diff options
Diffstat (limited to 'drivers/net/ethernet/freescale/dpaa/dpaa_eth.c')
-rw-r--r-- | drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 684 |
1 files changed, 575 insertions, 109 deletions
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ca74a684a904..fc68a32ce2f7 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1,32 +1,7 @@ -/* Copyright 2008 - 2016 Freescale Semiconductor Inc. +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later +/* + * Copyright 2008 - 2016 Freescale Semiconductor Inc. * Copyright 2020 NXP - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -53,6 +28,8 @@ #include <linux/dma-mapping.h> #include <linux/sort.h> #include <linux/phy_fixed.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> #include <soc/fsl/bman.h> #include <soc/fsl/qman.h> #include "fman.h" @@ -87,7 +64,7 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \ NETIF_MSG_LINK | NETIF_MSG_IFUP | \ - NETIF_MSG_IFDOWN) + NETIF_MSG_IFDOWN | NETIF_MSG_HW) #define DPAA_INGRESS_CS_THRESHOLD 0x10000000 /* Ingress congestion threshold on FMan ports @@ -174,12 +151,17 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result) #define DPAA_TIME_STAMP_SIZE 8 #define DPAA_HASH_RESULTS_SIZE 8 +#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \ + + DPAA_HASH_RESULTS_SIZE) +#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \ + XDP_PACKET_HEADROOM - DPAA_HWA_SIZE) #ifdef CONFIG_DPAA_ERRATUM_A050385 -#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\ - + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE)) +#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE) +#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \ + DPAA_RX_PRIV_DATA_A050385_SIZE : \ + DPAA_RX_PRIV_DATA_DEFAULT_SIZE) #else -#define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \ - dpaa_rx_extra_headroom) +#define DPAA_RX_PRIV_DATA_SIZE DPAA_RX_PRIV_DATA_DEFAULT_SIZE #endif #define DPAA_ETH_PCD_RXQ_NUM 128 @@ -215,12 +197,15 @@ static int dpaa_rx_extra_headroom; #define dpaa_get_max_mtu() \ (dpaa_max_frm - (VLAN_ETH_HLEN + ETH_FCS_LEN)) +static void dpaa_eth_cgr_set_speed(struct mac_device *mac_dev, int speed); + static int dpaa_netdev_init(struct net_device *net_dev, const struct net_device_ops *dpaa_ops, u16 tx_timeout) { struct dpaa_priv *priv = netdev_priv(net_dev); struct device *dev = net_dev->dev.parent; + struct mac_device *mac_dev = priv->mac_dev; struct dpaa_percpu_priv *percpu_priv; const u8 *mac_addr; int i, err; @@ -234,10 +219,10 @@ static int dpaa_netdev_init(struct net_device *net_dev, } net_dev->netdev_ops = dpaa_ops; - mac_addr = priv->mac_dev->addr; + mac_addr = mac_dev->addr; - net_dev->mem_start = priv->mac_dev->res->start; - net_dev->mem_end = priv->mac_dev->res->end; + net_dev->mem_start = (unsigned long)priv->mac_dev->res->start; + net_dev->mem_end = (unsigned long)priv->mac_dev->res->end; net_dev->min_mtu = ETH_MIN_MTU; net_dev->max_mtu = dpaa_get_max_mtu(); @@ -259,14 +244,29 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->features |= net_dev->hw_features; net_dev->vlan_features = net_dev->features; - memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len); - memcpy(net_dev->dev_addr, mac_addr, net_dev->addr_len); + if (is_valid_ether_addr(mac_addr)) { + memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len); + eth_hw_addr_set(net_dev, mac_addr); + } else { + eth_hw_addr_random(net_dev); + err = mac_dev->change_addr(mac_dev->fman_mac, + (const enet_addr_t *)net_dev->dev_addr); + if (err) { + dev_err(dev, "Failed to set random MAC address\n"); + return -EINVAL; + } + dev_info(dev, "Using random MAC address: %pM\n", + net_dev->dev_addr); + } net_dev->ethtool_ops = &dpaa_ethtool_ops; net_dev->needed_headroom = priv->tx_headroom; net_dev->watchdog_timeo = msecs_to_jiffies(tx_timeout); + mac_dev->net_dev = net_dev; + mac_dev->update_speed = dpaa_eth_cgr_set_speed; + /* start without the RUNNING flag, phylib controls it later */ netif_carrier_off(net_dev); @@ -294,10 +294,9 @@ static int dpaa_stop(struct net_device *net_dev) */ msleep(200); - err = mac_dev->stop(mac_dev); - if (err < 0) - netif_err(priv, ifdown, net_dev, "mac_dev->stop() = %d\n", - err); + if (mac_dev->phy_dev) + phy_stop(mac_dev->phy_dev); + mac_dev->disable(mac_dev->fman_mac); for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { error = fman_port_disable(mac_dev->port[i]); @@ -433,7 +432,7 @@ static int dpaa_set_mac_address(struct net_device *net_dev, void *addr) mac_dev = priv->mac_dev; err = mac_dev->change_addr(mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err < 0) { netif_err(priv, drv, net_dev, "mac_dev->change_addr() = %d\n", err); @@ -832,10 +831,10 @@ static int dpaa_eth_cgr_init(struct dpaa_priv *priv) initcgr.we_mask = cpu_to_be16(QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES); initcgr.cgr.cscn_en = QM_CGR_EN; - /* Set different thresholds based on the MAC speed. - * This may turn suboptimal if the MAC is reconfigured at a speed - * lower than its max, e.g. if a dTSEC later negotiates a 100Mbps link. - * In such cases, we ought to reconfigure the threshold, too. + /* Set different thresholds based on the configured MAC speed. + * This may turn suboptimal if the MAC is reconfigured at another + * speed, so MACs must call dpaa_eth_cgr_set_speed in their adjust_link + * callback. */ if (priv->mac_dev->if_support & SUPPORTED_10000baseT_Full) cs_th = DPAA_CS_THRESHOLD_10G; @@ -864,6 +863,31 @@ out_error: return err; } +static void dpaa_eth_cgr_set_speed(struct mac_device *mac_dev, int speed) +{ + struct net_device *net_dev = mac_dev->net_dev; + struct dpaa_priv *priv = netdev_priv(net_dev); + struct qm_mcc_initcgr opts = { }; + u32 cs_th; + int err; + + opts.we_mask = cpu_to_be16(QM_CGR_WE_CS_THRES); + switch (speed) { + case SPEED_10000: + cs_th = DPAA_CS_THRESHOLD_10G; + break; + case SPEED_1000: + default: + cs_th = DPAA_CS_THRESHOLD_1G; + break; + } + qm_cgr_cs_thres_set64(&opts.cgr.cs_thres, cs_th, 1); + + err = qman_update_cgr_safe(&priv->cgr_data.cgr, &opts); + if (err) + netdev_err(net_dev, "could not update speed: %d\n", err); +} + static inline void dpaa_setup_ingress(const struct dpaa_priv *priv, struct dpaa_fq *fq, const struct qman_fq *template) @@ -933,7 +957,7 @@ static void dpaa_fq_setup(struct dpaa_priv *priv, break; case FQ_TYPE_TX_CONF_MQ: priv->conf_fqs[conf_cnt++] = &fq->fq_base; - /* fall through */ + fallthrough; case FQ_TYPE_TX_CONFIRM: dpaa_setup_ingress(priv, fq, &fq_cbs->tx_defq); break; @@ -1111,6 +1135,25 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) dpaa_fq->fqid = qman_fq_fqid(fq); + if (dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT || + dpaa_fq->fq_type == FQ_TYPE_RX_PCD) { + err = xdp_rxq_info_reg(&dpaa_fq->xdp_rxq, dpaa_fq->net_dev, + dpaa_fq->fqid, 0); + if (err) { + dev_err(dev, "xdp_rxq_info_reg() = %d\n", err); + return err; + } + + err = xdp_rxq_info_reg_mem_model(&dpaa_fq->xdp_rxq, + MEM_TYPE_PAGE_ORDER0, NULL); + if (err) { + dev_err(dev, "xdp_rxq_info_reg_mem_model() = %d\n", + err); + xdp_rxq_info_unreg(&dpaa_fq->xdp_rxq); + return err; + } + } + return 0; } @@ -1140,6 +1183,11 @@ static int dpaa_fq_free_entry(struct device *dev, struct qman_fq *fq) } } + if ((dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT || + dpaa_fq->fq_type == FQ_TYPE_RX_PCD) && + xdp_rxq_info_is_reg(&dpaa_fq->xdp_rxq)) + xdp_rxq_info_unreg(&dpaa_fq->xdp_rxq); + qman_destroy_fq(fq); list_del(&dpaa_fq->list); @@ -1582,17 +1630,13 @@ static int dpaa_eth_refill_bpools(struct dpaa_priv *priv) { struct dpaa_bp *dpaa_bp; int *countptr; - int res; dpaa_bp = priv->dpaa_bp; if (!dpaa_bp) return -EINVAL; countptr = this_cpu_ptr(dpaa_bp->percpu_count); - res = dpaa_eth_refill_bpool(dpaa_bp, countptr); - if (res) - return res; - return 0; + return dpaa_eth_refill_bpool(dpaa_bp, countptr); } /* Cleanup function for outgoing frame descriptors that were built on Tx path, @@ -1606,6 +1650,9 @@ static int dpaa_eth_refill_bpools(struct dpaa_priv *priv) * * Return the skb backpointer, since for S/G frames the buffer containing it * gets freed here. + * + * No skb backpointer is set when transmitting XDP frames. Cleanup the buffer + * and return NULL in this case. */ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, const struct qm_fd *fd, bool ts) @@ -1616,6 +1663,7 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, dma_addr_t addr = qm_fd_addr(fd); void *vaddr = phys_to_virt(addr); const struct qm_sg_entry *sgt; + struct dpaa_eth_swbp *swbp; struct sk_buff *skb; u64 ns; int i; @@ -1644,11 +1692,20 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, } } else { dma_unmap_single(priv->tx_dma_dev, addr, - priv->tx_headroom + qm_fd_get_length(fd), + qm_fd_get_offset(fd) + qm_fd_get_length(fd), dma_dir); } - skb = *(struct sk_buff **)vaddr; + swbp = (struct dpaa_eth_swbp *)vaddr; + skb = swbp->skb; + + /* No skb backpointer is set when running XDP. An xdp_frame + * backpointer is saved instead. + */ + if (!skb) { + xdp_return_frame(swbp->xdpf); + return NULL; + } /* DMA unmapping is required before accessing the HW provided info */ if (ts && priv->tx_tstamp && @@ -1714,7 +1771,6 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (WARN_ONCE(!skb, "Build skb failure on Rx\n")) goto free_buffer; - WARN_ON(fd_off != priv->rx_headroom); skb_reserve(skb, fd_off); skb_put(skb, qm_fd_get_length(fd)); @@ -1862,8 +1918,8 @@ static int skb_to_contig_fd(struct dpaa_priv *priv, { struct net_device *net_dev = priv->net_dev; enum dma_data_direction dma_dir; + struct dpaa_eth_swbp *swbp; unsigned char *buff_start; - struct sk_buff **skbh; dma_addr_t addr; int err; @@ -1874,8 +1930,8 @@ static int skb_to_contig_fd(struct dpaa_priv *priv, buff_start = skb->data - priv->tx_headroom; dma_dir = DMA_TO_DEVICE; - skbh = (struct sk_buff **)buff_start; - *skbh = skb; + swbp = (struct dpaa_eth_swbp *)buff_start; + swbp->skb = skb; /* Enable L3/L4 hardware checksum computation. * @@ -1914,8 +1970,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, const enum dma_data_direction dma_dir = DMA_TO_DEVICE; const int nr_frags = skb_shinfo(skb)->nr_frags; struct net_device *net_dev = priv->net_dev; + struct dpaa_eth_swbp *swbp; struct qm_sg_entry *sgt; - struct sk_buff **skbh; void *buff_start; skb_frag_t *frag; dma_addr_t addr; @@ -1988,8 +2044,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, qm_fd_set_sg(fd, priv->tx_headroom, skb->len); /* DMA map the SGT page */ - skbh = (struct sk_buff **)buff_start; - *skbh = skb; + swbp = (struct dpaa_eth_swbp *)buff_start; + swbp->skb = skb; addr = dma_map_page(priv->tx_dma_dev, p, 0, priv->tx_headroom + DPAA_SGT_SIZE, dma_dir); @@ -2050,7 +2106,7 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, } #ifdef CONFIG_DPAA_ERRATUM_A050385 -int dpaa_a050385_wa(struct net_device *net_dev, struct sk_buff **s) +static int dpaa_a050385_wa_skb(struct net_device *net_dev, struct sk_buff **s) { struct dpaa_priv *priv = netdev_priv(net_dev); struct sk_buff *new_skb, *skb = *s; @@ -2095,7 +2151,7 @@ workaround: /* Workaround for DPAA_A050385 requires data start to be aligned */ start = PTR_ALIGN(new_skb->data, DPAA_A050385_ALIGN); - if (start - new_skb->data != 0) + if (start - new_skb->data) skb_reserve(new_skb, start - new_skb->data); skb_put(new_skb, skb->len); @@ -2103,6 +2159,15 @@ workaround: skb_copy_header(new_skb, skb); new_skb->dev = skb->dev; + /* Copy relevant timestamp info from the old skb to the new */ + if (priv->tx_tstamp) { + skb_shinfo(new_skb)->tx_flags = skb_shinfo(skb)->tx_flags; + skb_shinfo(new_skb)->hwtstamps = skb_shinfo(skb)->hwtstamps; + skb_shinfo(new_skb)->tskey = skb_shinfo(skb)->tskey; + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); + } + /* We move the headroom when we align it so we have to reset the * network and transport header offsets relative to the new data * pointer. The checksum offload relies on these offsets. @@ -2110,12 +2175,91 @@ workaround: skb_set_network_header(new_skb, skb_network_offset(skb)); skb_set_transport_header(new_skb, skb_transport_offset(skb)); - /* TODO: does timestamping need the result in the old skb? */ dev_kfree_skb(skb); *s = new_skb; return 0; } + +static int dpaa_a050385_wa_xdpf(struct dpaa_priv *priv, + struct xdp_frame **init_xdpf) +{ + struct xdp_frame *new_xdpf, *xdpf = *init_xdpf; + void *new_buff, *aligned_data; + struct page *p; + u32 data_shift; + int headroom; + + /* Check the data alignment and make sure the headroom is large + * enough to store the xdpf backpointer. Use an aligned headroom + * value. + * + * Due to alignment constraints, we give XDP access to the full 256 + * byte frame headroom. If the XDP program uses all of it, copy the + * data to a new buffer and make room for storing the backpointer. + */ + if (PTR_IS_ALIGNED(xdpf->data, DPAA_FD_DATA_ALIGNMENT) && + xdpf->headroom >= priv->tx_headroom) { + xdpf->headroom = priv->tx_headroom; + return 0; + } + + /* Try to move the data inside the buffer just enough to align it and + * store the xdpf backpointer. If the available headroom isn't large + * enough, resort to allocating a new buffer and copying the data. + */ + aligned_data = PTR_ALIGN_DOWN(xdpf->data, DPAA_FD_DATA_ALIGNMENT); + data_shift = xdpf->data - aligned_data; + + /* The XDP frame's headroom needs to be large enough to accommodate + * shifting the data as well as storing the xdpf backpointer. + */ + if (xdpf->headroom >= data_shift + priv->tx_headroom) { + memmove(aligned_data, xdpf->data, xdpf->len); + xdpf->data = aligned_data; + xdpf->headroom = priv->tx_headroom; + return 0; + } + + /* The new xdp_frame is stored in the new buffer. Reserve enough space + * in the headroom for storing it along with the driver's private + * info. The headroom needs to be aligned to DPAA_FD_DATA_ALIGNMENT to + * guarantee the data's alignment in the buffer. + */ + headroom = ALIGN(sizeof(*new_xdpf) + priv->tx_headroom, + DPAA_FD_DATA_ALIGNMENT); + + /* Assure the extended headroom and data don't overflow the buffer, + * while maintaining the mandatory tailroom. + */ + if (headroom + xdpf->len > DPAA_BP_RAW_SIZE - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + return -ENOMEM; + + p = dev_alloc_pages(0); + if (unlikely(!p)) + return -ENOMEM; + + /* Copy the data to the new buffer at a properly aligned offset */ + new_buff = page_address(p); + memcpy(new_buff + headroom, xdpf->data, xdpf->len); + + /* Create an XDP frame around the new buffer in a similar fashion + * to xdp_convert_buff_to_frame. + */ + new_xdpf = new_buff; + new_xdpf->data = new_buff + headroom; + new_xdpf->len = xdpf->len; + new_xdpf->headroom = priv->tx_headroom; + new_xdpf->frame_sz = DPAA_BP_RAW_SIZE; + new_xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + + /* Release the initial buffer */ + xdp_return_frame_rx_napi(xdpf); + + *init_xdpf = new_xdpf; + return 0; +} #endif static netdev_tx_t @@ -2166,7 +2310,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) #ifdef CONFIG_DPAA_ERRATUM_A050385 if (unlikely(fman_has_errata_a050385())) { - if (dpaa_a050385_wa(net_dev, &skb)) + if (dpaa_a050385_wa_skb(net_dev, &skb)) goto enomem; nonlinear = skb_is_nonlinear(skb); } @@ -2186,7 +2330,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) txq = netdev_get_tx_queue(net_dev, queue_mapping); /* LLTX requires to do our own update of trans_start */ - txq->trans_start = jiffies; + txq_trans_cond_update(txq); if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD); @@ -2250,8 +2394,11 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) { struct dpaa_napi_portal *np = container_of(napi, struct dpaa_napi_portal, napi); + int cleaned; + + np->xdp_act = 0; - int cleaned = qman_p_poll_dqrr(np->p, budget); + cleaned = qman_p_poll_dqrr(np->p, budget); if (cleaned < budget) { napi_complete_done(napi, cleaned); @@ -2260,6 +2407,9 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); } + if (np->xdp_act & XDP_REDIRECT) + xdp_do_flush(); + return cleaned; } @@ -2288,9 +2438,9 @@ static void dpaa_tx_conf(struct net_device *net_dev, } static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv, - struct qman_portal *portal) + struct qman_portal *portal, bool sched_napi) { - if (unlikely(in_irq() || !in_serving_softirq())) { + if (sched_napi) { /* Disable QMan IRQ and invoke NAPI */ qman_p_irqsource_remove(portal, QM_PIRQ_DQRI); @@ -2304,7 +2454,8 @@ static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv, static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_fq *dpaa_fq = container_of(fq, struct dpaa_fq, fq_base); struct dpaa_percpu_priv *percpu_priv; @@ -2320,7 +2471,7 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_eth_refill_bpools(priv); @@ -2329,29 +2480,199 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, return qman_cb_dqrr_consume; } +static int dpaa_xdp_xmit_frame(struct net_device *net_dev, + struct xdp_frame *xdpf) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct rtnl_link_stats64 *percpu_stats; + struct dpaa_percpu_priv *percpu_priv; + struct dpaa_eth_swbp *swbp; + struct netdev_queue *txq; + void *buff_start; + struct qm_fd fd; + dma_addr_t addr; + int err; + + percpu_priv = this_cpu_ptr(priv->percpu_priv); + percpu_stats = &percpu_priv->stats; + +#ifdef CONFIG_DPAA_ERRATUM_A050385 + if (unlikely(fman_has_errata_a050385())) { + if (dpaa_a050385_wa_xdpf(priv, &xdpf)) { + err = -ENOMEM; + goto out_error; + } + } +#endif + + if (xdpf->headroom < DPAA_TX_PRIV_DATA_SIZE) { + err = -EINVAL; + goto out_error; + } + + buff_start = xdpf->data - xdpf->headroom; + + /* Leave empty the skb backpointer at the start of the buffer. + * Save the XDP frame for easy cleanup on confirmation. + */ + swbp = (struct dpaa_eth_swbp *)buff_start; + swbp->skb = NULL; + swbp->xdpf = xdpf; + + qm_fd_clear_fd(&fd); + fd.bpid = FSL_DPAA_BPID_INV; + fd.cmd |= cpu_to_be32(FM_FD_CMD_FCO); + qm_fd_set_contig(&fd, xdpf->headroom, xdpf->len); + + addr = dma_map_single(priv->tx_dma_dev, buff_start, + xdpf->headroom + xdpf->len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(priv->tx_dma_dev, addr))) { + err = -EINVAL; + goto out_error; + } + + qm_fd_addr_set64(&fd, addr); + + /* Bump the trans_start */ + txq = netdev_get_tx_queue(net_dev, smp_processor_id()); + txq_trans_cond_update(txq); + + err = dpaa_xmit(priv, percpu_stats, smp_processor_id(), &fd); + if (err) { + dma_unmap_single(priv->tx_dma_dev, addr, + qm_fd_get_offset(&fd) + qm_fd_get_length(&fd), + DMA_TO_DEVICE); + goto out_error; + } + + return 0; + +out_error: + percpu_stats->tx_errors++; + return err; +} + +static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr, + struct dpaa_fq *dpaa_fq, unsigned int *xdp_meta_len) +{ + ssize_t fd_off = qm_fd_get_offset(fd); + struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; + struct xdp_buff xdp; + u32 xdp_act; + int err; + + xdp_prog = READ_ONCE(priv->xdp_prog); + if (!xdp_prog) + return XDP_PASS; + + xdp_init_buff(&xdp, DPAA_BP_RAW_SIZE - DPAA_TX_PRIV_DATA_SIZE, + &dpaa_fq->xdp_rxq); + xdp_prepare_buff(&xdp, vaddr + fd_off - XDP_PACKET_HEADROOM, + XDP_PACKET_HEADROOM, qm_fd_get_length(fd), true); + + /* We reserve a fixed headroom of 256 bytes under the erratum and we + * offer it all to XDP programs to use. If no room is left for the + * xdpf backpointer on TX, we will need to copy the data. + * Disable metadata support since data realignments might be required + * and the information can be lost. + */ +#ifdef CONFIG_DPAA_ERRATUM_A050385 + if (unlikely(fman_has_errata_a050385())) { + xdp_set_data_meta_invalid(&xdp); + xdp.data_hard_start = vaddr; + xdp.frame_sz = DPAA_BP_RAW_SIZE; + } +#endif + + xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp); + + /* Update the length and the offset of the FD */ + qm_fd_set_contig(fd, xdp.data - vaddr, xdp.data_end - xdp.data); + + switch (xdp_act) { + case XDP_PASS: +#ifdef CONFIG_DPAA_ERRATUM_A050385 + *xdp_meta_len = xdp_data_meta_unsupported(&xdp) ? 0 : + xdp.data - xdp.data_meta; +#else + *xdp_meta_len = xdp.data - xdp.data_meta; +#endif + break; + case XDP_TX: + /* We can access the full headroom when sending the frame + * back out + */ + xdp.data_hard_start = vaddr; + xdp.frame_sz = DPAA_BP_RAW_SIZE; + xdpf = xdp_convert_buff_to_frame(&xdp); + if (unlikely(!xdpf)) { + free_pages((unsigned long)vaddr, 0); + break; + } + + if (dpaa_xdp_xmit_frame(priv->net_dev, xdpf)) + xdp_return_frame_rx_napi(xdpf); + + break; + case XDP_REDIRECT: + /* Allow redirect to use the full headroom */ + xdp.data_hard_start = vaddr; + xdp.frame_sz = DPAA_BP_RAW_SIZE; + + err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog); + if (err) { + trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); + free_pages((unsigned long)vaddr, 0); + } + break; + default: + bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); + fallthrough; + case XDP_DROP: + /* Free the buffer */ + free_pages((unsigned long)vaddr, 0); + break; + } + + return xdp_act; +} + static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { + bool ts_valid = false, hash_valid = false; struct skb_shared_hwtstamps *shhwtstamps; + unsigned int skb_len, xdp_meta_len = 0; struct rtnl_link_stats64 *percpu_stats; struct dpaa_percpu_priv *percpu_priv; const struct qm_fd *fd = &dq->fd; dma_addr_t addr = qm_fd_addr(fd); + struct dpaa_napi_portal *np; enum qm_fd_format fd_format; struct net_device *net_dev; u32 fd_status, hash_offset; + struct qm_sg_entry *sgt; struct dpaa_bp *dpaa_bp; + struct dpaa_fq *dpaa_fq; struct dpaa_priv *priv; - unsigned int skb_len; struct sk_buff *skb; int *count_ptr; + u32 xdp_act; void *vaddr; + u32 hash; u64 ns; + dpaa_fq = container_of(fq, struct dpaa_fq, fq_base); fd_status = be32_to_cpu(fd->status); fd_format = qm_fd_get_format(fd); - net_dev = ((struct dpaa_fq *)fq)->net_dev; + net_dev = dpaa_fq->net_dev; priv = netdev_priv(net_dev); dpaa_bp = dpaa_bpid2pool(dq->fd.bpid); if (!dpaa_bp) @@ -2362,8 +2683,9 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); percpu_stats = &percpu_priv->stats; + np = &percpu_priv->np; - if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal))) + if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))) return qman_cb_dqrr_stop; /* Make sure we didn't run out of buffers */ @@ -2402,35 +2724,68 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); (*count_ptr)--; - if (likely(fd_format == qm_fd_contig)) + /* Extract the timestamp stored in the headroom before running XDP */ + if (priv->rx_tstamp) { + if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns)) + ts_valid = true; + else + WARN_ONCE(1, "fman_port_get_tstamp failed!\n"); + } + + /* Extract the hash stored in the headroom before running XDP */ + if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use && + !fman_port_get_hash_result_offset(priv->mac_dev->port[RX], + &hash_offset)) { + hash = be32_to_cpu(*(u32 *)(vaddr + hash_offset)); + hash_valid = true; + } + + if (likely(fd_format == qm_fd_contig)) { + xdp_act = dpaa_run_xdp(priv, (struct qm_fd *)fd, vaddr, + dpaa_fq, &xdp_meta_len); + np->xdp_act |= xdp_act; + if (xdp_act != XDP_PASS) { + percpu_stats->rx_packets++; + percpu_stats->rx_bytes += qm_fd_get_length(fd); + return qman_cb_dqrr_consume; + } skb = contig_fd_to_skb(priv, fd); - else + } else { + /* XDP doesn't support S/G frames. Return the fragments to the + * buffer pool and release the SGT. + */ + if (READ_ONCE(priv->xdp_prog)) { + WARN_ONCE(1, "S/G frames not supported under XDP\n"); + sgt = vaddr + qm_fd_get_offset(fd); + dpaa_release_sgt_members(sgt); + free_pages((unsigned long)vaddr, 0); + return qman_cb_dqrr_consume; + } skb = sg_fd_to_skb(priv, fd); + } if (!skb) return qman_cb_dqrr_consume; - if (priv->rx_tstamp) { + if (xdp_meta_len) + skb_metadata_set(skb, xdp_meta_len); + + /* Set the previously extracted timestamp */ + if (ts_valid) { shhwtstamps = skb_hwtstamps(skb); memset(shhwtstamps, 0, sizeof(*shhwtstamps)); - - if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns)) - shhwtstamps->hwtstamp = ns_to_ktime(ns); - else - dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n"); + shhwtstamps->hwtstamp = ns_to_ktime(ns); } skb->protocol = eth_type_trans(skb, net_dev); - if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use && - !fman_port_get_hash_result_offset(priv->mac_dev->port[RX], - &hash_offset)) { + /* Set the previously extracted hash */ + if (hash_valid) { enum pkt_hash_types type; /* if L4 exists, it was used in the hash generation */ type = be32_to_cpu(fd->status) & FM_FD_STAT_L4CV ? PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3; - skb_set_hash(skb, be32_to_cpu(*(u32 *)(vaddr + hash_offset)), - type); + skb_set_hash(skb, hash, type); } skb_len = skb->len; @@ -2448,7 +2803,8 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_percpu_priv *percpu_priv; struct net_device *net_dev; @@ -2459,7 +2815,7 @@ static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_tx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); @@ -2469,7 +2825,8 @@ static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_percpu_priv *percpu_priv; struct net_device *net_dev; @@ -2483,7 +2840,7 @@ static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_tx_conf(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); @@ -2529,7 +2886,7 @@ static void dpaa_eth_napi_enable(struct dpaa_priv *priv) for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); - percpu_priv->np.down = 0; + percpu_priv->np.down = false; napi_enable(&percpu_priv->np.napi); } } @@ -2542,7 +2899,7 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); - percpu_priv->np.down = 1; + percpu_priv->np.down = true; napi_disable(&percpu_priv->np.napi); } } @@ -2559,6 +2916,7 @@ static void dpaa_adjust_link(struct net_device *net_dev) /* The Aquantia PHYs are capable of performing rate adaptation */ #define PHY_VEND_AQUANTIA 0x03a1b400 +#define PHY_VEND_AQUANTIA2 0x31c31c00 static int dpaa_phy_init(struct net_device *net_dev) { @@ -2566,6 +2924,7 @@ static int dpaa_phy_init(struct net_device *net_dev) struct mac_device *mac_dev; struct phy_device *phy_dev; struct dpaa_priv *priv; + u32 phy_vendor; priv = netdev_priv(net_dev); mac_dev = priv->mac_dev; @@ -2578,9 +2937,11 @@ static int dpaa_phy_init(struct net_device *net_dev) return -ENODEV; } + phy_vendor = phy_dev->drv->phy_id & GENMASK(31, 10); /* Unless the PHY is capable of rate adaptation */ if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII || - ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) { + (phy_vendor != PHY_VEND_AQUANTIA && + phy_vendor != PHY_VEND_AQUANTIA2)) { /* remove any features not supported by the controller */ ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support); @@ -2615,11 +2976,12 @@ static int dpaa_open(struct net_device *net_dev) goto mac_start_failed; } - err = priv->mac_dev->start(mac_dev); + err = priv->mac_dev->enable(mac_dev->fman_mac); if (err < 0) { - netif_err(priv, ifup, net_dev, "mac_dev->start() = %d\n", err); + netif_err(priv, ifup, net_dev, "mac_dev->enable() = %d\n", err); goto mac_start_failed; } + phy_start(priv->mac_dev->phy_dev); netif_tx_start_all_queues(net_dev); @@ -2648,6 +3010,99 @@ static int dpaa_eth_stop(struct net_device *net_dev) return err; } +static bool xdp_validate_mtu(struct dpaa_priv *priv, int mtu) +{ + int max_contig_data = priv->dpaa_bp->size - priv->rx_headroom; + + /* We do not support S/G fragments when XDP is enabled. + * Limit the MTU in relation to the buffer size. + */ + if (mtu + VLAN_ETH_HLEN + ETH_FCS_LEN > max_contig_data) { + dev_warn(priv->net_dev->dev.parent, + "The maximum MTU for XDP is %d\n", + max_contig_data - VLAN_ETH_HLEN - ETH_FCS_LEN); + return false; + } + + return true; +} + +static int dpaa_change_mtu(struct net_device *net_dev, int new_mtu) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + + if (priv->xdp_prog && !xdp_validate_mtu(priv, new_mtu)) + return -EINVAL; + + net_dev->mtu = new_mtu; + return 0; +} + +static int dpaa_setup_xdp(struct net_device *net_dev, struct netdev_bpf *bpf) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct bpf_prog *old_prog; + int err; + bool up; + + /* S/G fragments are not supported in XDP-mode */ + if (bpf->prog && !xdp_validate_mtu(priv, net_dev->mtu)) { + NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP"); + return -EINVAL; + } + + up = netif_running(net_dev); + + if (up) + dpaa_eth_stop(net_dev); + + old_prog = xchg(&priv->xdp_prog, bpf->prog); + if (old_prog) + bpf_prog_put(old_prog); + + if (up) { + err = dpaa_open(net_dev); + if (err) { + NL_SET_ERR_MSG_MOD(bpf->extack, "dpaa_open() failed"); + return err; + } + } + + return 0; +} + +static int dpaa_xdp(struct net_device *net_dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return dpaa_setup_xdp(net_dev, xdp); + default: + return -EINVAL; + } +} + +static int dpaa_xdp_xmit(struct net_device *net_dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct xdp_frame *xdpf; + int i, nxmit = 0; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + if (!netif_running(net_dev)) + return -ENETDOWN; + + for (i = 0; i < n; i++) { + xdpf = frames[i]; + if (dpaa_xdp_xmit_frame(net_dev, xdpf)) + break; + nxmit++; + } + + return nxmit; +} + static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct dpaa_priv *priv = netdev_priv(dev); @@ -2712,8 +3167,11 @@ static const struct net_device_ops dpaa_ops = { .ndo_set_mac_address = dpaa_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = dpaa_set_rx_mode, - .ndo_do_ioctl = dpaa_ioctl, + .ndo_eth_ioctl = dpaa_ioctl, .ndo_setup_tc = dpaa_setup_tc, + .ndo_change_mtu = dpaa_change_mtu, + .ndo_bpf = dpaa_xdp, + .ndo_xdp_xmit = dpaa_xdp_xmit, }; static int dpaa_napi_add(struct net_device *net_dev) @@ -2725,8 +3183,7 @@ static int dpaa_napi_add(struct net_device *net_dev) for_each_possible_cpu(cpu) { percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu); - netif_napi_add(net_dev, &percpu_priv->np.napi, - dpaa_eth_poll, NAPI_POLL_WEIGHT); + netif_napi_add(net_dev, &percpu_priv->np.napi, dpaa_eth_poll); } return 0; @@ -2828,7 +3285,8 @@ out_error: return err; } -static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) +static u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl, + enum port_type port) { u16 headroom; @@ -2842,10 +3300,18 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) * * Also make sure the headroom is a multiple of data_align bytes */ - headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE + - DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE); + headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE); - return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); + if (port == RX) { +#ifdef CONFIG_DPAA_ERRATUM_A050385 + if (unlikely(fman_has_errata_a050385())) + headroom = XDP_PACKET_HEADROOM; +#endif + + return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT); + } else { + return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); + } } static int dpaa_eth_probe(struct platform_device *pdev) @@ -2902,7 +3368,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) } /* Do this here, so we can be verbose early */ - SET_NETDEV_DEV(net_dev, dev); + SET_NETDEV_DEV(net_dev, dev->parent); dev_set_drvdata(dev, net_dev); priv = netdev_priv(net_dev); @@ -2926,7 +3392,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) DMA_BIT_MASK(40)); if (err) { netdev_err(net_dev, "dma_coerce_mask_and_coherent() failed\n"); - return err; + goto free_netdev; } /* If fsl_fm_max_frm is set to a higher value than the all-common 1500, @@ -3013,8 +3479,8 @@ static int dpaa_eth_probe(struct platform_device *pdev) goto free_dpaa_fqs; } - priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]); - priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]); + priv->tx_headroom = dpaa_get_headroom(priv->buf_layout, TX); + priv->rx_headroom = dpaa_get_headroom(priv->buf_layout, RX); /* All real interfaces need their ports initialized */ err = dpaa_eth_init_ports(mac_dev, dpaa_bp, &port_fqs, |