From nobody Sun Apr 5 18:51:36 2026 Received: from mail-wr1-f53.google.com (mail-wr1-f53.google.com [209.85.221.53]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2EFCE3BED7F for ; Mon, 23 Mar 2026 18:28:43 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.221.53 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774290531; cv=none; b=pq56RtnEsaLD6V29QmqIhEG+m5uWTNX+/bbuDygBrROZ0sKwA8ArKbCzdunJMOlt7xTYYcEeOctZE0CwEobzsr/yPAQnlleUpwMmaFfILTIyAQNj6e3kl1gsdd6uI+yU1MCC2Qv3SQuapLa18smV5ooJmNPbLI4e/NAo8+HzbqA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774290531; c=relaxed/simple; bh=UTDFJf60h4k8PPwTFhEb7MQg4ytg1AGu01E3sA5SLp8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=cci9VcfIqActMiQaxACKlZ7eOOX6fljntiAT+8QjurJYMNu+b9SWjPjpPsoWxMdsKa1hNQIK+WNif+oVUXXckIIQQmRF3EK+AaZdVwKIeRSpsEb3btz5PaOieAsRUTZsW8lgsbFKIr4rupbG5jmaNVH1lYkmXgnozaQWzeBGnAA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=SKFBG4ga; arc=none smtp.client-ip=209.85.221.53 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="SKFBG4ga" Received: by mail-wr1-f53.google.com with SMTP id ffacd0b85a97d-43b40fb7f95so454496f8f.3 for ; Mon, 23 Mar 2026 11:28:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1774290522; x=1774895322; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=KPBuryN6n7btOiyeSAgPIZIWAfoaH/+/MuqQMs6eiTw=; b=SKFBG4gag2wG+zrG5XOUok4d7BrEcqAqTeloSnwhPKFOK82Le2TyhzFXvQz1q0rU7s jidY3YYPxIkVrdVQ2U2J3OE+PAZNoROdYfQpph7dET1h5lE8wlPi7OvM7tV7rA4jzx+v jJ0NB7zU+SflIFv+xDm9WyjMD2+IchU66T4AaN1Mcp7Hov8/2T4AnvvABlq5KEG//e4G yBMdc6iw+bZC6fbOuoyZ7C2NC+1ETyAYpCzsQUmLo+9WB2TsfqhpxDL5Rn1jPvy4gZzj hDFo4GXoLbLWT3ToWQELNxX6fff6syXHad44s6hPO5lTSDw6fMOOnMW8b49VRYHwW7gJ 4Jgw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1774290522; x=1774895322; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=KPBuryN6n7btOiyeSAgPIZIWAfoaH/+/MuqQMs6eiTw=; b=YbpsQ/xe4z7RGVCbeoqPMOwmrjH6M1YRLU5J9ItI0x+5NJBFAaoynyjJN31CQ2+KRW 89BwYTOXvSBLojfT9DJIut0whouSTykvT9Y4BQQZaIDO1S7fJ7CVp1y1u7qsgsxW2C14 o69ujIad9Jah8/y0IHSrO3YMnx0Ok+c/d9RGAipCA8FhEcEXQtXHYJbGtnQHE6MInEPn 9shFIKCFkoMty05SHouA28PhaCNHR0h+NeDFMMKRoHY9ZJhDq3kMMWRrSNPGOsUt9W9v RQsrZhL7pcWe5Y6mSxOpvEsCIgTsxai2yTxS9NLgn1v7bVXqnjez2Y+PyfhOghbH/Tpx gthA== X-Forwarded-Encrypted: i=1; AJvYcCWzrXnI9oGRGxHAAS+HKLdsIzWQuNSV6KIuNCHSxjSDPfoYvTdCeATteZGtQyJEX3PbKW+4y17xl4i6x3U=@vger.kernel.org X-Gm-Message-State: AOJu0YzxKUrMcFoPBfJuPUcEEhDW8Wl8WMzVYZsQI4SNsjaEYRMyzp7n EvIftyLDvUptHzM3z37NjdQtehfy7U2uvRsrDwCeBPog2aaiiz2cTiz7 X-Gm-Gg: ATEYQzxRDrTK/3jrWLQYfbp1u66rYyStOX8qMyo5KnRCmU139JQLgX5G2oBNbubf+yg F4jEV8vtmwcrFAtnq6FWRoW5l6ke/SLh8l7LmZFLE4l+2LYX9IQ4iUCigxdhrF/052ms2N+t3iI GaYZQRZX7t06VB24XZI+YSucgKuH74OPB5w5Wp5+QQCsAG03uOFabmoXeL6UJ/CzXMy5F6WVGGr 6JSfxXYw7v6/+OVuTXRzSFyfw9RmJbe2fUsXl6E0NUYwfWxkDi9dhQjKipxZ6eyL6icZeEGymOG Jul9w2frIRknYWaxoWnMwCXDyYRe2fPDpqOoJvGlrem0JzRFMNS0097nsE90lsJwB+VXCI24OPu 0xYZcsH6YDAM6am6nLR8ODSkLdXgUSeoCbEvVg4LnI3oycamjpt9/sUUf34zzLAx2ytg7UtCZgP U9I9RlI/Wu2kIBd1JYJcjNXiXRd2buiGRmRB0TaE8PenJcEN84LXaEC/dK34s+5cktKNmG3V0z+ hg= X-Received: