Backport of watchdog core triggered keepalive infrastructure v2

204 lines not on this page · raw message

index 027b1f43f12d..26aba9b17ac3 100644
@@ -10,8 +10,9 @@
 
 
 #include <linux/bitops.h>
-#include <linux/device.h>
 #include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
 #include <uapi/linux/watchdog.h>
 
 struct watchdog_ops;

@@ -61,12 +62,17 @@ struct watchdog_ops {
  * @bootstatus:	Status of the watchdog device at boot.
  * @timeout:	The watchdog devices timeout value (in seconds).
  * @min_timeout:The watchdog devices minimum timeout value (in seconds).
- * @max_timeout:The watchdog devices maximum timeout value (in seconds).
+ * @max_timeout:The watchdog devices maximum timeout value (in seconds)
+ *		as configurable from user space. Only relevant if
+ *		max_hw_heartbeat_ms is not provided.
+ * @max_hw_heartbeat_ms:
+ *		Hardware limit for maximum timeout, in milli-seconds.
+ *		Replaces max_timeout if specified.
  * @driver-data:Pointer to the drivers private data.
  * @lock:	Lock for watchdog core internal use only.
  * @status:	Field that contains the devices internal status bits.
- * @deferred: entry in wtd_deferred_reg_list which is used to
- *			   register early initialized watchdogs.
+ * @deferred:	Entry in wtd_deferred_reg_list which is used to
+ *		register early initialized watchdogs.
  *
  * The watchdog_device structure contains all information about a
  * watchdog timer device.

@@ -88,8 +94,11 @@ struct watchdog_device {
 	unsigned int timeout;
 	unsigned int min_timeout;
 	unsigned int max_timeout;
+	unsigned int max_hw_heartbeat_ms;
 	void *driver_data;
 	struct mutex lock;
+	unsigned long last_keepalive;
+	struct delayed_work work;
 	unsigned long status;
 /* Bit numbers for status flags */
 #define WDOG_ACTIVE		0	/* Is the watchdog running/active */

@@ -121,13 +130,18 @@ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigne
 {
 	/*
 	 * The timeout is invalid if
+	 * - the requested value is larger than UINT_MAX / 1000
+	 *   (since internal calculations are done in milli-seconds),
+	 * or
 	 * - the requested value is smaller than the configured minimum timeout,
 	 * or
-	 * - a maximum timeout is configured, and the requested value is larger
-	 *   than the maximum timeout.
+	 * - a maximum hardware timeout is not configured, a maximum timeout
+	 *   is configured, and the requested value is larger than the
+	 *   configured maximum timeout.
 	 */
-	return t < wdd->min_timeout ||
-		(wdd->max_timeout && t > wdd->max_timeout);
+	return t > UINT_MAX / 1000 || t < wdd->min_timeout ||
+		(!wdd->max_hw_heartbeat_ms && wdd->max_timeout &&
+		 t > wdd->max_timeout);
 }
 
 /* Use the following functions to manipulate watchdog driver specific data */

115 lines not on this page · raw message

index 26aba9b17ac3..cbe31d5b352c 100644
@@ -106,6 +106,7 @@ struct watchdog_device {
 #define WDOG_ALLOW_RELEASE	2	/* Did we receive the magic char ? */
 #define WDOG_NO_WAY_OUT		3	/* Is 'nowayout' feature set ? */
 #define WDOG_UNREGISTERED	4	/* Has the device been unregistered */
+#define WDOG_HW_RUNNING		5	/* True if HW watchdog running */
 	struct list_head deferred;
 };
 

@@ -118,6 +119,15 @@ static inline bool watchdog_active(struct watchdog_device *wdd)
 	return test_bit(WDOG_ACTIVE, &wdd->status);
 }
 
+/*
+ * Use the following function to check whether or not the hardware watchdog
+ * is running
+ */
+static inline bool watchdog_hw_running(struct watchdog_device *wdd)
+{
+	return test_bit(WDOG_HW_RUNNING, &wdd->status);
+}
+
 /* Use the following function to set the nowayout feature */
 static inline void watchdog_set_nowayout(struct watchdog_device *wdd, bool nowayout)
 {

index 873f13972cf4..41f1854d026b 100644
@@ -145,7 +145,7 @@ static int __watchdog_register_device(struct watchdog_device *wdd)
 		return -EINVAL;
 
