diff options
Diffstat (limited to 'drivers/net/ethernet')
158 files changed, 13235 insertions, 5519 deletions
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index b2522e84f482..13eb6a4d98d5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2184,25 +2184,6 @@ error_drop_packet: return NETDEV_TX_OK; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ena_netpoll(struct net_device *netdev) -{ - struct ena_adapter *adapter = netdev_priv(netdev); - int i; - - /* Dont schedule NAPI if the driver is in the middle of reset - * or netdev is down. - */ - - if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags) || - test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) - return; - - for (i = 0; i < adapter->num_queues; i++) - napi_schedule(&adapter->ena_napi[i].napi); -} -#endif /* CONFIG_NET_POLL_CONTROLLER */ - static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev, select_queue_fallback_t fallback) @@ -2368,9 +2349,6 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_change_mtu = ena_change_mtu, .ndo_set_mac_address = NULL, .ndo_validate_addr = eth_validate_addr, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ena_netpoll, -#endif /* CONFIG_NET_POLL_CONTROLLER */ }; static int ena_device_validate_params(struct ena_adapter *adapter, diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 29ebbf582010..9f23703dd509 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1031,6 +1031,7 @@ static int dec_lance_probe(struct device *bdev, const int type) int i, ret; unsigned long esar_base; unsigned char *esar; + const char *desc; if (dec_lance_debug && version_printed++ == 0) printk(version); @@ -1216,19 +1217,20 @@ static int dec_lance_probe(struct device *bdev, const int type) */ switch (type) { case ASIC_LANCE: - printk("%s: IOASIC onboard LANCE", name); + desc = "IOASIC onboard LANCE"; break; case PMAD_LANCE: - printk("%s: PMAD-AA", name); + desc = "PMAD-AA"; break; case PMAX_LANCE: - printk("%s: PMAX onboard LANCE", name); + desc = "PMAX onboard LANCE"; break; } for (i = 0; i < 6; i++) dev->dev_addr[i] = esar[i * 4]; - printk(", addr = %pM, irq = %d\n", dev->dev_addr, dev->irq); + printk("%s: %s, addr = %pM, irq = %d\n", + name, desc, dev->dev_addr, dev->irq); dev->netdev_ops = &lance_netdev_ops; dev->watchdog_timeo = 5*HZ; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 289129011b9f..151bdb629e8a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -878,8 +878,9 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x04, 0x0d01); phy_write(phy_data->phydev, 0x00, 0x9140); - phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->advertising = phy_data->phydev->supported; + phy_data->phydev->supported = PHY_10BT_FEATURES | + PHY_100BT_FEATURES | + PHY_1000BT_FEATURES; phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, @@ -950,8 +951,9 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) reg = phy_read(phy_data->phydev, 0x00); phy_write(phy_data->phydev, 0x00, reg & ~0x00800); - phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->advertising = phy_data->phydev->supported; + phy_data->phydev->supported = (PHY_10BT_FEATURES | + PHY_100BT_FEATURES | + PHY_1000BT_FEATURES); phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, @@ -1495,10 +1497,7 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata) if (!phy_data->phydev) return; - if (phy_data->phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phy_data->phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phy_data->phydev->advertising); if (phy_data->phydev->pause) { XGBE_SET_LP_ADV(lks, Pause); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 0dd59b09060b..7def1cb8ab9d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -870,8 +870,8 @@ err_exit: return err; } -int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) +static int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, + u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 147045757b10..4122553e224b 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -126,8 +126,8 @@ static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv, } /* Ethtool operations */ -static int bcm_sysport_set_rx_csum(struct net_device *dev, - netdev_features_t wanted) +static void bcm_sysport_set_rx_csum(struct net_device *dev, + netdev_features_t wanted) { struct bcm_sysport_priv *priv = netdev_priv(dev); u32 reg; @@ -157,12 +157,10 @@ static int bcm_sysport_set_rx_csum(struct net_device *dev, reg &= ~RXCHK_BRCM_TAG_EN; rxchk_writel(priv, reg, RXCHK_CONTROL); - - return 0; } -static int bcm_sysport_set_tx_csum(struct net_device *dev, - netdev_features_t wanted) +static void bcm_sysport_set_tx_csum(struct net_device *dev, + netdev_features_t wanted) { struct bcm_sysport_priv *priv = netdev_priv(dev); u32 reg; @@ -177,23 +175,24 @@ static int bcm_sysport_set_tx_csum(struct net_device *dev, else reg &= ~tdma_control_bit(priv, TSB_EN); tdma_writel(priv, reg, TDMA_CONTROL); - - return 0; } static int bcm_sysport_set_features(struct net_device *dev, netdev_features_t features) { - netdev_features_t changed = features ^ dev->features; - netdev_features_t wanted = dev->wanted_features; - int ret = 0; + struct bcm_sysport_priv *priv = netdev_priv(dev); - if (changed & NETIF_F_RXCSUM) - ret = bcm_sysport_set_rx_csum(dev, wanted); - if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) - ret = bcm_sysport_set_tx_csum(dev, wanted); + /* Read CRC forward */ + if (!priv->is_lite) + priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD); + else + priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) & + GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT); - return ret; + bcm_sysport_set_rx_csum(dev, features); + bcm_sysport_set_tx_csum(dev, features); + + return 0; } /* Hardware counters must be kept in sync because the order/offset @@ -285,6 +284,8 @@ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = { STAT_MIB_SOFT("alloc_rx_buff_failed", mib.alloc_rx_buff_failed), STAT_MIB_SOFT("rx_dma_failed", mib.rx_dma_failed), STAT_MIB_SOFT("tx_dma_failed", mib.tx_dma_failed), + STAT_MIB_SOFT("tx_realloc_tsb", mib.tx_realloc_tsb), + STAT_MIB_SOFT("tx_realloc_tsb_failed", mib.tx_realloc_tsb_failed), /* Per TX-queue statistics are dynamically appended */ }; @@ -1069,9 +1070,6 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) { u32 reg; - /* Stop monitoring MPD interrupt */ - intrl2_0_mask_set(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG); - /* Disable RXCHK, active filters and Broadcom tag matching */ reg = rxchk_readl(priv, RXCHK_CONTROL); reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK << @@ -1081,6 +1079,17 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) /* Clear the MagicPacket detection logic */ mpd_enable_set(priv, false); + reg = intrl2_0_readl(priv, INTRL2_CPU_STATUS); + if (reg & INTRL2_0_MPD) + netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n"); + + if (reg & INTRL2_0_BRCM_MATCH_TAG) { + reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) & + RXCHK_BRCM_TAG_MATCH_MASK; + netdev_info(priv->netdev, + "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg); + } + netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n"); } @@ -1105,7 +1114,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id) struct bcm_sysport_priv *priv = netdev_priv(dev); struct bcm_sysport_tx_ring *txr; unsigned int ring, ring_bit; - u32 reg; priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) & ~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS); @@ -1131,16 +1139,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id) if (priv->irq0_stat & INTRL2_0_TX_RING_FULL) bcm_sysport_tx_reclaim_all(priv); - if (priv->irq0_stat & INTRL2_0_MPD) - netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n"); - - if (priv->irq0_stat & INTRL2_0_BRCM_MATCH_TAG) { - reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) & - RXCHK_BRCM_TAG_MATCH_MASK; - netdev_info(priv->netdev, - "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg); - } - if (!priv->is_lite) goto out; @@ -1221,6 +1219,7 @@ static void bcm_sysport_poll_controller(struct net_device *dev) static struct sk_buff *bcm_sysport_insert_tsb(struct sk_buff *skb, struct net_device *dev) { + struct bcm_sysport_priv *priv = netdev_priv(dev); struct sk_buff *nskb; struct bcm_tsb *tsb; u32 csum_info; @@ -1231,13 +1230,16 @@ static struct sk_buff *bcm_sysport_insert_tsb(struct sk_buff *skb, /* Re-allocate SKB if needed */ if (unlikely(skb_headroom(skb) < sizeof(*tsb))) { nskb = skb_realloc_headroom(skb, sizeof(*tsb)); - dev_kfree_skb(skb); if (!nskb) { + dev_kfree_skb_any(skb); + priv->mib.tx_realloc_tsb_failed++; dev->stats.tx_errors++; dev->stats.tx_dropped++; return NULL; } + dev_consume_skb_any(skb); skb = nskb; + priv->mib.tx_realloc_tsb++; } tsb = skb_push(skb, sizeof(*tsb)); @@ -1973,16 +1975,14 @@ static int bcm_sysport_open(struct net_device *dev) else gib_set_pad_extension(priv); + /* Apply features again in case we changed them while interface was + * down + */ + bcm_sysport_set_features(dev, dev->features); + /* Set MAC address */ umac_set_hw_addr(priv, dev->dev_addr); - /* Read CRC forward */ - if (!priv->is_lite) - priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD); - else - priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) & - GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT); - phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link, 0, priv->phy_interface); if (!phydev) { @@ -2511,9 +2511,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) dev->netdev_ops = &bcm_sysport_netdev_ops; netif_napi_add(dev, &priv->napi, bcm_sysport_poll, 64); - /* HW supported features, none enabled by default */ - dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_HIGHDMA | - NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + dev->features |= NETIF_F_RXCSUM | NETIF_F_HIGHDMA | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + dev->hw_features |= dev->features; + dev->vlan_features |= dev->features; /* Request the WOL interrupt and advertise suspend if available */ priv->wol_irq_disabled = 1; @@ -2641,9 +2642,6 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) /* UniMAC receive needs to be turned on */ umac_enable_set(priv, CMD_RX_EN, 1); - /* Enable the