by 2002:a5d:5f53:0:b0:439:be82:1fd9 with SMTP id ffacd0b85a97d-43b6423b821mr19745350f8f.12.1774290522071; Mon, 23 Mar 2026 11:28:42 -0700 (PDT) Received: from turbo.teknoraver.net (net-37-119-137-97.cust.vodafonedsl.it. [37.119.137.97]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-43b64714decsm28448751f8f.31.2026.03.23.11.28.40 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 23 Mar 2026 11:28:41 -0700 (PDT) From: Matteo Croce X-Google-Original-From: Matteo Croce To: Tony Nguyen , Przemek Kitszel , Andrew Lunn , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , Mohsin Bashir Cc: netdev@vger.kernel.org, bpf@vger.kernel.org, intel-wired-lan@lists.osuosl.org, linux-kernel@vger.kernel.org Subject: [PATCH net-next v4 1/2] e1000e: add basic XDP support Date: Mon, 23 Mar 2026 19:28:22 +0100 Message-ID: <20260323182823.5813-2-teknoraver@meta.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260323182823.5813-1-teknoraver@meta.com> References: <20260323182823.5813-1-teknoraver@meta.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Add XDP support to the e1000e driver covering the actions defined by NETDEV_XDP_ACT_BASIC: XDP_DROP, XDP_PASS, XDP_TX and XDP_ABORTED. Infrastructure: - e1000_xdp_setup() / e1000_xdp() for program attach/detach with MTU validation and close/open cycle - ndo_bpf support in net_device_ops - xdp_rxq_info registration in setup/free_rx_resources Receive path: - e1000_alloc_rx_buffers_xdp() for page-based Rx buffer allocation with XDP_PACKET_HEADROOM - e1000_clean_rx_irq_xdp() as the XDP receive handler - e1000_run_xdp() to execute the XDP program on received packets - SKB building via napi_build_skb() for XDP_PASS with metadata, checksum offload and RSS hash support Transmit path: - e1000_xdp_xmit_ring() to DMA-map and enqueue an XDP frame - e1000_xdp_xmit_back() to convert an xdp_buff to a frame and send it - e1000_finalize_xdp() to flush the TX ring after XDP processing - TX completion via xdp_return_frame() with buffer type tracking Assisted-by: claude-opus-4-6 Signed-off-by: Matteo Croce --- drivers/net/ethernet/intel/Kconfig | 1 + drivers/net/ethernet/intel/e1000e/e1000.h | 18 +- drivers/net/ethernet/intel/e1000e/netdev.c | 533 ++++++++++++++++++++- 3 files changed, 540 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/inte= l/Kconfig index 288fa8ce53af..46e37cb68e70 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -63,6 +63,7 @@ config E1000E depends on PCI && (!SPARC32 || BROKEN) depends on PTP_1588_CLOCK_OPTIONAL select CRC32 + select PAGE_POOL help This driver supports the PCI-Express Intel(R) PRO/1000 gigabit ethernet family of adapters. For PCI or PCI-X e1000 adapters, diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethern= et/intel/e1000e/e1000.h index 63ebe00376f5..4c1175d4e5cb 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -19,10 +19,13 @@ #include #include #include +#include #include #include #include #include +#include +#include #include "hw.h" =20 struct e1000_info; @@ -126,12 +129,21 @@ struct e1000_ps_page { u64 dma; /* must be u64 - written to hw */ }; =20 +enum e1000_tx_buf_type { + E1000_TX_BUF_SKB =3D 0, + E1000_TX_BUF_XDP, +}; + /* wrappers around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct e1000_buffer { dma_addr_t dma; - struct sk_buff *skb; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; + enum e1000_tx_buf_type type; union { /* Tx */ struct { @@ -259,6 +271,10 @@ struct e1000_adapter { gfp_t gfp); struct e1000_ring *rx_ring; =20 + struct bpf_prog *xdp_prog; + struct xdp_rxq_info xdp_rxq; + struct page_pool *page_pool; + u32 rx_int_delay; u32 rx_abs_int_delay; =20 diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ether= net/intel/e1000e/netdev.c index 9befdacd6730..d77f208f00cc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -25,6 +25,10 @@ #include #include #include +#include +#include +#include +#include =20 #include "e1000.h" #define CREATE_TRACE_POINTS @@ -33,6 +37,11 @@ char e1000e_driver_name[] =3D "e1000e"; =20 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) + +#define E1000_XDP_PASS 0 +#define E1000_XDP_CONSUMED BIT(0) +#define E1000_XDP_TX BIT(1) + static int debug =3D -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=3Dnone,...,16=3Dall)"); @@ -708,6 +717,370 @@ static void e1000_alloc_rx_buffers(struct e1000_ring = *rx_ring, rx_ring->next_to_use =3D i; } =20 +static inline void e1000_rx_hash(struct net_device *netdev, __le32 rss, + struct sk_buff *skb) +{ + if (netdev->features & NETIF_F_RXHASH) + skb_set_hash(skb, le32_to_cpu(rss), PKT_HASH_TYPE_L3); +} + +/** + * e1000_xdp_xmit_ring - transmit an XDP frame on the TX ring + * @adapter: board private structure + * @tx_ring: Tx descriptor ring + * @xdpf: XDP frame to transmit + * + * Returns E1000_XDP_TX on success, E1000_XDP_CONSUMED on failure + **/ +static int e1000_xdp_xmit_ring(struct e1000_adapter *adapter, + struct e1000_ring *tx_ring, + struct xdp_frame *xdpf) +{ + struct e1000_buffer *buffer_info; + struct e1000_tx_desc *tx_desc; + dma_addr_t dma; + u16 i; + + if (e1000_desc_unused(tx_ring) < 1) + return E1000_XDP_CONSUMED; + + i =3D tx_ring->next_to_use; + buffer_info =3D &tx_ring->buffer_info[i]; + + dma =3D dma_map_single(&adapter->pdev->dev, xdpf->data, xdpf->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, dma)) + return E1000_XDP_CONSUMED; + + buffer_info->xdpf =3D xdpf; + buffer_info->type =3D E1000_TX_BUF_XDP; + buffer_info->dma =3D dma; + buffer_info->length =3D xdpf->len; + buffer_info->time_stamp =3D jiffies; + buffer_info->next_to_watch =3D i; + buffer_info->segs =3D 1; + buffer_info->bytecount =3D xdpf->len; + buffer_info->mapped_as_page =3D 0; + + tx_desc =3D E1000_TX_DESC(*tx_ring, i); + tx_desc->buffer_addr =3D cpu_to_le64(dma); + tx_desc->lower.data =3D cpu_to_le32(adapter->txd_cmd | + E1000_TXD_CMD_IFCS | + xdpf->len); + tx_desc->upper.data =3D 0; + + i++; + if (i =3D=3D tx_ring->count) + i =3D 0; + tx_ring->next_to_use =3D i; + + return E1000_XDP_TX; +} + +/** + * e1000_xdp_xmit_back - transmit an XDP buffer back on the same device + * @adapter: board private structure + * @xdp: XDP buffer to transmit + * + * Returns E1000_XDP_TX on success, E1000_XDP_CONSUMED on failure + **/ +static int e1000_xdp_xmit_back(struct e1000_adapter *adapter, + struct xdp_buff *xdp) +{ + struct xdp_frame *xdpf =3D xdp_convert_buff_to_frame(xdp); + + if (unlikely(!xdpf)) + return E1000_XDP_CONSUMED; + + return e1000_xdp_xmit_ring(adapter, adapter->tx_ring, xdpf); +} + +/** + * e1000_finalize_xdp - flush XDP operations after NAPI Rx loop + * @adapter: board private structure + * @xdp_xmit: bitmask of XDP actions taken during Rx processing + **/ +static void e1000_finalize_xdp(struct e1000_adapter *adapter, + unsigned int xdp_xmit) +{ + struct e1000_ring *tx_ring =3D adapter->tx_ring; + + if (xdp_xmit & E1000_XDP_TX) { + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_tdt_wa(tx_ring, + tx_ring->next_to_use); + else + writel(tx_ring->next_to_use, tx_ring->tail); + } +} + +/** + * e1000_run_xdp - run an XDP program on a received packet + * @adapter: board private structure + * @xdp: XDP buffer containing packet data + * + * Returns E1000_XDP_PASS, E1000_XDP_TX, or E1000_XDP_CONSUMED + **/ +static int e1000_run_xdp(struct e1000_adapter *adapter, struct xdp_buff *x= dp) +{ + struct bpf_prog *xdp_prog =3D READ_ONCE(adapter->xdp_prog); + struct net_device *netdev =3D adapter->netdev; + int result =3D E1000_XDP_PASS; + u32 act; + + if (!xdp_prog) + return E1000_XDP_PASS; + + prefetchw(xdp->data_hard_start); + + act =3D bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result =3D e1000_xdp_xmit_back(adapter, xdp); + if (result =3D=3D E1000_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result =3D E1000_XDP_CONSUMED; + break; + } + + return result; +} + +/** + * e1000_alloc_rx_buffers_xdp - Replace used receive buffers for XDP + * @rx_ring: Rx descriptor ring + * @cleaned_count: number to reallocate + * @gfp: flags for allocation + * + * Allocates page-based Rx buffers with XDP_PACKET_HEADROOM headroom. + **/ +static void e1000_alloc_rx_buffers_xdp(struct e1000_ring *rx_ring, + int cleaned_count, gfp_t gfp) +{ + struct e1000_adapter *adapter =3D rx_ring->adapter; + union e1000_rx_desc_extended *rx_desc; + struct e1000_buffer *buffer_info; + unsigned int i; + + i =3D rx_ring->next_to_use; + buffer_info =3D &rx_ring->buffer_info[i]; + + while (cleaned_count--) { + if (!buffer_info->page) { + buffer_info->page =3D page_pool_alloc_pages(adapter->page_pool, + gfp); + if (!buffer_info->page) { + adapter->alloc_rx_buff_failed++; + break; + } + } + + if (!buffer_info->dma) { + buffer_info->dma =3D page_pool_get_dma_addr(buffer_info->page) + + XDP_PACKET_HEADROOM; + } + + rx_desc =3D E1000_RX_DESC_EXT(*rx_ring, i); + rx_desc->read.buffer_addr =3D cpu_to_le64(buffer_info->dma); + + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* Force memory writes to complete before letting + * h/w know there are new descriptors to fetch. + */ + wmb(); + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_rdt_wa(rx_ring, i); + else + writel(i, rx_ring->tail); + } + i++; + if (i =3D=3D rx_ring->count) + i =3D 0; + buffer_info =3D &rx_ring->buffer_info[i]; + } + + rx_ring->next_to_use =3D i; +} + +/** + * e1000_clean_rx_irq_xdp - Receive with XDP processing + * @rx_ring: Rx descriptor ring + * @work_done: output parameter for indicating completed work + * @work_to_do: how many packets we can clean + * + * Page-based receive path that runs an XDP program on each packet. + **/ +static bool e1000_clean_rx_irq_xdp(struct e1000_ring *rx_ring, int *work_d= one, + int work_to_do) +{ + struct e1000_adapter *adapter =3D rx_ring->adapter; + struct net_device *netdev =3D adapter->netdev; + struct pci_dev *pdev =3D adapter->pdev; + union e1000_rx_desc_extended *rx_desc, *next_rxd; + struct e1000_buffer *buffer_info, *next_buffer; + struct xdp_buff xdp; + u32 length, staterr; + unsigned int i, crc_len; + int cleaned_count =3D 0; + bool cleaned =3D false; + unsigned int total_rx_bytes =3D 0, total_rx_packets =3D 0; + unsigned int xdp_xmit =3D 0; + + xdp_init_buff(&xdp, PAGE_SIZE, &adapter->xdp_rxq); + + i =3D rx_ring->next_to_clean; + rx_desc =3D E1000_RX_DESC_EXT(*rx_ring, i); + staterr =3D le32_to_cpu(rx_desc->wb.upper.status_error); + buffer_info =3D &rx_ring->buffer_info[i]; + + while (staterr & E1000_RXD_STAT_DD) { + struct sk_buff *skb; + int xdp_res; + + crc_len =3D 0; + if (*work_done >=3D work_to_do) + break; + (*work_done)++; + dma_rmb(); + + i++; + if (i =3D=3D rx_ring->count) + i =3D 0; + next_rxd =3D E1000_RX_DESC_EXT(*rx_ring, i); + prefetch(next_rxd); + + next_buffer =3D &rx_ring->buffer_info[i]; + + cleaned =3D true; + cleaned_count++; + + dma_sync_single_for_cpu(&pdev->dev, buffer_info->dma, + adapter->rx_buffer_len, + DMA_FROM_DEVICE); + buffer_info->dma =3D 0; + + length =3D le16_to_cpu(rx_desc->wb.upper.length); + + /* Multi-descriptor packets not supported with XDP */ + if (unlikely(!(staterr & E1000_RXD_STAT_EOP))) + adapter->flags2 |=3D FLAG2_IS_DISCARDING; + + if (adapter->flags2 & FLAG2_IS_DISCARDING) { + if (staterr & E1000_RXD_STAT_EOP) + adapter->flags2 &=3D ~FLAG2_IS_DISCARDING; + page_pool_put_full_page(adapter->page_pool, + buffer_info->page, true); + buffer_info->page =3D NULL; + goto next_desc; + } + + if (unlikely((staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) && + !(netdev->features & NETIF_F_RXALL))) { + page_pool_put_full_page(adapter->page_pool, + buffer_info->page, true); + buffer_info->page =3D NULL; + goto next_desc; + } + + /* adjust length to remove Ethernet CRC */ + if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) { + if (netdev->features & NETIF_F_RXFCS) + crc_len =3D 4; + else + length -=3D 4; + } + + /* Setup xdp_buff pointing at the page data */ + xdp_prepare_buff(&xdp, page_address(buffer_info->page), + XDP_PACKET_HEADROOM, length, true); + xdp_buff_clear_frags_flag(&xdp); + + xdp_res =3D e1000_run_xdp(adapter, &xdp); + + if (xdp_res =3D=3D E1000_XDP_PASS) { + total_rx_bytes +=3D length - crc_len; + total_rx_packets++; + + skb =3D napi_build_skb(xdp.data_hard_start, PAGE_SIZE); + if (unlikely(!skb)) { + page_pool_put_full_page(adapter->page_pool, + buffer_info->page, + true); + buffer_info->page =3D NULL; + goto next_desc; + } + + skb_mark_for_recycle(skb); + skb_reserve(skb, + xdp.data - xdp.data_hard_start); + skb_put(skb, xdp.data_end - xdp.data); + + if (xdp.data_meta !