From nobody Fri Apr 10 02:43:07 2026 Received: from smtpout-03.galae.net (smtpout-03.galae.net [185.246.85.4]) (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 BAE203E3D8B for ; Wed, 4 Mar 2026 18:25:00 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=185.246.85.4 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1772648702; cv=none; b=P2RvQBNtLS4k+tBJ4gJOxaeTGiBOeozWLSIIm7F5yObBzwGGzakZF+KOxna7czy6aMOF8RvQmn4wXO2BRWmspk060heGAOwRawFUF5B/slACPZqzVDipIEIqChwny4WOAOK3fHpbp+24v98f2+29qi9hmkx3yeaTYMm5Qjb1Ebk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1772648702; c=relaxed/simple; bh=vibvuKxVooPBJkXJkyFwoq08DAa9glaCCQBQpNxwfCg=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=GJn9TRUfyJvKwwBCJIcpb72CjqyBG7StR/ZJgXAoLNL3TmbFfbIrNzJttk+YIb7R/48cVTYIi5qtOvnmMTfr+ROKdvpB08pRbd1+uHyThd1CjulaRUI07dnWeiMTlr9yaq2G9fyxpriZ0FUR1thtGqHwHBv67bxAkSGuGjGHHYg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=bootlin.com; spf=pass smtp.mailfrom=bootlin.com; dkim=pass (2048-bit key) header.d=bootlin.com header.i=@bootlin.com header.b=CH56vEt7; arc=none smtp.client-ip=185.246.85.4 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=bootlin.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bootlin.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bootlin.com header.i=@bootlin.com header.b="CH56vEt7" Received: from smtpout-01.galae.net (smtpout-01.galae.net [212.83.139.233]) by smtpout-03.galae.net (Postfix) with ESMTPS id 7DD464E42545; Wed, 4 Mar 2026 18:24:59 +0000 (UTC) Received: from mail.galae.net (mail.galae.net [212.83.136.155]) by smtpout-01.galae.net (Postfix) with ESMTPS id 533FA5FF5C; Wed, 4 Mar 2026 18:24:59 +0000 (UTC) Received: from [127.0.0.1] (localhost [127.0.0.1]) by localhost (Mailerdaemon) with ESMTPSA id A89561036960A; Wed, 4 Mar 2026 19:24:56 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bootlin.com; s=dkim; t=1772648698; h=from:subject:date:message-id:to:cc:mime-version:content-type: content-transfer-encoding:in-reply-to:references; bh=s+cOyZ8u3T068fgeZVGs8jhtYZwKXq49c7tRInBCtPo=; b=CH56vEt7PpVL01KzdTpGssEy+FyW9dM1gqNqhUzRH9mM26f4fLsMwvUhzvzEW+TKeq+nVZ kdfRjfyj2q9nf2they9fVzl8dqNOGF5jkCz+HaxKLFzIalBifmgSbLooyow3m4Fbdcz5B1 ASLPyhqAFIvybKh9OwIZ+xoeWxHAsj/I4rhRuC0JSyX9KMK4cy30QNe9goQxwtZYWH/L6H VKuSfMOBWaXHjcCtWB1y2K3Abvm1GeDIwhh0SoHQf4kFtDglXainz5fYE225PhrNAuGjcC Ju0+LISdEDrnrnKdoJTTe3LIZcWMwonM6IPVB1k/n/iOcXtWbaKm/RyJPX/mYg== From: =?utf-8?q?Th=C3=A9o_Lebrun?= Date: Wed, 04 Mar 2026 19:24:31 +0100 Subject: [PATCH net-next 8/8] net: macb: add Tx zero-copy AF_XDP support Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260304-macb-xsk-v1-8-ba2ebe2bdaa3@bootlin.com> References: <20260304-macb-xsk-v1-0-ba2ebe2bdaa3@bootlin.com> In-Reply-To: <20260304-macb-xsk-v1-0-ba2ebe2bdaa3@bootlin.com> To: Nicolas Ferre , Claudiu Beznea , Andrew Lunn , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , Stanislav Fomichev , Richard Cochran Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, Vladimir Kondratiev , Gregory CLEMENT , =?utf-8?q?Beno=C3=AEt_Monin?= , Tawfik Bayouk , Thomas Petazzoni , Maxime Chevallier , =?utf-8?q?Th=C3=A9o_Lebrun?= X-Mailer: b4 0.14.3 X-Last-TLS-Session-Version: TLSv1.3 Add a new buffer type (to `enum macb_tx_buff_type`). Near the end of macb_tx_complete(), we go and read the XSK buffers using xsk_tx_peek_release_desc_batch() and append those buffers to our Tx ring. Additionally, in macb_tx_complete(), we signal to the XSK subsystem number of bytes completed and conditionally mark the need_wakeup flag. Lastly, we update XSK wakeup by writing the TCOMP bit in the per-queue IMR register, to ensure NAPI scheduling will take place. Signed-off-by: Th=C3=A9o Lebrun --- drivers/net/ethernet/cadence/macb.h | 1 + drivers/net/ethernet/cadence/macb_main.c | 91 ++++++++++++++++++++++++++++= +--- 2 files changed, 86 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cad= ence/macb.h index a9e6f0289ecb..5700a285c08a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -963,6 +963,7 @@ enum macb_tx_buff_type { MACB_TYPE_SKB, MACB_TYPE_XDP_TX, MACB_TYPE_XDP_NDO, + MACB_TYPE_XSK, }; =20 /* struct macb_tx_buff - data about an skb or xdp frame which is being diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/etherne= t/cadence/macb_main.c index ea1b0b8c4fab..fee1ebadcf20 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -986,21 +986,30 @@ static int macb_halt_tx(struct macb *bp) =20 static void macb_tx_release_buff(void *buff, enum macb_tx_buff_type type, = int budget) { - if (type =3D=3D MACB_TYPE_SKB) { + switch (type) { + case MACB_TYPE_SKB: napi_consume_skb(buff, budget); - } else if (type =3D=3D MACB_TYPE_XDP_TX) { - if (!budget) - xdp_return_frame(buff); - else + break; + case MACB_TYPE_XDP_TX: + if (budget) xdp_return_frame_rx_napi(buff); - } else { + else + xdp_return_frame(buff); + break; + case MACB_TYPE_XDP_NDO: xdp_return_frame(buff); + break; + case MACB_TYPE_XSK: + break; } } =20 static void macb_tx_unmap(struct macb *bp, struct macb_tx_buff *tx_buff, int budget) { + if (tx_buff->type =3D=3D MACB_TYPE_XSK) + return; + if (tx_buff->mapping) { if (tx_buff->mapped_as_page) dma_unmap_page(&bp->pdev->dev, tx_buff->mapping, @@ -1255,6 +1264,57 @@ static void macb_xdp_submit_buff(struct macb *bp, un= signed int queue_index, netif_stop_subqueue(netdev, queue_index); } =20 +static void macb_xdp_xmit_zc(struct macb *bp, unsigned int queue_index, in= t budget) +{ + struct macb_queue *queue =3D &bp->queues[queue_index]; + struct xsk_buff_pool *xsk =3D queue->xsk_pool; + dma_addr_t mapping; + u32 slot_available; + size_t bytes =3D 0; + u32 batch; + + guard(spinlock_irqsave)(&queue->tx_ptr_lock); + + /* This is a hard error, log it. */ + slot_available =3D CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring= _size); + if (slot_available < 1) { + netif_stop_subqueue(bp->dev, queue_index); + netdev_dbg(bp->dev, "tx_head =3D %u, tx_tail =3D %u\n", + queue->tx_head, queue->tx_tail); + return; + } + + batch =3D min_t(u32, slot_available, budget); + batch =3D xsk_tx_peek_release_desc_batch(xsk, batch); + if (!batch) + return; + + for (u32 i =3D 0; i < batch; i++) { + struct xdp_desc *desc =3D &xsk->tx_descs[i]; + + mapping =3D xsk_buff_raw_get_dma(xsk, desc->addr); + xsk_buff_raw_dma_sync_for_device(xsk, mapping, desc->len); + + macb_xdp_submit_buff(bp, queue_index, (struct macb_tx_buff){ + .ptr =3D NULL, + .mapping =3D mapping, + .size =3D desc->len, + .mapped_as_page =3D false, + .type =3D MACB_TYPE_XSK, + }); + + bytes +=3D desc->len; + } + + /* Make newly initialized descriptor visible to hardware */ + wmb(); + spin_lock(&bp->lock); + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); + spin_unlock(&bp->lock); + + netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index), bytes); +} + static int macb_tx_complete(struct macb_queue *queue, int budget) { struct macb *bp =3D queue->bp; @@ -1316,6 +1376,11 @@ static int macb_tx_complete(struct macb_queue *queue= , int budget) case MACB_TYPE_XDP_NDO: bytes +=3D tx_buff->size; break; + + case MACB_TYPE_XSK: + bytes +=3D tx_buff->size; + xsk_frames++; + break; } =20 packets++; @@ -1337,6 +1402,16 @@ static int macb_tx_complete(struct macb_queue *queue= , int budget) netif_wake_subqueue(bp->dev, queue_index); spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); =20 + if (queue->xsk_pool) { + if (xsk_frames) + xsk_tx_completed(queue->xsk_pool, xsk_frames); + + if (xsk_uses_need_wakeup(queue->xsk_pool)) + xsk_set_tx_need_wakeup(queue->xsk_pool); + + macb_xdp_xmit_zc(bp, queue_index, budget); + } + return packets; } =20 @@ -1616,6 +1691,10 @@ static int gem_xsk_wakeup(struct net_device *dev, u3= 2 qid, u32 flags) !napi_if_scheduled_mark_missed(&queue->napi_rx)) irqs |=3D MACB_BIT(RCOMP); =20 + if ((flags & XDP_WAKEUP_TX) && + !napi_if_scheduled_mark_missed(&queue->napi_tx)) + irqs |=3D MACB_BIT(TCOMP); + if (irqs) queue_writel(queue, IMR, irqs); =20 --=20 2.53.0