[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <a5c2ee3c-6643-4e67-acba-44384706e971@molgen.mpg.de>
Date: Tue, 2 Dec 2025 18:34:17 +0100
From: Paul Menzel <pmenzel@...gen.mpg.de>
To: Chwee-Lin Choong <chwee.lin.choong@...el.com>
Cc: Tony Nguyen <anthony.l.nguyen@...el.com>,
Przemek Kitszel <przemyslaw.kitszel@...el.com>,
Andrew Lunn <andrew+netdev@...n.ch>, "David S . Miller"
<davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
intel-wired-lan@...ts.osuosl.org, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org, Zdenek Bouska <zdenek.bouska@...mens.com>,
Faizal Rahim <faizal.abdul.rahim@...ux.intel.com>
Subject: Re: [Intel-wired-lan] [PATCH iwl-net v1] igc: Use 5KB TX packet
buffer per queue for TSN mode
Dear Chwee-Lin,
Thank you for your patch.
(Just a heads-up, that Zdenek’s email address was not properly quoted in
the Cc: list.)
In the summary you could be more specific to say, that you *decrease*
the size.
Am 02.12.25 um 13:23 schrieb Chwee-Lin Choong:
> Update IGC_TXPBSIZE_TSN to allocate 5KB per TX queue (TXQ0-TXQ3)
> as recommended in I225/I226 SW User Manual Section 7.5.4 for TSN
> operation.
Please elaborate on the problem (mention the 7 KB size and hangs), and
maybe Faizal remembers why they chose 7 KB.
Also, are there any performance drawbacks. (I know that avoiding hangs
tops that, but it would be good to know.)
> Fixes: 0d58cdc902da ("igc: optimize TX packet buffer utilization for TSN mode")
> Reported-by: Zdenek Bouska <zdenek.bouska@...mens.com>
> Closes: https://lore.kernel.org/netdev/AS1PR10MB5675DBFE7CE5F2A9336ABFA4EBEAA@AS1PR10MB5675.EURPRD10.PROD.OUTLOOK.COM/
> Signed-off-by: Chwee-Lin Choong <chwee.lin.choong@...el.com>
> ---
> drivers/net/ethernet/intel/igc/igc_defines.h | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
> index 498ba1522ca4..9482ab11f050 100644
> --- a/drivers/net/ethernet/intel/igc/igc_defines.h
> +++ b/drivers/net/ethernet/intel/igc/igc_defines.h
> @@ -443,9 +443,10 @@
> #define IGC_TXPBSIZE_DEFAULT ( \
> IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \
> IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4))
> +/* TSN value following I225/I226 SW User Manual Section 7.5.4 */
> #define IGC_TXPBSIZE_TSN ( \
> - IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \
> - IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4))
> + IGC_TXPB0SIZE(5) | IGC_TXPB1SIZE(5) | IGC_TXPB2SIZE(5) | \
> + IGC_TXPB3SIZE(5) | IGC_OS2BMCPBSIZE(4))
Reading the commit message of commit 0d58cdc902da ("igc: optimize TX
packet buffer utilization for TSN mode"), it says, that the goal is to
split up 32 KB. What is happening to the 8 KB that are freed up now?
> #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */
> #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */
With a more elaborate commit message, feel free to add:
Reviewed-by: Paul Menzel <pmenzel@...gen.mpg.de>
Kind regards,
Paul
Powered by blists - more mailing lists