interrupt wake-up source */ - intrl2_0_mask_clear(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG); - netif_dbg(priv, wol, ndev, "entered WOL mode\n"); return 0; @@ -2716,7 +2714,6 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) struct net_device *dev = dev_get_drvdata(d); struct bcm_sysport_priv *priv = netdev_priv(dev); unsigned int i; - u32 reg; int ret; if (!netif_running(dev)) @@ -2760,12 +2757,8 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) goto out_free_rx_ring; } - /* Enable rxhck */ - if (priv->rx_chk_en) { - reg = rxchk_readl(priv, RXCHK_CONTROL); - reg |= RXCHK_EN; - rxchk_writel(priv, reg, RXCHK_CONTROL); - } + /* Restore enabled features */ + bcm_sysport_set_features(dev, dev->features); rbuf_init(priv); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 046c6c1d97fd..a7a230884a87 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -607,6 +607,8 @@ struct bcm_sysport_mib { u32 alloc_rx_buff_failed; u32 rx_dma_failed; u32 tx_dma_failed; + u32 tx_realloc_tsb; + u32 tx_realloc_tsb_failed; }; /* HW maintains a large list of counters */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 61957b0bbd8c..e2d92548226a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1884,8 +1884,11 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) { tx_pkts++; /* return full budget so NAPI will complete. */ - if (unlikely(tx_pkts > bp->tx_wake_thresh)) + if (unlikely(tx_pkts > bp->tx_wake_thresh)) { rx_pkts = budget; + raw_cons = NEXT_RAW_CMP(raw_cons); + break; + } } else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) { if (likely(budget)) rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event); @@ -1913,7 +1916,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) } raw_cons = NEXT_RAW_CMP(raw_cons); - if (rx_pkts == budget) + if (rx_pkts && rx_pkts == budget) break; } @@ -2027,8 +2030,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget) while (1) { work_done += bnxt_poll_work(bp, bnapi, budget - work_done); - if (work_done >= budget) + if (work_done >= budget) { + if (!budget) + BNXT_CP_DB_REARM(cpr->cp_doorbell, + cpr->cp_raw_cons); break; + } if (!bnxt_has_work(bp, cpr)) { if (napi_complete_done(napi, work_done)) @@ -3010,10 +3017,11 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; - dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, - bp->hwrm_cmd_resp_dma_addr); - - bp->hwrm_cmd_resp_addr = NULL; + if (bp->hwrm_cmd_resp_addr) { + dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, + bp->hwrm_cmd_resp_dma_addr); + bp->hwrm_cmd_resp_addr = NULL; + } } static int bnxt_alloc_hwrm_resources(struct bnxt *bp) @@ -4643,7 +4651,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; enables |= ring_grps ? FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; - enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; + enables |= vnics ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0; req->num_rx_rings = cpu_to_le16(rx_rings); req->num_hw_ring_grps = cpu_to_le16(ring_grps); @@ -8614,7 +8622,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, *max_tx = hw_resc->max_tx_rings; *max_rx = hw_resc->max_rx_rings; *max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp), - hw_resc->max_irqs); + hw_resc->max_irqs - bnxt_get_ulp_msix_num(bp)); *max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs); max_ring_grps = hw_resc->max_hw_ring_grps; if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) { @@ -9050,6 +9058,7 @@ init_err_cleanup_tc: bnxt_clear_int_mode(bp); init_err_pci_clean: + bnxt_free_hwrm_resources(bp); bnxt_cleanup_pci(bp); init_err_free: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index ddc98c359488..a85d2be986af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -98,13 +98,13 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1); for (i = 0; i < max_tc; i++) { - u8 qidx; + u8 qidx = bp->tc_to_qidx[i]; req.enables |= cpu_to_le32( - QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << i); + QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << + qidx); memset(&cos2bw, 0, sizeof(cos2bw)); - qidx = bp->tc_to_qidx[i]; cos2bw.queue_id = bp->q_info[qidx].queue_id; if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) { cos2bw.tsa = diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 790c684f08ab..140dbd62106d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -21,9 +21,22 @@ static const struct devlink_ops bnxt_dl_ops = { #endif /* CONFIG_BNXT_SRIOV */ }; +enum bnxt_dl_param_id { + BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, +}; + static const struct bnxt_dl_nvm_param nvm_params[] = { {DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV, BNXT_NVM_SHARED_CFG, 1}, + {DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, NVM_OFF_IGNORE_ARI, + BNXT_NVM_SHARED_CFG, 1}, + {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10}, + {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7}, + {BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK, + BNXT_NVM_SHARED_CFG, 1}, }; static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, @@ -55,8 +68,22 