Message-ID: <bd604c16-0f5c-479c-aa13-932f1570e5b5@engleder-embedded.com>
Date: Tue, 4 Feb 2025 21:18:25 +0100
From: Gerhard Engleder <gerhard@...leder-embedded.com>
To: anthony.l.nguyen@...el.com
Cc: intel-wired-lan@...ts.osuosl.org, netdev@...r.kernel.org,
 linux-pci@...r.kernel.org, przemyslaw.kitszel@...el.com,
 andrew+netdev@...n.ch, davem@...emloft.net, kuba@...nel.org,
 edumazet@...gle.com, pabeni@...hat.com, bhelgaas@...gle.com,
 pmenzel@...gen.mpg.de, aleksander.lobakin@...el.com,
 Gerhard Engleder <eg@...a.com>, Vitaly Lifshits <vitaly.lifshits@...el.com>,
 Avigail Dahan <avigailx.dahan@...el.com>, Simon Horman <horms@...nel.org>
Subject: Re: [PATCH iwl-next v4] e1000e: Fix real-time violations on link up

On 06.01.25 12:17, Simon Horman wrote:
> On Thu, Dec 19, 2024 at 08:27:43PM +0100, Gerhard Engleder wrote:
>> From: Gerhard Engleder <eg@...a.com>
>>
>> Link down and up triggers update of MTA table. This update executes many
>> PCIe writes and a final flush. Thus, PCIe will be blocked until all
>> writes are flushed. As a result, DMA transfers of other targets suffer
>> from delay in the range of 50us. This results in timing violations on
>> real-time systems during link down and up of e1000e in combination with
>> an Intel i3-2310E Sandy Bridge CPU.
>>
>> The i3-2310E is quite old. Launched 2011 by Intel but still in use as
>> robot controller. The exact root cause of the problem is unclear and
>> this situation won't change as Intel support for this CPU has ended
>> years ago. Our experience is that the number of posted PCIe writes needs
>> to be limited at least for real-time systems. With posted PCIe writes a
>> much higher throughput can be generated than with PCIe reads which
>> cannot be posted. Thus, the load on the interconnect is much higher.
>> Additionally, a PCIe read waits until all posted PCIe writes are done.
>> Therefore, the PCIe read can block the CPU for much more than 10us if a
>> lot of PCIe writes were posted before. Both issues are the reason why we
>> are limiting the number of posted PCIe writes in row in general for our
>> real-time systems, not only for this driver.
>>
>> A flush after a low enough number of posted PCIe writes eliminates the
>> delay but also increases the time needed for MTA table update. The
>> following measurements were done on i3-2310E with e1000e for 128 MTA
>> table entries:
>>
>> Single flush after all writes: 106us
>> Flush after every write:       429us
>> Flush after every 2nd write:   266us
>> Flush after every 4th write:   180us
>> Flush after every 8th write:   141us
>> Flush after every 16th write:  121us
>>
>> A flush after every 8th write delays the link up by 35us and the
>> negative impact to DMA transfers of other targets is still tolerable.
>>
>> Execute a flush after every 8th write. This prevents overloading the
>> interconnect with posted writes.
>>
>> Signed-off-by: Gerhard Engleder <eg@...a.com>
>> Link: https://lore.kernel.org/netdev/f8fe665a-5e6c-4f95-b47a-2f3281aa0e6c@lunn.ch/T/
>> CC: Vitaly Lifshits <vitaly.lifshits@...el.com>
>> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@...el.com>
>> Tested-by: Avigail Dahan <avigailx.dahan@...el.com>
>> ---
>> v4:
>> - add PREEMPT_RT dependency again (Vitaly Lifshits)
>> - fix comment styple (Alexander Lobakin)
>> - add to comment each 8th and explain why (Alexander Lobakin)
>> - simplify check for every 8th write (Alexander Lobakin)
>>
>> v3:
>> - mention problematic platform explicitly (Bjorn Helgaas)
>> - improve comment (Paul Menzel)
>>
>> v2:
>> - remove PREEMPT_RT dependency (Andrew Lunn, Przemek Kitszel)
> 
> Reviewed-by: Simon Horman <horms@...nel.org>

Is there anything left from my side to get this change over iwl-next
into net-next?

Gerhard

Powered by blists - more mailing lists