=3D xdp.data) + skb_metadata_set(skb, xdp.data - xdp.data_meta); + + e1000_rx_checksum(adapter, staterr, skb); + e1000_rx_hash(netdev, + rx_desc->wb.lower.hi_dword.rss, skb); + e1000_receive_skb(adapter, netdev, skb, staterr, + rx_desc->wb.upper.vlan); + + /* page consumed by skb */ + buffer_info->page =3D NULL; + } else if (xdp_res & E1000_XDP_TX) { + xdp_xmit |=3D xdp_res; + total_rx_bytes +=3D length - crc_len; + total_rx_packets++; + /* page consumed by XDP TX */ + buffer_info->page =3D NULL; + } else { + /* XDP_DROP / XDP_ABORTED - recycle page */ + page_pool_put_full_page(adapter->page_pool, + buffer_info->page, true); + buffer_info->page =3D NULL; + } + +next_desc: + rx_desc->wb.upper.status_error &=3D cpu_to_le32(~0xFF); + + if (cleaned_count >=3D E1000_RX_BUFFER_WRITE) { + adapter->alloc_rx_buf(rx_ring, cleaned_count, + GFP_ATOMIC); + cleaned_count =3D 0; + } + + rx_desc =3D next_rxd; + buffer_info =3D next_buffer; + staterr =3D le32_to_cpu(rx_desc->wb.upper.status_error); + } + rx_ring->next_to_clean =3D i; + + if (xdp_xmit) + e1000_finalize_xdp(adapter, xdp_xmit); + + cleaned_count =3D e1000_desc_unused(rx_ring); + if (cleaned_count) + adapter->alloc_rx_buf(rx_ring, cleaned_count, GFP_ATOMIC); + + adapter->total_rx_bytes +=3D total_rx_bytes; + adapter->total_rx_packets +=3D total_rx_packets; + return cleaned; +} + /** * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split * @rx_ring: Rx descriptor ring @@ -896,13 +1269,6 @@ static void e1000_alloc_jumbo_rx_buffers(struct e1000= _ring *rx_ring, } } =20 -static inline void e1000_rx_hash(struct net_device *netdev, __le32 rss, - struct sk_buff *skb) -{ - if (netdev->features & NETIF_F_RXHASH) - skb_set_hash(skb, le32_to_cpu(rss), PKT_HASH_TYPE_L3); -} - /** * e1000_clean_rx_irq - Send received data up the network stack * @rx_ring: Rx descriptor ring @@ -1075,13 +1441,17 @@ static void e1000_put_txbuf(struct e1000_ring *tx_r= ing, buffer_info->length, DMA_TO_DEVICE); buffer_info->dma =3D 0; } - if (buffer_info->skb) { + if (buffer_info->type =3D=3D E1000_TX_BUF_XDP) { + xdp_return_frame(buffer_info->xdpf); + buffer_info->xdpf =3D NULL; + } else if (buffer_info->skb) { if (drop) dev_kfree_skb_any(buffer_info->skb); else dev_consume_skb_any(buffer_info->skb); buffer_info->skb =3D NULL; } + buffer_info->type =3D E1000_TX_BUF_SKB; buffer_info->time_stamp =3D 0; } =20 @@ -1242,7 +1612,8 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_= ring) if (cleaned) { total_tx_packets +=3D buffer_info->segs; total_tx_bytes +=3D buffer_info->bytecount; - if (buffer_info->skb) { + if (buffer_info->type =3D=3D E1000_TX_BUF_SKB && + buffer_info->skb) { bytes_compl +=3D