The panic is only there for debug purposes at first expiry.
Watchdog timeout behavior (second expiry) is not changed.
I added the panic as a config option, enabled by default.
François-Nicolas
>From 5e1680aa0df9f49459cdc7211ba80d6934f65fbd Mon Sep 17 00:00:00 2001
From: Francois-Nicolas Muller <francois-nicolas.muller@xxxxxxxxx>
Date: Tue, 20 Jan 2015 14:55:42 +0100
Subject: [PATCH] Adding TCO watchdog warning interrupt handling.
This feature is useful to root cause watchdog expiration.
It is activated by boot parameter 'warn_irq' (disabled by default).
Upon first expiration of the TCO watchdog, a warning interrupt is fired, then
the interrupt handler dumps registers and call stack of all available cpus.
TCO watchdog reloads with 2.4 seconds timeout for second expiration.
If CONFIG_ITCO_WARN_PANIC is set, the warning interrupt also calls panic()
which notifies the panic handlers then reboots the platform, depending on
CONFIG_PANIC_TIMEOUT value :
- If CONFIG_PANIC_TIMEOUT is zero or greater than 3 seconds, TCO watchdog will
reset the platform if second expiration happens before TCO has been kicked
again.
- If CONFIG_PANIC_TIMEOUT is < 0, platform will reboot immediately (emergency
restart procedure).
- If CONFIG_PANIC_TIMEOUT is 1 or 2 seconds, platform will reboot after 1 or 2
seconds delay (emergency restart procedure).
Change-Id: I48dcb9d38218c8218e35f9969f064b9d5cf316f1
Signed-off-by: Francois-Nicolas Muller <francois-nicolas.muller@xxxxxxxxx>
---
drivers/watchdog/Kconfig | 13 +++++++++
drivers/watchdog/iTCO_wdt.c | 66 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 79 insertions(+)
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 79d2589..15c3807 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -674,6 +674,19 @@ config ITCO_VENDOR_SUPPORT
devices. At this moment we only have additional support for some
SuperMicro Inc. motherboards.
+config ITCO_WARNING_PANIC
+ bool "Intel TCO Timer/Watchdog panic on warning interrupt"
+ depends on ITCO_WDT
+ default y
+ ---help---
+ Force a call to panic() when TCO warning interrupt occurs.
+
+ Warning interrupt happens if warn_irq module parameter is set and
+ TCO timer first expires.
+
+ If not set, only cpu backtraces are dumped, no call to panic() and
+ no notification of panic are done.
+
config IT8712F_WDT
tristate "IT8712F (Smart Guardian) Watchdog Timer"
depends on X86
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index e802a54..e7c5169 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -49,6 +49,8 @@
/* Module and version information */
#define DRV_NAME "iTCO_wdt"
#define DRV_VERSION "1.11"
+#define DRV_NAME_ACPI "iTCO_wdt_wirq"
+#define TCO_CLASS DRV_NAME
/* Includes */
#include <linux/module.h> /* For module specific items */
@@ -68,6 +70,9 @@
#include <linux/pm.h> /* For suspend/resume */
#include <linux/mfd/core.h>
#include <linux/mfd/lpc_ich.h>
+#include <linux/nmi.h>
+#include <linux/acpi.h>
+#include <acpi/actypes.h>
#include "iTCO_vendor.h"
@@ -107,6 +112,12 @@ static struct { /* this is private data for the iTCO_wdt device */
bool started;
} iTCO_wdt_private;
+static const struct acpi_device_id iTCO_wdt_ids[] = {
+ {"8086229C", 0},
+ {"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, iTCO_wdt_ids);
+
/* module parameters */
#define WATCHDOG_TIMEOUT 30 /* 30 sec default heartbeat */
static int heartbeat = WATCHDOG_TIMEOUT; /* in seconds */
