Use TCO watchdog first timeout (pretimeout) to dump CPU backtraces
and ease debug of watchdog expiration causes.
TCO logic generates a SCI interrupt, then its handler dumps all CPU
backtraces and calls panic (in order to execute registered panic
callbacks).
SCI interrupt number (GPE) is configured from ACPI tables.
Signed-off-by: Francois-Nicolas Muller <francois-nicolas.muller@xxxxxxxxx>
---
Thanks Guenter for your review.
> If I recall correctly, the iTCO watchdog can also generate an NMI.
> Would it make sense to add support for handling this NMI as well ?
As far as I know, there is no NMI option for TCO watchdog interrupt.
Do you have any documentation about this ?
Here is a new version (v2) of the patch:
- rebased on latest kernel
- fixed coding style issues
Francois-Nicolas
---
drivers/watchdog/iTCO_wdt.c | 50 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 3c3fd41..cd2569a 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -68,6 +68,8 @@
#include <linux/io.h> /* For inb/outb/... */
#include <linux/mfd/core.h>
#include <linux/mfd/lpc_ich.h>
+#include <linux/nmi.h>
+#include <linux/acpi.h>
#include "iTCO_vendor.h"
@@ -127,6 +129,12 @@ 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)");
+#define DEFAULT_PRETIMEOUT 0
+static bool pretimeout = DEFAULT_PRETIMEOUT;
+module_param(pretimeout, bool, 0);
+MODULE_PARM_DESC(pretimeout, "Enable watchdog pretimeout (default="
+ __MODULE_STRING(DEFAULT_PRETIMEOUT) ")");
+
/*
* Some TCO specific functions
*/
@@ -201,6 +209,45 @@ static int iTCO_wdt_unset_NO_REBOOT_bit(void)
return ret; /* returns: 0 = OK, -EIO = Error */
}
+static unsigned char *tco_hid = "8086229C";
+
+static u32 iTCO_wdt_pretimeout_handler(acpi_handle gpe_device, u32 gpe,
+ void *context)
+{
+ /* dump backtraces for all available cores */
+ trigger_all_cpu_backtrace();
+
+ /* call panic notifiers */
+ panic("Kernel Watchdog");
+
+ return ACPI_INTERRUPT_HANDLED;
+}
+
+static acpi_status __init iTCO_wdt_register_gpe(acpi_handle handle,
+ u32 lvl, void *context, void **rv)
+{
+ unsigned long long gpe;
+ acpi_status status;
+ union acpi_object object = { 0 };
+ struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
+
+ status = acpi_evaluate_object(handle, "_GPE", NULL, &buffer);
+ if (ACPI_FAILURE(status))
+ return status;
+
+ if (object.type != ACPI_TYPE_INTEGER)
+ return AE_BAD_DATA;
+
+ gpe = object.integer.value;
+ status = acpi_install_gpe_handler(NULL, gpe, ACPI_GPE_EDGE_TRIGGERED,
+ iTCO_wdt_pretimeout_handler, NULL);
+ if (ACPI_FAILURE(status))
+ return status;
+
+ acpi_enable_gpe(NULL, gpe);
+ return AE_OK;
+}
+
static int iTCO_wdt_start(struct watchdog_device *wd_dev)
{
unsigned int val;
@@ -641,6 +688,9 @@ static int __init iTCO_wdt_init_module(void)
if (err)
return err;
+ if (pretimeout)
+ acpi_get_devices(tco_hid, iTCO_wdt_register_gpe, NULL, NULL);
+
return 0;
}
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-watchdog" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
