From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 054A94A260F for ; Sat, 5 Sep 2026 12:52:10 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788612732; cv=none; b=PYshxmW4wqnj6yOsL7SxqjilMu1PQkGiucu+o3OKPoibAz6niu0PBmjeC4T8kTATDDoL4GPxFZ3krcv6QyZXGDo9/ccVzVr2faiVqyUOHXxmAuZ23j1HrTzps0tO4ujP5MqErKqR8EyE9MPysQiLRWfOFoko6y93Jr1MsLNa6xk= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788612732; c=relaxed/simple; bh=SwU7O5u2Zi+0MO7A5w4CrHOUj77vcKhfx446RwYJXHw=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=Tj1RCM9Lkx/n8pxdsVW59pJBDkNfUEtSjKS1F96gJRh5DfgMU1g5Eq6rv3UEkvk3OeMYc9QQl3anIknMpBwC+LmVWUnfOG41RvxnSyENG6srLOoXsgFyiY8oUyU09g4/DW/FR7AesNYdMB7Gb0CvdRESUbf3uw8hd7iEBEID/Ew= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=V/3O0UO2; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="V/3O0UO2" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 420911F00A3D; Sat, 5 Sep 2026 12:52:09 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1788612729; bh=SwU7O5u2Zi+0MO7A5w4CrHOUj77vcKhfx446RwYJXHw=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=V/3O0UO2N7TAuDTcDreqSlhtwladrlO5QKUy1e5/D9xvoT985R3Bj7itqN8mcyR02 88VjkIbjtq9Vg0JTxy3TkQTtdqpNco4x2EEAJ2Fi3aNLeUl+G3BQeospCtFZXpjYW7 YG0NuinBhPqGLQDqLMpBwMzwsOJoxQwOQpH1WaS+CWgAWxFLVSQt4dfgFcIVpgPrfz HnqVAEp4jXmB9Ju92NFz43erb9yRMLef7FNj4W2uw4N8+wPNSBah+WygeQMQSq/HiM yfchUeKczzuPXxkqK7u0pEQJcbmEXvupPfM9uOzXVPc79FyKJqQqQGTFnNcNVz4fmW pYyA9O8jPcgAg== Date: Sat, 5 Sep 2026 14:52:07 +0200 From: Lorenzo Bianconi To: Jakub Kicinski Cc: Paolo Abeni , Andrew Lunn , "David S. Miller" , Eric Dumazet , Alexander Lobakin , linux-arm-kernel@lists.infradead.org, linux-mediatek@lists.infradead.org, netdev@vger.kernel.org, Madhur Agrawal Subject: Re: [PATCH net-next v5] net: airoha: add HW GRO offload support Message-ID: References: <20260831-airoha-eth-lro-v5-1-6b0f50401121@kernel.org> <1ef90408-99b6-42fb-a7c6-7e5bca20c46d@redhat.com> <20260903162558.2679c1d1@kernel.org> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="CrcWeQCa+fXKdkYr" Content-Disposition: inline In-Reply-To: <20260903162558.2679c1d1@kernel.org> --CrcWeQCa+fXKdkYr Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable > On Thu, 3 Sep 2026 17:45:50 +0200 Lorenzo Bianconi wrote: > > > Lacking more details from the vendor, I think you need to use a > > > pktdrill-like sender, explicitly sets the segment lengths to some not > > > mergeable (like, i.e. 200-300-400) but otherwise fitting a GRO packet > > > (i.e. same hdr except for the sequence number and push flag allowed o= nly > > > in the last packet), ensure that the aggregation timeout lasts long > > > enough to receive all of them, and check if the engine really aggrega= tes > > > them or not. =20 > >=20 > > I think in the example you pointed out (length 200,300,400) the hw engi= ne will > > create a single TCP packet composed by 3 segments (with gso_size =3D 30= 0) while > > sw GRO will just push sigle skbs. I agree this is just a GRO approximat= ion. > > If it is not enough I am fine to switch back to LRO implementation. >=20 > FWIW the gro.py test covers that and many more cases.. ack, thx for the pointer. I run data_sml_lrg test available in gro.py and I can confirm the hw aggregates the transmitted packets (even if it is not supposed to do it). I will switch back to LRO in v6. Regards, Lorenzo --CrcWeQCa+fXKdkYr Content-Type: application/pgp-signature; name=signature.asc -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQTquNwa3Txd3rGGn7Y6cBh0uS2trAUCapwQdwAKCRA6cBh0uS2t rPirAQC2OncL2LAuHYc8s0bUpffO3Nka35iD1jYtzPuIluDdaAEAwfTd23B04aYZ UlRKhK+AWicClQ7Sknyr1xeLgqtENgA= =U/DL -----END PGP SIGNATURE----- --CrcWeQCa+fXKdkYr--