From: Jakub Kicinski <kuba@kernel.org>
To: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: netdev@vger.kernel.org, davem@davemloft.net, edumazet@google.com,
pabeni@redhat.com, Jesper Dangaard Brouer <hawk@kernel.org>,
Alexander Duyck <alexander.duyck@gmail.com>,
Yonglong Liu <liuyonglong@huawei.com>,
Yunsheng Lin <linyunsheng@huawei.com>
Subject: Re: [RFC net] net: make page pool stall netdev unregistration to avoid IOMMU crashes
Date: Thu, 8 Aug 2024 06:52:28 -0700 [thread overview]
Message-ID: <20240808065228.4188e5d3@kernel.org> (raw)
In-Reply-To: <CAC_iWj+G_Rrqw8R5PR3vZsL5Oid+_tzNOLOg6Hoo1jt3vhGx5A@mail.gmail.com>
On Thu, 8 Aug 2024 14:12:34 +0300 Ilias Apalodimas wrote:
> In any case why do you want to hold on the IOMMU? The network
> interface -- at least in theory -- should be down and we wont be
> processing any more packets.
I should have you a link to Yonglong's report:
https://lore.kernel.org/all/8743264a-9700-4227-a556-5f931c720211@huawei.com/
we get_device() hoping that it will keep the IOMMU machinery active
(even if the device won't use the page we need to unmap it when it's
freed), but it sounds like IOMMU dies when driver is unbound. Even if
there are outstanding references to the device.
I occasionally hit this problem reloading drivers during development,
TBH, too. And we have been told we "use the API wrong" so let's fix
it on our end?..
next prev parent reply other threads:[~2024-08-08 13:52 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-06 15:16 [RFC net] net: make page pool stall netdev unregistration to avoid IOMMU crashes Jakub Kicinski
2024-08-07 7:03 ` Yonglong Liu
2024-08-07 14:27 ` Jakub Kicinski
2024-08-08 1:11 ` Yonglong Liu
2024-08-07 11:00 ` Yunsheng Lin
2024-08-07 14:29 ` Jakub Kicinski
2024-08-08 12:52 ` Yonglong Liu
2024-08-08 14:05 ` Jakub Kicinski
2024-08-09 6:06 ` Yonglong Liu
2024-08-10 3:57 ` Jakub Kicinski
2024-08-14 10:09 ` Yonglong Liu
2024-08-14 14:56 ` Jakub Kicinski
2024-08-08 11:12 ` Ilias Apalodimas
2024-08-08 13:52 ` Jakub Kicinski [this message]
2024-08-08 14:30 ` Ilias Apalodimas
2024-08-08 14:51 ` Jakub Kicinski
2024-09-05 10:47 ` Yunsheng Lin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240808065228.4188e5d3@kernel.org \
--to=kuba@kernel.org \
--cc=alexander.duyck@gmail.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=ilias.apalodimas@linaro.org \
--cc=linyunsheng@huawei.com \
--cc=liuyonglong@huawei.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).