On Fri, Feb 21, 2020 at 5:50 AM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote: > > A few exceptions (like #DB and #BP) can happen at any location in the > code, this then means that tracers should treat events from these > exceptions as NMI-like. We could be holding locks with interrupts > disabled for instance. > > Similarly, #MC is an actual NMI-like exception. > > -dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) > +dotraplinkage notrace void do_int3(struct pt_regs *regs, long error_code) > { > if (poke_int3_handler(regs)) > return; > > - /* > - * Use ist_enter despite the fact that we don't use an IST stack. > - * We can be called from a kprobe in non-CONTEXT_KERNEL kernel > - * mode or even during context tracking state changes. > - * > - * This means that we can't schedule. That's okay. > - */ > - ist_enter(regs); > + nmi_enter(); I agree with the change, but some commentary might be nice. Maybe copy from here: https://git.kernel.org/pub/scm/linux/kernel/git/luto/linux.git/commit/?h=x86/idtentry&id=061eaa900b4f63601ab6381ab431fcef8dfd84be