On Sat, 9 Dec 2023 20:23:09 +0100 Lorenzo Bianconi wrote: > Are we going to use these page_pools just for virtual devices (e.g. veth) or > even for hw NICs? If we do not bound the page_pool to a netdevice I think we > can't rely on it to DMA map/unmap the buffer, right? Right, I don't think it's particularly useful for HW NICs. Maybe for allocating skb heads? We could possibly kill struct page_frag_1k and use PP page / frag instead. But not sure how Eric would react :) > Moreover, are we going to rework page_pool stats first? It seems a bit weird to > have a percpu struct with a percpu pointer in it, right? The per-CPU stuff is for recycling, IIRC. Even if PP is for a single CPU we can still end up freeing packets which used its pages anywhere in the system. I don't disagree that we may end up with a lot of stats on a large system, but seems tangential to per-cpu page pools.
