Re: nForce 4 corrupting data written to HDD
> I cannot confirm this. IIRC most people (if not all) had the problem
> solved when using MEM=2G or so.
That's because there appear to be two distinct problems. I just got off the phone with my counterpart at Red Hat. What they're seeing is a 4 KiB page being zerod unexpectedly. When they don't use the IOMMU (such as booting with "mem=2g") the problem goes away. That failure mode could be a Linux kernel defect or a hardware defect. The failure mode I'm seeing on my system are random 32-bit words of four of nine files being corrupted. My problem could not possibly be a kernel defect and definitely has nothing to do with the use of the hardware IOMMU as the corruption occurs with only 2 GiB installed, "mem=1g" as well as "iommu=soft".