[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <0277b2b5-b3f4-41da-8c18-e6131f908fd3@redhat.com>
Date: Thu, 14 Aug 2025 11:39:41 +0200
From: Paolo Abeni <pabeni@...hat.com>
To: Jakub Kicinski <kuba@...nel.org>, davem@...emloft.net
Cc: netdev@...r.kernel.org, edumazet@...gle.com, andrew+netdev@...n.ch,
horms@...nel.org, donald.hunter@...il.com, michael.chan@...adcom.com,
pavan.chebbi@...adcom.com, willemdebruijn.kernel@...il.com,
ecree.xilinx@...il.com, andrew@...n.ch
Subject: Re: [PATCH net-next v4 1/4] net: ethtool: support including Flow
Label in the flow hash for RSS
On 8/12/25 1:42 AM, Jakub Kicinski wrote:
> It is expected that the hash communicated to the host
> may change if the Flow Label changes. This may be surprising
> to some host software, but I don't expect the devices
> can compute two Toeplitz hashes, one with the Flow Label
> for queue selection and one without for the rx hash
> communicated to the host. Besides, changing the hash
> may potentially help to change the path thru host queues.
> User can disable NETIF_F_RXHASH if they require a stable
> flow hash.
FWIW, my understanding is that the S/W computed RX hash includes by
default the flow label, as skb_get_hash()/__skb_get_hash_net() dissect
with FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL and the latter force the
flowlabel inclusion when available.
AFAICS enabling RXH_IP6_FL will make the H/W and S/W hashing consistent.
/P
Powered by blists - more mailing lists