diff options
| author | Jens Axboe <axboe@kernel.dk> | 2024-09-17 08:32:53 -0600 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2024-09-17 08:32:53 -0600 |
| commit | 42b16d3ac371a2fac9b6f08fd75f23f34ba3955a (patch) | |
| tree | d15a2fe1f7441361b972bc787af5122adc3fcb71 /drivers/net/ethernet | |
| parent | 4208c562a27899212e8046080555e0f204e0579a (diff) | |
| parent | 98f7e32f20d28ec452afb208f9cffc08448a2652 (diff) | |
Merge tag 'v6.11' into for-6.12/block
Merge in 6.11 final to get the fix for preventing deadlocks on an
elevator switch, as there's a fixup for that patch.
* tag 'v6.11': (1788 commits)
Linux 6.11
Revert "KVM: VMX: Always honor guest PAT on CPUs that support self-snoop"
pinctrl: pinctrl-cy8c95x0: Fix regcache
cifs: Fix signature miscalculation
mm: avoid leaving partial pfn mappings around in error case
drm/xe/client: add missing bo locking in show_meminfo()
drm/xe/client: fix deadlock in show_meminfo()
drm/xe/oa: Enable Xe2+ PES disaggregation
drm/xe/display: fix compat IS_DISPLAY_STEP() range end
drm/xe: Fix access_ok check in user_fence_create
drm/xe: Fix possible UAF in guc_exec_queue_process_msg
drm/xe: Remove fence check from send_tlb_invalidation
drm/xe/gt: Remove double include
net: netfilter: move nf flowtable bpf initialization in nf_flow_table_module_init()
PCI: Fix potential deadlock in pcim_intx()
workqueue: Clear worker->pool in the worker thread context
net: tighten bad gso csum offset check in virtio_net_hdr
netlink: specs: mptcp: fix port endianness
net: dpaa: Pad packets to ETH_ZLEN
mptcp: pm: Fix uaf in __timer_delete_sync
...
Diffstat (limited to 'drivers/net/ethernet')
89 files changed, 1287 insertions, 751 deletions
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ffa74c26ee53..04a623b3eee2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5056,7 +5056,7 @@ void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr) list_del_init(&fltr->list); } -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) +static void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) { struct bnxt_filter_base *usr_fltr, *tmp; @@ -7591,19 +7591,20 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) int rx = bp->rx_nr_rings, stat; int vnic, grp = rx; - if (hw_resc->resv_tx_rings != bp->tx_nr_rings && - bp->hwrm_spec_code >= 0x10601) - return true; - /* Old firmware does not need RX ring reservations but we still * need to setup a default RSS map when needed. With new firmware * we go through RX ring reservations first and then set up the * RSS map for the successfully reserved RX rings when needed. */ - if (!BNXT_NEW_RM(bp)) { + if (!BNXT_NEW_RM(bp)) bnxt_check_rss_tbl_no_rmgr(bp); + + if (hw_resc->resv_tx_rings != bp->tx_nr_rings && + bp->hwrm_spec_code >= 0x10601) + return true; + + if (!BNXT_NEW_RM(bp)) return false; - } vnic = bnxt_get_total_vnics(bp, rx); @@ -7649,8 +7650,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num); static int __bnxt_reserve_rings(struct bnxt *bp) { struct bnxt_hw_rings hwr = {0}; + int rx_rings, old_rx_rings, rc; int cp = bp->cp_nr_rings; - int rx_rings, rc; int ulp_msix = 0; bool sh = false; int tx_cp; @@ -7684,6 +7685,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) hwr.grp = bp->rx_nr_rings; hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr); hwr.stat = bnxt_get_func_stat_ctxs(bp); + old_rx_rings = bp->hw_resc.resv_rx_rings; rc = bnxt_hwrm_reserve_rings(bp, &hwr); if (rc) @@ -7738,7 +7740,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (!bnxt_rings_ok(bp, &hwr)) return -ENOMEM; - if (!netif_is_rxfh_configured(bp->dev)) + if (old_rx_rings != bp->hw_resc.resv_rx_rings && + !netif_is_rxfh_configured(bp->dev)) bnxt_set_dflt_rss_indir_tbl(bp, NULL); if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) { @@ -10245,7 +10248,7 @@ static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp) } } -void bnxt_clear_rss_ctxs(struct bnxt *bp) +static void bnxt_clear_rss_ctxs(struct bnxt *bp) { struct ethtool_rxfh_context *ctx; unsigned long context; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 6bbdc718c3a7..059a6f81c1a8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2790,7 +2790,6 @@ void bnxt_set_ring_params(struct bnxt *); int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, bool async_only); int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp); @@ -2842,7 +2841,6 @@ int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, bool all); -void bnxt_clear_rss_ctxs(struct bnxt *bp); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d00ef0063820..4cf9bf8b01b0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -968,9 +968,6 @@ static int bnxt_set_channels(struct net_device *dev, return -EINVAL; } - bnxt_clear_usr_fltrs(bp, true); - if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) - bnxt_clear_rss_ctxs(bp); if (netif_running(dev)) { if (BNXT_PF(bp)) { /* TODO CHIMP_FW: Send message to all VF's @@ -1863,8 +1860,14 @@ static void bnxt_modify_rss(struct bnxt *bp, struct ethtool_rxfh_context *ctx, } static int bnxt_rxfh_context_check(struct bnxt *bp, + const struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { + if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) { + NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported"); + return -EOPNOTSUPP; + } + if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) { NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported"); return -EOPNOTSUPP; @@ -1888,7 +1891,7 @@ static int bnxt_create_rxfh_context(struct net_device *dev, struct bnxt_vnic_info *vnic; int rc; - rc = bnxt_rxfh_context_check(bp, extack); + rc = bnxt_rxfh_context_check(bp, rxfh, extack); if (rc) return rc; @@ -1915,8 +1918,12 @@ static int bnxt_create_rxfh_context(struct net_device *dev, if (rc) goto out; + /* Populate defaults in the context */ bnxt_set_dflt_rss_indir_tbl(bp, ctx); + ctx->hfunc = ETH_RSS_HASH_TOP; memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE); + memcpy(ethtool_rxfh_context_key(ctx), + bp->rss_hash_key, HW_HASH_KEY_SIZE); rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings); if (rc) { @@ -1953,7 +1960,7 @@ static int bnxt_modify_rxfh_context(struct net_device *dev, struct bnxt_rss_ctx *rss_ctx; int rc; - rc = bnxt_rxfh_context_check(bp, extack); + rc = bnxt_rxfh_context_check(bp, rxfh, extack); if (rc) return rc; @@ -1990,7 +1997,6 @@ static int bnxt_set_rxfh(struct net_device *dev, bnxt_modify_rss(bp, NULL, NULL, rxfh); - bnxt_clear_usr_fltrs(bp, false); if (netif_running(bp->dev)) { bnxt_close_nic(bp, false, false); rc = bnxt_open_nic(bp, false, false); @@ -5280,7 +5286,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, .cap_rss_ctx_supported = 1, - .rxfh_max_context_id = BNXT_MAX_ETH_RSS_CTX, + .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), .supported_coalesce_params = ETHTOOL_COALESCE_USECS | diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 345681d5007e..f88b641533fc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, * redirect is coming from a frame received by the * bnxt_en driver. */ - rx_buf = &rxr->rx_buf_ring[cons]; - mapping = rx_buf->mapping - bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, - BNXT_RX_PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 1248792d7fd4..0715ea5bf13e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -42,19 +42,15 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct bcmgenet_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; - if (dev->phydev) { + if (dev->phydev) phy_ethtool_get_wol(dev->phydev, wol); - if (wol->supported) - return; - } - if (!device_can_wakeup(kdev)) { - wol->supported = 0; - wol->wolopts = 0; + /* MAC is not wake-up capable, return what the PHY does */ + if (!device_can_wakeup(kdev)) return; - } - wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; + /* Overlay MAC capabilities with that of the PHY queried before */ + wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; memset(wol->sopass, 0, sizeof(wol->sopass)); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 11665be3a22c..dcd3f54ed0cf 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5250,8 +5250,8 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wol & MACB_WOL_ENABLED) { /* Check for IP address in WOL ARP mode */ idev = __in_dev_get_rcu(bp->dev); - if (idev && idev->ifa_list) - ifa = rcu_access_pointer(idev->ifa_list); + if (idev) + ifa = rcu_dereference(idev->ifa_list); if ((bp->wolopts & WAKE_ARP) && !ifa) { netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a40c266c37f2..608cc6af5af1 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1054,18 +1054,12 @@ static int phy_interface_mode(u8 lmac_type) static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) { - struct lmac *lmac, **priv; + struct lmac *lmac; u64 cfg; lmac = &bgx->lmac[lmacid]; lmac->bgx = bgx; - lmac->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); - if (!lmac->netdev) - return -ENOMEM; - priv = netdev_priv(lmac->netdev); - *priv = lmac; - if ((lmac->lmac_type == BGX_MODE_SGMII) || (lmac->lmac_type == BGX_MODE_QSGMII) || (lmac->lmac_type == BGX_MODE_RGMII)) { @@ -1191,7 +1185,6 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) (lmac->lmac_type != BGX_MODE_10G_KR) && lmac->phydev) phy_disconnect(lmac->phydev); - free_netdev(lmac->netdev); lmac->phydev = NULL; } @@ -1653,6 +1646,23 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_get_qlm_mode(bgx); + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + struct lmac *lmacp, **priv; + + lmacp = &bgx->lmac[lmac]; + lmacp->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); + + if (!lmacp->netdev) { + for (int i = 0; i < lmac; i++) + free_netdev(bgx->lmac[i].netdev); + err = -ENOMEM; + goto err_enable; + } + + priv = netdev_priv(lmacp->netdev); + *priv = lmacp; + } + err = bgx_init_phy(bgx); if (err) goto err_enable; @@ -1692,8 +1702,10 @@ static void bgx_remove(struct pci_dev *pdev) u8 lmac; /* Disable all LMACs */ - for (lmac = 0; lmac < bgx->lmac_count; lmac++) + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { bgx_lmac_disable(bgx, lmac); + free_netdev(bgx->lmac[lmac].netdev); + } pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 786ceae34488..dd9e68465e69 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs, * in the Compressed Filter Tuple. */ if (tp->vlan_shift >= 0 && fs->mask.ivlan) - ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift; + ntuple |= (u64)(FT_VLAN_VLD_F | + fs->val.ivlan) << tp->vlan_shift; if (tp->port_shift >= 0 && fs->mask.iport) ntuple |= (u64)fs->val.iport << tp->port_shift; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index fddfd1dd5070..4c546c3aef0f 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -572,7 +572,7 @@ static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed) (*processed)++; return true; - drop: +drop: /* Clean rxdes0 (which resets own bit) */ rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask); priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer); @@ -656,6 +656,11 @@ static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv) ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat); txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask); + /* Ensure the descriptor config is visible before setting the tx + * pointer. + */ + smp_wmb(); + priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer); return true; @@ -809,6 +814,11 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, dma_wmb(); first->txdes0 = cpu_to_le32(f_ctl_stat); + /* Ensure the descriptor config is visible before setting the tx + * pointer. + */ + smp_wmb(); + /* Update next TX pointer */ priv->tx_pointer = pointer; @@ -829,7 +839,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; - dma_err: +dma_err: if (net_ratelimit()) netdev_err(netdev, "map tx fragment failed\n"); @@ -851,7 +861,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, * last fragment, so we know ftgmac100_free_tx_packet() * hasn't freed the skb yet. */ - drop: +drop: /* Drop the packet */ dev_kfree_skb_any(skb); netdev->stats.tx_dropped++; @@ -1344,7 +1354,7 @@ static void ftgmac100_reset(struct ftgmac100 *priv) ftgmac100_init_all(priv, true); netdev_dbg(netdev, "Reset done !\n"); - bail: +bail: if (priv->mii_bus) mutex_unlock(&priv->mii_bus->mdio_lock); if (netdev->phydev) @@ -1543,15 +1553,15 @@ static int ftgmac100_open(struct net_device *netdev) return 0; - err_ncsi: +err_ncsi: napi_disable(&priv->napi); netif_stop_queue(netdev); - err_alloc: +err_alloc: ftgmac100_free_buffers(priv); free_irq(netdev->irq, netdev); - err_irq: +err_irq: netif_napi_del(&priv->napi); - err_hw: +err_hw: iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); ftgmac100_free_rings(priv); return err; diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h index 63b3e02fab16..4968f6f0bdbc 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.h +++ b/drivers/net/ethernet/faraday/ftgmac100.h @@ -84,7 +84,7 @@ FTGMAC100_INT_RPKT_BUF) /* All the interrupts we care about */ -#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF | \ +#define FTGMAC100_INT_ALL (FTGMAC100_INT_RXTX | \ FTGMAC100_INT_BAD) /* diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cfe6b57b1da0..4a55e521c17e 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2272,12 +2272,12 @@ static netdev_tx_t dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) { const int queue_mapping = skb_get_queue_mapping(skb); - bool nonlinear = skb_is_nonlinear(skb); struct rtnl_link_stats64 *percpu_stats; struct dpaa_percpu_priv *percpu_priv; struct netdev_queue *txq; struct dpaa_priv *priv; struct qm_fd fd; + bool nonlinear; int offset = 0; int err = 0; @@ -2287,6 +2287,13 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) qm_fd_clear_fd(&fd); + /* Packet data is always read as 32-bit words, so zero out any part of + * the skb which might be sent if we have to pad the packet + */ + if (__skb_put_padto(skb, ETH_ZLEN, false)) + goto enomem; + + nonlinear = skb_is_nonlinear(skb); if (!nonlinear) { /* We're going to store the skb backpointer at the beginning * of the data buffer, so we need a privately owned skb diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index a71f848adc05..a293b08f36d4 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw) static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw) { - int *count, i; + int *count, ret, i; for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) { + ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid); count = ðsw->buf_count; - *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid); + *count += ret; - if (unlikely(*count < BUFS_PER_CMD)) + if (unlikely(ret < BUFS_PER_CMD)) return -ENOMEM; } diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index e32f6724f568..2e4f3e1782a2 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -775,6 +775,9 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + if (fep->pps_enable) + fec_ptp_enable_pps(fep, 0); + cancel_delayed_work_sync(&fep->time_keep); hrtimer_cancel(&fep->perout_timer); if (fep->ptp_clock) diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 3480ff5c7ed6..5a8b490ab3ad 