[PATCH 1/2] watchdog: introduce watchdog.open_timeout commandline parameter

From: Rasmus Villemoes
Date: Tue Nov 28 2017 - 05:36:08 EST


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.

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, ...).

The existing handle_boot_enabled parameter has the same purpose, but
that is only usable when the hardware watchdog has a sufficiently long
timeout (possibly configured by the bootloader). Many hardware watchdogs
cannot be configured, or can only be configured up to a certain value,
making the timeout short enough that it is completely impossible to have
userspace ready soon enough. Hence it is necessary for the kernel to
handle those watchdogs for a while.

The open timeout is also used as a maximum time for an application to
re-open /dev/watchdogN after closing it.

A value of 0 (the default) means infinite timeout, preserving the
current behaviour.

The unit is milliseconds rather than seconds because that covers more
use cases. For example, one can effectively disable the kernel handling
by setting the open_timeout to 1 ms. There are also customers with very
strict requirements that may want to set the open_timeout to something
like 4500 ms, which combined with a hardware watchdog that must be
pinged every 250 ms ensures userspace is up no more than 5 seconds after
the bootloader hands control to the kernel (250 ms until the driver gets
registered and kernel handling starts, 4500 ms of kernel handling, and
then up to 250 ms from the last ping until userspace takes over).

Signed-off-by: Rasmus Villemoes <rasmus.villemoes@xxxxxxxxx>
Reviewed-by: Esben Haabendal <esben@xxxxxxxxxxxx>
---
Documentation/watchdog/watchdog-parameters.txt | 8 ++++++++
drivers/watchdog/watchdog_dev.c | 27 +++++++++++++++++++++++++-
2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index 6f9d7b4..5363bf3 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 milliseconds, for which the watchdog framework will take care of
+pinging a 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 1e971a5..b4985db 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -67,6 +67,7 @@ struct watchdog_core_data {
struct mutex lock;
unsigned long last_keepalive;
unsigned long last_hw_keepalive;
+ unsigned long open_deadline;
struct delayed_work work;
unsigned long status; /* Internal status bits */
#define _WDOG_DEV_OPEN 0 /* Opened ? */
@@ -83,6 +84,19 @@ static struct workqueue_struct *watchdog_wq;

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)
+{
+ if (!open_timeout)
+ return false;
+ return time_is_before_jiffies(data->open_deadline);
+}
+
+static void watchdog_set_open_deadline(struct watchdog_core_data *data)
+{
+ data->open_deadline = jiffies + msecs_to_jiffies(open_timeout);
+}

static inline bool watchdog_need_worker(struct watchdog_device *wdd)
{
@@ -200,7 +214,13 @@ 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 work_struct *work)
@@ -861,6 +881,7 @@ static int watchdog_release(struct inode *inode, struct file *file)
watchdog_ping(wdd);
}

+ watchdog_set_open_deadline(wd_data);
watchdog_update_worker(wdd);

/* make sure that /dev/watchdog can be re-opened */
@@ -959,6 +980,7 @@ 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 = jiffies - 1;
+ watchdog_set_open_deadline(wd_data);

/*
* If the watchdog is running, prevent its driver from being unloaded,
@@ -1156,3 +1178,6 @@ 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 milliseconds for userspace to take over handling enabled watchdogs (0 = infinite)");
--
2.7.4