summaryrefslogtreecommitdiff
path: root/kernel/hung_task.c
diff options
context:
space:
mode:
authorGuilherme G. Piccoli <gpiccoli@canonical.com>2020-06-08 07:40:45 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-08 21:05:56 +0300
commit0ec9dc9bcba0a62b0844e54c1caf6b8b0bf6b5b4 (patch)
tree4f943adb6612e5161748b68437650507e78643d2 /kernel/hung_task.c
parentf117955a2255721a6a0e9cecf6cad3a6eb43cbc3 (diff)
downloadlinux-0ec9dc9bcba0a62b0844e54c1caf6b8b0bf6b5b4.tar.xz
kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected
Commit 401c636a0eeb ("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: Guilherme G. Piccoli <gpiccoli@canonical.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Kees 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.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/hung_task.c')
-rw-r--r--kernel/hung_task.c20
1 files changed, 18 insertions, 2 deletions
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index b22b5eeab3cb..ce76f490126c 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -53,9 +53,18 @@ 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:
@@ -127,6 +136,9 @@ 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();
@@ -191,10 +203,14 @@ 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,