On Sun, 11 Mar 2001, Keith Owens wrote:
> Works for me. It even makes kdb simpler.
agreed. Also, touch_nmi_watchdog() is stateless and is thus much less
prone to locking bugs.
i've attached nmi-watchdog-2.4.2-A1 that implements touch_nmi_watchdog(),
ontop of 2.4.2-ac18, and changes show_state() to use this interface. (the
patch also takes the NMI counters out of the obscure in-function place
they used to be.)
the patch compiles & boots just fine on 2.4.2-ac18 in both SMP and
APIC-less-UP mode. The NMI watchdog is functional, and SysRq-T does not
cause a lockup if used with a slow serial console that takes more than 5
seconds to output the tasklist.
Ingo
--- linux/include/linux/irq.h.orig Sun Mar 11 11:20:21 2001
+++ linux/include/linux/irq.h Sun Mar 11 11:22:27 2001
@@ -57,18 +57,16 @@
#include <asm/hw_irq.h> /* the arch dependent stuff */
/**
- * nmi_watchdog_disable - disable NMI watchdog checking.
+ * touch_nmi_watchdog - restart NMI watchdog timeout.
*
- * If the architecture supports the NMI watchdog, nmi_watchdog_disable() may be used
- * to temporarily disable it. Use nmi_watchdog_enable() later on. It is implemented
- * via an up/down counter, so you must keep the calls balanced.
+ * If the architecture supports the NMI watchdog, touch_nmi_watchdog()
+ * may be used to reset the timeout - for code which intentionally
+ * disables interrupts for a long time. This call is stateless.
*/
#ifdef ARCH_HAS_NMI_WATCHDOG
-extern void nmi_watchdog_disable(void);
-extern void nmi_watchdog_enable(void);
+extern void touch_nmi_watchdog(void);
#else
-#define nmi_watchdog_disable() do{} while(0)
-#define nmi_watchdog_enable() do{} while(0)
+# define touch_nmi_watchdog() do { } while(0)
#endif
extern int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *);
--- linux/drivers/char/sysrq.c.orig Sun Mar 11 11:30:46 2001
+++ linux/drivers/char/sysrq.c Sun Mar 11 11:31:12 2001
@@ -72,9 +72,9 @@
/*
* Interrupts are disabled, and serial consoles are slow. So
- * Let's suspend the NMI watchdog.
+ * let's re-start the NMI watchdog timeout.
*/
- nmi_watchdog_disable();
+ touch_nmi_watchdog();
console_loglevel = 7;
printk(KERN_INFO "SysRq: ");
switch (key) {
@@ -158,7 +158,6 @@
/* Don't use 'A' as it's handled specially on the Sparc */
}
- nmi_watchdog_enable();
console_loglevel = orig_log_level;
}
--- linux/arch/i386/kernel/nmi.c.orig Sun Mar 11 11:24:34 2001
+++ linux/arch/i386/kernel/nmi.c Sun Mar 11 11:30:06 2001
@@ -226,37 +226,36 @@
}
static spinlock_t nmi_print_lock = SPIN_LOCK_UNLOCKED;
-static atomic_t nmi_watchdog_disabled = ATOMIC_INIT(0);
-void nmi_watchdog_disable(void)
-{
- atomic_inc(&nmi_watchdog_disabled);
-}
+/*
+ * the best way to detect wether a CPU has a 'hard lockup' problem
+ * is to check it's local APIC timer IRQ counts. If they are not
+ * changing then that CPU has some problem.
+ *
+ * as these watchdog NMI IRQs are generated on every CPU, we only
+ * have to check the current processor.
+ *
+ * since NMIs dont listen to _any_ locks, we have to be extremely
+ * careful not to rely on unsafe variables. The printk might lock
+ * up though, so we have to break up any console locks first ...
+ * [when there will be more tty-related locks, break them up
+ * here too!]
+ */
+
+static unsigned int
+ last_irq_sums [NR_CPUS],
+ alert_counter [NR_CPUS];
-void nmi_watchdog_enable(void)
+void touch_nmi_watchdog (void)
{
- atomic_dec(&nmi_watchdog_disabled);
+ /*
+ * Just reset the alert counter:
+ */
+ alert_counter[smp_processor_id()] = 0;
}
void nmi_watchdog_tick (struct pt_regs * regs)
{
- /*
- * the best way to detect wether a CPU has a 'hard lockup' problem
- * is to check it's local APIC timer IRQ counts. If they are not
- * changing then that CPU has some problem.
- *
- * as these watchdog NMI IRQs are broadcasted to every CPU, here
- * we only have to check the current processor.
- *
- * since NMIs dont listen to _any_ locks, we have to be extremely
- * careful not to rely on unsafe variables. The printk might lock
- * up though, so we have to break up any console locks first ...
- * [when there will be more tty-related locks, break them up
- * here too!]
- */
-
- static unsigned int last_irq_sums [NR_CPUS],
- alert_counter [NR_CPUS];
/*
* Since current-> is always on the stack, and we always switch
@@ -266,7 +265,7 @@
sum = apic_timer_irqs[cpu];
- if (last_irq_sums[cpu] == sum && atomic_read(&nmi_watchdog_disabled) == 0) {
+ if (last_irq_sums[cpu] == sum) {
/*
* Ayiee, looks like this CPU is stuck ...
* wait a few IRQs (5 seconds) before doing the oops ...