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -495,7 +495,7 @@ static int gve_set_channels(struct net_device *netdev, return -EINVAL; } - if (!netif_carrier_ok(netdev)) { + if (!netif_running(netdev)) { priv->tx_cfg.num_queues = new_tx; priv->rx_cfg.num_queues = new_rx; return 0; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 9744b426940e..661566db68c8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1566,7 +1566,7 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, u32 status; old_prog = READ_ONCE(priv->xdp_prog); - if (!netif_carrier_ok(priv->dev)) { + if (!netif_running(priv->dev)) { WRITE_ONCE(priv->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); @@ -1847,7 +1847,7 @@ int gve_adjust_queues(struct gve_priv *priv, rx_alloc_cfg.qcfg = &new_rx_config; tx_alloc_cfg.num_rings = new_tx_config.num_queues; - if (netif_carrier_ok(priv->dev)) { + if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; } @@ -2064,7 +2064,7 @@ static int gve_set_features(struct net_device *netdev, if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) { netdev->features ^= NETIF_F_LRO; - if (netif_carrier_ok(netdev)) { + if (netif_running(netdev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); if (err) goto revert_features; @@ -2359,7 +2359,7 @@ err: int gve_reset(struct gve_priv *priv, bool attempt_teardown) { - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); int err; dev_info(&priv->pdev->dev, "Performing reset\n"); @@ -2700,7 +2700,7 @@ static void gve_shutdown(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct gve_priv *priv = netdev_priv(netdev); - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); rtnl_lock(); if (was_up && gve_close(priv->dev)) { @@ -2718,7 +2718,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); struct gve_priv *priv = netdev_priv(netdev); - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); priv->suspend_cnt++; rtnl_lock(); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a5fc0209d628..4cbc4d069a1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) struct net_device *netdev = handle->kinfo.netdev; struct hns3_nic_priv *priv = netdev_priv(netdev); + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + hns3_nic_net_stop(netdev); + if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) { netdev_warn(netdev, "already uninitialized\n"); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index e132c2f09560..cc7f46c0b35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1598,8 +1598,7 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) { u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0}; struct hclge_mod_reg_common_msg msg; - u8 i, j, num; - u32 loop_time; + u8 i, j, num, loop_time; num = ARRAY_SIZE(hclge_ssu_reg_common_msg); for (i = 0; i < num; i++) { @@ -1609,7 +1608,8 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) loop_time = 1; loop_para[0] = 0; if (msg.need_para) { - loop_time = hdev->ae_dev->dev_specs.tnl_num; + loop_time = min(hdev->ae_dev->dev_specs.tnl_num, + HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE); for (j = 0; j < loop_time; j++) loop_para[j] = j + 1; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 82574ce0194f..6c33195a1168 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + + if (ret) + return ret; - return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + hdev->hw.mac.req_speed = speed; + hdev->hw.mac.req_duplex = duplex; + + return 0; } static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) @@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev) if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) hdev->hw.mac.duplex = HCLGE_MAC_FULL; - ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, - hdev->hw.mac.duplex, hdev->hw.mac.lane_num); - if (ret) - return ret; - if (hdev->hw.mac.support_autoneg) { ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg); if (ret) return ret; } + if (!hdev->hw.mac.autoneg) { + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed, + hdev->hw.mac.req_duplex, + hdev->hw.mac.lane_num); + if (ret) + return ret; + } + mac->link = 0; if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) { @@ -11444,7 +11456,7 @@ static void hclge_pci_uninit(struct hclge_dev *hdev) pcim_iounmap(pdev, hdev->hw.hw.io_base); pci_free_irq_vectors(pdev); - pci_release_mem_regions(pdev); + pci_release_regions(pdev); pci_disable_device(pdev); } @@ -11516,8 +11528,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev) dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static void hclge_clear_resetting_state(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 85fb11de43a1..80079657afeb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev) if (ret) netdev_err(netdev, "failed to adjust link.\n"); + hdev->hw.mac.req_speed = (u32)speed; + hdev->hw.mac.req_duplex = (u8)duplex; + ret = hclge_cfg_flowctrl(hdev); if (ret) netdev_err(netdev, "failed to configure flow control.\n"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3735d2fed11f..094a7c7b5592 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev) ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static u32 hclgevf_get_fw_version(struct hnae3_handle *handle) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 00fed5a61d62..62ef8e2fb5f1 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) return -EIO; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pf->hw.bus.func; + attrs.phys.port_number = pf->hw.pf_id; /* As FW supports only port split options for whole device, * set port split options only for first PF. @@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) return -EINVAL; attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = pf->hw.bus.func; + attrs.pci_vf.pf = pf->hw.pf_id; attrs.pci_vf.vf = vf->vf_id; ice_devlink_set_switch_id(pf, &attrs.switch_id); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 99a75a59078e..ce8b5505b16d 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -318,6 +318,7 @@ enum ice_vsi_state { ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, + ICE_VSI_REBUILD_PENDING, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -411,6 +412,7 @@ struct ice_vsi { struct ice_tx_ring **xdp_rings; /* XDP ring array */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ + struct mutex xdp_state_lock; struct net_device **target_netdevs; @@ -765,18 +767,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi, } /** - * ice_xsk_pool - get XSK buffer pool bound to a ring + * ice_rx_xsk_pool - assign XSK buff pool to Rx ring * @ring: Rx ring to use * - * Returns a pointer to xsk_buff_pool structure if there is a buffer pool - * present, NULL otherwise. + * Sets XSK buff pool pointer on Rx ring. */ -static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) +static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring) { struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - return ice_get_xp_from_qid(vsi, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** @@ -801,7 +802,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) if (!ring) return; - ring->xsk_pool = ice_get_xp_from_qid(vsi, qid); + WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 5d396c1a7731..c158749a80e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_tx_ring(tx_ring, q_vector->tx) { - ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX, - NULL); + ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx) tx_ring->q_vector = NULL; - } - ice_for_each_rx_ring(rx_ring, q_vector->rx) { - ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX, - NULL); + + ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx) rx_ring->q_vector = NULL; - } /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) @@ -513,6 +508,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) } /** + * ice_get_frame_sz - calculate xdp_buff::frame_sz + * @rx_ring: the ring being configured + * + * Return frame size based on underlying PAGE_SIZE + */ +static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) +{ + unsigned int frame_sz; + +#if (PAGE_SIZE >= 8192) + frame_sz = rx_ring->rx_buf_len; +#else + frame_sz = ice_rx_pg_size(rx_ring) / 2; +#endif + + return frame_sz; +} + +/** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured * @@ -536,7 +550,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return err; } - ring->xsk_pool = ice_xsk_pool(ring); + ice_rx_xsk_pool(ring); if (ring->xsk_pool) { xdp_rxq_info_unreg(&ring->xdp_rxq); @@ -576,7 +590,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } } - xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); @@ -597,7 +611,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return 0; } - ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs); if (!ok) { u16 pf_q = ring->vsi->rxq_map[ring->q_index]; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 8c990c976132..bc79ba974e49 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4673,10 +4673,10 @@ static int ice_get_port_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, if (err) return err; - fec_stats->uncorrectable_blocks.total = (fec_corr_high_val << 16) + - fec_corr_low_val; - fec_stats->corrected_blocks.total = (fec_uncorr_high_val << 16) + - fec_uncorr_low_val; + fec_stats->corrected_blocks.total = (fec_corr_high_val << 16) + + fec_corr_low_val; + fec_stats->uncorrectable_blocks.total = (fec_uncorr_high_val << 16) + + fec_uncorr_low_val; return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f559e60992fa..2405e5ed9128 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -447,6 +447,7 @@ static void ice_vsi_free(struct ice_vsi *vsi) ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); + mutex_destroy(&vsi->xdp_state_lock); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); } @@ -626,6 +627,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, pf->next_vsi); + mutex_init(&vsi->xdp_state_lock); + unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -2286,9 +2289,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi) ice_vsi_map_rings_to_vectors(vsi); - /* Associate q_vector rings to napi */ - ice_vsi_set_napi_queues(vsi); - vsi->stat_offsets_loaded = false; /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -2413,20 +2413,13 @@ void ice_vsi_decfg(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; int err; - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && - !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); if (err) dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", vsi->vsi_num, err); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) /* return value check can be skipped here, it always returns * 0 if reset is in progress */ @@ -2528,7 +2521,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (q = 0; q < q_vector->num_ring_tx; q++) { ice_write_itr(&q_vector->tx, 0); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - if (ice_is_xdp_ena_vsi(vsi)) { + if (vsi->xdp_rings) { u32 xdp_txq = txq + vsi->num_xdp_txq; wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0); @@ -2628,6 +2621,7 @@ void ice_vsi_close(struct ice_vsi *vsi) if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) ice_down(vsi); + ice_vsi_clear_napi_queues(vsi); ice_vsi_free_irq(vsi); ice_vsi_free_tx_rings(vsi); ice_vsi_free_rx_rings(vsi); @@ -2671,8 +2665,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { - if (test_bit(ICE_VSI_DOWN, vsi->state)) - return; + bool already_down = test_bit(ICE_VSI_DOWN, vsi->state); set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); @@ -2680,134 +2673,70 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); - - ice_vsi_close(vsi); + already_down = test_bit(ICE_VSI_DOWN, vsi->state); + if (!already_down) + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); - } else { + } else if (!already_down) { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL && !already_down) { ice_vsi_close(vsi); } } /** - * __ice_queue_set_napi - Set the napi instance for the queue - * @dev: device to which NAPI and queue belong - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context - * @locked: is the rtnl_lock already held - * - * Set the napi instance for the queue. Caller indicates the lock status. - */ -static void -__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi, - bool locked) -{ - if (!locked) - rtnl_lock(); - netif_queue_set_napi(dev, queue_index, type, napi); - if (!locked) - rtnl_unlock(); -} - -/** - * ice_queue_set_napi - Set the napi instance for the queue - * @vsi: VSI being configured - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context + * ice_vsi_set_napi_queues - associate netdev queues with napi + * @vsi: VSI pointer * - * Set the napi instance for the queue. The rtnl lock state is derived from the - * execution path. + * Associate queue[s] with napi for all vectors. + * The caller must hold rtnl_lock. */ -void -ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi) +void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - if (!vsi->netdev) + if (!netdev) return; - if (current_work() == &pf->serv_task || - test_bit(ICE_PREPARED_FOR_RESET, pf->state) || - test_bit(ICE_DOWN, pf->state) || - test_bit(ICE_SUSPENDED, pf->state)) - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - false); - else - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - true); -} - -/** - * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * @locked: is the rtnl_lock already held - * - * Associate the q_vector napi with all the queue[s] on the vector. - * Caller indicates the lock status. - */ -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked) -{ - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; - - ice_for_each_rx_ring(rx_ring, q_vector->rx) - __ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi, - locked); + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, + &vsi->rx_rings[q_idx]->q_vector->napi); - ice_for_each_tx_ring(tx_ring, q_vector->tx) - __ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi, - locked); + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); -} - -/** - * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * - * Associate the q_vector napi with all the queue[s] on the vector - */ -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector) -{ - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; - - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_queue_set_napi(q_vector->vsi, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi); + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_queue_set_napi(q_vector->vsi, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi); - /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + } } /** - * ice_vsi_set_napi_queues + * ice_vsi_clear_napi_queues - dissociate netdev queues from napi * @vsi: VSI pointer * - * Associate queue[s] with napi for all vectors + * Clear the association between all VSI queues queue[s] and napi. + * The caller must hold rtnl_lock. */ -void ice_vsi_set_napi_queues(struct ice_vsi *vsi) +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { - int i; + struct net_device *netdev = vsi->netdev; + int q_idx; - if (!vsi->netdev) + if (!netdev) return; - ice_for_each_q_vector(vsi, i) - ice_q_vector_set_napi_queues(vsi->q_vectors[i]); + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); + + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL); } /** @@ -2828,6 +2757,14 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_rss_clean(vsi); ice_vsi_close(vsi); + + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped + */ + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + ice_cfg_sw_lldp(vsi, false, false); + ice_vsi_decfg(vsi); /* retain SW VSI data structure since it is needed to unregister and @@ -3039,19 +2976,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; + mutex_lock(&vsi->xdp_state_lock); + ret = ice_vsi_realloc_stat_arrays(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; ice_vsi_decfg(vsi); ret = ice_vsi_cfg_def(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (!coalesce) - return -ENOMEM; + if (!coalesce) { + ret = -ENOMEM; + goto decfg; + } prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); @@ -3059,22 +3000,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (ret) { if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vsi_cfg_tc_lan; + goto free_coalesce; } - kfree(coalesce); - return ice_schedule_reset(pf, ICE_RESET_PFR); + ret = ice_schedule_reset(pf, ICE_RESET_PFR); + goto free_coalesce; } ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); - kfree(coalesce); - - return 0; + clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state); -err_vsi_cfg_tc_lan: - ice_vsi_decfg(vsi); +free_coalesce: kfree(coalesce); -err_vsi_cfg: +decfg: + if (ret) + ice_vsi_decfg(vsi); +unlock: + mutex_unlock(&vsi->xdp_state_lock); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 94ce8964dda6..36d86535695d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); -void -ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi); - -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked); - -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector); - void ice_vsi_set_napi_queues(struct ice_vsi *vsi); +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi); + int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ec636be4d17d..ea780d468579 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -559,6 +559,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + synchronize_irq(pf->oicr_irq.virq); + ice_unplug_aux_dev(pf); /* Notify VFs of impending reset */ @@ -606,11 +608,15 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt)); } } + + if (vsi->netdev) + netif_device_detach(vsi->netdev); skip: /* clear SW filtering DB */ ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ + set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state); ice_pf_dis_all_vsi(pf, false); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) @@ -2948,7 +2954,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) { struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; - if (rx_ring->xsk_pool) + if (READ_ONCE(rx_ring->xsk_pool)) napi_schedule(&rx_ring->q_vector->napi); } } @@ -2999,8 +3005,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; - bool if_running = netif_running(vsi->netdev); int ret = 0, xdp_ring_err = 0; + bool if_running; if (prog && !prog->aux->xdp_has_frags) { if (frame_size > ice_max_xdp_frame_size(vsi)) { @@ -3011,13 +3017,17 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } /* hot swap progs and avoid toggling link */ - if (ice_is_xdp_ena_vsi(vsi) == !!prog) { + if (ice_is_xdp_ena_vsi(vsi) == !!prog || + test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) { ice_vsi_assign_bpf_prog(vsi, prog); return 0; } + if_running = netif_running(vsi->netdev) && + !test_and_set_bit(ICE_VSI_DOWN, vsi->state); + /* need to stop netdev while setting up the program for Rx rings */ - if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + if (if_running) { ret = ice_down(vsi); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); @@ -3083,21 +3093,28 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ice_netdev_priv *np = netdev_priv(dev); struct ice_vsi *vsi = np->vsi; + int ret; if (vsi->type != ICE_VSI_PF) { NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI"); return -EINVAL; } + mutex_lock(&vsi->xdp_state_lock); + switch (xdp->command) { case XDP_SETUP_PROG: - return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + break; case XDP_SETUP_XSK_POOL: - return ice_xsk_pool_setup(vsi, xdp->xsk.pool, - xdp->xsk.queue_id); + ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); + break; default: - return -EINVAL; + ret = -EINVAL; } + + mutex_unlock(&vsi->xdp_state_lock); + return ret; } /** @@ -3553,11 +3570,9 @@ static void ice_napi_add(struct ice_vsi *vsi) if (!vsi->netdev) return; - ice_for_each_q_vector(vsi, v_idx) { + ice_for_each_q_vector(vsi, v_idx) netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, ice_napi_poll); - __ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false); - } } /** @@ -5348,7 +5363,6 @@ err_load: ice_deinit(pf); err_init: ice_adapter_put(pdev); - pci_disable_device(pdev); return err; } @@ -5455,7 +5469,6 @@ static void ice_remove(struct pci_dev *pdev) ice_set_wake(pf); ice_adapter_put(pdev); - pci_disable_device(pdev); } /** @@ -5535,7 +5548,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) if (ret) goto err_reinit; ice_vsi_map_rings_to_vectors(pf->vsi[v]); + rtnl_lock(); ice_vsi_set_napi_queues(pf->vsi[v]); + rtnl_unlock(); } ret = ice_req_irq_msix_misc(pf); @@ -5549,8 +5564,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) err_reinit: while (v--) - if (pf->vsi[v]) + if (pf->vsi[v]) { + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); + } return ret; } @@ -5615,6 +5634,9 @@ static int ice_suspend(struct device *dev) ice_for_each_vsi(pf, v) { if (!pf->vsi[v]) continue; + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); } ice_clear_interrupt_scheme(pf); @@ -7228,7 +7250,7 @@ int ice_down(struct ice_vsi *vsi) if (tx_err) netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", vsi->vsi_num, tx_err); - if (!tx_err && ice_is_xdp_ena_vsi(vsi)) { + if (!tx_err && vsi->xdp_rings) { tx_err = ice_vsi_stop_xdp_tx_rings(vsi); if (tx_err) netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n", @@ -7245,7 +7267,7 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) ice_for_each_xdp_txq(vsi, i) ice_clean_tx_ring(vsi->xdp_rings[i]); @@ -7450,6 +7472,8 @@ int ice_vsi_open(struct ice_vsi *vsi) err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); if (err) goto err_set_qs; + + ice_vsi_set_napi_queues(vsi); } err = ice_up_complete(vsi); @@ -7587,6 +7611,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf) */ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { + struct ice_vsi *vsi = ice_get_main_vsi(pf); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; bool dvm; @@ -7729,6 +7754,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_rebuild_arfs(pf); } + if (vsi && vsi->netdev) + netif_device_attach(vsi->netdev); + ice_update_pf_netdev_link(pf); /* tell the firmware we are up */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e2786cc13286..ef2e858f49bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1477,6 +1477,10 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; + /* Skip HW writes if reset is in progress */ + if (pf->hw.reset_ongoing) + return; + switch (hw->ptp.phy_model) { case ICE_PHY_E810: /* Do not reconfigure E810 PHY */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index fe8847184cb1..79d91e95358c 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -3194,7 +3194,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) - return 0; + return -EEXIST; /* Update the previously created VSI list set with * the new VSI ID passed in @@ -3264,7 +3264,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, list_head = &sw->recp_list[recp_id].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { - if (list_itr->vsi_list_info) { + if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { map_info = list_itr->vsi_list_info; if (test_bit(vsi_handle, map_info->vsi_map)) { *vsi_list_id = map_info->vsi_list_id; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8bb743f78fcb..c9bc3f1add5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - rx_ring->xdp_prog = NULL; + WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; @@ -522,30 +522,6 @@ err: } /** - * ice_rx_frame_truesize - * @rx_ring: ptr to Rx ring - * @size: size - * - * calculate the truesize with taking into the account PAGE_SIZE of - * underlying arch - */ -static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) -{ - unsigned int truesize; - -#if (PAGE_SIZE < 8192) - truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else - truesize = rx_ring->rx_offset ? - SKB_DATA_ALIGN(rx_ring->rx_offset + size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : - SKB_DATA_ALIGN(size); -#endif - return truesize; -} - -/** * ice_run_xdp - Executes an XDP program on initialized xdp_buff * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program @@ -837,16 +813,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) if (!dev_page_is_reusable(page)) return false; -#if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; -#else +#if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) + (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; -#endif /* PAGE_SIZE < 8192) */ +#endif /* PAGE_SIZE >= 8192) */ /* If we have drained the page fragment pool we need to update * the pagecnt_bias and page count so that we fully restock the @@ -949,12 +924,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = -#if (PAGE_SIZE < 8192) - page_count(rx_buf->page); -#else - 0; -#endif + rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page); if (!size) @@ -1160,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) bool failure; u32 first; - /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ -#if (PAGE_SIZE < 8192) - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); -#endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1223,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) hard_start = page_address(rx_buf->page) + rx_buf->page_offset - offset; xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); -#if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); -#endif xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { break; @@ -1521,10 +1482,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_tx_ring(tx_ring, q_vector->tx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool); bool wd; - if (tx_ring->xsk_pool) - wd = ice_xmit_zc(tx_ring); + if (xsk_pool) + wd = ice_xmit_zc(tx_ring, xsk_pool); else if (ice_ring_is_xdp(tx_ring)) wd = true; else @@ -1550,6 +1512,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = budget; ice_for_each_rx_ring(rx_ring, q_vector->rx) { + struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool); int cleaned; /* A dedicated path for zero-copy allows making a single @@ -1557,7 +1520,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * ice_clean_rx_irq function and makes the codebase cleaner. */ cleaned = rx_ring->xsk_pool ? - ice_clean_rx_irq_zc(rx_ring, budget_per_ring) : + ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) : ice_clean_rx_irq(rx_ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a65955eb23c0..5dee829bfc47 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -39,7 +39,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats)); memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0, sizeof(vsi_stat->tx_ring_stats[q_idx]->stats)); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0, sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats)); } @@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) { - synchronize_rcu(); + if (vsi->xdp_rings) ice_clean_tx_ring(vsi->xdp_rings[q_idx]); - } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, * ice_qvec_cfg_msix - Enable IRQ for given queue vector * @vsi: the VSI that contains queue vector * @q_vector: queue vector + * @qid: queue index */ static void -ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) +ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid) { u16 reg_idx = q_vector->reg_idx; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; + int q, _qid = qid; ice_cfg_itr(hw, q_vector); - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx, - q_vector->tx.itr_idx); + for (q = 0; q < q_vector->num_ring_tx; q++) { + ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx); + _qid++; + } + + _qid = qid; - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx, - q_vector->rx.itr_idx); + for (q = 0; q < q_vector->num_ring_rx; q++) { + ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx); + _qid++; + } ice_flush(hw); } @@ -163,7 +165,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) struct ice_q_vector *q_vector; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - int timeout = 50; + int fail = 0; int err; if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) @@ -173,40 +175,33 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) rx_ring = vsi->rx_rings[q_idx]; q_vector = rx_ring->q_vector; - while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) { - timeout--; - if (!timeout) - return -EBUSY; - usleep_range(1000, 2000); - } + synchronize_net(); + netif_carrier_off(vsi->netdev); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_qvec_dis_irq(vsi, rx_ring, q_vector); ice_qvec_toggle_napi(vsi, q_vector, false); - netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); - if (err) - return err; - if (ice_is_xdp_ena_vsi(vsi)) { + if (!fail) + fail = err; + if (vsi->xdp_rings) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(&txq_meta, 0, sizeof(txq_meta)); ice_fill_txq_meta(vsi, xdp_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring, &txq_meta); - if (err) - return err; + if (!fail) + fail = err; } - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); - if (err) - return err; + ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); - return 0; + return fail; } /** @@ -219,40 +214,47 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { struct ice_q_vector *q_vector; + int fail = 0; + bool link_up; int err; err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx); - if (err) - return err; + if (!fail) + fail = err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_single_rxq(vsi, q_idx); - if (err) - return err; + if (!fail) + fail = err; q_vector = vsi->rx_rings[q_idx]->q_vector; - ice_qvec_cfg_msix(vsi, q_vector); + ice_qvec_cfg_msix(vsi, q_vector, q_idx); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); - if (err) - return err; + if (!fail) + fail = err; ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); - netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - clear_bit(ICE_CFG_BUSY, vsi->state); + /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */ + synchronize_net(); + ice_get_link_status(vsi->port_info, &link_up); + if (link_up) { + netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + netif_carrier_on(vsi->netdev); + } - return 0; + return fail; } /** @@ -379,7 +381,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) goto