 	/* Mandatory operations need to be supported */
-	if (wdd->ops->start == NULL || wdd->ops->stop == NULL)
+	if (!wdd->ops->start || (!wdd->ops->stop && !wdd->max_hw_heartbeat_ms))
 		return -EINVAL;
 
 	watchdog_check_min_max_timeout(wdd);

index f38d4abf5ede..7cefe9aad123 100644
@@ -237,7 +237,11 @@ static int watchdog_stop(struct watchdog_device *wdd)
 		goto out_stop;
 	}
 
-	err = wdd->ops->stop(wdd);
+	if (wdd->ops->stop)
+		err = wdd->ops->stop(wdd);
+	else
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
+
 	if (err == 0) {
 		clear_bit(WDOG_ACTIVE, &wdd->status);
 		watchdog_update_worker(wdd);

index 29ef719a6a3c..378e7c5dfc50 100644
@@ -25,7 +25,6 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>

@@ -34,7 +33,6 @@
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/regmap.h>
-#include <linux/timer.h>
 #include <linux/watchdog.h>
 
 #define DRIVER_NAME "imx2-wdt"

@@ -62,7 +60,6 @@
 struct imx2_wdt_device {
 	struct clk *clk;
 	struct regmap *regmap;
-	struct timer_list timer;	/* Pings the watchdog when closed */
 	struct watchdog_device wdog;
 	struct notifier_block restart_handler;
 };

@@ -151,16 +148,6 @@ static int imx2_wdt_ping(struct watchdog_device *wdog)
 	return 0;
 }
 
-static void imx2_wdt_timer_ping(unsigned long arg)
-{
-	struct watchdog_device *wdog = (struct watchdog_device *)arg;
-	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
-
-	/* ping it every wdog->timeout / 2 seconds to prevent reboot */
-	imx2_wdt_ping(wdog);
-	mod_timer(&wdev->timer, jiffies + wdog->timeout * HZ / 2);
-}
-
 static int imx2_wdt_set_timeout(struct watchdog_device *wdog,
 				unsigned int new_timeout)
 {

@@ -177,40 +164,19 @@ static int imx2_wdt_start(struct watchdog_device *wdog)
 {
 	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
-	if (imx2_wdt_is_running(wdev)) {
-		/* delete the timer that pings the watchdog after close */
-		del_timer_sync(&wdev->timer);
+	if (imx2_wdt_is_running(wdev))
 		imx2_wdt_set_timeout(wdog, wdog->timeout);
-	} else
+	else
 		imx2_wdt_setup(wdog);
 
-	return imx2_wdt_ping(wdog);
-}
-
-static int imx2_wdt_stop(struct watchdog_device *wdog)
-{
-	/*
-	 * We don't need a clk_disable, it cannot be disabled once started.
-	 * We use a timer to ping the watchdog while /dev/watchdog is closed
-	 */
-	imx2_wdt_timer_ping((unsigned long)wdog);
-	return 0;
-}
-
-static inline void imx2_wdt_ping_if_active(struct watchdog_device *wdog)
-{
-	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+	set_bit(WDOG_HW_RUNNING, &wdog->status);
 
-	if (imx2_wdt_is_running(wdev)) {
-		imx2_wdt_set_timeout(wdog, wdog->timeout);
-		imx2_wdt_timer_ping((unsigned long)wdog);
-	}
+	return imx2_wdt_ping(wdog);
 }
 
 static const struct watchdog_ops imx2_wdt_ops = {
 	.owner = THIS_MODULE,
 	.start = imx2_wdt_start,
-	.stop = imx2_wdt_stop,
 	.ping = imx2_wdt_ping,
 	.set_timeout = imx2_wdt_set_timeout,
 };

@@ -257,7 +223,7 @@ static int __init imx2_wdt_probe(struct platform_device *pdev)
 	wdog->info		= &imx2_wdt_info;
 	wdog->ops		= &imx2_wdt_ops;
 	wdog->min_timeout	= 1;
-	wdog->max_timeout	= IMX2_WDT_MAX_TIME;
+	wdog->max_hw_heartbeat_ms = IMX2_WDT_MAX_TIME * 1000;
 	wdog->parent		= &pdev->dev;
 
 	ret = clk_prepare_enable(wdev->clk);

@@ -277,9 +243,10 @@ static int __init imx2_wdt_probe(struct platform_device *pdev)
 	watchdog_set_nowayout(wdog, nowayout);
 	watchdog_init_timeout(wdog, timeout, &pdev->dev);
 
-	setup_timer(&wdev->timer, imx2_wdt_timer_ping, (unsigned long)wdog);
-
-	imx2_wdt_ping_if_active(wdog);
+	if (imx2_wdt_is_running(wdev)) {
+		imx2_wdt_set_timeout(wdog, wdog->timeout);
+		set_bit(WDOG_HW_RUNNING, &wdog->status);
+	}
 
 	/*
 	 * Disable the watchdog power down counter at boot. Otherwise the power

@@ -320,7 +287,6 @@ static int __exit imx2_wdt_remove(struct platform_device *pdev)
 	watchdog_unregister_device(wdog);
 
 	if (imx2_wdt_is_running(wdev)) {
-		del_timer_sync(&wdev->timer);
 		imx2_wdt_ping(wdog);
 		dev_crit(&pdev->dev, "Device removed: Expect reboot!\n");
 	}

@@ -334,10 +300,9 @@ static void imx2_wdt_shutdown(struct platform_device *pdev)
 
 	if (imx2_wdt_is_running(wdev)) {
 		/*
-		 * We are running, we need to delete the timer but will
-		 * give max timeout before reboot will take place
+		 * We are running, configure max timeout before reboot
+		 * will take place.
 		 */
-		del_timer_sync(&wdev->timer);
 		imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME);
 		imx2_wdt_ping(wdog);
 		dev_crit(&pdev->dev, "Device shutdown: Expect reboot!\n");

@@ -355,10 +320,6 @@ static int imx2_wdt_suspend(struct device *dev)
 	if (imx2_wdt_is_running(wdev)) {
 		imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME);
 		imx2_wdt_ping(wdog);
-
-		/* The watchdog is not active */
-		if (!watchdog_active(wdog))
-			del_timer_sync(&wdev->timer);
 	}
 
 	clk_disable_unprepare(wdev->clk);

@@ -384,19 +345,10 @@ static int imx2_wdt_resume(struct device *dev)
 		 * watchdog again.
 		 */
 		imx2_wdt_setup(wdog);
+	}
+	if (imx2_wdt_is_running(wdev)) {
 		imx2_wdt_set_timeout(wdog, wdog->timeout);
 		imx2_wdt_ping(wdog);
-	} else if (imx2_wdt_is_running(wdev)) {
-		/* Resuming from non-deep sleep state. */
-		imx2_wdt_set_timeout(wdog, wdog->timeout);
-		imx2_wdt_ping(wdog);
-		/*
-		 * But the watchdog is not active, then start
-		 * the timer again.
-		 */
-		if (!watchdog_active(wdog))
-			mod_timer(&wdev->timer,
-				  jiffies + wdog->timeout * HZ / 2);
 	}
 
 	return 0;

index 7cefe9aad123..e98e4294ec92 100644
@@ -596,7 +596,6 @@ static int watchdog_release(struct inode *inode, struct file *file)
 	if (!watchdog_hw_running(wdd))
 		module_put(wdd->ops->owner);
 
-	cancel_delayed_work_sync(&wdd->work);
 	watchdog_update_worker(wdd);
 
