Received-SPF: pass (google.com: domain of linux-kernel+bounces-15876-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20231214020530.2267499-1-almasrymina@google.com>
 <20231214020530.2267499-5-almasrymina@google.com> <ddffff98-f3de-6a5d-eb26-636dacefe9aa@huawei.com>
 <CAHS8izO2nDHuxKau8iLcAmnho-1TYkzW09MBZ80+JzOo9YyVFA@mail.gmail.com>
 <20231215021114.ipvdx2bwtxckrfdg@google.com> <20231215190126.1040fa12@kernel.org>
 <CALvZod5myy2SvuCMNmqjjYeNONqSArV+8y8mrkfnNeog8WLjng@mail.gmail.com>
 <CAHS8izOLBtjHOqbTS_PiTNe+rTE=jboDWDM9zS108B57vVNcwA@mail.gmail.com>
 <CAHS8izMkCwv3jak9KUHeDUrkwBNNpdYk4voEX7Cbp7mTpNAQdA@mail.gmail.com>
 <54f226ef-df2d-9f32-fa3f-e846d6510758@huawei.com> <CAHS8izP63wXGH+Q3y1H=ycT=AHYnhGveBnuyF_rYioAjZ=Hn=g@mail.gmail.com>
 <7c6d35e3-165f-5883-1c1b-fce82c976028@huawei.com> <CAHS8izNqeiK1tq=48LMbbqq5B4d2mhgbuKRvnFtiBngf73jXZg@mail.gmail.com>
 <fda068d0-f7fb-90fc-cdd6-1f853a4a225f@huawei.com>
In-Reply-To: <fda068d0-f7fb-90fc-cdd6-1f853a4a225f@huawei.com>
From: Mina Almasry <almasrymina@google.com>
Date: Wed, 3 Jan 2024 10:38:31 -0800
Message-ID: <CAHS8izNAxB=DQzSBOGbm6SsiL1cLSijj9n=g3d3egSxnOcBibQ@mail.gmail.com>
Subject: Re: [RFC PATCH net-next v1 4/4] net: page_pool: use netmem_t instead
 of struct page in API
To: Yunsheng Lin <linyunsheng@huawei.com>
Cc: Shakeel Butt <shakeelb@google.com>, Jakub Kicinski <kuba@kernel.org>, linux-kernel@vger.kernel.org, 
	netdev@vger.kernel.org, bpf@vger.kernel.org, 
	Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>, 
	Dave Hansen <dave.hansen@linux.intel.com>, x86@kernel.org, 
	"H. Peter Anvin" <hpa@zytor.com>, Greg Kroah-Hartman <gregkh@linuxfoundation.org>, 
	"Rafael J. Wysocki" <rafael@kernel.org>, Sumit Semwal <sumit.semwal@linaro.org>, 
	=?UTF-8?Q?Christian_K=C3=B6nig?= <christian.koenig@amd.com>, 
	Michael Chan <michael.chan@broadcom.com>, "David S. Miller" <davem@davemloft.net>, 
	Eric Dumazet <edumazet@google.com>, Paolo Abeni <pabeni@redhat.com>, 
	Alexei Starovoitov <ast@kernel.org>, Daniel Borkmann <daniel@iogearbox.net>, 
	Jesper Dangaard Brouer <hawk@kernel.org>, John Fastabend <john.fastabend@gmail.com>, Wei Fang <wei.fang@nxp.com>, 
	Shenwei Wang <shenwei.wang@nxp.com>, Clark Wang <xiaoning.wang@nxp.com>, 
	NXP Linux Team <linux-imx@nxp.com>, Jeroen de Borst <jeroendb@google.com>, 
	Praveen Kaligineedi <pkaligineedi@google.com>, Shailend Chand <shailend@google.com>, 
	Yisen Zhuang <yisen.zhuang@huawei.com>, Salil Mehta <salil.mehta@huawei.com>, 
	Jesse Brandeburg <jesse.brandeburg@intel.com>, Tony Nguyen <anthony.l.nguyen@intel.com>, 
	Thomas Petazzoni <thomas.petazzoni@bootlin.com>, Marcin Wojtas <mw@semihalf.com>, 
	Russell King <linux@armlinux.org.uk>, Sunil Goutham <sgoutham@marvell.com>, 
	Geetha sowjanya <gakula@marvell.com>, Subbaraya Sundeep <sbhatta@marvell.com>, 
	hariprasad <hkelam@marvell.com>, Felix Fietkau <nbd@nbd.name>, John Crispin <john@phrozen.org>, 
	Sean Wang <sean.wang@mediatek.com>, Mark Lee <Mark-MC.Lee@mediatek.com>, 
	Lorenzo Bianconi <lorenzo@kernel.org>, Matthias Brugger <matthias.bgg@gmail.com>, 
	AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>, 
	Saeed Mahameed <saeedm@nvidia.com>, Leon Romanovsky <leon@kernel.org>, 
	Horatiu Vultur <horatiu.vultur@microchip.com>, UNGLinuxDriver@microchip.com, 
	"K. Y. Srinivasan" <kys@microsoft.com>, Haiyang Zhang <haiyangz@microsoft.com>, Wei Liu <wei.liu@kernel.org>, 
	Dexuan Cui <decui@microsoft.com>, Jassi Brar <jaswinder.singh@linaro.org>, 
