* Woodruff, Richard <r-woodruff2@xxxxxx> [080115 09:28]: > > * Previously to synchronize better we had to put the barriers at the > > writes to the PIC as it by default had a buffered type. However, > other > > devices were strongly ordered, thus they were more safe. If you > recall > > Catalin also asked for patches to controllers to fix this on ARM11. > Last > > time this spurious flared up it was because in open source resyncing > these > > barriers were dropped. > > BTW, Looking at the current omap-git tree vs. the TI tree's I see that > the sync_p_port() write calls are not there. If you add them in you > probably will have a 80% drop in issues. To get 100 I think device > attribute memory needs changing. > > If you look at old mails I gave some lengthy descriptions why they were > there for ARM11. They were there based observed failures. Yeah. That patch should be updated to have it available for arm in general. Tony - To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