 	/* make sure that /dev/watchdog can be re-opened */

index 41f1854d026b..5de14c51bf95 100644
@@ -88,7 +88,7 @@ static void watchdog_check_min_max_timeout(struct watchdog_device *wdd)
 	 * Check that we have valid min and max timeout values, if
 	 * not reset them both to 0 (=not used or unknown)
 	 */
-	if (wdd->min_timeout > wdd->max_timeout) {
+	if (!wdd->max_hw_heartbeat_ms && wdd->min_timeout > wdd->max_timeout) {
 		pr_info("Invalid min and max timeout values, resetting to 0!\n");
 		wdd->min_timeout = 0;
 		wdd->max_timeout = 0;

index e98e4294ec92..2a204bb56705 100644
@@ -67,9 +67,13 @@ static inline bool watchdog_need_worker(struct watchdog_device *wdd)
 	 *   thus is aware that the framework supports generating heartbeat
 	 *   requests.
 	 * - Userspace requests a longer timeout than the hardware can handle.
+	 *
+	 * Alternatively, if userspace has not opened the watchdog
+	 * device, we take care of feeding the watchdog if it is
+	 * running.
 	 */
-	return hm && ((watchdog_active(wdd) && t > hm) ||
-		      (t && !watchdog_active(wdd) && watchdog_hw_running(wdd)));
+	return (hm && watchdog_active(wdd) && t > hm) ||
+		(t && !watchdog_active(wdd) && watchdog_hw_running(wdd));
 }
 
 static long watchdog_next_keepalive(struct watchdog_device *wdd)

@@ -81,7 +85,7 @@ static long watchdog_next_keepalive(struct watchdog_device *wdd)
 	unsigned int hw_heartbeat_ms;
 
 	virt_timeout = wdd->last_keepalive + msecs_to_jiffies(timeout_ms);
-	hw_heartbeat_ms = min(timeout_ms, wdd->max_hw_heartbeat_ms);
+	hw_heartbeat_ms = min_not_zero(timeout_ms, wdd->max_hw_heartbeat_ms);
 	keepalive_interval = msecs_to_jiffies(hw_heartbeat_ms / 2);
 
 	if (!watchdog_active(wdd))

index 2a204bb56705..263d7fa0ef31 100644
@@ -731,8 +731,15 @@ int __init watchdog_dev_init(void)
 	}
 
 	err = alloc_chrdev_region(&watchdog_devt, 0, MAX_DOGS, "watchdog");
-	if (err < 0)
+	if (err < 0) {
 		pr_err("watchdog: unable to allocate char dev region\n");
+		goto err_alloc;
+	}
+
+	return 0;
+
+err_alloc:
+	destroy_workqueue(watchdog_wq);
 	return err;
 }
 

index 263d7fa0ef31..1edc3d78636b 100644
@@ -241,10 +241,12 @@ static int watchdog_stop(struct watchdog_device *wdd)
 		goto out_stop;
 	}
 
-	if (wdd->ops->stop)
+	if (wdd->ops->stop) {
+		clear_bit(WDOG_HW_RUNNING, &wdd->status);
 		err = wdd->ops->stop(wdd);
-	else
+	} else {
 		set_bit(WDOG_HW_RUNNING, &wdd->status);
+	}
 
 	if (err == 0) {
 		clear_bit(WDOG_ACTIVE, &wdd->status);

index 1edc3d78636b..8ca87ae467f2 100644
@@ -53,6 +53,9 @@ static struct watchdog_device *old_wdd;
 
 static struct workqueue_struct *watchdog_wq;
 
+static bool handle_boot_enabled =
+	IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED);
+
 static inline bool watchdog_need_worker(struct watchdog_device *wdd)
 {
 	/* All variables in milli-seconds */

@@ -683,10 +686,15 @@ int watchdog_dev_register(struct watchdog_device *wdd)
 	 * and schedule an immediate ping.
 	 */
 	if (watchdog_hw_running(wdd)) {
-		__module_get(wdd->ops->owner);
-		if (wdd->ops->ref)
-			wdd->ops->ref(wdd);
-		queue_delayed_work(watchdog_wq, &wdd->work, 0);
+		if (handle_boot_enabled) {
+			__module_get(wdd->ops->owner);
+			if (wdd->ops->ref)
+				wdd->ops->ref(wdd);
+			queue_delayed_work(watchdog_wq, &wdd->work, 0);
+		} else {
+			pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n",
+					wdd->id);
+		}
 	}
 
 	return 0;

@@ -756,3 +764,8 @@ void __exit watchdog_dev_exit(void)
 	unregister_chrdev_region(watchdog_devt, MAX_DOGS);
 	destroy_workqueue(watchdog_wq);
 }
+
+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)) ")");