[GIT PULL] softlockup detector updates for v2.6.30

From: Ingo Molnar
Date: Sat Mar 28 2009 - 19:00:39 EST

Linus,

Please pull the latest softlockup-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git softlockup-for-linus

Note: CONFIG_DETECT_HUNG_TASK defaults to Y here, because that was
its previous (implict) default from the softlockup watchdog. Should
this default to N perhaps?

Thanks,

Ingo

------------------>
Frederic Weisbecker (1):
softlockup: ensure the task has been switched out once

Ingo Molnar (1):
softlockup: move 'one' to the softlockup section in sysctl.c

Mandeep Singh Baines (7):
softlockup: decouple hung tasks check from softlockup detection
softlockup: fix to allow compiling with !DETECT_HUNG_TASK
softlockup: fix potential race in hung_task when resetting timeout
softlockup: remove unused definition for spawn_softlockup_task
softlockup: check all tasks in hung_task
softlockup: convert read_lock in hung_task to rcu_read_lock
softlockup: remove timestamp checking from hung_task


include/linux/sched.h | 18 +++--
kernel/Makefile | 1 +
kernel/fork.c | 8 +-
kernel/hung_task.c | 217 +++++++++++++++++++++++++++++++++++++++++++++++++
kernel/softlockup.c | 100 -----------------------
kernel/sysctl.c | 19 ++++-
lib/Kconfig.debug | 38 +++++++++
7 files changed, 286 insertions(+), 115 deletions(-)
create mode 100644 kernel/hung_task.c

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1d19c02..3a843fa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -297,17 +297,11 @@ extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
struct file *filp, void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
-extern unsigned long sysctl_hung_task_check_count;
-extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_warnings;
extern int softlockup_thresh;
#else
static inline void softlockup_tick(void)
{
}
-static inline void spawn_softlockup_task(void)
-{
-}
static inline void touch_softlockup_watchdog(void)
{
}
@@ -316,6 +310,15 @@ static inline void touch_all_softlockup_watchdogs(void)
}
#endif

+#ifdef CONFIG_DETECT_HUNG_TASK
+extern unsigned int sysctl_hung_task_panic;
+extern unsigned long sysctl_hung_task_check_count;
+extern unsigned long sysctl_hung_task_timeout_secs;
+extern unsigned long sysctl_hung_task_warnings;
+extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer,
+ size_t *lenp, loff_t *ppos);
+#endif

/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
@@ -1260,9 +1263,8 @@ struct task_struct {
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
- unsigned long last_switch_timestamp;
unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
diff --git a/kernel/Makefile b/kernel/Makefile
index e4791b3..3e43fd1 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -74,6 +74,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
+obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
diff --git a/kernel/fork.c b/kernel/fork.c
index 6715ebc..b82214b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -644,6 +644,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)

tsk->min_flt = tsk->maj_flt = 0;
tsk->nvcsw = tsk->nivcsw = 0;
+#ifdef CONFIG_DETECT_HUNG_TASK
+ tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+#endif

tsk->mm = NULL;
tsk->active_mm = NULL;
@@ -1046,11 +1049,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,

p->default_timer_slack_ns = current->timer_slack_ns;

