Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752865Ab3DVVKh (ORCPT ); Mon, 22 Apr 2013 17:10:37 -0400 Received: from longford.logfs.org ([213.229.74.203]:58885 "EHLO longford.logfs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751628Ab3DVVKf (ORCPT ); Mon, 22 Apr 2013 17:10:35 -0400 Date: Mon, 22 Apr 2013 15:43:47 -0400 From: =?utf-8?B?SsO2cm4=?= Engel To: Alan Cox , Hans de Goede , Wim Van Sebroeck Cc: linux-kernel@vger.kernel.org Subject: [PATCH] Watchdog: add pretimeout Message-ID: <20130422194347.GA14907@logfs.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8009 Lines: 235 This patch adds a pretimeout with three actions to the generic watchdog code: 1) Print a kernel message. 2) Send a signal to the userspace process holding /dev/watchdogX open. 3) Call sys_sync. I have found all of the above to be useful. If the system gets rebooted by a watchdog, you first want to notice that it happened (1). Next you want userspace logfiles from the time when it failed to acknowledge the watchdog. (2) gives cooperating userspace a chance to flush userspace buffers and (3) increases the chances of those logfiles surviving the reboot. Given that this patch changes the userspace ABI, now would be a good time to raise concerns. The most likely problem I see is using SIGILL to notify userspace. Then again, whatever signal you pick will have other meanings attached, so the only choices are not to notify userspace or to pick some lesser of many evils. Signed-off-by: Joern Engel --- drivers/watchdog/watchdog_core.c | 29 ++++++++++++++++++++++ drivers/watchdog/watchdog_dev.c | 50 ++++++++++++++++++++++++++++++++++++++ include/linux/watchdog.h | 8 ++++++ 3 files changed, 87 insertions(+) diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 3796434..349a2c4 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -36,12 +36,35 @@ #include /* For __init/__exit/... */ #include /* For ida_* macros */ #include /* For IS_ERR macros */ +#include /* For send_sig */ +#include /* For send_sig */ +#include /* For sys_sync */ #include "watchdog_core.h" /* For watchdog_dev_register/... */ static DEFINE_IDA(watchdog_ida); static struct class *watchdog_class; +static void watchdog_pretimeout_fire(unsigned long data) +{ + struct watchdog_device *wdd = (void *)data; + + pr_emerg("Watchdog will fire in %ds\n", wdd->pretimeout_delta); + spin_lock(&wdd->pretimeout_task_lock); + if (wdd->pretimeout_task) { + send_sig(SIGILL, wdd->pretimeout_task, 0); + pr_emerg("Sent SIGILL to %d\n", wdd->pretimeout_task->pid); + } else + pr_emerg("Noone around to notify\n"); + spin_unlock(&wdd->pretimeout_task_lock); + schedule_work(&wdd->pretimeout_work); +} + +static void watchdog_pretimeout_sync(struct work_struct *unused) +{ + sys_sync(); +} + /** * watchdog_register_device() - register a watchdog device * @wdd: watchdog device @@ -79,6 +102,12 @@ int watchdog_register_device(struct watchdog_device *wdd) * corrupted in a later stage then we expect a kernel panic! */ + init_timer(&wdd->pretimeout_timer); + wdd->pretimeout_timer.function = watchdog_pretimeout_fire; + wdd->pretimeout_timer.data = (unsigned long)wdd; + spin_lock_init(&wdd->pretimeout_task_lock); + INIT_WORK(&wdd->pretimeout_work, watchdog_pretimeout_sync); + mutex_init(&wdd->lock); id = ida_simple_get(&watchdog_ida, 0, MAX_DOGS, GFP_KERNEL); if (id < 0) diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index ef8edec..d231228 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -73,6 +73,10 @@ static int watchdog_ping(struct watchdog_device *wddev) if (!watchdog_active(wddev)) goto out_ping; + if (wddev->pretimeout) + mod_timer(&wddev->pretimeout_timer, + jiffies + wddev->pretimeout * HZ); + if (wddev->ops->ping) err = wddev->ops->ping(wddev); /* ping the watchdog */ else @@ -106,6 +110,10 @@ static int watchdog_start(struct watchdog_device *wddev) if (watchdog_active(wddev)) goto out_start; + if (wddev->pretimeout) + mod_timer(&wddev->pretimeout_timer, + jiffies + wddev->pretimeout * HZ); + err = wddev->ops->start(wddev); if (err == 0) set_bit(WDOG_ACTIVE, &wddev->status); @@ -145,6 +153,9 @@ static int watchdog_stop(struct watchdog_device *wddev) goto out_stop; } + if (wddev->pretimeout) + del_timer(&wddev->pretimeout_timer); + err = wddev->ops->stop(wddev); if (err == 0) clear_bit(WDOG_ACTIVE, &wddev->status); @@ -185,6 +196,24 @@ out_status: return err; } +/** + * watchdog_set_pretimeout - set the watchdog timer pretimeout + * @wddev: the watchdog device to set the pretimeout for + * @new_delta: the new pretimeout (as delta to the timeout) + * @new_timeout: the new timeout + */ +static int watchdog_set_pretimeout(struct watchdog_device *wddev, + unsigned int new_delta, unsigned int new_timeout) +{ + if (new_delta >= new_timeout) + return -EINVAL; + wddev->pretimeout_delta = new_delta; + wddev->pretimeout = new_timeout - new_delta; + pr_info("WATCHDOG: set pretimeout %d - %d = %d\n", new_timeout, new_delta, + wddev->pretimeout); + return 0; +} + /* * watchdog_set_timeout: set the watchdog timer timeout * @wddev: the watchdog device to set the timeout for @@ -373,9 +402,20 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, return -EOPNOTSUPP; watchdog_ping(wdd); return 0; + case WDIOC_SETPRETIMEOUT: + if (get_user(val, p)) + return -EFAULT; + if (watchdog_set_pretimeout(wdd, val, wdd->timeout)) + return -EINVAL; + /* Fall through */ + case WDIOC_GETPRETIMEOUT: + return put_user(wdd->pretimeout_delta, p); case WDIOC_SETTIMEOUT: if (get_user(val, p)) return -EFAULT; + err = watchdog_set_pretimeout(wdd, wdd->pretimeout_delta, val); + if (err < 0) + return err; err = watchdog_set_timeout(wdd, val); if (err < 0) return err; @@ -413,6 +453,7 @@ static int watchdog_open(struct inode *inode, struct file *file) { int err = -EBUSY; struct watchdog_device *wdd; + unsigned long flags; /* Get the corresponding watchdog device */ if (imajor(inode) == MISC_MAJOR) @@ -435,6 +476,10 @@ static int watchdog_open(struct inode *inode, struct file *file) if (err < 0) goto out_mod; + spin_lock_irqsave(&wdd->pretimeout_task_lock, flags); + wdd->pretimeout_task = current; + spin_unlock_irqrestore(&wdd->pretimeout_task_lock, flags); + file->private_data = wdd; if (wdd->ops->ref) @@ -463,6 +508,7 @@ out: static int watchdog_release(struct inode *inode, struct file *file) { struct watchdog_device *wdd = file->private_data; + unsigned long flags; int err = -EBUSY; /* @@ -483,6 +529,10 @@ static int watchdog_release(struct inode *inode, struct file *file) watchdog_ping(wdd); } + spin_lock_irqsave(&wdd->pretimeout_task_lock, flags); + wdd->pretimeout_task = NULL; + spin_unlock_irqrestore(&wdd->pretimeout_task_lock, flags); + /* Allow the owner module to be unloaded again */ module_put(wdd->ops->owner); diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 3a9df2f..90e7135 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -59,6 +59,8 @@ struct watchdog_ops { * @info: Pointer to a watchdog_info structure. * @ops: Pointer to the list of watchdog operations. * @bootstatus: Status of the watchdog device at boot. + * @pretimeout_delta: The watchdog devices pretimeout value (in s before timeout). + * @pretimeout: The watchdog devices pretimeout value (in absolute seconds). * @timeout: The watchdog devices timeout value. * @min_timeout:The watchdog devices minimum timeout value. * @max_timeout:The watchdog devices maximum timeout value. @@ -82,7 +84,13 @@ struct watchdog_device { struct device *parent; const struct watchdog_info *info; const struct watchdog_ops *ops; + struct task_struct *pretimeout_task; + spinlock_t pretimeout_task_lock; + struct timer_list pretimeout_timer; + struct work_struct pretimeout_work; unsigned int bootstatus; + unsigned int pretimeout_delta; + unsigned int pretimeout; unsigned int timeout; unsigned int min_timeout; unsigned int max_timeout; -- 1.7.10.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/