failure; } - if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); + if_running = !test_bit(ICE_VSI_DOWN, vsi->state) && + ice_is_xdp_ena_vsi(vsi); if (if_running) { struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; @@ -459,6 +462,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, /** * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Place the @count of descriptors onto Rx ring. Handle the ring wrap @@ -467,7 +471,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, * * Returns true if all allocations were successful, false if any fail. */ -static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; @@ -479,8 +484,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) xdp = ice_xdp_buf(rx_ring, ntu); if (ntu + count >= rx_ring->count) { - nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, - rx_desc, + nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, rx_ring->count - ntu); if (nb_buffs_extra != rx_ring->count - ntu) { ntu += nb_buffs_extra; @@ -493,7 +497,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, 0); } - nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count); + nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count); ntu += nb_buffs; if (ntu == rx_ring->count) @@ -509,6 +513,7 @@ exit: /** * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers * @rx_ring: Rx ring + * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW * @count: The number of buffers to allocate * * Wrapper for internal allocation routine; figure out how many tail @@ -516,7 +521,8 @@ exit: * * Returns true if all calls to internal alloc routine succeeded */ -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) { u16 rx_thresh = ICE_RING_QUARTER(rx_ring); u16 leftover, i, tail_bumps; @@ -525,9 +531,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) leftover = count - (tail_bumps * rx_thresh); for (i = 0; i < tail_bumps; i++) - if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) + if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh)) return false; - return __ice_alloc_rx_bufs_zc(rx_ring, leftover); + return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover); } /** @@ -596,8 +602,10 @@ out: /** * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring + * @xsk_pool: AF_XDP buffer pool pointer */ -static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -648,7 +656,7 @@ skip: if (xdp_ring->next_to_clean >= cnt) xdp_ring->next_to_clean -= cnt; if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + xsk_tx_completed(xsk_pool, xsk_frames); return completed_frames; } @@ -657,6 +665,7 @@ skip: * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX * @xdp: XDP buffer to xmit * @xdp_ring: XDP ring to produce descriptor onto + * @xsk_pool: AF_XDP buffer pool pointer * * note that this function works directly on xdp_buff, no need to convert * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning @@ -666,7 +675,8 @@ skip: * was not enough space on XDP ring */ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, - struct ice_tx_ring *xdp_ring) + struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; @@ -680,7 +690,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, free_space = ICE_DESC_UNUSED(xdp_ring); if (free_space < ICE_RING_QUARTER(xdp_ring)) - free_space += ice_clean_xdp_irq_zc(xdp_ring); + free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); if (unlikely(!free_space)) goto busy; @@ -700,7 +710,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, dma_addr_t dma; dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size); tx_buf->xdp = xdp; tx_buf->type = ICE_TX_BUF_XSK_TX; @@ -742,12 +752,14 @@ busy: * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action + * @xsk_pool: AF_XDP buffer pool pointer * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool) { int err, result = ICE_XDP_PASS; u32 act; @@ -758,7 +770,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (!err) return ICE_XDP_REDIR; - if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS) + if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS) result = ICE_XDP_EXIT; else result = ICE_XDP_CONSUMED; @@ -769,7 +781,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: break; case XDP_TX: - result = ice_xmit_xdp_tx_zc(xdp, xdp_ring); + result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool); if (result == ICE_XDP_CONSUMED) goto out_failure; break; @@ -821,14 +833,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring + * @xsk_pool: AF_XDP buffer pool pointer * @budget: NAPI budget * * Returns number of processed packets on success, remaining budget on failure. */ -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; - struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; u32 ntc = rx_ring->next_to_clean; u32 ntu = rx_ring->next_to_use; struct xdp_buff *first = NULL; @@ -891,7 +905,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring, + xsk_pool); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { @@ -940,7 +955,8 @@ construct_skb: rx_ring->next_to_clean = ntc; entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) - failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); + failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, + entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); @@ -963,17 +979,19 @@ construct_skb: /** * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor * @xdp_ring: XDP ring to produce the HW Tx descriptor on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @desc: AF_XDP descriptor to pull the DMA address and length from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, +static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc, unsigned int *total_bytes) { struct ice_tx_desc *tx_desc; dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); + dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len); tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -986,10 +1004,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, /** * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, +static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, unsigned int *total_bytes) { u16 ntu = xdp_ring->next_to_use; @@ -999,8 +1020,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { dma_addr_t dma; - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len); + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); @@ -1016,60 +1037,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de /** * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from * @nb_pkts: count of packets to be send * @total_bytes: bytes accumulator that will be used for stats update */ -static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, - u32 nb_pkts, unsigned int *total_bytes) +static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, + struct xsk_buff_pool *xsk_pool, + struct xdp_desc *descs, u32 nb_pkts, + unsigned int *total_bytes) { u32 batched, leftover, i; batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); leftover = nb_pkts & (PKTS_PER_BATCH - 1); for (i = 0; i < batched; i += PKTS_PER_BATCH) - ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes); for (; i < batched + leftover; i++) - ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); + ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes); } /** * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @xsk_pool: AF_XDP buffer pool pointer * * Returns true if there is no more work that needs to be done, false otherwise */ -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool) { - struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; + struct xdp_desc *descs = xsk_pool->tx_descs; u32 nb_pkts, nb_processed = 0; unsigned int total_bytes = 0; int budget; - ice_clean_xdp_irq_zc(xdp_ring); + ice_clean_xdp_irq_zc(xdp_ring, xsk_pool); + + if (!netif_carrier_ok(xdp_ring->vsi->netdev) || + !netif_running(xdp_ring->vsi->netdev)) + return true; budget = ICE_DESC_UNUSED(xdp_ring); budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); - nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); if (!nb_pkts) return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { nb_processed = xdp_ring->count - xdp_ring->next_to_use; - ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed, + &total_bytes); xdp_ring->next_to_use = 0; } - ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, - &total_bytes); + ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed], + nb_pkts - nb_processed, &total_bytes); ice_set_rs_bit(xdp_ring); ice_xdp_ring_update_tail(xdp_ring); ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); - if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) - xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); return nb_pkts < budget; } @@ -1091,7 +1121,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_VSI_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) @@ -1102,7 +1132,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, ring = vsi->rx_rings[queue_id]->xdp_ring; - if (!ring->xsk_pool) + if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; /* The idea here is that if NAPI is running, mark a miss, so diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 6fa181f080ef..45adeb513253 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -20,16 +20,20 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); -int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, + int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool); int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else -static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring) +static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, + struct xsk_buff_pool __always_unused *xsk_pool) { return false; } @@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, static inline int ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, int __always_unused budget) { return 0; @@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, static inline bool ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, + struct xsk_buff_pool __always_unused *xsk_pool, u16 __always_unused count) { return false; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 5dbf2b4ba1b0..0b6c8fd5bc90 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -900,8 +900,8 @@ static void idpf_vport_stop(struct idpf_vport *vport) vport->link_up = false; idpf_vport_intr_deinit(vport); - idpf_vport_intr_rel(vport); idpf_vport_queues_rel(vport); + idpf_vport_intr_rel(vport); np->state = __IDPF_VPORT_DOWN; } @@ -1335,9 +1335,8 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport) /** * idpf_vport_open - Bring up a vport * @vport: vport to bring up - * @alloc_res: allocate queue resources */ -static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) +static int idpf_vport_open(struct idpf_vport *vport) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct idpf_adapter *adapter = vport->adapter; @@ -1350,45 +1349,43 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) /* we do not allow interface up just yet */ netif_carrier_off(vport->netdev); - if (alloc_res) { - err = idpf_vport_queues_alloc(vport); - if (err) - return err; - } - err = idpf_vport_intr_alloc(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to allocate interrupts for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + return err; } + err = idpf_vport_queues_alloc(vport); + if (err) + goto intr_rel; + err = idpf_vport_queue_ids_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue ids for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_vport_intr_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize interrupts for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_rx_bufs_init_all(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_queue_reg_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } idpf_rx_init_buf_tail(vport); @@ -1455,10 +1452,10 @@ unmap_queue_vectors: idpf_send_map_unmap_queue_vector_msg(vport, false); intr_deinit: idpf_vport_intr_deinit(vport); -intr_rel: - idpf_vport_intr_rel(vport); queues_rel: idpf_vport_queues_rel(vport); +intr_rel: + idpf_vport_intr_rel(vport); return err; } @@ -1539,7 +1536,7 @@ void idpf_init_task(struct work_struct *work) np = netdev_priv(vport->netdev); np->state = __IDPF_VPORT_DOWN; if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) - idpf_vport_open(vport, true); + idpf_vport_open(vport); /* Spawn and return 'idpf_init_task' work queue until all the * default vports are created @@ -1898,9 +1895,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, goto free_vport; } - err = idpf_vport_queues_alloc(new_vport); - if (err) - goto free_vport; if (current_state <= __IDPF_VPORT_DOWN) { idpf_send_delete_queues_msg(vport); } else { @@ -1932,17 +1926,23 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, err = idpf_set_real_num_queues(vport); if (err) - goto err_reset; + goto err_open; if (current_state == __IDPF_VPORT_UP) - err = idpf_vport_open(vport, false); + err = idpf_vport_open(vport); kfree(new_vport); return err; err_reset: - idpf_vport_queues_rel(new_vport); + idpf_send_add_queues_msg(vport, vport->num_txq, vport->num_complq, + vport->num_rxq, vport->num_bufq); + +err_open: + if (current_state == __IDPF_VPORT_UP) + idpf_vport_open(vport); + free_vport: kfree(new_vport); @@ -2171,7 +2171,7 @@ static int idpf_open(struct net_device *netdev) idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - err = idpf_vport_open(vport, true); + err = idpf_vport_open(vport); idpf_vport_ctrl_unlock(netdev); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index af2879f03b8d..585c3dadd9bf 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3576,9 +3576,7 @@ static void idpf_vport_intr_napi_dis_all(struct idpf_vport *vport) */ void idpf_vport_intr_rel(struct idpf_vport *vport) { - int i, j, v_idx; - - for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { + for (u32 v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; kfree(q_vector->complq); @@ -3593,26 +3591,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport) free_cpumask_var(q_vector->affinity_mask); } - /* Clean up the mapping of queues to vectors */ - for (i = 0; i < vport->num_rxq_grp; i++) { - struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; - - if (idpf_is_queue_model_split(vport->rxq_model)) - for (j = 0; j < rx_qgrp->splitq.num_rxq_sets; j++) - rx_qgrp->splitq.rxq_sets[j]->rxq.q_vector = NULL; - else - for (j = 0; j < rx_qgrp->singleq.num_rxq; j++) - rx_qgrp->singleq.rxqs[j]->q_vector = NULL; - } - - if (idpf_is_queue_model_split(vport->txq_model)) - for (i = 0; i < vport->num_txq_grp; i++) - vport->txq_grps[i].complq->q_vector = NULL; - else - for (i = 0; i < vport->num_txq_grp; i++) - for (j = 0; j < vport->txq_grps[i].num_txq; j++) - vport->txq_grps[i].txqs[j]->q_vector = NULL; - kfree(vport->q_vectors); vport->q_vectors = NULL; } @@ -3780,13 +3758,15 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /** * idpf_vport_intr_req_irq - get MSI-X vectors from the OS for the vport * @vport: main vport structure - * @basename: name for the vector */ -static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) +static