buffer_info->skb->len; pkts_compl++; } @@ -1696,7 +2067,12 @@ static void e1000_clean_rx_ring(struct e1000_ring *r= x_ring) } =20 if (buffer_info->page) { - put_page(buffer_info->page); + if (adapter->page_pool) + page_pool_put_full_page(adapter->page_pool, + buffer_info->page, + false); + else + put_page(buffer_info->page); buffer_info->page =3D NULL; } =20 @@ -2350,6 +2726,30 @@ int e1000e_setup_tx_resources(struct e1000_ring *tx_= ring) return err; } =20 +static int e1000_create_page_pool(struct e1000_adapter *adapter) +{ + struct page_pool_params pp_params =3D { + .flags =3D PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size =3D adapter->rx_ring->count, + .nid =3D NUMA_NO_NODE, + .dev =3D &adapter->pdev->dev, + .napi =3D &adapter->napi, + .dma_dir =3D DMA_FROM_DEVICE, + .offset =3D XDP_PACKET_HEADROOM, + .max_len =3D adapter->rx_buffer_len, + }; + + adapter->page_pool =3D page_pool_create(&pp_params); + if (IS_ERR(adapter->page_pool)) { + int err =3D PTR_ERR(adapter->page_pool); + + adapter->page_pool =3D NULL; + return err; + } + + return 0; +} + /** * e1000e_setup_rx_resources - allocate Rx resources (Descriptors) * @rx_ring: Rx descriptor ring @@ -2389,8 +2789,31 @@ int e1000e_setup_rx_resources(struct e1000_ring *rx_= ring) rx_ring->next_to_use =3D 0; rx_ring->rx_skb_top =3D NULL; =20 + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&adapter->xdp_rxq)) + xdp_rxq_info_unreg(&adapter->xdp_rxq); + + err =3D e1000_create_page_pool(adapter); + if (err) + goto err_pages; + + err =3D xdp_rxq_info_reg(&adapter->xdp_rxq, adapter->netdev, 0, + adapter->napi.napi_id); + if (err) + goto err_page_pool; + err =3D xdp_rxq_info_reg_mem_model(&adapter->xdp_rxq, + MEM_TYPE_PAGE_POOL, + adapter->page_pool); + if (err) { + xdp_rxq_info_unreg(&adapter->xdp_rxq); + goto err_page_pool; + } + return 0; =20 +err_page_pool: + page_pool_destroy(adapter->page_pool); + adapter->page_pool =3D NULL; err_pages: for (i =3D 0; i < rx_ring->count; i++) { buffer_info =3D &rx_ring->buffer_info[i]; @@ -2463,6 +2886,14 @@ void e1000e_free_rx_resources(struct e1000_ring *rx_= ring) =20 e1000_clean_rx_ring(rx_ring); =20 + if (xdp_rxq_info_is_reg(&adapter->xdp_rxq)) + xdp_rxq_info_unreg(&adapter->xdp_rxq); + + if (adapter->page_pool) { + page_pool_destroy(adapter->page_pool); + adapter->page_pool =3D NULL; + } + for (i =3D 0; i < rx_ring->count; i++) kfree(rx_ring->buffer_info[i].ps_pages); =20 @@ -3185,7 +3616,11 @@ static void e1000_configure_rx(struct e1000_adapter = *adapter) u64 rdba; u32 rdlen, rctl, rxcsum, ctrl_ext; =20 - if (adapter->rx_ps_pages) { + if (adapter->xdp_prog) { + rdlen =3D rx_ring->count * sizeof(union e1000_rx_desc_extended); + adapter->clean_rx =3D e1000_clean_rx_irq_xdp; + adapter->alloc_rx_buf =3D e1000_alloc_rx_buffers_xdp; + } else if (adapter->rx_ps_pages) { /* this is a 32 byte descriptor */ rdlen =3D rx_ring->count * sizeof(union e1000_rx_desc_packet_split); @@ -6049,6 +6484,12 @@ static int e1000_change_mtu(struct net_device *netde= v, int new_mtu) return -EINVAL; } =20 + /* XDP requires standard MTU */ + if (adapter->xdp_prog && new_mtu > ETH_DATA_LEN) { + e_err("Jumbo Frames not supported while XDP program is active.