From a2e514453861dd39b53b7a50b6771bd3f9852078 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Tue, 21 Aug 2018 21:55:52 -0700 Subject: kernel/hung_task.c: allow to set checking interval separately from timeout Currently task hung checking interval is equal to timeout, as the result hung is detected anywhere between timeout and 2*timeout. This is fine for most interactive environments, but this hurts automated testing setups (syzbot). In an automated setup we need to strictly order CPU lockup < RCU stall < workqueue lockup < task hung < silent loss, so that RCU stall is not detected as task hung and task hung is not detected as silent machine loss. The large variance in task hung detection timeout requires setting silent machine loss timeout to a very large value (e.g. if task hung is 3 mins, then silent loss need to be set to ~7 mins). The additional 3 minutes significantly reduce testing efficiency because usually we crash kernel within a minute, and this can add hours to bug localization process as it needs to do dozens of tests. Allow setting checking interval separately from timeout. This allows to set timeout to, say, 3 minutes, but checking interval to 10 secs. The interval is controlled via a new hung_task_check_interval_secs sysctl, similar to the existing hung_task_timeout_secs sysctl. The default value of 0 results in the current behavior: checking interval is equal to timeout. [akpm@linux-foundation.org: update hung_task_timeout_max's comment] Link: http://lkml.kernel.org/r/20180611111004.203513-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov Cc: Paul E. McKenney Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f22f76b7a138..dbdcb6673b27 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -145,7 +145,10 @@ static int minolduid; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ #ifdef CONFIG_DETECT_HUNG_TASK static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #endif @@ -1090,6 +1093,14 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dohung_task_timeout_secs, .extra2 = &hung_task_timeout_max, }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, + }, { .procname = "hung_task_warnings", .data = &sysctl_hung_task_warnings, -- cgit v1.2.3 From 5f733e8a2dd130eaeed24cbaef49d349206cdb8b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 21 Aug 2018 22:01:06 -0700 Subject: kernel/sysctl.c: fix typos in comments Fix a few typos/spellos in kernel/sysctl.c. Link: http://lkml.kernel.org/r/bb09a8b9-f984-6dd4-b07b-3ecaf200862e@infradead.org Signed-off-by: Randy Dunlap Acked-by: Kees Cook Cc: "Luis R. Rodriguez" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index dbdcb6673b27..71ceb6c13c1a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,7 +225,7 @@ static int proc_dopipe_max_size(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ -/* Note: sysrq code uses it's own private copy */ +/* Note: sysrq code uses its own private copy */ static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; static int sysrq_sysctl_handler(struct ctl_table *table, int write, @@ -1976,13 +1976,13 @@ static void warn_sysctl_write(struct ctl_table *table) } /** - * proc_first_pos_non_zero_ignore - check if firs position is allowed + * proc_first_pos_non_zero_ignore - check if first position is allowed * @ppos: file position * @table: the sysctl table * * Returns true if the first position is non-zero and the sysctl_writes_strict * mode indicates this is not allowed for numeric input types. String proc - * hadlers can ignore the return value. + * handlers can ignore the return value. */ static bool proc_first_pos_non_zero_ignore(loff_t *ppos, struct ctl_table *table) -- cgit v1.2.3