From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=205.220.168.131 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794481790; b=ok2ENidc6tzKBsGVPxxPk+o95Qq8YLCwVB2sGSJlBYk/tQZk9Nnzyl74qjWzzVopN4o2 1+zyjr/RLNwcHLxlmkKSwsi4axt+o/hFqJOQM/XKgLAEdi94IYXS3gx9EwbA4AReNXPyf N+VRl92oBCj90wsIAbvP9P/siSfe92IAfTbPF2wXhoq4uj/8h5jlOq3zt4IfdifVGTo8G MnCl5baWNoixltb7DHWLT62H5jfpb8pDB4VtXLFFMHnBd50DyWVan3JCoVLUHCcyNO0Fk QJdRS3UZERSquc3SMtvDhHALeVHYPqmbqkGEEzBM8/jLGBo4aCwdRxy+SSKnmXbYOgg== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794481790; h=DMARC-Filter:Received:DKIM-Signature:Received:Received: DKIM-Signature:X-Google-DKIM-Signature:X-Forwarded-Encrypted: X-Gm-Message-State:X-Gm-Gg:X-Received:X-Received:Received:Date:From: Cc:Subject:Message-ID:References:MIME-Version:Content-Type: Content-Disposition:In-Reply-To:o:X-Proofpoint-ORIG-GUID: X-Proofpoint-GUID:X-Authority-Analysis:X-Proofpoint-Spam-Info: X-Proofpoint-Spam-Details-Enc:X-Proofpoint-Virus-Version: X-Proofpoint-Spam-Details; bh=N8Sxm8XiSudcNG9BW8w5hvCi8/CmVau/gswvd5wgkPk=; b=RwVyMDwyQKdD/io3g7xaoFOWewuBnrl7hoHhcrJgfJ2x0IFKUwwvPQk70TDOGXnFlG5F DySxm9j+Yg4LHVjBHspzGlxF01OIjKJ0atqmOYc/Iia5D2CaPy1mFO5pZnUMcM068dOFc 3EcuKgmtcIFQEqsHwBLvq7EVXgQqkMjiBZYQlmeZfB2SAQ3KdUCZppsOPRFeJocXaPniA qD303JQxZAiMG/ynEDoM7kEtzuulrkHIBDUW2RgpaNXt9cRxFvwALKO+Q0I6bvn6IQ0Vn ZW6FwiNY/hxk6PSj/53j3pC2r4lxyeMKJSvb30/jJaAm7/zEJImik3RAL/cnPZKWHdw== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=oss.qualcomm.com; spf=pass smtp.mailfrom=oss.qualcomm.com; dkim=pass header.d=qualcomm.com header.i=@qualcomm.com header.a=rsa-sha256 header.s=qcppdkim1 header.b=aZRczmZN; dkim=pass header.d=oss.qualcomm.com header.i=@oss.qualcomm.com header.a=rsa-sha256 header.s=google header.b=ZTZjtkJy; arc=none smtp.remote-ip=205.220.168.131 Received: from mx0a-0031df01.pphosted.com (mx0a-0031df01.pphosted.com [205.220.168.131]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 21F9A606A321 for ; Thu, 12 Nov 2026 11:09:50 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 21F9A606A321 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=qualcomm.com header.i=@qualcomm.com header.a=rsa-sha256 header.s=qcppdkim1 header.b=aZRczmZN; dkim=pass (2048-bit key) header.d=oss.qualcomm.com header.i=@oss.qualcomm.com header.a=rsa-sha256 header.s=google header.b=ZTZjtkJy Received: from pps.filterd (m0279862.