On Wednesday, January 14, 2015 04:38:49 PM Muller, Francois-nicolas wrote:
> From 54d2ff5e13c1b35d5019b82376dabb903ebe30d6 Mon Sep 17 00:00:00 2001
> From: Francois-Nicolas Muller <[email protected]>
> Date: Wed, 14 Jan 2015 14:27:43 +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 cores.
>
> Finally panic() is called and notifies the panic handlers if any. At the same
> time, the TCO watchdog reloads with 2.4 seconds timeout value.
>
> When warning interrupt is enabled, platform reboot depends 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: I009c41f2f3dc3bd091b4d2a45b4ea0be85c8ce27
> Signed-off-by: Francois-Nicolas Muller <[email protected]>
> ---
> drivers/watchdog/iTCO_wdt.c | 64
> +++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 64 insertions(+)
>
> diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
> index e802a54..a8c16d2 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},
This is not a proper ACPI or PNP device name as far as I can say.
What is it?
> + {"", 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 +137,11 @@ 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,
> + "Watchdog trigs a panic at first expiration (default=0)");
> +
> /*
> * Some TCO specific functions
> */
> @@ -200,6 +216,35 @@ 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();
> + panic("Kernel Watchdog");
> +
> + /* This code should not be reached */
> + return IRQ_HANDLED;
> +}
> +
> +static int iTCO_wdt_acpi_add(struct acpi_device *device)
> +{
> + unsigned long long gpe;
> + acpi_status status;
> +
The code below seems to mean: "If the device _HID returns '8086229C', there
should be a _GPE object under it which then returns the number of the GPE
to bind to within the FADT GPE blocks."
Where is this documented?
> + 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 +673,15 @@ 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 +692,22 @@ 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");
> }
>
> --
> 1.9.1
And does it build for CONFIG_ACPI unset?
--
To unsubscribe from this list: send the line "unsubscribe linux-watchdog" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