	Ilias Apalodimas <ilias.apalodimas@linaro.org>, 
	Alexandre Torgue <alexandre.torgue@foss.st.com>, Jose Abreu <joabreu@synopsys.com>, 
	Maxime Coquelin <mcoquelin.stm32@gmail.com>, Siddharth Vadapalli <s-vadapalli@ti.com>, 
	Ravi Gunasekaran <r-gunasekaran@ti.com>, Roger Quadros <rogerq@kernel.org>, 
	Jiawen Wu <jiawenwu@trustnetic.com>, Mengyuan Lou <mengyuanlou@net-swift.com>, 
	Ronak Doshi <doshir@vmware.com>, VMware PV-Drivers Reviewers <pv-drivers@vmware.com>, 
	Ryder Lee <ryder.lee@mediatek.com>, Shayne Chen <shayne.chen@mediatek.com>, 
	Kalle Valo <kvalo@kernel.org>, Juergen Gross <jgross@suse.com>, 
	Stefano Stabellini <sstabellini@kernel.org>, 
	Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>, Andrii Nakryiko <andrii@kernel.org>, 
	Martin KaFai Lau <martin.lau@linux.dev>, Song Liu <song@kernel.org>, 
	Yonghong Song <yonghong.song@linux.dev>, KP Singh <kpsingh@kernel.org>, 
	Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>, Jiri Olsa <jolsa@kernel.org>, 
	Stefan Hajnoczi <stefanha@redhat.com>, Stefano Garzarella <sgarzare@redhat.com>, Shuah Khan <shuah@kernel.org>, 
	=?UTF-8?B?TWlja2HDq2wgU2FsYcO8bg==?= <mic@digikod.net>, 
	Nathan Chancellor <nathan@kernel.org>, Nick Desaulniers <ndesaulniers@google.com>, 
	Bill Wendling <morbo@google.com>, Justin Stitt <justinstitt@google.com>, 
	Jason Gunthorpe <jgg@nvidia.com>, Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Jan 3, 2024 at 1:47=E2=80=AFAM Yunsheng Lin <linyunsheng@huawei.com=
> wrote:
>
> On 2024/1/3 0:14, Mina Almasry wrote:
> >
> > The idea being that skb_frag_page() can return NULL if the frag is not
> > paged, and the relevant callers are modified to handle that.
>
> There are many existing drivers which are not expecting NULL returning fo=
r
> skb_frag_page() as those drivers are not supporting devmem, adding additi=
onl
> checking overhead in skb_frag_page() for those drivers does not make much
> sense, IMHO, it may make more sense to introduce a new helper for the dri=
ver
> supporting devmem or networking core that needing dealing with both norma=
l
> page and devmem.
>
> And we are also able to keep the old non-NULL returning semantic for
> skb_frag_page().

I think I'm seeing agreement that the direction we're heading into
here is that most net stack & drivers should use the abstract netmem
type, and only specific code that needs a page or devmem (like
tcp_receive_zerocopy or tcp_recvmsg_dmabuf) will be the ones that
unpack the netmem and get the underlying page or devmem, using
skb_frag_page() or something like skb_frag_dmabuf(), etc.

As Jason says repeatedly, I'm not allowed to blindly cast a netmem to
a page and assume netmem=3D=3Dpage. Netmem can only be cast to a page
after checking the low bits and verifying the netmem is actually a
page. I think any suggestions that blindly cast a netmem to page
without the checks will get nacked by Jason & Christian, so the
checking in the specific cases where the code needs to know the
underlying memory type seems necessary.

IMO I'm not sure the checking is expensive. With likely/unlikely &
static branches the checks should be very minimal or a straight no-op.
For example in RFC v2 where we were doing a lot of checks for devmem
(we don't do that anymore for RFCv5), I had run the page_pool perf
tests and proved there is little to no perf regression:

https://lore.kernel.org/netdev/CAHS8izM4w2UETAwfnV7w+ZzTMxLkz+FKO+xTgRdtYKz=
V8RzqXw@mail.gmail.com/

--=20
Thanks,
Mina