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 6ACB4cj63893148 for ; Thu, 12 Nov 2026 11:09:49 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=qualcomm.com; h= cc:content-type:date:from:in-reply-to:message-id:mime-version :references:subject; s=qcppdkim1; bh=N8Sxm8XiSudcNG9BW8w5hvCi8/C mVau/gswvd5wgkPk=; b=aZRczmZNEnYsaFzeBhuPfu4rnEXN04hXMUB5/K7TEDg I/Ww4v8ot1+yIuz0l3V0LWg3kplM2IweieQ+Ga6VIhcJpbK2enkqkKywJ0jVqXUD FmOWV6/mnzhWUM9wAG29dHJEd+QE48nTlX4ga/AiOwk/Rq5nafrQORIBGzTaaBnk /enlTcT6fCXQPuxivCspDFfp8tKlVxt/TjEtsuFkNMNv8O3iMAPDW+yaCrlFQWUq ftvzQOWzupdzxSXKCiJ69t1EcQSYbAi8pJ4yhwpvLmOwyEldRkkK/6dUd0Jvtvcg L8KFnOttc4fEshfUlaEHwRatzwPpRqcxexLL9gdstJg== Received: from mail-qk1-f198.google.com (mail-qk1-f198.google.com [209.85.222.198]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 4hw6re19j5-1 (version=TLSv1.3 cipher=TLS_AES_128_GCM_SHA256 bits=128 verify=NOT) for ; Thu, 12 Nov 2026 11:09:49 +0000 (GMT) Received: by mail-qk1-f198.google.com with SMTP id af79cd13be357-93f5844cb60so164373285a.0 for ; Thu, 12 Nov 2026 03:09:49 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oss.qualcomm.com; s=google; t=1794481788; x=1795086588; darn=vger.kernel.org; h=o:in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:from:date:from:to:cc:subject:date :message-id:reply-to:content-type; bh=N8Sxm8XiSudcNG9BW8w5hvCi8/CmVau/gswvd5wgkPk=; b=ZTZjtkJylXZu4lpuwE4nE+o+M6DP2vhg9Uxb2VlJcFNPpnkPeK77zaTMRxAMOteVr3 9Tm6NWIG91u+pSOfthuw/KqZ8/9MWcvRBEoIsIz7ig2xfGHjcz9BkSx7yGWKAW10K7LS 7+JenCZ3j7nNFN9kCVO7hKJah+mrU0cB6Vq0ozeps2OANijbDqS29QWTXp4Sq0nHfE84 i6BTH6FpwRaVOlMIZWMj6aYQPsz9yBjaOpynMV6hfNiXuBcfqznnUTzEYxd/H46P2zcC g2Ed1w90n0c83z4Qeoc/us88o3ybk9JbBWZK7aiC/XwGoASae/JtxoW7dHSnHE5QJn9Q RZbg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1794481788; x=1795086588; h=o:in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:from:date:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=N8Sxm8XiSudcNG9BW8w5hvCi8/CmVau/gswvd5wgkPk=; b=sf/aekrPzLsCky5jGsAIdAxMt8sCJdOvhudsgyHOaojrrkSUs0syXvHTZ1Eoo2NTie WevjuUrPLj4I+nvcx2zJstgIv2uLNWzBeC6nm0ePei5owlc3Anr9Uxzi2qv8KXYedeLC MEnZHAfgI8OzL6XCD6LDD02Xtefy72/ErVBNLPS/6N6VWJ6uqnoNstIVpIrNUtvp+enV Vo/wnmVYW+6YRmvRI3GA2JalmPbLd3mOQsh3jHotQD9/wvcZXFhou7442u27s5Ez4VHk qhQTh/ENEaXqG6frJLMcHdlGdVQjZEUMfmRM6FJU11C9bQl2cVrvWUwE+WLExPgZQEjT Zwiw== X-Forwarded-Encrypted: i=1; AL+hErHAp+b4uRF9EXKgZhaoVPRWg11ZnnD/BkqRLn9tanFSO/qdmrc1t1AluJLMxuR+P3AxymA=@vger.kernel.org X-Gm-Message-State: APuU4Z+Q8/JbsXWdoslWlVSTzEucz6WP2uFo2ukAUHr9PDD8vQ0NH/9h J9Y7P2jtQAEc1HsOWHA/7vDkw1kSeTRmV9/pU0rBCOFrU6z7/xhH3vOo5Xw4WGHHGAmH9q3OC3d 4aV51I+Vt5wnMDbPPWuNAzJcBk2GTfIJn/d0B7CrishefWllPOxRr/9A= X-Gm-Gg: AYBFou1AQYD2TxIO9rDLL3s9ohHRfepmEc1uv5AuTjDsxRw9hUGWYUhdXO+kCIfRJZN /Ul676EpiM1QE8W17nEyYZwaXta3vjqa46bl9odifZTl+dyByWqrhZMlsv6TYQZZNC77WCjhnyy ahiJTIC5H3Jc4Ru2b3MhSRyJtTld0BHJOflYf/tUJXa3IJZmxFWwNycwrwFwAcauPhfuwGw9OPP 8/I4edXi867OqOeiKeDJJu2ZXMBU7XpsIOl5xuTKqYPAYY7Sc1slFbn6cF2lsGpH9NfEwWgdgMk LsifG55QvxjEL2zSTGyrGxRaM7PHv/eZB9x1oA5Hwn0lQJ37ZKnkShXyM06mHhen93oxsO4XWAC Z12xLp9xg9BtvBsw1QAJ8xPu3Eb2rXK1/y+gAXp0AurDE5ZxzHy2diFgRdYZzWiQ= X-Received: by 2002:a05:620a:412:b0:93f:4498:603a with SMTP id af79cd13be357-94933140d8cmr273168085a.35.1794481788206; Thu, 12 Nov 2026 03:09:48 -0800 (PST) X-Received: by 2002:a05:620a:412:b0:93f:4498:603a with SMTP id af79cd13be357-94933140d8cmr273166685a.35.1794481787607; Thu, 12 Nov 2026 03:09:47 -0800 (PST) Received: from localhost ([93.66.104.131]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-4ba08e423dfsm120060095e9.1.2026.11.12.03.09.45 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 12 Nov 2026 03:09:46 -0800 (PST) Date: Thu, 12 Nov 2026 12:09:45 +0100 From: Lorenzo Bianconi Cc: Maxime Chevallier , Andrew Lunn , "David S. Miller" , Eric Dumazet , Paolo Abeni , Maxime Coquelin , Alexandre Torgue , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , Stanislav Fomichev , Jose Abreu , Ong Boon Leong , netdev@vger.kernel.org, linux-arm-kernel@lists.infradead.org, bpf@vger.kernel.org, Nicolai Buchwitz Subject: Re: [PATCH net-next v9] net: stmmac: rework stmmac_rx to support XDP rx multi-buff Message-ID: References: <20261106-stmmac-rx-mb-v9-1-c099c923664b@oss.qualcomm.com> <20261111181341.56706354@kernel.org> X-Mailing-List: bpf@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="b5Zoifa3Cp4gU6eN" Content-Disposition: inline In-Reply-To: <20261111181341.56706354@kernel.org> o: Jakub Kicinski X-Proofpoint-ORIG-GUID: TsSLPF8Hg3SL7qPvUCf38DcaQDY-Rlag X-Proofpoint-GUID: TsSLPF8Hg3SL7qPvUCf38DcaQDY-Rlag X-Authority-Analysis: v=2.4 cv=NJhAaE6g c=1 sm=1 tr=0 ts=6af59e7d cx=c_pps a=qKBjSQ1v91RyAK45QCPf5w==:117 a=cAAIdyqZgEis9HJxay2Blw==:17 a=9cW_t1CCXrUA:10 a=zJRp6_cAMcgA:10 a=s4-Qcg_JpJYA:10 a=VkNPw1HP01LnGYTKEx00:22 a=u7WPNUs3qKkmUXheDGA7:22 a=_K5XuSEh1TEqbUxoQ0s3:22 a=07NEhHcJ6ct1wQha1QwA:9 a=CjuIK1q_8ugA:10 a=HwC5dmO7DALaZ-7ppEoA:9 a=NFOGd7dJGGMPyQGDc5-O:22 X-Proofpoint-Spam-Info: AW1haW4tMjYxMTEyMDA0NCBTYWx0ZWRfXz/MCjloF7tGS /ffsE+BlpxBl9tP7NWbf2XJvRXUny3jVNofC8tEo2iM0BPNtttcmTn9ozzhe2uQ7Kwtrwl+uy38 MOAUUtdyOCJxw9ETLPSglVdVdL5ItVo= X-Proofpoint-Spam-Details-Enc: AW1haW4tMjYxMTEyMDA0NCBTYWx0ZWRfX+tReSVuVr0dR tWpecX/N8F5MqHDR2DLX5qqhUEG/0nkFcUgbPWzx+eux8/mN08uLCQmv3IZx5TcqOzigLLQ+R4q HPwA0k0CBt1T+5nqF2NTw/3txQ+zDXZNfrhFe3y8DwwtTWiAffdCIhlaBSdhPIlYwXlKyukjaE0 