\n"); + return -EINVAL; + } + /* Jumbo frame workaround on 82579 and newer requires CRC be stripped */ if ((adapter->hw.mac.type >=3D e1000_pch2lan) && !(adapter->flags2 & FLAG2_CRC_STRIPPING) && @@ -7331,6 +7772,71 @@ static int e1000_set_features(struct net_device *net= dev, return 1; } =20 +/** + * e1000_xdp_setup - add/remove an XDP program + * @netdev: network interface device structure + * @bpf: XDP program setup structure + **/ +static int e1000_xdp_setup(struct net_device *netdev, struct netdev_bpf *b= pf) +{ + struct e1000_adapter *adapter =3D netdev_priv(netdev); + struct bpf_prog *prog =3D bpf->prog, *old_prog; + bool running =3D netif_running(netdev); + bool need_reset; + + /* XDP is incompatible with jumbo frames */ + if (prog && netdev->mtu > ETH_DATA_LEN) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "XDP is not supported with jumbo frames"); + return -EINVAL; + } + + /* Validate frame fits in a single page with XDP headroom */ + if (prog && netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN + + XDP_PACKET_HEADROOM > PAGE_SIZE) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "Frame size too large for XDP"); + return -EINVAL; + } + + old_prog =3D xchg(&adapter->xdp_prog, prog); + need_reset =3D (!!prog !=3D !!old_prog); + + /* Transition between XDP and non-XDP requires ring reconfiguration */ + if (need_reset && running) + e1000e_close(netdev); + + if (old_prog) + bpf_prog_put(old_prog); + + if (!need_reset) + return 0; + + if (running) { + int err =3D e1000e_open(netdev); + + if (err) { + /* Remove the XDP program since interface is down */ + xchg(&adapter->xdp_prog, NULL); + if (prog) + bpf_prog_put(prog); + return err; + } + } + + return 0; +} + +static int e1000_xdp(struct net_device *netdev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return e1000_xdp_setup(netdev, xdp); + default: + return -EINVAL; + } +} + static const struct net_device_ops e1000e_netdev_ops =3D { .ndo_open =3D e1000e_open, .ndo_stop =3D e1000e_close, @@ -7353,6 +7859,7 @@ static const struct net_device_ops e1000e_netdev_ops = =3D { .ndo_features_check =3D passthru_features_check, .ndo_hwtstamp_get =3D e1000e_hwtstamp_get, .ndo_hwtstamp_set =3D e1000e_hwtstamp_set, + .ndo_bpf =3D e1000_xdp, }; =20 /** @@ -7563,6 +8070,8 @@ static int e1000_probe(struct pci_dev *pdev, const st= ruct pci_device_id *ent) netdev->max_mtu =3D adapter->max_hw_frame_size - (VLAN_ETH_HLEN + ETH_FCS_LEN); =20 + netdev->xdp_features =3D NETDEV_XDP_ACT_BASIC; + if (e1000e_enable_mng_pass_thru(&adapter->hw)) adapter->flags |=3D FLAG_MNG_PT_ENABLED; =20 @@ -7776,6 +8285,8 @@ static void e1000_remove(struct pci_dev *pdev) e1000e_release_hw_control(adapter); =20 e1000e_reset_interrupt_capability(adapter); + if (adapter->xdp_prog) + bpf_prog_put(adapter->xdp_prog); kfree(adapter->tx_ring); kfree(adapter->rx_ring); =20 --=20 2.53.0