int idpf_vport_intr_req_irq(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; + const char *drv_name, *if_name, *vec_name; int vector, err, irq_num, vidx; - const char *vec_name; + + drv_name = dev_driver_string(&adapter->pdev->dev); + if_name = netdev_name(vport->netdev); for (vector = 0; vector < vport->num_q_vectors; vector++) { struct idpf_q_vector *q_vector = &vport->q_vectors[vector]; @@ -3804,8 +3784,8 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) else continue; - name = kasprintf(GFP_KERNEL, "%s-%s-%d", basename, vec_name, - vidx); + name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, + vec_name, vidx); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, name, q_vector); @@ -4326,7 +4306,6 @@ error: */ int idpf_vport_intr_init(struct idpf_vport *vport) { - char *int_name; int err; err = idpf_vport_intr_init_vec_idx(vport); @@ -4340,11 +4319,7 @@ int idpf_vport_intr_init(struct idpf_vport *vport) if (err) goto unroll_vectors_alloc; - int_name = kasprintf(GFP_KERNEL, "%s-%s", - dev_driver_string(&vport->adapter->pdev->dev), - vport->netdev->name); - - err = idpf_vport_intr_req_irq(vport, int_name); + err = idpf_vport_intr_req_irq(vport); if (err) goto unroll_vectors_alloc; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 11be39f435f3..1ef4cb871452 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -33,6 +33,7 @@ #include <linux/bpf_trace.h> #include <linux/pm_runtime.h> #include <linux/etherdevice.h> +#include <linux/lockdep.h> #ifdef CONFIG_IGB_DCA #include <linux/dca.h> #endif @@ -2914,8 +2915,11 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } +/* This function assumes __netif_tx_lock is held by the caller. */ static void igb_xdp_ring_update_tail(struct igb_ring *ring) { + lockdep_assert_held(&txring_txq(ring)->_xmit_lock); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. */ @@ -3000,11 +3004,11 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nxmit++; } - __netif_tx_unlock(nq); - if (unlikely(flags & XDP_XMIT_FLUSH)) igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + return nxmit; } @@ -4808,6 +4812,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, #if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif @@ -6959,10 +6964,20 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) static void igb_tsync_interrupt(struct igb_adapter *adapter) { + const u32 mask = (TSINTR_SYS_WRAP | E1000_TSICR_TXTS | + TSINTR_TT0 | TSINTR_TT1 | + TSINTR_AUTT0 | TSINTR_AUTT1); struct e1000_hw *hw = &adapter->hw; u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; + if (hw->mac.type == e1000_82580) { + /* 82580 has a hardware bug that requires an explicit + * write to clear the TimeSync interrupt cause. + */ + wr32(E1000_TSICR, tsicr & mask); + } + if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) @@ -8853,12 +8868,14 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { + unsigned int total_bytes = 0, total_packets = 0; struct igb_adapter *adapter = q_vector->adapter; struct igb_ring *rx_ring = q_vector->rx.ring; - struct sk_buff *skb = rx_ring->skb; - unsigned int total_bytes = 0, total_packets = 0; u16 cleaned_count = igb_desc_unused(rx_ring); + struct sk_buff *skb = rx_ring->skb; + int cpu = smp_processor_id(); unsigned int xdp_xmit = 0; + struct netdev_queue *nq; struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; @@ -8986,7 +9003,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) if (xdp_xmit & IGB_XDP_TX) { struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); } u64_stats_update_begin(&rx_ring->rx_syncp); diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..511384f3ec5c 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -404,6 +404,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index cb5c7b09e8a0..0a095cdea4fb 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6306,21 +6306,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - break; - case TAPRIO_CMD_DESTROY: - return igc_tsn_clear_schedule(adapter); - case TAPRIO_CMD_STATS: - igc_taprio_stats(adapter->netdev, &qopt->stats); - return 0; - case TAPRIO_CMD_QUEUE_STATS: - igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); - return 0; - default: - return -EOPNOTSUPP; - } - if (qopt->base_time < 0) return -ERANGE; @@ -6330,12 +6315,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; @@ -6429,7 +6418,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: + return -EOPNOTSUPP; + } + if (err) return err; @@ -7408,6 +7413,7 @@ static void igc_io_resume(struct pci_dev *pdev) rtnl_lock(); if (netif_running(netdev)) { if (igc_open(netdev)) { + rtnl_unlock(); netdev_err(netdev, "igc_open failed after reset\n"); return; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..d68fa7f3d5f0 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { @@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -262,14 +311,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } -int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..98ec845a86bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -7,5 +7,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b06e24562973..d8be0e4dcb07 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IP)) return csum; skb_set_network_header(skb, ETH_HLEN); - if ((ip_hdr(skb)->protocol != IPPROTO_UDP) || - (skb->len < (ETH_HLEN + - (ip_hdr(skb)->ihl << 2) + - sizeof(struct udphdr)))) { + + if (ip_hdr(skb)->protocol != IPPROTO_UDP || + skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) { skb_reset_network_header(skb); return csum; } - skb_set_transport_header(skb, - ETH_HLEN + (ip_hdr(skb)->ihl << 2)); + skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb)); csum = udp_hdr(skb)->check; skb_reset_transport_header(skb); skb_reset_network_header(skb); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 8c45ad983abc..0d62a33afa80 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port, static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en) { struct mvpp2_port *port; - int i; + int i, j; for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; if (port->priv->percpu_pools) { - for (i = 0; i < port->nrxqs; i++) - mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i], + for (j = 0; j < port->nrxqs; j++) + mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j], port->tx_fc & en); } else { mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 03ee93fd9e94..db2db0738ee4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -319,6 +319,7 @@ struct nix_mark_format { /* smq(flush) to tl1 cir/pir info */ struct nix_smq_tree_ctx { + u16 schq; u64 cir_off; u64 cir_val; u64 pir_off; @@ -328,8 +329,6 @@ struct nix_smq_tree_ctx { /* smq flush context */ struct nix_smq_flush_ctx { int smq; - u16 tl1_schq; - u16 tl2_schq; struct nix_smq_tree_ctx smq_tree_ctx[NIX_TXSCH_LVL_CNT]; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 3e09d2285814..daf4b951e905 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu, return ret; } -static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) +static bool validate_and_update_reg_offset(struct rvu *rvu, + struct cpt_rd_wr_reg_msg *req, + u64 *reg_offset) { u64 offset = req->reg_offset; int blkaddr, num_lfs, lf; @@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) if (lf < 0) return false; + /* Translate local LF's offset to global CPT LF's offset to + * access LFX register. + */ + *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3); + return true; } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) { /* Registers that can be accessed from PF */ @@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, struct cpt_rd_wr_reg_msg *rsp) { u64 offset = req->reg_offset; - int blkaddr, lf; + int blkaddr; blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); if (blkaddr < 0) @@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, !is_cpt_vf(rvu, req->hdr.pcifunc)) return CPT_AF_ERR_ACCESS_DENIED; - if (!is_valid_offset(rvu, req)) + if (!validate_and_update_reg_offset(rvu, req, &offset)) return CPT_AF_ERR_ACCESS_DENIED; - /* Translate local LF used by VFs to global CPT LF */ - lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc, - (offset & 0xFFF) >> 3); - - /* Translate local LF's offset to global CPT LF's offset */ - offset &= 0xFF000; - offset += lf << 3; - - rsp->reg_offset = offset; + rsp->reg_offset = req->reg_offset; rsp->ret_val = req->ret_val; rsp->is_write = req->is_write; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 222f9e00b836..82832a24fbd8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2259,14 +2259,13 @@ static void nix_smq_flush_fill_ctx(struct rvu *rvu, int blkaddr, int smq, schq = smq; for (lvl = NIX_TXSCH_LVL_SMQ; lvl <= NIX_TXSCH_LVL_TL1; lvl++) { smq_tree_ctx = &smq_flush_ctx->smq_tree_ctx[lvl]; + smq_tree_ctx->schq = schq; if (lvl == NIX_TXSCH_LVL_TL1) { - smq_flush_ctx->tl1_schq = schq; smq_tree_ctx->cir_off = NIX_AF_TL1X_CIR(schq); smq_tree_ctx->pir_off = 0; smq_tree_ctx->pir_val = 0; parent_off = 0; } else if (lvl == NIX_TXSCH_LVL_TL2) { - smq_flush_ctx->tl2_schq = schq; smq_tree_ctx->cir_off = NIX_AF_TL2X_CIR(schq); smq_tree_ctx->pir_off = NIX_AF_TL2X_PIR(schq); parent_off = NIX_AF_TL2X_PARENT(schq); @@ -2301,8 +2300,8 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr, { struct nix_txsch *txsch; struct nix_hw *nix_hw; + int tl2, tl2_schq; u64 regoff; - int tl2; nix_hw = get_nix_hw(rvu->hw, blkaddr); if (!nix_hw) @@ -2310,16 +2309,17 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr, /* loop through all TL2s with matching PF_FUNC */ txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL2]; + tl2_schq = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL2].schq; for (tl2 = 0; tl2 < txsch->schq.max; tl2++) { /* skip the smq(flush) TL2 */ - if (tl2 == smq_flush_ctx->tl2_schq) + if (tl2 == tl2_schq) continue; /* skip unused TL2s */ if (TXSCH_MAP_FLAGS(txsch->pfvf_map[tl2]) & NIX_TXSCHQ_FREE) continue; /* skip if PF_FUNC doesn't match */ if ((TXSCH_MAP_FUNC(txsch->pfvf_map[tl2]) & ~RVU_PFVF_FUNC_MASK) != - (TXSCH_MAP_FUNC(txsch->pfvf_map[smq_flush_ctx->tl2_schq] & + (TXSCH_MAP_FUNC(txsch->pfvf_map[tl2_schq] & ~RVU_PFVF_FUNC_MASK))) continue; /* enable/disable XOFF */ @@ -2361,10 +2361,12 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, int smq, u16 pcifunc, int nixlf) { struct nix_smq_flush_ctx *smq_flush_ctx; + int err, restore_tx_en = 0, i; int pf = rvu_get_pf(pcifunc); u8 cgx_id = 0, lmac_id = 0; - int err, restore_tx_en = 0; - u64 cfg; + u16 tl2_tl3_link_schq; + u8 link, link_level; + u64 cfg, bmap = 0; if (!is_rvu_otx2(rvu)) { /* Skip SMQ flush if pkt count is zero */ @@ -2388,16 +2390,38 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, true); nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, false); - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq)); - /* Do SMQ flush and set enqueue xoff */ - cfg |= BIT_ULL(50) | BIT_ULL(49); - rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg); - /* Disable backpressure from physical link, * otherwise SMQ flush may stall. */ rvu_cgx_enadis_rx_bp(rvu, pf, false); + link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL) & 0x01 ? + NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2; + tl2_tl3_link_schq = smq_flush_ctx->smq_tree_ctx[link_level].schq; + link = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL1].schq; + + /* SMQ set enqueue xoff */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq)); + cfg |= BIT_ULL(50); + rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg); + + /* Clear all NIX_AF_TL3_TL2_LINK_CFG[ENA] for the TL3/TL2 queue */ + for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) { + cfg = rvu_read64(rvu, blkaddr, + NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link)); + if (!(cfg & BIT_ULL(12))) + continue; + bmap |= (1 << i); + cfg &= ~BIT_ULL(12); + rvu_write64(rvu, blkaddr, + NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg); + } + + /* Do SMQ flush and set enqueue xoff */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq)); + cfg |= BIT_ULL(50) | BIT_ULL(49); + rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg); + /* Wait for flush to complete */ err = rvu_poll_reg(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), BIT_ULL(49), true); @@ -2406,6 +2430,17 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, "NIXLF%d: SMQ%d flush failed, txlink might be busy\n", nixlf, smq); + /* Set NIX_AF_TL3_TL2_LINKX_CFG[ENA] for the TL3/TL2 queue */ + for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) { + if (!(bmap & (1 << i))) + continue; + cfg = rvu_read64(rvu, blkaddr, + NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link)); + cfg |= BIT_ULL(12); + rvu_write64(rvu, blkaddr, + NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg); + } + /* clear XOFF on TL2s */ nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, true); nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, false); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 61334a71058c..e212a4ba9275 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL; - if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP; if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP; + hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); } @@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5fd82c67b6ab..d9e241423bc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -130,7 +130,7 @@ struct page_pool; #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 #define MLX5E_DEFAULT_LRO_TIMEOUT 32 -#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 +#define MLX5E_DEFAULT_SHAMPO_TIMEOUT 1024 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3 @@ -998,6 +998,7 @@ void mlx5e_build_ptys2ethtool_map(void); bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode); +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len); void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq); void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 6c9ccccca81e..64b62ed17b07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -928,7 +928,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_headers_entry_size, mlx5e_shampo_get_log_hd_entry_size(mdev, params)); MLX5_SET(rqc, rqc, reservation_timeout, - params->packet_merge.timeout); + mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT)); MLX5_SET(rqc, rqc, shampo_match_criteria_type, params->packet_merge.shampo.match_criteria_type); MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, @@ -1087,6 +1087,20 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, return wqebbs; } +#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 + +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) +{ + int i; + + /* The supported periods are organized in ascending order */ + for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) + if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) + break; + + return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); +} + static u32 mlx5e_mpwrq_total_umr_wqebbs(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 749b2ec0436e..3f8986f9d862 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -108,6 +108,7 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param); +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 22918b2ef7f1..09433b91be17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } + mutex_lock(&priv->state_lock); err = mlx5e_safe_reopen_channels(priv); + mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 8cf8ba2622f2..71a168746ebe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -932,6 +932,7 @@ err_rule: mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: + *attr = *old_attr; kfree(old_attr); err_attr: kvfree(spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 6e00afe4671b..797db853de36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap)) caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD; - if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || - MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)) + if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) && + ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))) caps |= MLX5_IPSEC_CAP_PRIO; if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 00d5661dc62e..1cf3c54d343e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -139,6 +139,10 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT); MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy, ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100BASE_TX, legacy, + ETHTOOL_LINK_MODE_100baseT_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_T, legacy, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT); MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy, ETHTOOL_LINK_MODE_10000baseT_Full_BIT); MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy, @@ -204,6 +208,12 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_8_400GBASE_CR8, ext, + ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT); MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_1_100GBASE_CR_KR, ext, ETHTOOL_LINK_MODE_100000baseKR_Full_BIT, ETHTOOL_LINK_MODE_100000baseSR_Full_BIT, @@ -1409,7 +1419,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + if (err) { + netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err); + goto out; + } + mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc0357..773624bb2c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; } eth_ft = get_flow_table(priv, fs, num_tuples); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6f686fabed44..16b67c457b60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1236,6 +1236,14 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq) rq->mpwqe.actual_wq_head = wq->head; rq->mpwqe.umr_in_progress = 0; rq->mpwqe.umr_completed = 0; + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u16 len; + + len = (shampo->pi - shampo->ci) & shampo->hd_per_wq; + mlx5e_shampo_fill_umr(rq, len); + } } void mlx5e_free_rx_descs(struct mlx5e_rq *rq) @@ -3020,15 +3028,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); @@ -5167,18 +5178,6 @@ const struct net_device_ops mlx5e_netdev_ops = { #endif }; -static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) -{ - int i; - - /* The supported periods are organized in ascending order */ - for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) - if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) - break; - - return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); -} - void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { struct mlx5e_params *params = &priv->channels.params; @@ -5308,7 +5307,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *rq_stats; ASSERT_RTNL(); - if (mlx5e_is_uplink_rep(priv)) + if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) return; channel_stats = priv->channel_stats[i]; @@ -5328,6 +5327,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_sq_stats *sq_stats; ASSERT_RTNL(); + if (!priv->stats_nch) + return; + /* no special case needed for ptp htb etc since txq2sq_stats is kept up * to date for active sq_stats, otherwise get_base_stats takes care of * inactive sqs. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 225da8d691fc..de9d01036c28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -735,6 +735,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) ksm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); + ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); if (!ksm_entries) return 0; @@ -962,26 +963,31 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq) sq->cc = sqcc; } -static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, - struct mlx5e_icosq *sq) +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len) { - struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); - struct mlx5e_shampo_hd *shampo; - /* assume 1:1 relationship between RQ and icosq */ - struct mlx5e_rq *rq = &c->rq; - int end, from, len = umr.len; + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + int end, from, full_len = len; - shampo = rq->mpwqe.shampo; end = shampo->hd_per_wq; from = shampo->ci; - if (from + len > shampo->hd_per_wq) { + if (from + len > end) { len -= end - from; bitmap_set(shampo->bitmap, from, end - from); from = 0; } bitmap_set(shampo->bitmap, from, len); - shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1); + shampo->ci = (shampo->ci + full_len) & (shampo->hd_per_wq - 1); +} + +static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, + struct mlx5e_icosq *sq) +{ + struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); + /* assume 1:1 relationship between RQ and icosq */ + struct mlx5e_rq *rq = &c->rq; + + mlx5e_shampo_fill_umr(rq, umr.len); } int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c index 255bc8b749f9..8587cd572da5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -319,7 +319,7 @@ int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting) return -EPERM; mutex_lock(&esw->state_lock); - if (esw->mode != MLX5_ESWITCH_LEGACY) { + if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw)) { err = -EOPNOTSUPP; goto out; } @@ -339,7 +339,7 @@ int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) if (!mlx5_esw_allowed(esw)) return -EPERM; - if (esw->mode != MLX5_ESWITCH_LEGACY) + if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw)) return -EOPNOTSUPP; *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 20146a2dc7f4..02a3563f51ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -312,6 +312,25 @@ static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw, return err; } +static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type) +{ + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TSAR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw, struct mlx5_vport *vport, u32 max_rate, u32 bw_share) @@ -323,6 +342,9 @@ static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw, void *vport_elem; int err; + if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT)) + return -EOPNOTSUPP; + parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix; MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); @@ -421,6 +443,7 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_esw_rate_group *group; + __be32 *attr; u32 divider; int err; @@ -428,6 +451,12 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex if (!group) return ERR_PTR(-ENOMEM); + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, esw->qos.root_tsar_ix); err = mlx5_create_scheduling_element_cmd(esw->dev, @@ -526,25 +555,6 @@ static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw, return err; } -static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type) -{ - switch (type) { - case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_TSAR; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_VPORT; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_VPORT_TC; - case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: - return MLX5_CAP_QOS(dev, esw_element_type) & - ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; - } - return false; -} - static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; @@ -555,7 +565,8 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) return -EOPNOTSUPP; - if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR) || + !(MLX5_CAP_QOS(dev, esw_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR)) return -EOPNOTSUPP; MLX5_SET(scheduling_context, tsar_ctx, element_type, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 979c49ae6b5c..b43ca0b762c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + struct devlink *devlink = priv_to_devlink(dev); /* if this is the driver that initiated the fw reset, devlink completed the reload */ if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) { @@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); else mlx5_load_one(dev, true); - devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0, + devl_lock(devlink); + devlink_remote_reload_actions_performed(devlink, 0, BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); + devl_unlock(devlink); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index f7b01b3f0cba..1477db7f5307 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -48,6 +48,7 @@ static struct mlx5_irq * irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc) { struct irq_affinity_desc auto_desc = {}; + struct mlx5_irq *irq; u32 irq_index; int err; @@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de else cpu_get(pool, cpumask_first(&af_desc->mask)); } - return mlx5_irq_alloc(pool, irq_index, - cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, - NULL); + irq = mlx5_irq_alloc(pool, irq_index, + cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, + NULL); + if (IS_ERR(irq)) + xa_erase(&pool->irqs, irq_index); + return irq; } /* Looking for the IRQ with the smallest refcount that fits req_mask. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d0871c46b8c5..cf8045b92689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, goto unlock; for (i = 0; i < ldev->ports; i++) { - if (ldev->pf[MLX5_LAG_P1].netdev == slave) { + if (ldev->pf[i].netdev == slave) { port = i; break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c index 234cd00f71a1..b7d4b1a2baf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c @@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } @@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f6deb5a3f820..eeb0b7ea05f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) } static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, - u8 *host_buses, u8 *sd_group) + u8 *host_buses) { u32 out[MLX5_ST_SZ_DW(mpir_reg)]; int err; @@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, if (err) return err; - err = mlx5_query_nic_vport_sd_group(dev, sd_group); - if (err) - return err; - *sdm = MLX5_GET(mpir_reg, out, sdm); *host_buses = MLX5_GET(mpir_reg, out, host_buses); @@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev) if (mlx5_core_is_ecpf(dev)) return 0; + err = mlx5_query_nic_vport_sd_group(dev, &sd_group); + if (err) + return err; + + if (!sd_group) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; - err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + err = mlx5_query_sd(dev, &sdm, &host_buses); if (err) return err; if (!sdm) return 0; - if (!sd_group) - return 0; - group_id = mlx5_sd_group_id(dev, sd_group); if (!mlx5_sd_is_supported(dev, host_buses)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 527da58c7953..2ec33c4a2a3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2142,7 +2142,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health poll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -2177,6 +2176,7 @@ static void shutdown(struct pci_dev *pdev) mlx5_core_info(dev, "Shutdown was called\n"); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); @@ -2217,6 +2217,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */ + { PCI_VDEVICE(MELLANOX, 0x1025) }, /* ConnectX-9 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c index 8bce730b5c5b..db2bd3ad63ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c @@ -28,6 +28,9 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id, { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; + if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP)) + return -EOPNOTSUPP; + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id); MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP); @@ -44,6 +47,10 @@ int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; void *attr; + if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_TSAR) || + !(MLX5_CAP_QOS(mdev, nic_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR)) + return -EOPNOTSUPP; + MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id); MLX5_SET(scheduling_context, sched_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index b2986175d9af..b706f1486504 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) struct mlx5_core_dev *mdev = sf_dev->mdev; set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_drain_health_wq(mdev); mlx5_unload_one(mdev, false); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 042ca0349124..d1db04baa1fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -7,7 +7,7 @@ /* don't try to optimize STE allocation if the stack is too constaraining */ #define DR_RULE_MAX_STES_OPTIMIZED 0 #else -#define DR_RULE_MAX_STES_OPTIMIZED 5 +#define DR_RULE_MAX_STES_OPTIMIZED 2 #endif #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index bc94e75a7aeb..e7777700ee18 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -40,6 +40,7 @@ */ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3 /* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF @@ -175,6 +176,13 @@ enum mlxbf_gige_res { int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv); void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index b157f0f1c5a8..385a56ac7348 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev) if (err) goto napi_deinit; + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX); + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX); + mlxbf_gige_enable_multicast_rx(priv); + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; + unsigned int i; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ; + for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++) + mlxbf_gige_disable_mac_rx_filter(priv, i); + mlxbf_gige_disable_multicast_rx(priv); + mlxbf_gige_disable_promisc(priv); + /* Write initial MAC address to hardware */ mlxbf_gige_initial_mac(priv); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 98a8681c21b9..4d14cb13fd64 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -62,6 +62,8 @@ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 699984358493..eb62620b63c7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -11,15 +11,31 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" -void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, - unsigned int index, u64 dmac) +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv) { void __iomem *base = priv->base; - u64 control; + u64 data; - /* Write destination MAC to specified MAC RX filter */ - writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + - (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; /* Enable MAC receive filter mask for specified index */ control = readq(base + MLXBF_GIGE_CONTROL); @@ -27,6 +43,28 @@ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, writeq(control, base + MLXBF_GIGE_CONTROL); } +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 *dmac) { diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index 86034ea4ba5b..c002ede36402 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -20,7 +20,7 @@ if NET_VENDOR_META config FBNIC tristate "Meta Platforms Host Network Interface" depends on X86_64 || COMPILE_TEST - depends on S390=n + depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI select PHYLINK diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index 51d9423b08a6..f2a5a36fdacd 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -1442,18 +1442,8 @@ static void vcap_api_encode_rule_test(struct kunit *test) vcap_enable_lookups(&test_vctrl, &test_netdev, 0, 0, rule->cookie, false); - vcap_free_rule(rule); - - /* Check that the rule has been freed: tricky to access since this - * memory should not be accessible anymore - */ - KUNIT_EXPECT_PTR_NE(test, NULL, rule); - ret = list_empty(&rule->keyfields); - KUNIT_EXPECT_EQ(test, true, ret); - ret = list_empty(&rule->actionfields); - KUNIT_EXPECT_EQ(test, true, ret); - - vcap_del_rule(&test_vctrl, &test_netdev, id); + ret = vcap_del_rule(&test_vctrl, &test_netdev, id); + KUNIT_EXPECT_EQ(test, 0, ret); } static void vcap_api_set_rule_counter_test(struct kunit *test) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index cafded2f9382..a00f915c5188 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -52,9 +52,33 @@ static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx, return 0; } +static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq, + struct hwc_work_request *req) +{ + struct device *dev = hwc_rxq->hwc->dev; + struct gdma_sge *sge; + int err; + + sge = &req->sge; + sge->address = (u64)req->buf_sge_addr; + sge->mem_key = hwc_rxq->msg_buf->gpa_mkey; + sge->size = req->buf_len; + + memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request)); + req->wqe_req.sgl = sge; + req->wqe_req.num_sge = 1; + req->wqe_req.client_data_unit = 0; + + err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL); + if (err) + dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err); + return err; +} + static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len, - const struct gdma_resp_hdr *resp_msg) + struct hwc_work_request *rx_req) { + const struct gdma_resp_hdr *resp_msg = rx_req->buf_va; struct hwc_caller_ctx *ctx; int err; @@ -62,6 +86,7 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len, hwc->inflight_msg_res.map)) { dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", resp_msg->response.hwc_msg_id); + mana_hwc_post_rx_wqe(hwc->rxq, rx_req); return; } @@ -75,30 +100,13 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len, memcpy(ctx->output_buf, resp_msg, resp_len); out: ctx->error = err; - complete(&ctx->comp_event); -} - -static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq, - struct hwc_work_request *req) -{ - struct device *dev = hwc_rxq->hwc->dev; - struct gdma_sge *sge; - int err; - - sge = &req->sge; - sge->address = (u64)req->buf_sge_addr; - sge->mem_key = hwc_rxq->msg_buf->gpa_mkey; - sge->size = req->buf_len; - memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request)); - req->wqe_req.sgl = sge; - req->wqe_req.num_sge = 1; - req->wqe_req.client_data_unit = 0; + /* Must post rx wqe before complete(), otherwise the next rx may + * hit no_wqe error. + */ + mana_hwc_post_rx_wqe(hwc->rxq, rx_req); - err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL); - if (err) - dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err); - return err; + complete(&ctx->comp_event); } static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, @@ -235,14 +243,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, return; } - mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, resp); + mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req); - /* Do no longer use 'resp', because the buffer is posted to the HW - * in the below mana_hwc_post_rx_wqe(). + /* Can no longer use 'resp', because the buffer is posted to the HW + * in mana_hwc_handle_resp() above. */ resp = NULL; - - mana_hwc_post_rx_wqe(hwc_rxq, rx_req); } static void mana_hwc_tx_event_handler(void *ctx, u32 gdma_txq_id, diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d2f07e179e86..3d151700f658 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM; - *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE; *datasize = mtu + ETH_HLEN; } @@ -1788,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1799,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } @@ -1862,10 +1872,12 @@ static void mana_destroy_txq(struct mana_port_context *apc) for (i = 0; i < apc->num_queues; i++) { napi = &apc->tx_qp[i].tx_cq.napi; - napi_synchronize(napi); - napi_disable(napi); - netif_napi_del(napi); - + if (apc->tx_qp[i].txq.napi_initialized) { + napi_synchronize(napi); + napi_disable(napi); + netif_napi_del(napi); + apc->tx_qp[i].txq.napi_initialized = false; + } mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq); @@ -1921,6 +1933,7 @@ static int mana_create_txq(struct mana_port_context *apc, txq->ndev = net; txq->net_txq = netdev_get_tx_queue(net, i); txq->vp_offset = apc->tx_vp_offset; + txq->napi_initialized = false; skb_queue_head_init(&txq->pending_skbs); memset(&spec, 0, sizeof(spec)); @@ -1987,6 +2000,7 @@ static int mana_create_txq(struct mana_port_context *apc, netif_napi_add_tx(net, &cq->napi, mana_poll); napi_enable(&cq->napi); + txq->napi_initialized = true; mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); } @@ -1998,7 +2012,7 @@ out: } static void mana_destroy_rxq(struct mana_port_context *apc, - struct mana_rxq *rxq, bool validate_state) + struct mana_rxq *rxq, bool napi_initialized) { struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; @@ -2013,15 +2027,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc, napi = &rxq->rx_cq.napi; - if (validate_state) + if (napi_initialized) { napi_synchronize(napi); - napi_disable(napi); + napi_disable(napi); + netif_napi_del(napi); + } xdp_rxq_info_unreg(&rxq->xdp_rxq); - netif_napi_del(napi); - mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); mana_deinit_cq(apc, &rxq->rx_cq); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..3d72aa7b1305 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot, return VLAN_N_VID - bridge_num - 1; } +/** + * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID + * + * @ocelot: Switch private data structure + * @port: Index of ingress port + * + * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN + * component conformance" suggest that a C-VLAN component should only recognize + * and filter on C-Tags, and an S-VLAN component should only recognize and + * process based on C-Tags. + * + * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN + * components are largely represented by a bridge with vlan_protocol 802.1Q, + * and S-VLAN components by a bridge with vlan_protocol 802.1ad. + * + * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware + * design is non-conformant, because the switch assigns each frame to a VLAN + * based on an entirely different question, as detailed in figure "Basic VLAN + * Classification Flow" from its manual and reproduced below. + * + * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register + * if VLAN_AWARE_ENA[port] and frame has outer tag then: + * if VLAN_INNER_TAG_ENA[port] and frame has inner tag then: + * TAG_TYPE = (Frame.InnerTPID <> 0x8100) + * Set PCP, DEI, VID to values from inner VLAN header + * else: + * TAG_TYPE = (Frame.OuterTPID <> 0x8100) + * Set PCP, DEI, VID to values from outer VLAN header + * if VID == 0 then: + * VID = VLAN_CFG.VLAN_VID + * + * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN + * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1 + * (if 802.1ad). It will classify based on whichever of the tags is "outer", no + * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]). + * + * In the VLAN Table, the TAG_TYPE information is not accessible - just the + * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs: + * C-VLAN X, and S-VLAN X. + * + * Whereas the Linux bridge behavior is to only filter on frames with a TPID + * equal to the vlan_protocol, and treat everything else as VLAN-untagged. + * + * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5, + * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame + * should be treated as 802.1Q-untagged, and classified to the PVID of that + * bridge port. Not to VID=3, and not to VID=5. + * + * The VCAP IS1 TCAM has everything we need to overwrite the choices made in + * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key, + * and it can modify the classified VID in the action. Thus, for each port + * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to + * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q + * PVID of the port. This effectively makes it appear to the outside world as + * if those packets were processed as VLAN-untagged. + * + * The rule needs to be updated each time the bridge PVID changes, and needs + * to be deleted if the bridge PVID is deleted, or if the port becomes + * VLAN-unaware. + */ +static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port); + struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1]; + struct ocelot_port *ocelot_port = ocelot->ports[port]; + const struct ocelot_bridge_vlan *pvid_vlan; + struct ocelot_vcap_filter *filter; + int err, val, pcp, dei; + bool vid_replace_ena; + u16 vid; + + pvid_vlan = ocelot_port->pvid_vlan; + vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan; + + filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie, + false); + if (!vid_replace_ena) { + /* If the reclassification filter doesn't need to exist, delete + * it if it was previously installed, and exit doing nothing + * otherwise. + */ + if (filter) + return ocelot_vcap_filter_del(ocelot, filter); + + return 0; + } + + /* The reclassification rule must apply. See if it already exists + * or if it must be created. + */ + + /* Treating as VLAN-untagged means using as classified VID equal to + * the bridge PVID, and PCP/DEI set to the port default QoS values. + */ + vid = pvid_vlan->vid; + val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port); + pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val); + dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL); + + if (filter) { + bool changed = false; + + /* Filter exists, just update it */ + if (filter->action.vid != vid) { + filter->action.vid = vid; + changed = true; + } + if (filter->action.pcp != pcp) { + filter->action.pcp = pcp; + changed = true; + } + if (filter->action.dei != dei) { + filter->action.dei = dei; + changed = true; + } + + if (!changed) + return 0; + + return ocelot_vcap_filter_replace(ocelot, filter); + } + + /* Filter doesn't exist, create it */ + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->ingress_port_mask = BIT(port); + filter->vlan.tpid = OCELOT_VCAP_BIT_1; + filter->prio = 1; + filter->id.cookie = cookie; + filter->id.tc_offload = false; + filter->block_id = VCAP_IS1; + filter->type = OCELOT_VCAP_FILTER_OFFLOAD; + filter->lookup = 0; + filter->action.vid_replace_ena = true; + filter->action.pcp_dei_ena = true; + filter->action.vid = vid; + filter->action.pcp = pcp; + filter->action.dei = dei; + + err = ocelot_vcap_filter_add(ocelot, filter, NULL); + if (err) + kfree(filter); + + return err; +} + /* Default vlan to clasify for untagged frames (may be zero) */ -static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, - const struct ocelot_bridge_vlan *pvid_vlan) +static int ocelot_port_set_pvid(struct ocelot *ocelot, int port, + const struct ocelot_bridge_vlan *pvid_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge); @@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, * happens automatically), but also 802.1p traffic which gets * classified to VLAN 0, but that is always in our RX filter, so it * would get accepted were it not for this setting. + * + * Also, we only support the bridge 802.1Q VLAN protocol, so + * 802.1ad-tagged frames (carrying S-Tags) should be considered + * 802.1Q-untagged, and also dropped. */ if (!pvid_vlan && ocelot_port->vlan_aware) val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA; ocelot_rmw_gix(ocelot, val, ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA, ANA_PORT_DROP_CFG, port); + + return ocelot_update_vlan_reclassify_rule(ocelot, port); } static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot, @@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, ANA_PORT_VLAN_CFG, port); - ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + if (err) + return err; + ocelot_port_manage_port_tag(ocelot, port); return 0; @@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, return err; /* Default ingress vlan classification */ - if (pvid) - ocelot_port_set_pvid(ocelot, port, - ocelot_bridge_vlan_find(ocelot, vid)); + if (pvid) { + err = ocelot_port_set_pvid(ocelot, port, + ocelot_bridge_vlan_find(ocelot, vid)); + if (err) + return err; + } /* Untagged egress vlan clasification */ ocelot_port_manage_port_tag(ocelot, port); @@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return err; /* Ingress */ - if (del_pvid) - ocelot_port_set_pvid(ocelot, port, NULL); + if (del_pvid) { + err = ocelot_port_set_pvid(ocelot, port, NULL); + if (err) + return err; + } /* Egress */ ocelot_port_manage_port_tag(ocelot, port); @@ -1099,6 +1265,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp); +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1317,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err; + lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1394,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS); + lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1193,28 +1405,55 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct net_device *dev = skb->dev; + u64 vlan_tci, tag_type; + int qos_class; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + + qos_class = netdev_get_num_tc(dev) ? + netdev_get_prio_tc_map(dev, skb->priority) : skb->priority; + + memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); + ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_qos_class(ifh, qos_class); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) { - u32 ifh[OCELOT_TAG_LEN / 4] = {0}; + u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; + lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); @@ -1247,6 +1486,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2532,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio) ANA_PORT_QOS_CFG, port); - return 0; + return ocelot_update_vlan_reclassify_rule(ocelot, port); } EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio); @@ -2929,6 +3170,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock); ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..00326ae8c708 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -665,8 +665,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); - memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; } diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 73cdec5ca6a3..5734b86aed5b 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix, vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged); + vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid); vcap_key_set(vcap, &data, VCAP_IS1_HK_VID, tag->vid.value, tag->vid.mask); vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP, diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da..c09dd2e3343c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; @@ -69,6 +71,8 @@ out: if (err < 0) ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index c647033f3ad2..f2f07bf88545 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -32,7 +32,7 @@ #define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */ #define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ #define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ -#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */ +#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 4) /* 4s */ struct ionic_dev_bar { void __iomem *vaddr; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index aa0cc31dfe6e..86774d9922d8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3220,7 +3220,7 @@ int ionic_lif_alloc(struct ionic *ionic) netdev->netdev_ops = &ionic_netdev_ops; ionic_ethtool_set_ops(netdev); - netdev->watchdog_timeo = 2 * HZ; + netdev->watchdog_timeo = 5 * HZ; netif_carrier_off(netdev); lif->identity = lid; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 714d2e804694..3507c2e28110 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4349,7 +4349,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, if (unlikely(!rtl_tx_slots_avail(tp))) { if (net_ratelimit()) netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - goto err_stop_0; + netif_stop_queue(dev); + return NETDEV_TX_BUSY; } opts[1] = rtl8169_tx_vlan_tag(skb); @@ -4405,11 +4406,6 @@ err_dma_0: dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; - -err_stop_0: - netif_stop_queue(dev); - dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; } static unsigned int rtl_last_frag_len(struct sk_buff *skb) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index d3c5306f1c41..93a78fd0737b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -573,8 +573,6 @@ static inline u32 mtl_low_credx_base_addr(const struct dwmac4_addrs *addrs, #define GMAC_PHYIF_CTRLSTATUS_LNKSTS BIT(19) #define GMAC_PHYIF_CTRLSTATUS_JABTO BIT(20) #define GMAC_PHYIF_CTRLSTATUS_FALSECARDET BIT(21) -/* LNKMOD */ -#define GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK 0x1 /* LNKSPEED */ #define GMAC_PHYIF_CTRLSTATUS_SPEED_125 0x2 #define GMAC_PHYIF_CTRLSTATUS_SPEED_25 0x1 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f98741d2607e..31c387cc5f26 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -786,7 +786,7 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) else x->pcs_speed = SPEED_10; - x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK); + x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD); pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed, x->pcs_duplex ? "Full" : "Half"); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 81d9f21086ec..b06b8872b4eb 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -156,12 +156,13 @@ #define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7 /* XDP */ -#define AM65_CPSW_XDP_CONSUMED 2 -#define AM65_CPSW_XDP_REDIRECT 1 +#define AM65_CPSW_XDP_CONSUMED BIT(1) +#define AM65_CPSW_XDP_REDIRECT BIT(0) #define AM65_CPSW_XDP_PASS 0 /* Include headroom compatible with both skb and xdpf */ -#define AM65_CPSW_HEADROOM (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN) +#define AM65_CPSW_HEADROOM_NA (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN) +#define AM65_CPSW_HEADROOM ALIGN(AM65_CPSW_HEADROOM_NA, sizeof(long)) static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave, const u8 *dev_addr) @@ -933,7 +934,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); if (unlikely(!host_desc)) { ndev->stats.tx_dropped++; - return -ENOMEM; + return AM65_CPSW_XDP_CONSUMED; /* drop */ } am65_cpsw_nuss_set_buf_type(tx_chn, host_desc, buf_type); @@ -942,7 +943,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, pkt_len, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(tx_chn->dma_dev, dma_buf))) { ndev->stats.tx_dropped++; - ret = -ENOMEM; + ret = AM65_CPSW_XDP_CONSUMED; /* drop */ goto pool_free; } @@ -977,6 +978,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, /* Inform BQL */ netdev_tx_completed_queue(netif_txq, 1, pkt_len); ndev->stats.tx_errors++; + ret = AM65_CPSW_XDP_CONSUMED; /* drop */ goto dma_unmap; } @@ -996,7 +998,9 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, int desc_idx, int cpu, int *len) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct am65_cpsw_ndev_priv *ndev_priv; struct net_device *ndev = port->ndev; + struct am65_cpsw_ndev_stats *stats; int ret = AM65_CPSW_XDP_CONSUMED; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; @@ -1004,6 +1008,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, struct bpf_prog *prog; struct page *page; u32 act; + int err; prog = READ_ONCE(port->xdp_prog); if (!prog) @@ -1013,6 +1018,9 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, /* XDP prog might have changed packet data and boundaries */ *len = xdp->data_end - xdp->data; + ndev_priv = netdev_priv(ndev); + stats = this_cpu_ptr(ndev_priv->stats); + switch (act) { case XDP_PASS: ret = AM65_CPSW_XDP_PASS; @@ -1023,31 +1031,36 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, xdpf = xdp_convert_buff_to_frame(xdp); if (unlikely(!xdpf)) - break; + goto drop; __netif_tx_lock(netif_txq, cpu); - ret = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf, + err = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf, AM65_CPSW_TX_BUF_TYPE_XDP_TX); __netif_tx_unlock(netif_txq); - if (ret) - break; + if (err) + goto drop; - ndev->stats.rx_bytes += *len; - ndev->stats.rx_packets++; + u64_stats_update_begin(&stats->syncp); + stats->rx_bytes += *len; + stats->rx_packets++; + u64_stats_update_end(&stats->syncp); ret = AM65_CPSW_XDP_CONSUMED; goto out; case XDP_REDIRECT: if (unlikely(xdp_do_redirect(ndev, xdp, prog))) - break; + goto drop; - ndev->stats.rx_bytes += *len; - ndev->stats.rx_packets++; + u64_stats_update_begin(&stats->syncp); + stats->rx_bytes += *len; + stats->rx_packets++; + u64_stats_update_end(&stats->syncp); ret = AM65_CPSW_XDP_REDIRECT; goto out; default: bpf_warn_invalid_xdp_action(ndev, prog, act); fallthrough; case XDP_ABORTED: +drop: trace_xdp_exception(ndev, prog, act); fallthrough; case XDP_DROP: @@ -1056,7 +1069,6 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, page = virt_to_head_page(xdp->data); am65_cpsw_put_page(rx_chn, page, true, desc_idx); - out: return ret; } @@ -1095,7 +1107,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info) } static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, - u32 flow_idx, int cpu) + u32 flow_idx, int cpu, int *xdp_state) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; u32 buf_dma_len, pkt_len, port_id = 0, csum_info; @@ -1114,6 +1126,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, void **swdata; u32 *psdata; + *xdp_state = AM65_CPSW_XDP_PASS; ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_idx, &desc_dma); if (ret) { if (ret != -ENODATA) @@ -1161,15 +1174,13 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, } if (port->xdp_prog) { - xdp_init_buff(&xdp, AM65_CPSW_MAX_PACKET_SIZE, &port->xdp_rxq); - - xdp_prepare_buff(&xdp, page_addr, skb_headroom(skb), + xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq); + xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM, pkt_len, false); - - ret = am65_cpsw_run_xdp(common, port, &xdp, desc_idx, - cpu, &pkt_len); - if (ret != AM65_CPSW_XDP_PASS) - return ret; + *xdp_state = am65_cpsw_run_xdp(common, port, &xdp, desc_idx, + cpu, &pkt_len); + if (*xdp_state != AM65_CPSW_XDP_PASS) + goto allocate; /* Compute additional headroom to be reserved */ headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb); @@ -1193,9 +1204,13 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, stats->rx_bytes += pkt_len; u64_stats_update_end(&stats->syncp); +allocate: new_page = page_pool_dev_alloc_pages(rx_chn->page_pool); - if (unlikely(!new_page)) + if (unlikely(!new_page)) { + dev_err(dev, "page alloc failed\n"); return -ENOMEM; + } + rx_chn->pages[desc_idx] = new_page; if (netif_dormant(ndev)) { @@ -1229,8 +1244,9 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx); int flow = AM65_CPSW_MAX_RX_FLOWS; int cpu = smp_processor_id(); - bool xdp_redirect = false; + int xdp_state_or = 0; int cur_budget, ret; + int xdp_state; int num_rx = 0; /* process every flow */ @@ -1238,12 +1254,11 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) cur_budget = budget - num_rx; while (cur_budget--) { - ret = am65_cpsw_nuss_rx_packets(common, flow, cpu); - if (ret) { - if (ret == AM65_CPSW_XDP_REDIRECT) - xdp_redirect = true; + ret = am65_cpsw_nuss_rx_packets(common, flow, cpu, + &xdp_state); + xdp_state_or |= xdp_state; + if (ret) break; - } num_rx++; } @@ -1251,7 +1266,7 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) break; } - if (xdp_redirect) + if (xdp_state_or & AM65_CPSW_XDP_REDIRECT) xdp_do_flush(); dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget); @@ -1918,12 +1933,13 @@ static int am65_cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf) static int am65_cpsw_ndo_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, u32 flags) { + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; int cpu = smp_processor_id(); int i, nxmit = 0; - tx_chn = &am65_ndev_to_common(ndev)->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES]; + tx_chn = &common->tx_chns[cpu % common->tx_ch_num]; netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); __netif_tx_lock(netif_txq, cpu); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 3e51b3a9b0a5..e3451beed323 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1452,6 +1452,7 @@ static const struct prueth_pdata am654_icssg_pdata = { static const struct prueth_pdata am64x_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_RING, + .quirk_10m_link_issue = 1, .switch_mode = 1, }; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 1d57b047817b..b54bffda027b 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -426,9 +426,9 @@ enum WX_MSCA_CMD_value { #define WX_MIN_RXD 128 #define WX_MIN_TXD 128 -/* Number of Transmit and Receive Descriptors must be a multiple of 8 */ -#define WX_REQ_RX_DESCRIPTOR_MULTIPLE 8 -#define WX_REQ_TX_DESCRIPTOR_MULTIPLE 8 +/* Number of Transmit and Receive Descriptors must be a multiple of 128 */ +#define WX_REQ_RX_DESCRIPTOR_MULTIPLE 128 +#define WX_REQ_TX_DESCRIPTOR_MULTIPLE 128 #define WX_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ #define VMDQ_P(p) p diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index ec54b18c5fe7..a5e9b779c44d 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx) MAC_SYM_PAUSE | MAC_ASYM_PAUSE; config->mac_managed_pm = true; - phy_mode = PHY_INTERFACE_MODE_RGMII_ID; - __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces); + /* The MAC only has add the Tx delay and it can not be modified. + * So just disable TX delay in PHY, and it is does not matter to + * internal phy. + */ + phy_mode = PHY_INTERFACE_MODE_RGMII_RXID; + __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces); phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops); if (IS_ERR(phylink)) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..1223fcc1a8da 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -160,16 +160,17 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ +#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ @@ -308,7 +309,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF -/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */ @@ -435,6 +436,8 @@ struct skbuf_dma_descriptor { * @tx_bytes: TX byte count for statistics * @tx_stat_sync: Synchronization object for TX stats * @dma_err_task: Work structure to process Axi DMA errors + * @stopping: Set when @dma_err_task shouldn't do anything because we are + * about to stop the device. * @tx_irq: Axidma TX IRQ number * @rx_irq: Axidma RX IRQ number * @eth_irq: Ethernet core IRQ number @@ -506,6 +509,7 @@ struct axienet_local { struct u64_stats_sync tx_stat_sync; struct work_struct dma_err_task; + bool stopping; int tx_irq; int rx_irq; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index e342f387c3dd..9eb300fc3590 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p) */ static void axienet_set_multicast_list(struct net_device *ndev) { - int i; + int i = 0; u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev); @@ -450,7 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev) } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; - i = 0; + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -469,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev) axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } } else { @@ -476,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - - for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; - reg |= i; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); - axienet_iow(lp, XAE_AF0_OFFSET, 0); - axienet_iow(lp, XAE_AF1_OFFSET, 0); - } - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } + + for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { + reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg |= i; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + axienet_iow(lp, XAE_FFE_OFFSET, 0); + } } /** @@ -1459,6 +1460,7 @@ static int axienet_init_legacy_dma(struct net_device *ndev) struct axienet_local *lp = netdev_priv(ndev); /* Enable worker thread for Axi DMA error handling */ + lp->stopping = false; INIT_WORK(&lp->dma_err_task, axienet_dma_err_handler); napi_enable(&lp->napi_rx); @@ -1579,6 +1581,9 @@ static int axienet_stop(struct net_device *ndev) dev_dbg(&ndev->dev, "axienet_close()\n"); if (!lp->use_dmaengine) { + WRITE_ONCE(lp->stopping, true); + flush_work(&lp->dma_err_task); + napi_disable(&lp->napi_tx); napi_disable(&lp->napi_rx); } @@ -2153,6 +2158,10 @@ static void axienet_dma_err_handler(struct work_struct *work) dma_err_task); struct net_device *ndev = lp->ndev; + /* Don't bother if we are going to stop anyway */ + if (READ_ONCE(lp->stopping)) + return; + napi_disable(&lp->napi_tx); napi_disable(&lp->napi_rx); @@ -2219,9 +2228,9 @@ static void axienet_dma_err_handler(struct work_struct *work) ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN)); axienet_set_mac_address(ndev, NULL); axienet_set_multicast_list(ndev); - axienet_setoptions(ndev, lp->options); napi_enable(&lp->napi_rx); napi_enable(&lp->napi_tx); + axienet_setoptions(ndev, lp->options); } /** |