On Mon, Oct 28, 2024 at 09:54:49AM +0530, Srinivasulu Thanneeru wrote: > On Sun, Oct 27, 2024 at 10:23 PM Leon Romanovsky <leon@xxxxxxxxxx> wrote: > > > > From: Leon Romanovsky <leonro@xxxxxxxxxx> > > > > The existing .map_page() callback provides both allocating of IOVA > > and linking DMA pages. That combination works great for most of the > > callers who use it in control paths, but is less effective in fast > > paths where there may be multiple calls to map_page(). > > Can you please share perf stats with this patch in fast path, if available? I don't have this data for HMM and VFIO as they have other benefits from this series except performance. For NVMe, I don't have the data yet, but it will come https://lore.kernel.org/all/cover.1730037261.git.leon@xxxxxxxxxx/, as it is the main performant user of this API. This is the main reason why NVMe series is marked as RFC yet. Thanks