[PATCH 2/3] hung_task: Add hung_task_sys_info sysctl to dump sys info on task-hung

[Feng Tang <feng.tang@linux.alibaba.com>]

When task-hung happens, developers may need different kinds of system
information (call-stacks, memory info, locks, etc.) to help debugging.

Add 'hung_task_sys_info' sysctl knob to take human readable string like
"tasks,mem,timers,locks,ftrace,...", and when task-hung happens, all
requested information will be dumped. (refer kernel/sys_info.c for more
details).

Meanwhile, the newly introduced sys_info() call is used to unify some
existing info-dumping knobs.

Signed-off-by: Feng Tang <feng.tang@linux.alibaba.com>
---
 Documentation/admin-guide/sysctl/kernel.rst |  5 +++
 kernel/hung_task.c                          | 39 +++++++++++++++------
 2 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index a397eeccaea7..45b4408dad31 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -422,6 +422,11 @@ the system boot.
 
 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
 
+hung_task_sys_info
+==================
+A comma separated list of extra system information to be dumped when
+hung task is detected, for example, "tasks,mem,timers,locks,...".
+Refer 'panic_sys_info' section below for more details.
 
 hung_task_timeout_secs
 ======================
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 84b4b049faa5..102be5a8e75a 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -24,6 +24,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/hung_task.h>
 #include <linux/rwsem.h>
+#include <linux/sys_info.h>
 
 #include <trace/events/sched.h>
 
@@ -60,12 +61,23 @@ static unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
 static 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;
 
+/*
+ * A bitmask to control what kinds of system info to be printed when
+ * a hung task is detected, it could be task, memory, lock etc. Refer
+ * include/linux/sys_info.h for detailed bit definition.
+ */
+static unsigned long hung_task_si_mask;
+
+/*
+ * There are several sysctl knobs, and this serves as the runtime
+ * effective sys_info knob
+ */
+static unsigned long cur_si_mask;
+
 #ifdef CONFIG_SMP
 /*
  * Should we dump all CPUs backtraces in a hung task event?
@@ -235,9 +247,10 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout,
 	total_hung_task = sysctl_hung_task_detect_count - prev_detect_count;
 	trace_sched_process_hang(t);
 
+	cur_si_mask = hung_task_si_mask;
 	if (sysctl_hung_task_panic && total_hung_task >= sysctl_hung_task_panic) {
 		console_verbose();
-		hung_task_show_lock = true;
+		cur_si_mask |= SYS_INFO_LOCKS;
 		hung_task_call_panic = true;
 	}
 
@@ -260,10 +273,10 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout,
 			" disables this message.\n");
 		sched_show_task(t);
 		debug_show_blocker(t, timeout);
-		hung_task_show_lock = true;
+		cur_si_mask |= SYS_INFO_LOCKS;
 
 		if (sysctl_hung_task_all_cpu_backtrace)
-			hung_task_show_all_bt = true;
+			cur_si_mask |= SYS_INFO_ALL_BT;
 		if (!sysctl_hung_task_warnings)
 			pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n");
 	}
@@ -313,7 +326,6 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	if (test_taint(TAINT_DIE) || did_panic)
 		return;
 
-	hung_task_show_lock = false;
 	rcu_read_lock();
 	for_each_process_thread(g, t) {
 
@@ -329,12 +341,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	}
  unlock:
 	rcu_read_unlock();
-	if (hung_task_show_lock)
-		debug_show_all_locks();
 
-	if (hung_task_show_all_bt) {
-		hung_task_show_all_bt = false;
-		trigger_all_cpu_backtrace();
+	if (unlikely(cur_si_mask)) {
+		sys_info(cur_si_mask);
+		cur_si_mask = 0;
 	}
 
 	if (hung_task_call_panic)
@@ -435,6 +445,13 @@ static const struct ctl_table hung_task_sysctls[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+	{
+		.procname	= "hung_task_sys_info",
+		.data		= &hung_task_si_mask,
+		.maxlen         = sizeof(hung_task_si_mask),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sys_info_handler,
+	},
 };
 
 static void __init hung_task_sysctl_init(void)
-- 
2.43.5