On Thu, Feb 04 2021 at 16:11, Andy Lutomirski wrote: > On Thu, Feb 4, 2021 at 6:26 AM Lai Jiangshan <jiangshan...@gmail.com> wrote: >> When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU >> GSBASE value via __per_cpu_offset or pcpu_unit_offsets. >> >> When data breakpoint is set on __per_cpu_offset[cpu] (read-write >> operation), the specific cpu will be stuck in the infinite #DB loop. >> RCU will try to send NMI to the specific cpu, but it is not working >> either since NMI also relies on paranoid_entry(). > > Should we consider having a .percpu..noinstr section and having > objtool enforce this?
I think so. Thanks, tglx