On 08/03/2016 01:12 PM, Benjamin Herrenschmidt wrote:
I'm not sure if there are other cases with softmmu for example, where we do get an exact host PC and thus where the -2 might take us back too far.
I don't think there are. Almost everywhere we have the call return address. It's only this case of signal handling where we have an exception address.
I don't see your patch upstream yet so feel free to fold my change into yours.
Will do, thanks. I think this will be waiting for 2.8. r~