snqHBxYagekrztWWugWgu4ru6VIIj6HIDZUDKm2jpuCfvEMQErj5ZndDhOt3GwfxR0Urw12FdDj mHg89I4h3vAjJlo8nPj2l0TVHe6cUn1OLfHx6thXh1jiHQPwVex5bGO7QItJEfgpfwJdbXtPL02 Khw/m7sFSyaN2rfuxKqIXFLDlvtoEIpqE6oE5Eg2oflxTYyDJX3i2YxrJq61ScjphDQlF8Yh3vK CuFGf76xOQ/7QEBOjtWXveSBf+4Tm3kBbTiwDzxi4dQP6BYxUOVbxW1OsdPEhPhjKVec0+ovjyV qO5cOixMDLMnjGUZ9GA== X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1176,Hydra:6.1.138,FMLib:17.12.100.49 definitions=2026-11-12_01,2026-11-11_03,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 impostorscore=0 phishscore=0 spamscore=0 clxscore=1015 malwarescore=0 adultscore=0 bulkscore=0 lowpriorityscore=0 suspectscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2611040001 definitions=main-2611120044 --b5Zoifa3Cp4gU6eN Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable > On Fri, 06 Nov 2026 11:54:19 +0100 Lorenzo Bianconi wrote: > > +static struct sk_buff *stmmac_build_skb(struct xdp_buff *xdp) > > +{ > > + struct skb_shared_info *sinfo =3D xdp_get_shared_info_from_buff(xdp); > > + u32 metasize =3D xdp->data - xdp->data_meta; > > + struct sk_buff *skb; > > + u8 num_frags =3D 0; > > + > > + if (unlikely(xdp_buff_has_frags(xdp))) > > + num_frags =3D sinfo->nr_frags; > > + > > + skb =3D napi_build_skb(xdp->data_hard_start, xdp->frame_sz); > > + if (!skb) > > + return NULL; > > + > > + skb_mark_for_recycle(skb); > > + skb_reserve(skb, xdp->data - xdp->data_hard_start); > > + skb_put(skb, xdp->data_end - xdp->data); > > + if (metasize) > > + skb_metadata_set(skb, metasize); > > + > > + if (unlikely(xdp_buff_has_frags(xdp))) > > + xdp_update_skb_frags_info(skb, num_frags, sinfo->xdp_frags_size, > > + sinfo->xdp_frags_truesize, > > + xdp_buff_get_skb_flags(xdp)); > > + return skb; > > +} >=20 > This is almost identical to xdp_build_skb_from_buff(), why not use the > common code? Right, this is almost xdp_build_skb_from_buff() but we can't use directly it here since it runs eth_type_trans() and we would need to run stmmac_rx_vlan= (). I guess we can refactor xdp_build_skb_from_buff() in something like: struct sk_buff *__xdp_build_skb_from_buff(const struct xdp_buff *xdp) { // Do not run eth_type_trans() .... return skb; } static inline struct sk_buff *dp_build_skb_from_buff(const struct xdp_buff = *xdp) { __xdp_build_skb_from_buff() skb->protocol =3D eth_type_trans(); return skb; } >=20 > > +static void > > +stmmac_xdp_put_buff(struct stmmac_rx_queue *rx_q, struct xdp_buff *xdp, > > + bool allow_direct) > > +{ > > + struct skb_shared_info *sinfo =3D xdp_get_shared_info_from_buff(xdp); > > + int