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID; bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE; - if (nvm_param.num_bits == 1) - buf = &val->vbool; + switch (bytesize) { + case 1: + if (nvm_param.num_bits == 1) + buf = &val->vbool; + else + buf = &val->vu8; + break; + case 2: + buf = &val->vu16; + break; + case 4: + buf = &val->vu32; + break; + default: + return -EFAULT; + } data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize, &data_dma_addr, GFP_KERNEL); @@ -78,8 +105,12 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, memcpy(buf, data_addr, bytesize); dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr); - if (rc) + if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { + netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n"); + return -EACCES; + } else if (rc) { return -EIO; + } return 0; } @@ -88,9 +119,15 @@ static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id, { struct hwrm_nvm_get_variable_input req = {0}; struct bnxt *bp = bnxt_get_bp_from_dl(dl); + int rc; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1); - return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); + rc = bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); + if (!rc) + if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK) + ctx->val.vbool = !ctx->val.vbool; + + return rc; } static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id, @@ -100,14 +137,55 @@ static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id, struct bnxt *bp = bnxt_get_bp_from_dl(dl); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1); + + if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK) + ctx->val.vbool = !ctx->val.vbool; + return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); } +static int bnxt_dl_msix_validate(struct devlink *dl, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + int max_val = -1; + + if (id == DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX) + max_val = BNXT_MSIX_VEC_MAX; + + if (id == DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN) + max_val = BNXT_MSIX_VEC_MIN_MAX; + + if (val.vu32 > max_val) { + NL_SET_ERR_MSG_MOD(extack, "MSIX value is exceeding the range"); + return -EINVAL; + } + + return 0; +} + static const struct devlink_param bnxt_dl_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT), bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, NULL), + DEVLINK_PARAM_GENERIC(IGNORE_ARI, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + NULL), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + bnxt_dl_msix_validate), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + bnxt_dl_msix_validate), + DEVLINK_PARAM_DRIVER(BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, + "gre_ver_check", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + NULL), }; int bnxt_dl_register(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 2f68dc048390..5b6b2c7d97cf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -33,8 +33,15 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) } } +#define NVM_OFF_MSIX_VEC_PER_PF_MAX 108 +#define NVM_OFF_MSIX_VEC_PER_PF_MIN 114 +#define NVM_OFF_IGNORE_ARI 164 +#define NVM_OFF_DIS_GRE_VER_CHECK 171 #define NVM_OFF_ENABLE_SRIOV 401 +#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MIN_MAX 128 + enum bnxt_nvm_dir_type { BNXT_NVM_SHARED_CFG = 40, BNXT_NVM_PORT_CFG, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index b574fe8e974e..9a25c05aa571 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -521,7 +521,8 @@ int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode) return 0; } -int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode) +int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct bnxt *bp = bnxt_get_bp_from_dl(devlink); int rc = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h index 38b9a75ad724..d7287651422f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h @@ -30,7 +30,8 @@ static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev) bool bnxt_dev_is_vf_rep(struct net_device *dev); int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode); -int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode); +int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); #else diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index eb96b0613cf6..825a28e5b544 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -1732,7 +1732,7 @@ int liquidio_set_fec(struct lio *lio, int on_off) if (oct->props[lio->ifidx].fec != oct->props[lio->ifidx].fec_boot) { dev_dbg(&oct->pci_dev->dev, - "Reloade driver to chang fec to %s\n", + "Reload driver to change fec to %s\n", oct->props[lio->ifidx].fec ? "on" : "off"); } @@ -1796,7 +1796,7 @@ int liquidio_get_fec(struct lio *lio) if (oct->props[lio->ifidx].fec != oct->props[lio->ifidx].fec_boot) { dev_dbg(&oct->pci_dev->dev, - "Reloade driver to chang fec to %s\n", + "Reload driver to change fec to %s\n", oct->props[lio->ifidx].fec ? "on" : "off"); } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 9d70e5c6157f..3d24133e5e49 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3144,7 +3144,8 @@ liquidio_eswitch_mode_get(struct devlink *devlink, u16 *mode) } static int -liquidio_eswitch_mode_set(struct devlink *devlink, u16 mode) +liquidio_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct lio_devlink_priv *priv; struct octeon_device *oct; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 8b0a253a18d8..1e82b9efe447 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2158,6 +2158,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_QSET_PARAMS) + return -EINVAL; if (t.qset_idx >= SGE_QSETS) return -EINVAL; if (!in_range(t.intr_lat, 0, M_NEWTIMER) || @@ -2257,6 +2259,9 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_QSET_PARAMS) + return -EINVAL; + /* Display qsets for all ports when offload enabled */ if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) { q1 = 0; @@ -2302,6 +2307,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; + if (edata.cmd != CHELSIO_SET_QSET_NUM) + return -EINVAL; if (edata.val < 1 || (edata.val > 1 && !(adapter->flags & USING_MSIX))) return -EINVAL; @@ -2342,6 +2349,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_LOAD_FW) + return -EINVAL; /* Check t.len sanity ? */ fw_data = memdup_user(useraddr + sizeof(t), t.len); if (IS_ERR(fw_data)) @@ -2365,6 +2374,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SETMTUTAB) + return -EINVAL; if (m.nmtus != NMTUS) return -EINVAL; if (m.mtus[0] < 81) /* accommodate SACK */ @@ -2406,6 +2417,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SET_PM) + return -EINVAL; if (!is_power_of_2(m.rx_pg_sz) || !is_power_of_2(m.tx_pg_sz)) return -EINVAL; /* not power of 2 */ @@ -2439,6 +2452,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_MEM) + return -EINVAL; if ((t.addr & 7) || (t.len & 7)) return -EINVAL; if (t.mem_id == MEM_CM) @@ -2491,6 +2506,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EAGAIN; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_TRACE_FILTER) + return -EINVAL; tp = (const struct trace_params *)&t.sip; if (t.config_tx) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index 6ba3104ff7eb..9bd5f755a0e0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -300,8 +300,8 @@ void cxgb4_dcb_handle_fw_update(struct adapter *adap, enum cxgb4_dcb_state_input input = ((pcmd->u.dcb.control.all_syncd_pkd & FW_PORT_CMD_ALL_SYNCD_F) - ? CXGB4_DCB_STATE_FW_ALLSYNCED - : CXGB4_DCB_STATE_FW_INCOMPLETE); + ? CXGB4_DCB_INPUT_FW_ALLSYNCED + : CXGB4_DCB_INPUT_FW_INCOMPLETE); if (dcb->dcb_version != FW_PORT_DCB_VER_UNKNOWN) { dcb_running_version = FW_PORT_CMD_DCB_VERSION_G( diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h index 02040b99c78a..484ee8290090 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h @@ -67,7 +67,7 @@ do { \ if ((__dcb)->dcb_version == FW_PORT_DCB_VER_IEEE) \ cxgb4_dcb_state_fsm((__dev), \ - CXGB4_DCB_STATE_FW_ALLSYNCED); \ + CXGB4_DCB_INPUT_FW_ALLSYNCED); \ } while (0) /* States we can be in for a port's Data Center Bridging. diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index 7fc656680299..52edb688942b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -38,7 +38,6 @@ #include "cxgb4.h" #include "sched.h" -/* Spinlock must be held by caller */ static int t4_sched_class_fw_cmd(struct port_info *pi, struct ch_sched_params *p, enum sched_fw_ops op) @@ -67,7 +66,6 @@ static int t4_sched_class_fw_cmd(struct port_info *pi, return err; } -/* Spinlock must be held by caller */ static int t4_sched_bind_unbind_op(struct port_info *pi, void *arg, enum sched_bind_type type, bool bind) { @@ -163,7 +161,6 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) if (e && index >= 0) { int i = 0; - spin_lock(&e->lock); list_for_each_entry(qe, &e->queue_list, list) { if (i == index) break; @@ -171,10 +168,8 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) } err = t4_sched_bind_unbind_op(pi, (void *)qe, SCHED_QUEUE, false); - if (err) { - spin_unlock(&e->lock); - goto out; - } + if (err) + return err; list_del(&qe->list); kvfree(qe); @@ -182,9 +177,7 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) e->state = SCHED_STATE_UNUSED; memset(&e->info, 0, sizeof(e->info)); } - spin_unlock(&e->lock); } -out: return err; } @@ -210,10 +203,8 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) /* Unbind queue from any existing class */ err = t4_sched_queue_unbind(pi, p); - if (err) { - kvfree(qe); - goto out; - } + if (err) + goto out_err; /* Bind queue to specified class */ memset(qe, 0, sizeof(*qe)); @@ -221,18 +212,16 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) memcpy(&qe->param, p, sizeof(qe->param)); e = &s->tab[qe->param.class]; - spin_lock(&e->lock); err = t4_sched_bind_unbind_op(pi, (void *)qe, SCHED_QUEUE, true); - if (err) { - kvfree(qe); - spin_unlock(&e->lock); - goto out; - } + if (err) + goto out_err; list_add_tail(&qe->list, &e->queue_list); atomic_inc(&e->refcnt); - spin_unlock(&e->lock); -out: + return err; + +out_err: + kvfree(qe); return err; } @@ -296,8 +285,6 @@ int cxgb4_sched_class_bind(struct net_device *dev, void *arg, enum sched_bind_type type) { struct port_info *pi = netdev2pinfo(dev); - struct sched_table *s; - int err = 0; u8 class_id; if (!can_sched(dev)) @@ -323,12 +310,8 @@ int cxgb4_sched_class_bind(struct