5efa92f754
There is not that much use for it on a single CPU, however, deadlock between kernel and system task can be delected. Or a runaway loop. If a kernel gets locked up the timer interrupts don't occure (as all interrupts are disabled in kernel mode). The only chance is to interrupt the kernel by a non-maskable interrupt. This patch generates NMIs using performance counters. It uses the most widely available performace counters. As the performance counters are highly model-specific this patch is not guaranteed to work on every machine. Unfortunately this is also true for KVM :-/ On the other hand adding this feature for other models is not extremely difficult and the framework makes it hopefully easy enough. Depending on the frequency of the CPU an NMI is generated at most about every 0.5s If the cpu's speed is less then 2Ghz it is generated at most every 1s. In general an NMI is generated much less often as the performance counter counts down only if the cpu is not idle. Therefore the overhead of this feature is fairly minimal even if the load is high. Uppon detecting that the kernel is locked up the kernel dumps the state of the kernel registers and panics. Local APIC must be enabled for the watchdog to work. The code is _always_ compiled in, however, it is only enabled if watchdog=<non-zero> is set in the boot monitor. One corner case is serial console debugging. As dumping a lot of stuff to the serial link may take a lot of time, the watchdog does not detect lockups during this time!!! as it would result in too many false positives. 10 nmi have to be handled before the lockup is detected. This means something between ~5s to 10s. Another corner case is that the watchdog is enabled only after the paging is enabled as it would be pure madness to try to get it right.
36 lines
1.2 KiB
C
36 lines
1.2 KiB
C
#ifndef __WATCHDOG_H__
|
|
#define __WATCHDOG_H__
|
|
|
|
#include "kernel.h"
|
|
#include "arch/i386/watchdog.h"
|
|
|
|
extern int watchdog_enabled; /* if set to non-zero the watch dog is enabled */
|
|
extern unsigned watchdog_local_timer_ticks; /* is timer still ticking? */
|
|
|
|
/*
|
|
* as the implementation is not only architecture dependent but like in x86 case
|
|
* very much model specific, we need to keep a collection of methods that
|
|
* implement it in runtime after the correct arch/model was detected
|
|
*/
|
|
|
|
typedef void (* arch_watchdog_method_t)(int);
|
|
|
|
struct arch_watchdog {
|
|
arch_watchdog_method_t init; /* initial setup */
|
|
arch_watchdog_method_t reinit; /* reinitialization after a tick */
|
|
unsigned resetval;
|
|
};
|
|
|
|
extern struct arch_watchdog *watchdog;
|
|
|
|
/* let the arch code do whatever it needs to setup the watchdog */
|
|
int arch_watchdog_init(void);
|
|
/* if the watchdog detects lockup, let the arch code to handle it */
|
|
void arch_watchdog_lockup(struct nmi_frame * frame);
|
|
|
|
/* generic NMI handler. Takes one agument which points to where the arch
|
|
* specific low level handler dumped CPU information and can be inspected by the
|
|
* arch specific code of the watchdog implementaion */
|
|
void nmi_watchdog_handler(struct nmi_frame * frame);
|
|
|
|
#endif /* __WATCHDOG_H__ */
|