[PATCH 2/3] rfi-flush: Make it possible to call setup_rfi_flush() again

Michael Ellerman mpe at ellerman.id.au
Sat Mar 17 01:18:45 AEDT 2018

Mauricio Faria de Oliveira <mauricfo at linux.vnet.ibm.com> writes:

> On 03/13/2018 03:36 PM, Michal Suchánek wrote:
>> On Tue, 13 Mar 2018 15:13:11 -0300
>> Mauricio Faria de Oliveira<mauricfo at linux.vnet.ibm.com>  wrote:
>>> On 03/13/2018 02:59 PM, Michal Suchánek wrote:
>>>> Maybe it would make more sense to move the messages to the function
>>>> that actually patches in the instructions?
>>> That helps, but if the instructions are not patched (e.g.,
>>> no_rfi_flush) then there is no information about what the system
>>> actually supports, which is useful for diagnostics/debugging (and
>>> patch verification!:-)  )
>> Can't you patch with debugfs in that case?
> For development purposes, yes, sure; but unfortunately sometimes only a
> dmesg output or other offline/postmortem data is available.
> And there's the user case where he is not aware/willing/allowed to use
> the debugfs switch.
> I still think the correct, informative messages are a good way to go :)

Yeah I agree.

We probably want to do both, print what's available at boot, and print
what's actually patched when the patching happens.


More information about the Linuxppc-dev mailing list