-#ifdef CONFIG_DETECT_SOFTLOCKUP
- p->last_switch_count = 0;
- p->last_switch_timestamp = 0;
-#endif
-
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
new file mode 100644
index 0000000..022a492
--- /dev/null
+++ b/kernel/hung_task.c
@@ -0,0 +1,217 @@
+/*
+ * Detect Hung Task
+ *
+ * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+
+/*
+ * The number of tasks checked:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+
+/*
+ * Limit number of tasks checked in a batch.
+ *
+ * This value controls the preemptibility of khungtaskd since preemption
+ * is disabled during the critical section. It also controls the size of
+ * the RCU grace period. So it needs to be upper-bound.
+ */
+#define HUNG_TASK_BATCHING 1024
+
+/*
+ * Zero means infinite timeout - no checking done:
+ */
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+
+unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+
+static int __read_mostly did_panic;
+
+static struct task_struct *watchdog_task;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * hung task is detected:
+ */
+unsigned int __read_mostly sysctl_hung_task_panic =
+ CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
+
+static int __init hung_task_panic_setup(char *str)
+{
+ sysctl_hung_task_panic = simple_strtoul(str, NULL, 0);
+
+ return 1;
+}
+__setup("hung_task_panic=", hung_task_panic_setup);
+
+static int
+hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
+{
+ did_panic = 1;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+ .notifier_call = hung_task_panic,
+};
+
+static void check_hung_task(struct task_struct *t, unsigned long timeout)
+{
+ unsigned long switch_count = t->nvcsw + t->nivcsw;
+
+ /*
+ * Ensure the task is not frozen.
+ * Also, when a freshly created task is scheduled once, changes
+ * its state to TASK_UNINTERRUPTIBLE without having ever been
+ * switched out once, it musn't be checked.
+ */
+ if (unlikely(t->flags & PF_FROZEN || !switch_count))
+ return;
+
+ if (switch_count != t->last_switch_count) {
+ t->last_switch_count = switch_count;
+ return;
+ }
+ if (!sysctl_hung_task_warnings)
+ return;
+ sysctl_hung_task_warnings--;
+
+ /*
+ * Ok, the task did not get scheduled for more than 2 minutes,
+ * complain:
+ */
+ printk(KERN_ERR "INFO: task %s:%d blocked for more than "
+ "%ld seconds.\n", t->comm, t->pid, timeout);
+ printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
+ " disables this message.\n");
+ sched_show_task(t);
+ __debug_show_held_locks(t);
+
+ touch_nmi_watchdog();
+
+ if (sysctl_hung_task_panic)
+ panic("hung_task: blocked tasks");
+}
+
+/*
+ * To avoid extending the RCU grace period for an unbounded amount of time,
+ * periodically exit the critical section and enter a new one.
+ *
+ * For preemptible RCU it is sufficient to call rcu_read_unlock in order
+ * exit the grace period. For classic RCU, a reschedule is required.
+ */
+static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
+{
+ get_task_struct(g);
+ get_task_struct(t);
+ rcu_read_unlock();
+ cond_resched();
+ rcu_read_lock();
+ put_task_struct(t);
+ put_task_struct(g);
+}
+
+/*
+ * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
+ * a really long time (120 seconds). If that happens, print out
+ * a warning.
+ */
+static void check_hung_uninterruptible_tasks(unsigned long timeout)
+{
+ int max_count = sysctl_hung_task_check_count;
+ int batch_count = HUNG_TASK_BATCHING;
+ struct task_struct *g, *t;
+
+ /*
+ * If the system crashed already then all bets are off,
+ * do not report extra hung tasks:
+ */
+ if (test_taint(TAINT_DIE) || did_panic)
+ return;
+
+ rcu_read_lock();
+ do_each_thread(g, t) {
+ if (!--max_count)
+ goto unlock;
+ if (!--batch_count) {
+ batch_count = HUNG_TASK_BATCHING;
+ rcu_lock_break(g, t);
+ /* Exit if t or g was unhashed during refresh. */
+ if (t->state == TASK_DEAD || g->state == TASK_DEAD)
+ goto unlock;
+ }
+ /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+ if (t->state == TASK_UNINTERRUPTIBLE)
+ check_hung_task(t, timeout);
+ } while_each_thread(g, t);
+ unlock:
+ rcu_read_unlock();
+}
+
+static unsigned long timeout_jiffies(unsigned long timeout)
+{
+ /* timeout of 0 will disable the watchdog */
+ return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT;
+}
+
+/*
+ * Process updating of timeout sysctl
+ */
+int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret;
+
+ ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+ if (ret || !write)
+ goto out;
+
+ wake_up_process(watchdog_task);
+
+ out:
+ return ret;
+}
+
+/*
+ * kthread which checks for tasks stuck in D state
+ */
+static int watchdog(void *dummy)
+{
+ set_user_nice(current, 0);
+
+ for ( ; ; ) {
+ unsigned long timeout = sysctl_hung_task_timeout_secs;
+
+ while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
+ timeout = sysctl_hung_task_timeout_secs;
+
+ check_hung_uninterruptible_tasks(timeout);
+ }
+
+ return 0;
+}
+
+static int __init hung_task_init(void)
+{
+ atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+ watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");
+
+ return 0;
+}
+
+module_init(hung_task_init);
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 85d5a24..88796c3 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -166,97 +166,11 @@ void softlockup_tick(void)
}

