watchdog: introduce watchdog_suspend() and watchdog_resume()

This interface can be utilized to deactivate the hard and soft lockup
detector temporarily.  Callers are expected to minimize the duration of
deactivation.  Multiple deactivations are allowed to occur in parallel but
should be rare in practice.

[akpm@linux-foundation.org: remove unneeded static initialization]
Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com>
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Stephane Eranian <eranian@google.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 088714537d1033416eac88ae2ec52a13e32c0d27..e9f213c337bb33cb79f6ccb2d225fda8f4bc972a 100644 (file)
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -82,6 +82,8 @@ extern int proc_watchdog_thresh(struct ctl_table *, int ,
                                void __user *, size_t *, loff_t *);
 extern int proc_watchdog_cpumask(struct ctl_table *, int,
                                 void __user *, size_t *, loff_t *);
+extern int watchdog_suspend(void);
+extern void watchdog_resume(void);
 #endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6c489e49c610237c0cf5fbc33f7c76d84755c474..e6eb5b69721280dcbb6ef454a878caacc5a01f54 100644 (file)
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -67,6 +67,7 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 #define for_each_watchdog_cpu(cpu) \
        for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
 
+static int __read_mostly watchdog_suspended;
 static int __read_mostly watchdog_running;
 static u64 __read_mostly sample_period;
 
@@ -700,6 +701,50 @@ static void watchdog_unpark_threads(void)
        put_online_cpus();
 }
 
+/*
+ * Suspend the hard and soft lockup detector by parking the watchdog threads.
+ */
+int watchdog_suspend(void)
+{
+       int ret = 0;
+
+       mutex_lock(&watchdog_proc_mutex);
+       /*
+        * Multiple suspend requests can be active in parallel (counted by
+        * the 'watchdog_suspended' variable). If the watchdog threads are
+        * running, the first caller takes care that they will be parked.
+        * The state of 'watchdog_running' cannot change while a suspend
+        * request is active (see related changes in 'proc' handlers).
+        */
+       if (watchdog_running && !watchdog_suspended)
+               ret = watchdog_park_threads();
+
+       if (ret == 0)
+               watchdog_suspended++;
+
+       mutex_unlock(&watchdog_proc_mutex);
+
+       return ret;
+}
+
+/*
+ * Resume the hard and soft lockup detector by unparking the watchdog threads.
+ */
+void watchdog_resume(void)
+{
+       mutex_lock(&watchdog_proc_mutex);
+
+       watchdog_suspended--;
+       /*
+        * The watchdog threads are unparked if they were previously running
+        * and if there is no more active suspend request.
+        */
+       if (watchdog_running && !watchdog_suspended)
+               watchdog_unpark_threads();
+
+       mutex_unlock(&watchdog_proc_mutex);
+}
+
 static void restart_watchdog_hrtimer(void *info)
 {
        struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
@@ -818,6 +863,12 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 
        mutex_lock(&watchdog_proc_mutex);
 
+       if (watchdog_suspended) {
+               /* no parameter changes allowed while watchdog is suspended */
+               err = -EAGAIN;
+               goto out;
+       }
+
        /*
         * If the parameter is being read return the state of the corresponding
         * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
@@ -903,6 +954,12 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
 
        mutex_lock(&watchdog_proc_mutex);
 
+       if (watchdog_suspended) {
+               /* no parameter changes allowed while watchdog is suspended */
+               err = -EAGAIN;
+               goto out;
+       }
+
        old = ACCESS_ONCE(watchdog_thresh);
        err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
@@ -934,6 +991,13 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
        int err;
 
        mutex_lock(&watchdog_proc_mutex);
+
+       if (watchdog_suspended) {
+               /* no parameter changes allowed while watchdog is suspended */
+               err = -EAGAIN;
+               goto out;
+       }
+
        err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
        if (!err && write) {
                /* Remove impossible cpus to keep sysctl output cleaner. */
@@ -951,6 +1015,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
                                pr_err("cpumask update failed\n");
                }
        }
+out:
        mutex_unlock(&watchdog_proc_mutex);
        return err;
 }