[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241028064634.GE1615717@unreal>
Date: Mon, 28 Oct 2024 08:46:34 +0200
From: Leon Romanovsky <leon@...nel.org>
To: Srinivasulu Thanneeru <dev.srinivasulu@...il.com>
Cc: Jens Axboe <axboe@...nel.dk>, Jason Gunthorpe <jgg@...pe.ca>,
Robin Murphy <robin.murphy@....com>, Joerg Roedel <joro@...tes.org>,
Will Deacon <will@...nel.org>, Christoph Hellwig <hch@....de>,
Sagi Grimberg <sagi@...mberg.me>, Keith Busch <kbusch@...nel.org>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Logan Gunthorpe <logang@...tatee.com>,
Yishai Hadas <yishaih@...dia.com>,
Shameer Kolothum <shameerali.kolothum.thodi@...wei.com>,
Kevin Tian <kevin.tian@...el.com>,
Alex Williamson <alex.williamson@...hat.com>,
Marek Szyprowski <m.szyprowski@...sung.com>,
Jérôme Glisse <jglisse@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Jonathan Corbet <corbet@....net>, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-block@...r.kernel.org,
linux-rdma@...r.kernel.org, iommu@...ts.linux.dev,
linux-nvme@...ts.infradead.org, linux-pci@...r.kernel.org,
kvm@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH 05/18] dma: Provide an interface to allow allocate IOVA
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@...nel.org> wrote:
> >
> > From: Leon Romanovsky <leonro@...dia.com>
> >
> > 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@kernel.org/,
as it is the main performant user of this API.
This is the main reason why NVMe series is marked as RFC yet.
Thanks
Powered by blists - more mailing lists