The watchdog framework takes care of feeding a hardware watchdog until
userspace opens /dev/watchdogN. If that never happens for some reason
(buggy init script, corrupt root filesystem or whatnot) but the kernel
itself is fine, the machine stays up indefinitely. This patch allows
setting an upper limit for how long the kernel will take care of the
watchdog, thus ensuring that the watchdog will eventually reset the
machine.
A value of 0 (the default) means infinite timeout, preserving the
current behaviour.
This is particularly useful for embedded devices where some fallback
logic is implemented in the bootloader (e.g., use a different root
partition, boot from network, ...).
There is already handle_boot_enabled serving a similar purpose. However,
such a binary choice is unsuitable if the hardware watchdog cannot be
programmed by the bootloader to provide a timeout long enough for
userspace to get up and running. Many of the embedded devices we see use
external (gpio-triggered) watchdogs with a fixed timeout of the order of
1-2 seconds.
The open timeout only applies for the first open from
userspace. Should userspace need to close the watchdog device, with
the intention of re-opening it shortly, the application can emulate
the open timeout feature by combining the nowayout feature with an
appropriate WDIOC_SETTIMEOUT immediately prior to closing the device.
Signed-off-by: Rasmus Villemoes <rasmus.villemoes@xxxxxxxxx>
---
.../watchdog/watchdog-parameters.txt | 8 +++++
drivers/watchdog/watchdog_dev.c | 36 ++++++++++++++++++-
2 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index 0b88e333f9e1..32d3606caa65 100644
--- a/Documentation/watchdog/watchdog-parameters.txt
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -8,6 +8,14 @@ See Documentation/admin-guide/kernel-parameters.rst for information on
providing kernel parameters for builtin drivers versus loadable
modules.
+The watchdog core parameter watchdog.open_timeout is the maximum time,
+in seconds, for which the watchdog framework will take care of pinging
+a running hardware watchdog until userspace opens the corresponding
+/dev/watchdogN device. A value of 0 (the default) means an infinite
+timeout. Setting this to a non-zero value can be useful to ensure that
+either userspace comes up properly, or the board gets reset and allows
+fallback logic in the bootloader to try something else.
+
-------------------------------------------------
acquirewdt:
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 252a7c7b6592..e4b51db48f0e 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -69,6 +69,7 @@ struct watchdog_core_data {
struct mutex lock;
ktime_t last_keepalive;
ktime_t last_hw_keepalive;
+ ktime_t open_deadline;
struct hrtimer timer;
struct kthread_work work;
unsigned long status; /* Internal status bits */
@@ -87,6 +88,19 @@ static struct kthread_worker *watchdog_kworker;
static bool handle_boot_enabled =
IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED);
+static unsigned open_timeout;
+
+static bool watchdog_past_open_deadline(struct watchdog_core_data *data)
+{
+ return ktime_after(ktime_get(), data->open_deadline);
+}
+
+static void watchdog_set_open_deadline(struct watchdog_core_data *data)
+{
+ data->open_deadline = open_timeout ?
+ ktime_get() + ktime_set(open_timeout, 0) : KTIME_MAX;
+}
+
static inline bool watchdog_need_worker(struct watchdog_device *wdd)
{
/* All variables in milli-seconds */
@@ -211,7 +225,13 @@ static bool watchdog_worker_should_ping(struct watchdog_core_data *wd_data)
{
struct watchdog_device *wdd = wd_data->wdd;
- return wdd && (watchdog_active(wdd) || watchdog_hw_running(wdd));
+ if (!wdd)
+ return false;
+
+ if (watchdog_active(wdd))
+ return true;
+
+ return watchdog_hw_running(wdd) && !watchdog_past_open_deadline(wd_data);
}
static void watchdog_ping_work(struct kthread_work *work)
@@ -824,6 +844,15 @@ static int watchdog_open(struct inode *inode, struct file *file)
if (!hw_running)
kref_get(&wd_data->kref);
+ /*
+ * open_timeout only applies for the first open from
+ * userspace. Set open_deadline to infinity so that the kernel
+ * will take care of an always-running hardware watchdog in
+ * case the device gets magic-closed or WDIOS_DISABLECARD is
+ * applied.
+ */
+ wd_data->open_deadline = KTIME_MAX;
+
/* dev/watchdog is a virtual (and thus non-seekable) filesystem */
return stream_open(inode, file);
@@ -983,6 +1012,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno)
/* Record time of most recent heartbeat as 'just before now'. */
wd_data->last_hw_keepalive = ktime_sub(ktime_get(), 1);
+ watchdog_set_open_deadline(wd_data);
/*
* If the watchdog is running, prevent its driver from being unloaded,
@@ -1181,3 +1211,7 @@ module_param(handle_boot_enabled, bool, 0444);
MODULE_PARM_DESC(handle_boot_enabled,
"Watchdog core auto-updates boot enabled watchdogs before userspace takes over (default="
__MODULE_STRING(IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED)) ")");
+
+module_param(open_timeout, uint, 0644);
+MODULE_PARM_DESC(open_timeout,
+ "Maximum time (in seconds, 0 means infinity) for userspace to take over a running watchdog (default=0)");
--
2.20.1
