> One could try clearing the store bit in the page fault handler, but then > that might cause a loop. > Not sure it has any practical meaning though. > > Anyhow, you are welcome to have a look at the patches I have been tossing out.
The store bit in do_page_fault() is -very- important (and the only DSISR bit that is as I wrote earlier). The generic code must know if a fault is caused by a load or a store since the later is what will cause copy_on_write to happen for example, or dirty to be set, etc.. Ben. _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev