636a ("kernel/hung_task.c: show all hung tasks before
panic") introduced a change in that we started to show all CPUs
backtraces when a hung task is detected _and_ the sysctl/kernel
parameter "hung_task_panic" is set.  The idea is good, because usually
when observing deadlocks (that may lead to hung tasks), the culprit is
another task holding a lock and not necessarily the task detected as
hung.

The problem with this approach is that dumping backtraces is a slightly
expensive task, specially printing that on console (and specially in
many CPU machines, as servers commonly found nowadays).  So, users that
plan to collect a kdump to investigate the hung tasks and narrow down
the deadlock definitely don't need the CPUs backtrace on dmesg/console,
which will delay the panic and pollute the log (crash tool would easily
grab all CPUs traces with 'bt -a' command).

Also, there's the reciprocal scenario: some users may be interested in
seeing the CPUs backtraces but not have the system panic when a hung
task is detected.  The current approach hence is almost as embedding a
policy in the kernel, by forcing the CPUs backtraces' dump (only) on
hung_task_panic.

This patch decouples the panic event on hung task from the CPUs
backtraces dump, by creating (and documenting) a new sysctl called
"hung_task_all_cpu_backtrace", analog to the approach taken on soft/hard
lockups, that have both a panic and an "all_cpu_backtrace" sysctl to
allow individual control.  The new mechanism for dumping the CPUs
backtraces on hung task detection respects "hung_task_warnings" by not
dumping the traces in case there's no warnings left.
Signed-off-by: NGuilherme G. Piccoli <gpiccoli@canonical.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: NKees Cook <keescook@chromium.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: http://lkml.kernel.org/r/20200327223646.20779-1-gpiccoli@canonical.comSigned-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NBixuan Cui <cuibixuan@huawei.com>
Reviewed-by: NCheng Jian <cj.chengjian@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

Documentation/sysctl/kernel.txt

@@ -337,6 +337,20 @@ Default value is "/sbin/hotplug".
 
 ==============================================================
 
+hung_task_all_cpu_backtrace:
+
+If this option is set, the kernel will send an NMI to all CPUs to dump
+their backtraces when a hung task is detected. This file shows up if
+CONFIG_DETECT_HUNG_TASK and CONFIG_SMP are enabled.
+
+0: Won't show all CPUs backtraces when a hung task is detected.
+This is the default behavior.
+
+1: Will non-maskably interrupt all CPUs and dump their backtraces when
+a hung task is detected.
+
+==============================================================
+
 hung_task_panic:
 
 Controls the kernel's behavior when a hung task is detected.

include/linux/sched/sysctl.h

@@ -7,6 +7,13 @@
 struct ctl_table;
 
 #ifdef CONFIG_DETECT_HUNG_TASK
+
+#ifdef CONFIG_SMP
+extern unsigned int sysctl_hung_task_all_cpu_backtrace;
+#else
+#define sysctl_hung_task_all_cpu_backtrace 2
+#endif /* CONFIG_SMP */
+
 extern int	     sysctl_hung_task_check_count;
 extern unsigned int  sysctl_hung_task_panic;
 extern unsigned long sysctl_hung_task_timeout_secs;

kernel/hung_task.c

@@ -51,9 +51,18 @@ int __read_mostly sysctl_hung_task_warnings = 10;
 static int __read_mostly did_panic;
 static bool hung_task_show_lock;
 static bool hung_task_call_panic;
+static bool hung_task_show_all_bt;
 
 static struct task_struct *watchdog_task;
 
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in a hung task event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace;
+#endif /* CONFIG_SMP */
+
 /*
  * Should we panic (and reboot, if panic_timeout= is set) when a
  * hung task is detected:
@@ -135,6 +144,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 			" disables this message.\n");
 		sched_show_task(t);
 		hung_task_show_lock = true;
+
+		if (sysctl_hung_task_all_cpu_backtrace)
+			hung_task_show_all_bt = true;
 	}
 
 	touch_nmi_watchdog();
@@ -199,10 +211,14 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	rcu_read_unlock();
 	if (hung_task_show_lock)
 		debug_show_all_locks();
-	if (hung_task_call_panic) {
+
+	if (hung_task_show_all_bt) {
+		hung_task_show_all_bt = false;
 		trigger_all_cpu_backtrace();
-		panic("hung_task: blocked tasks");
 	}
+
+	if (hung_task_call_panic)
+		panic("hung_task: blocked tasks");
 }
 
 static long hung_timeout_jiffies(unsigned long last_checked,

kernel/sysctl.c

@@ -1071,6 +1071,17 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
+#ifdef CONFIG_SMP
+	{
+		.procname	= "hung_task_all_cpu_backtrace",
+		.data		= &sysctl_hung_task_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname	= "hung_task_panic",
 		.data		= &sysctl_hung_task_panic,