From: Jakub Kicinski <kuba@kernel.org>
To: Alexander Lobakin <aleksander.lobakin@intel.com>
Cc: Eric Dumazet <edumazet@google.com>,
Heiner Kallweit <hkallweit1@gmail.com>,
Paolo Abeni <pabeni@redhat.com>,
David Miller <davem@davemloft.net>,
Realtek linux nic maintainers <nic_swsd@realtek.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
Ken Milmore <ken.milmore@gmail.com>
Subject: Re: [PATCH net 2/2] r8169: disable interrupts also for GRO-scheduled NAPI
Date: Tue, 14 May 2024 07:11:00 -0700 [thread overview]
Message-ID: <20240514071100.70fcca3e@kernel.org> (raw)
In-Reply-To: <CANn89i+yKgXGHUyJxVLYTAMKj7wpoV+8X7UR8cWh75yxVLSA6Q@mail.gmail.com>
On Tue, 14 May 2024 13:05:55 +0200 Eric Dumazet wrote:
> > napi_schedule() // we disabled interrupts
> > napi_poll() // we polled < budget frames
> > napi_complete_done() // reenable the interrupts, no repoll
> > hrtimer_start() // GRO flush is queued
> > napi_schedule()
> > napi_poll() // GRO flush, BUT interrupts are enabled
I thought the bug is because of a race with disable.
But there's already a synchronize_net() after disable, so NAPI poll
must fully exit before we mask in rtl8169_cleanup().
If the bug is double-enable you describe the fix is just making
the race window smaller. But I don't think that's the bug.
BTW why are events only acked in rtl8169_interrupt() and not
rtl8169_poll()?
next prev parent reply other threads:[~2024-05-14 14:11 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-14 6:49 [PATCH net 0/2] r8169: Fix GRO-related issue with not disabled device interrupts Heiner Kallweit
2024-05-14 6:50 ` [PATCH net 1/2] net: add napi_schedule_prep variant with more granular return value Heiner Kallweit
2024-05-14 11:07 ` Eric Dumazet
2024-05-14 11:40 ` Heiner Kallweit
2024-05-14 6:52 ` [PATCH net 2/2] r8169: disable interrupts also for GRO-scheduled NAPI Heiner Kallweit
2024-05-14 9:45 ` Eric Dumazet
2024-05-14 10:52 ` Alexander Lobakin
2024-05-14 11:05 ` Eric Dumazet
2024-05-14 11:17 ` Alexander Lobakin
2024-05-14 14:27 ` Eric Dumazet
2024-05-14 11:29 ` Heiner Kallweit
2024-05-14 14:11 ` Jakub Kicinski [this message]
2024-05-14 16:35 ` Heiner Kallweit
2024-05-14 16:49 ` Jakub Kicinski
2024-05-14 17:09 ` Heiner Kallweit
2024-05-14 17:47 ` Jakub Kicinski
2024-05-14 17:49 ` Jakub Kicinski
2024-05-14 20:47 ` Ken Milmore
2024-05-15 5:53 ` Heiner Kallweit
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=20240514071100.70fcca3e@kernel.org \
--to=kuba@kernel.org \
--cc=aleksander.lobakin@intel.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hkallweit1@gmail.com \
--cc=ken.milmore@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=nic_swsd@realtek.com \
--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).