On Thu, Sep 06, 2018 at 04:27:47PM -0700, Sai Praneeth Prakhya wrote:
> @@ -790,6 +792,13 @@ no_context(struct pt_regs *regs, unsigned long error_code,
> return;
>
> /*
> + * Buggy firmware could access regions which might page fault, try to
> + * recover from such faults.
> + */
> + if (efi_recover_from_page_fault(address))
> + return;
> +
> + /*
> * Oops. The kernel tried to access some bad page. We'll have to
> * terminate things with extreme prejudice:
> */
> +int efi_recover_from_page_fault(unsigned long phys_addr)
> +{
> + /* Recover from page faults caused *only* by the firmware */
> + if (current->active_mm != &efi_mm)
> + return 0;
> +
> + /*
> + * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
> + * page faulting on these addresses isn't expected.
> + */
> + if (phys_addr >= 0x0000 && phys_addr <= 0x0fff)
> + return 0;
> +
> + /*
> + * Print stack trace as it might be useful to know which EFI Runtime
> + * Service is buggy.
> + */
> + WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n",
> + phys_addr);
> +
> + /*
> + * Buggy efi_reset_system() is handled differently from other EFI
> + * Runtime Services as it doesn't use efi_rts_wq. Although,
> + * native_machine_emergency_restart() says that machine_real_restart()
> + * could fail, it's better not to compilcate this fault handler
> + * because this case occurs *very* rarely and hence could be improved
> + * on a need by basis.
> + */
> + if (efi_rts_work.efi_rts_id == RESET_SYSTEM) {
> + pr_info("efi_reset_system() buggy! Reboot through BIOS\n");
> + machine_real_restart(MRR_BIOS);
> + return 0;
> + }
> +
> + /* Firmware has caused page fault, hence, freeze efi_rts_wq. */
> + set_current_state(TASK_UNINTERRUPTIBLE);
This doesn't freeze it, as such, it just sets the state.
> +
> + /*
> + * Before calling EFI Runtime Service, the kernel has switched the
> + * calling process to efi_mm. Hence, switch back to task_mm.
> + */
> + arch_efi_call_virt_teardown();
> +
> + /* Signal error status to the efi caller process */
> + efi_rts_work.status = EFI_ABORTED;
> + complete(&efi_rts_work.efi_rts_comp);
> +
> + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
> + pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n");
> + schedule();
So what happens when we get a spurious wakeup and return from this?
Quite possibly you want something like:
for (;;) {
set_current_state(TASK_IDLE);
schedule();
}
here. The TASK_UNINTERRUPTIBLE thing will cause the load-avg to spike;
is that what you want?
> +
> + return 0;
> +}