@@ -126,6 +137,13 @@ module_param(turn_SMI_watchdog_clear_off, int, 0);
MODULE_PARM_DESC(turn_SMI_watchdog_clear_off,
"Turn off SMI clearing watchdog (depends on TCO-version)(default=1)");
+static bool warn_irq;
+module_param(warn_irq, bool, 0);
+MODULE_PARM_DESC(warn_irq,
+ "Dump all cpus backtraces at first watchdog timer expiration (default=0)");
+
+static bool warn_irq_panic = CONFIG_ITCO_WARNING_PANIC;
+
/*
* Some TCO specific functions
*/
@@ -200,6 +218,35 @@ static int iTCO_wdt_unset_NO_REBOOT_bit(void)
return ret; /* returns: 0 = OK, -EIO = Error */
}
+static u32 iTCO_wdt_wirq(acpi_handle gpe_device, u32 gpe, void *context)
+{
+ trigger_all_cpu_backtrace();
+ if (warn_irq_panic)
+ panic("Kernel Watchdog");
+
+ return IRQ_HANDLED;
+}
+
+static int iTCO_wdt_acpi_add(struct acpi_device *device)
+{
+ unsigned long long gpe;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(device->handle, "_GPE", NULL, &gpe);
+ if (ACPI_FAILURE(status))
+ return -EINVAL;
+
+ status = acpi_install_gpe_handler(NULL, gpe, ACPI_GPE_EDGE_TRIGGERED,
+ iTCO_wdt_wirq, NULL);
+ if (ACPI_FAILURE(status))
+ return -ENODEV;
+
+ acpi_enable_gpe(NULL, gpe);
+
+ pr_debug("interrupt=SCI GPE=0x%02llx", gpe);
+ return 0;
+}
+
static int iTCO_wdt_start(struct watchdog_device *wd_dev)
{
unsigned int val;
@@ -628,6 +675,15 @@ static struct platform_driver iTCO_wdt_driver = {
},
};
+static struct acpi_driver iTCO_wdt_acpi_driver = {
+ .name = DRV_NAME_ACPI,
+ .class = TCO_CLASS,
+ .ids = iTCO_wdt_ids,
+ .ops = {
+ .add = iTCO_wdt_acpi_add,
+ },
+};
+
static int __init iTCO_wdt_init_module(void)
{
int err;
@@ -638,12 +694,22 @@ static int __init iTCO_wdt_init_module(void)
if (err)
return err;
+ if (warn_irq) {
+ err = acpi_bus_register_driver(&iTCO_wdt_acpi_driver);
+ if (err) {
+ platform_driver_unregister(&iTCO_wdt_driver);
+ return err;
+ }
+ }
+
return 0;
}
static void __exit iTCO_wdt_cleanup_module(void)
{
platform_driver_unregister(&iTCO_wdt_driver);
+ if (warn_irq)
+ acpi_bus_unregister_driver(&iTCO_wdt_acpi_driver);
pr_info("Watchdog Module Unloaded\n");
}
--
1.7.9.5
-----Original Message-----
From: Guenter Roeck [mailto:linux@xxxxxxxxxxxx]
Sent: Thursday, January 15, 2015 3:49 PM
To: Muller, Francois-nicolas
Cc: Darren Hart; 'platform-driver-x86@xxxxxxxxxxxxxxx'; Rafael Wysocki; Linux ACPI Mailing List; linux-watchdog@xxxxxxxxxxxxxxx; Wim Van Sebroeck
Subject: Re: [PATCH] TCO Watchdog warning interrupt driver creation
On 01/15/2015 05:27 AM, Muller, Francois-nicolas wrote:
> TCO driver is anyway auto-loaded by mfd driver lpc_ich as a sub-function of it.
>
> The aim of my patch is only to add warning interrupt support in TCO driver.
> For this it need the GPE number which is exposed by Bios in acpi tables.
> So the patch registers also the TCO driver as an acpi driver to be able to retrieve this value.
>
> The acpi code part is only required by the interrupt handling support, not needed for the loading of the driver itself (already done by lpc_ich).
>
> In this context I don't see the point of dissociating the driver part from the loading, unless the loading would need to be reverted later.
>
Ok, makes sense.
Regarding the patch itself, I'll leave it up to Wim to decide what to do.
Personally I dislike the notion of panicing as response to a watchdog timeout.
Guenter
--
To unsubscribe from this list: send the line "unsubscribe platform-driver-x86" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
