On Tue, Apr 06, 2021 at 08:43:19PM +0000, Jianxiong Gao wrote:
Hi all,
This series of backports fixes the SWIOTLB library to maintain the page offset when mapping a DMA address. The bug that motivated this patch series manifested when running a 5.4 kernel as a SEV guest with an NVMe device. However, any device that infers information from the page offset and is accessed through the SWIOTLB will benefit from this bug fix.
I feel like we have tried to backport this in the past, right? Have you looked in the stable archives?
What is wrong with just using 5.10.y instead for this type of hardware? What prevents you from doing that instead of backporting this new feature as this has never worked properly with this hardware on older kernels.
thanks,
greg k-h