/*
- * Have a reasonable limit on the number of tasks checked:
- */
-unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
-
-/*
- * Zero means infinite timeout - no checking done:
- */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
-
-unsigned long __read_mostly sysctl_hung_task_warnings = 10;
-
-/*
- * Only do the hung-tasks check on one CPU:
- */
-static int check_cpu __read_mostly = -1;
-
-static void check_hung_task(struct task_struct *t, unsigned long now)
-{
- unsigned long switch_count = t->nvcsw + t->nivcsw;
-
- if (t->flags & PF_FROZEN)
- return;
-
- if (switch_count != t->last_switch_count || !t->last_switch_timestamp) {
- t->last_switch_count = switch_count;
- t->last_switch_timestamp = now;
- return;
- }
- if ((long)(now - t->last_switch_timestamp) <
- sysctl_hung_task_timeout_secs)
- return;
- if (!sysctl_hung_task_warnings)
- return;
- sysctl_hung_task_warnings--;
-
- /*
- * Ok, the task did not get scheduled for more than 2 minutes,
- * complain:
- */
- printk(KERN_ERR "INFO: task %s:%d blocked for more than "
- "%ld seconds.\n", t->comm, t->pid,
- sysctl_hung_task_timeout_secs);
- printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
- " disables this message.\n");
- sched_show_task(t);
- __debug_show_held_locks(t);
-
- t->last_switch_timestamp = now;
- touch_nmi_watchdog();
-
- if (softlockup_panic)
- panic("softlockup: blocked tasks");
-}
-
-/*
- * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
- * a really long time (120 seconds). If that happens, print out
- * a warning.
- */
-static void check_hung_uninterruptible_tasks(int this_cpu)
-{
- int max_count = sysctl_hung_task_check_count;
- unsigned long now = get_timestamp(this_cpu);
- struct task_struct *g, *t;
-
- /*
- * If the system crashed already then all bets are off,
- * do not report extra hung tasks:
- */
- if (test_taint(TAINT_DIE) || did_panic)
- return;
-
- read_lock(&tasklist_lock);
- do_each_thread(g, t) {
- if (!--max_count)
- goto unlock;
- /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
- if (t->state == TASK_UNINTERRUPTIBLE)
- check_hung_task(t, now);
- } while_each_thread(g, t);
- unlock:
- read_unlock(&tasklist_lock);
-}
-
-/*
* The watchdog thread - runs every second and touches the timestamp.
*/
static int watchdog(void *__bind_cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
- int this_cpu = (long)__bind_cpu;

sched_setscheduler(current, SCHED_FIFO, &param);

@@ -276,11 +190,6 @@ static int watchdog(void *__bind_cpu)
if (kthread_should_stop())
break;

- if (this_cpu == check_cpu) {
- if (sysctl_hung_task_timeout_secs)
- check_hung_uninterruptible_tasks(this_cpu);
- }
-
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
@@ -312,18 +221,9 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- check_cpu = cpumask_any(cpu_online_mask);
wake_up_process(per_cpu(watchdog_task, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- if (hotcpu == check_cpu) {
- /* Pick any other online cpu. */
- check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
- }
- break;
-
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(watchdog_task, hotcpu))
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c5ef44f..6d2aeff 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -90,6 +90,9 @@ extern int rcutorture_runnable;
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */

/* Constants used for minimum and maximum */
+#if defined(CONFIG_DETECT_HUNG_TASK) || defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
+static int one = 1;
+#endif
#ifdef CONFIG_DETECT_SOFTLOCKUP
static int sixty = 60;
static int neg_one = -1;
@@ -100,7 +103,6 @@ static int two = 2;
#endif

static int zero;
-static int one = 1;
static unsigned long one_ul = 1;
static int one_hundred = 100;

@@ -815,6 +817,19 @@ static struct ctl_table kern_table[] = {
.extra1 = &neg_one,
.extra2 = &sixty,
},
+#endif
+#ifdef CONFIG_DETECT_HUNG_TASK
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "hung_task_panic",
+ .data = &sysctl_hung_task_panic,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{
.ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_check_count",
@@ -830,7 +845,7 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_dohung_task_timeout_secs,
.strategy = &sysctl_intvec,
},
{
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8fee0a1..5a26298 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -186,6 +186,44 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
default 1 if BOOTPARAM_SOFTLOCKUP_PANIC

+config DETECT_HUNG_TASK
+ bool "Detect Hung Tasks"
+ depends on DEBUG_KERNEL
+ default y
+ help
+ Say Y here to enable the kernel to detect "hung tasks",
+ which are bugs that cause the task to be stuck in
+ uninterruptible "D" state indefinitiley.
+
+ When a hung task is detected, the kernel will print the
+ current stack trace (which you should report), but the
+ task will stay in uninterruptible state. If lockdep is
+ enabled then all held locks will also be reported. This
+ feature has negligible overhead.
+
+config BOOTPARAM_HUNG_TASK_PANIC
+ bool "Panic (Reboot) On Hung Tasks"
+ depends on DETECT_HUNG_TASK
+ help
+ Say Y here to enable the kernel to panic on "hung tasks",
+ which are bugs that cause the kernel to leave a task stuck
+ in uninterruptible "D" state.
+
+ The panic can be used in combination with panic_timeout,
+ to cause the system to reboot automatically after a
+ hung task has been detected. This feature is useful for
+ high-availability systems that have uptime guarantees and
+ where a hung tasks must be resolved ASAP.
+
+ Say N if unsure.
+
+config BOOTPARAM_HUNG_TASK_PANIC_VALUE
+ int
+ depends on DETECT_HUNG_TASK
+ range 0 1
+ default 0 if !BOOTPARAM_HUNG_TASK_PANIC
+ default 1 if BOOTPARAM_HUNG_TASK_PANIC
+
config SCHED_DEBUG
bool "Collect scheduler debugging info"
depends on DEBUG_KERNEL && PROC_FS
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/