Skip to contentSkip to conversation

x86_64: add nmi_exit to die_nmi

PATCH In review Corey Minyard 2 participants 2 messages Apr 27, 2006 – Apr 29, 2006

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 x86_64: add nmi_exit to die_nmi

Playing with NMI watchdog on x86_64, I discovered that it didn't do what I expected. It always panic-ed, even when it didn't happen from interrupt context. This patch solves that problem for me. Also, in this case, do_exit() will be called with interrupts disabled, I believe. Would it be wise to also call local_irq_enable() after nmi_exit()?

Currently, on x86_64, any NMI watchdog timeout will cause a panic because the irq count will always be set to be in an interrupt when do_exit() is called from die_nmi(). If we add nmi_exit() to the die_nmi() call (since the nmi will never exit "normally") it seems to solve this problem. The following small program can be used to trigger the NMI watchdog to reproduce this:
main ()

  {
        iopl(3);
        for (;;) asm("cli");

}

arch/x86_64/kernel/traps.c +1 -0
index 0ebb281..872ddfc 100644
@@ -472,6 +472,7 @@ void __kprobes die_nmi(char *str, struct
 		panic("nmi watchdog");
 	printk("console shuts up ...\n");
 	oops_end(flags);
+	nmi_exit();
 	do_exit(SIGSEGV);
 }
 
#1 lore raw
Quoted 3 lines · Corey Minyard

Playing with NMI watchdog on x86_64, I discovered that it didn't do what I expected. It always panic-ed, even when it didn't happen from interrupt context.

Hmm, I don't think that's true. Or at least it worked at some point. Ok maybe something regressed.

Quoted 4 lines

This patch solves that
problem for me. Also, in this case, do_exit() will be called with interrupts disabled, I believe. Would it be wise to also call local_irq_enable() after nmi_exit()?

Probably yes. I added that with the the patch.

Thanks,
-Andi