i; > > + > > + if (likely(!xdp_buff_has_frags(xdp))) > > + goto out; > > + > > + for (i =3D 0; i < sinfo->nr_frags; i++) > > + page_pool_put_full_page(rx_q->page_pool, > > + skb_frag_page(&sinfo->frags[i]), > > + allow_direct); > > +out: > > + page_pool_put_full_page(rx_q->page_pool, virt_to_head_page(xdp->data), > > + allow_direct); > > +} ack, we can rework xdp_return_buff() adding the capability to specify napi_direct. > > + > > +static int stmmac_xdp_shrink_tail(struct stmmac_rx_queue *rx_q, > > + struct xdp_buff *xdp, int offset) > > +{ > > + struct skb_shared_info *sinfo; > > + int i; > > + > > + if (unlikely(offset < 0 || > > + offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) > > + return -EINVAL; > > + > > + if (likely(!xdp_buff_has_frags(xdp))) { > > + xdp->data_end -=3D offset; > > + return 0; > > + } > > + > > + sinfo =3D xdp_get_shared_info_from_buff(xdp); > > + for (i =3D sinfo->nr_frags - 1; i >=3D 0 && offset > 0; i--) { > > + skb_frag_t *frag =3D &sinfo->frags[i]; > > + int delta =3D min_t(int, offset, skb_frag_size(frag)); > > + > > + if (delta =3D=3D skb_frag_size(frag)) { > > + /* The whole frag is consumed by the strip: return it > > + * to the page pool right away. Its ring slot still > > + * carries the page DMA address until stmmac_rx_refill() > > + * re-arms it at the end of the NAPI poll. This is > > + * safe because HW cannot touch the slot until then. > > + */ > > + page_pool_put_full_page(rx_q->page_pool, > > + skb_frag_page(frag), true); > > + sinfo->nr_frags--; > > + sinfo->xdp_frags_truesize -=3D xdp->frame_sz; > > + } else { > > + skb_frag_size_sub(frag, delta); > > + } > > + > > + sinfo->xdp_frags_size -=3D delta; > > + offset -=3D delta; > > + } > > + > > + if (unlikely(!sinfo->nr_frags)) { > > + xdp_buff_clear_frags_flag(xdp); > > + xdp_buff_clear_frag_pfmemalloc(xdp); > > + xdp->data_end -=3D offset; > > + } > > + > > + return 0; > > +} I guess we can exctract the logic from bpf_xdp_adjust_tail()/bpf_xdp_frags_shrink_tail() and create a helper we can reuse it in stmmac and filter.c. What do you think? Regards, Lorenzo >=20 > These two OTOH could easily become new common helpers, they seem to do > nothing stmmac specific? --b5Zoifa3Cp4gU6eN Content-Type: application/pgp-signature; name=signature.asc -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQTquNwa3Txd3rGGn7Y6cBh0uS2trAUCavWeeQAKCRA6cBh0uS2t rPFeAP0VMe/78PkVnBIxUEdWOxWNS8mn/VHlUChXe7LArItcnAD/Z3cRi1H98JVr c0eziNWwRX+hmLoGHFwU5ALqhPHhXg8= =ojdi -----END PGP SIGNATURE----- --b5Zoifa3Cp4gU6eN--