net_device *dev, void *arg, if (class_id == SCHED_CLS_NONE) return -ENOTSUPP; - s = pi->sched_tbl; - write_lock(&s->rw_lock); - err = t4_sched_class_bind_unbind_op(pi, arg, type, true); - write_unlock(&s->rw_lock); + return t4_sched_class_bind_unbind_op(pi, arg, type, true); - return err; } /** @@ -343,8 +326,6 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, enum sched_bind_type type) { struct port_info *pi = netdev2pinfo(dev); - struct sched_table *s; - int err = 0; u8 class_id; if (!can_sched(dev)) @@ -367,12 +348,7 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, if (!valid_class_id(dev, class_id)) return -EINVAL; - s = pi->sched_tbl; - write_lock(&s->rw_lock); - err = t4_sched_class_bind_unbind_op(pi, arg, type, false); - write_unlock(&s->rw_lock); - - return err; + return t4_sched_class_bind_unbind_op(pi, arg, type, false); } /* If @p is NULL, fetch any available unused class */ @@ -425,7 +401,6 @@ static struct sched_class *t4_sched_class_lookup(struct port_info *pi, static struct sched_class *t4_sched_class_alloc(struct port_info *pi, struct ch_sched_params *p) { - struct sched_table *s = pi->sched_tbl; struct sched_class *e; u8 class_id; int err; @@ -441,7 +416,6 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi, if (class_id != SCHED_CLS_NONE) return NULL; - write_lock(&s->rw_lock); /* See if there's an exisiting class with same * requested sched params */ @@ -452,27 +426,19 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi, /* Fetch any available unused class */ e = t4_sched_class_lookup(pi, NULL); if (!e) - goto out; + return NULL; memcpy(&np, p, sizeof(np)); np.u.params.class = e->idx; - - spin_lock(&e->lock); /* New class */ err = t4_sched_class_fw_cmd(pi, &np, SCHED_FW_OP_ADD); - if (err) { - spin_unlock(&e->lock); - e = NULL; - goto out; - } + if (err) + return NULL; memcpy(&e->info, &np, sizeof(e->info)); atomic_set(&e->refcnt, 0); e->state = SCHED_STATE_ACTIVE; - spin_unlock(&e->lock); } -out: - write_unlock(&s->rw_lock); return e; } @@ -517,14 +483,12 @@ struct sched_table *t4_init_sched(unsigned int sched_size) return NULL; s->sched_size = sched_size; - rwlock_init(&s->rw_lock); for (i = 0; i < s->sched_size; i++) { memset(&s->tab[i], 0, sizeof(struct sched_class)); s->tab[i].idx = i; s->tab[i].state = SCHED_STATE_UNUSED; INIT_LIST_HEAD(&s->tab[i].queue_list); - spin_lock_init(&s->tab[i].lock); atomic_set(&s->tab[i].refcnt, 0); } return s; @@ -545,11 +509,9 @@ void t4_cleanup_sched(struct adapter *adap) for (i = 0; i < s->sched_size; i++) { struct sched_class *e; - write_lock(&s->rw_lock); e = &s->tab[i]; if (e->state == SCHED_STATE_ACTIVE) t4_sched_class_free(pi, e); - write_unlock(&s->rw_lock); } kvfree(s); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h index 3a49e00a38a1..168fb4ce3759 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.h +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h @@ -69,13 +69,11 @@ struct sched_class { u8 idx; struct ch_sched_params info; struct list_head queue_list; - spinlock_t lock; /* Per class lock */ atomic_t refcnt; }; struct sched_table { /* per port scheduling table */ u8 sched_size; - rwlock_t rw_lock; /* Table lock */ struct sched_class tab[0]; }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index f85eab57e9e1..cb523949c812 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4204,6 +4204,7 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox, */ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port) { + unsigned int fw_caps = adap->params.fw_caps_support; struct fw_port_cmd c; memset(&c, 0, sizeof(c)); @@ -4211,9 +4212,14 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port) FW_CMD_REQUEST_F | FW_CMD_EXEC_F | FW_PORT_CMD_PORTID_V(port)); c.action_to_len16 = - cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) | + cpu_to_be32(FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_L1_CFG + : FW_PORT_ACTION_L1_CFG32) | FW_LEN16(c)); - c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP32_ANEG); + if (fw_caps == FW_CAPS16) + c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP_ANEG); + else + c.u.l1cfg32.rcap32 = cpu_to_be32(FW_PORT_CAP32_ANEG); return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index b8f75a22fb6c..f152da1ce046 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -753,7 +753,6 @@ struct cpl_abort_req_rss { }; struct cpl_abort_req_rss6 { - WR_HDR; union opcode_tid ot; __be32 srqidx_status; }; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 74d122616e76..534787291b44 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4002,8 +4002,6 @@ static int be_enable_vxlan_offloads(struct be_adapter *adapter) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->features |= NETIF_F_GSO_UDP_TUNNEL; dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", be16_to_cpu(port)); @@ -4025,8 +4023,6 @@ static void be_disable_vxlan_offloads(struct be_adapter *adapter) adapter->vxlan_port = 0; netdev->hw_enc_features = 0; - netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL); - netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL); } static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs, @@ -5320,6 +5316,7 @@ static void be_netdev_init(struct net_device *netdev) struct be_adapter *adapter = netdev_priv(netdev); netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX; if ((be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS)) diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 7a30276e1ba6..d3a62bc1f1c6 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -96,13 +96,6 @@ config GIANFAR on the 8540. source "drivers/net/ethernet/freescale/dpaa/Kconfig" - -config FSL_DPAA2_ETH - tristate "Freescale DPAA2 Ethernet" - depends on FSL_MC_BUS && FSL_MC_DPIO - depends on NETDEVICES && ETHERNET - ---help--- - Ethernet driver for Freescale DPAA2 SoCs, using the - Freescale MC bus driver +source "drivers/net/ethernet/freescale/dpaa2/Kconfig" endif # NET_VENDOR_FREESCALE diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 84843de25c7b..6e0f47f2c8a3 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2731,8 +2731,6 @@ out_error: return err; } -static const struct of_device_id dpaa_match[]; - static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) { u16 headroom; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 5d0fdf667b82..13d6e2272ece 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -182,7 +182,6 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, struct phy_device *phydev; bool rx_pause, tx_pause; struct dpaa_priv *priv; - u32 newadv, oldadv; int err; priv = netdev_priv(net_dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig new file mode 100644 index 000000000000..a7f365db0eed --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig @@ -0,0 +1,17 @@ +config FSL_DPAA2_ETH + tristate "Freescale DPAA2 Ethernet" + depends on FSL_MC_BUS && FSL_MC_DPIO + depends on ARCH_LAYERSCAPE || COMPILE_TEST + help + This is the DPAA2 Ethernet driver supporting Freescale SoCs + with DPAA2 (DataPath Acceleration Architecture v2). + The driver manages network objects discovered on the Freescale + MC bus. + +config FSL_DPAA2_PTP_CLOCK + tristate "Freescale DPAA2 PTP Clock" + depends on FSL_DPAA2_ETH && POSIX_TIMERS + select PTP_1588_CLOCK + help + This driver adds support for using the DPAA2 1588 timer module + as a PTP clock. diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile index 9315ecdba612..2f424e0a8225 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Makefile +++ b/drivers/net/ethernet/freescale/dpaa2/Makefile @@ -3,9 +3,11 @@ # Makefile for the Freescale DPAA2 Ethernet controller # -obj-$(CONFIG_FSL_DPAA2_ETH) += fsl-dpaa2-eth.o +obj-$(CONFIG_FSL_DPAA2_ETH) += fsl-dpaa2-eth.o +obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK) += fsl-dpaa2-ptp.o -fsl-dpaa2-eth-objs := dpaa2-eth.o dpaa2-ethtool.o dpni.o +fsl-dpaa2-eth-objs := dpaa2-eth.o dpaa2-ethtool.o dpni.o +fsl-dpaa2-ptp-objs := dpaa2-ptp.o dprtc.o # Needed by the tracing framework CFLAGS_dpaa2-eth.o := -I$(src) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index c282d5ca06d6..156080d42a6c 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -289,10 +289,11 @@ err_frame_format: * * Observance of NAPI budget is not our concern, leaving that to the caller. */ -static int consume_frames(struct dpaa2_eth_channel *ch) +static int consume_frames(struct dpaa2_eth_channel *ch, + enum dpaa2_eth_fq_type *type) { struct dpaa2_eth_priv *priv = ch->priv; - struct dpaa2_eth_fq *fq; + struct dpaa2_eth_fq *fq = NULL; struct dpaa2_dq *dq; const struct dpaa2_fd *fd; int cleaned = 0; @@ -311,12 +312,23 @@ static int consume_frames(struct dpaa2_eth_channel *ch) fd = dpaa2_dq_fd(dq); fq = (struct dpaa2_eth_fq *)(uintptr_t)dpaa2_dq_fqd_ctx(dq); - fq->stats.frames++; fq->consume(priv, ch, fd, &ch->napi, fq->flowid); cleaned++; } while (!is_last); + if (!cleaned) + return 0; + + fq->stats.frames += cleaned; + ch->stats.frames += cleaned; + + /* A dequeue operation only pulls frames from a single queue + * into the store. Return the frame queue type as an out param. + */ + if (type) + *type = fq->type; + return cleaned; } @@ -921,14 +933,16 @@ static int pull_channel(struct dpaa2_eth_channel *ch) static int dpaa2_eth_poll(struct napi_struct *napi, int budget) { struct dpaa2_eth_channel *ch; - int cleaned = 0, store_cleaned; struct dpaa2_eth_priv *priv; + int rx_cleaned = 0, txconf_cleaned = 0; + enum dpaa2_eth_fq_type type; + int store_cleaned; int err; ch = container_of(napi, struct dpaa2_eth_channel, napi); priv = ch->priv; - while (cleaned < budget) { + do { err = pull_channel(ch); if (unlikely(err)) break; @@ -936,30 +950,32 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) /* Refill pool if appropriate */ refill_pool(priv, ch, priv->bpid); - store_cleaned = consume_frames(ch); - cleaned += store_cleaned; + store_cleaned = consume_frames(ch, &type); + if (type == DPAA2_RX_FQ) + rx_cleaned += store_cleaned; + else + txconf_cleaned += store_cleaned; - /* If we have enough budget left for a full store, - * try a new pull dequeue, otherwise we're done here + /* If we either consumed the whole NAPI budget with Rx frames + * or we reached the Tx confirmations threshold, we're done. */ - if (store_cleaned == 0 || - cleaned > budget - DPAA2_ETH_STORE_SIZE) - break; - } - - if (cleaned < budget && napi_complete_done(napi, cleaned)) { - /* Re-enable data available notifications */ - do { - err = dpaa2_io_service_rearm(ch->dpio, &ch->nctx); - cpu_relax(); - } while (err == -EBUSY); - WARN_ONCE(err, "CDAN notifications rearm failed on core %d", - ch->nctx.desired_cpu); - } + if (rx_cleaned >= budget || + txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) + return budget; + } while (store_cleaned); - ch->stats.frames += cleaned; + /* We didn't consume the entire budget, so finish napi and + * re-enable data availability notifications + */ + napi_complete_done(napi, rx_cleaned); + do { + err = dpaa2_io_service_rearm(ch->dpio, &ch->nctx); + cpu_relax(); + } while (err == -EBUSY); + WARN_ONCE(err, "CDAN notifications rearm failed on core %d", + ch->nctx.desired_cpu); - return cleaned; + return max(rx_cleaned, 1); } static void enable_ch_napi(struct dpaa2_eth_priv *priv) @@ -1076,7 +1092,7 @@ static u32 drain_channel(struct dpaa2_eth_priv *priv, do { pull_channel(ch); - drained = consume_frames(ch); + drained = consume_frames(ch, NULL); total += drained; } while (drained); @@ -1897,6 +1913,11 @@ static int setup_dpni(struct fsl_mc_device *ls_dev) if (err) goto close; + priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) * + dpaa2_eth_fs_count(priv), GFP_KERNEL); + if (!priv->cls_rules) + goto close; + return 0; close: @@ -2004,7 +2025,7 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv, } /* Supported header fields for Rx hash distribution key */ -static const struct dpaa2_eth_hash_fields hash_fields[] = { +static const struct dpaa2_eth_dist_fields dist_fields[] = { { /* L2 header */ .rxnfc_field = RXH_L2DA, @@ -2012,6 +2033,18 @@ static const struct dpaa2_eth_hash_fields hash_fields[] = { .cls_field = NH_FLD_ETH_DA, .size = 6, }, { + .cls_prot = NET_PROT_ETH, + .cls_field = NH_FLD_ETH_SA, + .size = 6, + }, { + /* This is the last ethertype field parsed: + * depending on frame format, it can be the MAC ethertype + * or the VLAN etype. + */ + .cls_prot = NET_PROT_ETH, + .cls_field = NH_FLD_ETH_TYPE, + .size = 2, + }, { /* VLAN header */ .rxnfc_field = RXH_VLAN, .cls_prot = NET_PROT_VLAN, @@ -2049,33 +2082,122 @@ static const struct dpaa2_eth_hash_fields hash_fields[] = { }, }; -/* Set RX hash options +/* Configure the Rx hash key using the legacy API */ +static int config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +{ + struct device *dev = priv->net_dev->dev.parent; + struct dpni_rx_tc_dist_cfg dist_cfg; + int err; + + memset(&dist_cfg, 0, sizeof(dist_cfg)); + + dist_cfg.key_cfg_iova = key; + dist_cfg.dist_size = dpaa2_eth_queue_count(priv); + dist_cfg.dist_mode = DPNI_DIST_MODE_HASH; + + err = dpni_set_rx_tc_dist(priv->mc_io, 0, priv->mc_token, 0, &dist_cfg); + if (err) + dev_err(dev, "dpni_set_rx_tc_dist failed\n"); + + return err; +} + +/* Configure the Rx hash key using the new API */ +static int config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +{ + struct device *dev = priv->net_dev->dev.parent; + struct dpni_rx_dist_cfg dist_cfg; + int err; + + memset(&dist_cfg, 0, sizeof(dist_cfg)); + + dist_cfg.key_cfg_iova = key; + dist_cfg.dist_size = dpaa2_eth_queue_count(priv); + dist_cfg.enable = 1; + + err = dpni_set_rx_hash_dist(priv->mc_io, 0, priv->mc_token, &dist_cfg); + if (err) + dev_err(dev, "dpni_set_rx_hash_dist failed\n"); + + return err; +} + +/* Configure the Rx flow classification key */ +static int config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key) +{ + struct device *dev = priv->net_dev->dev.parent; + struct dpni_rx_dist_cfg dist_cfg; + int err; + + memset(&dist_cfg, 0, sizeof(dist_cfg)); + + dist_cfg.key_cfg_iova = key; + dist_cfg.dist_size = dpaa2_eth_queue_count(priv); + dist_cfg.enable = 1; + + err = dpni_set_rx_fs_dist(priv->mc_io, 0, priv->mc_token, &dist_cfg); + if (err) + dev_err(dev, "dpni_set_rx_fs_dist failed\n"); + + return err; +} + +/* Size of the Rx flow classification key */ +int dpaa2_eth_cls_key_size(void) +{ + int i, size = 0; + + for (i = 0; i < ARRAY_SIZE(dist_fields); i++) + size += dist_fields[i].size; + + return size; +} + +/* Offset of header field in Rx classification key */ +int dpaa2_eth_cls_fld_off(int prot, int field) +{ + int i, off = 0; + + for (i = 0; i < ARRAY_SIZE(dist_fields); i++) { + if (dist_fields[i].cls_prot == prot && + dist_fields[i].cls_field == field) + return off; + off += dist_fields[i].size; + } + + WARN_ONCE(1, "Unsupported header field used for Rx flow cls\n"); + return 0; +} + +/* Set Rx distribution (hash or flow classification) key * flags is a combination of RXH_ bits */ -int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) +int dpaa2_eth_set_dist_key(struct net_device *net_dev, + enum dpaa2_eth_rx_dist type, u64 flags) { struct device *dev = net_dev->dev.parent; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpkg_profile_cfg cls_cfg; - struct dpni_rx_tc_dist_cfg dist_cfg; u32 rx_hash_fields = 0; + dma_addr_t key_iova; u8 *dma_mem; int i; int err = 0; - if (!dpaa2_eth_hash_enabled(priv)) { - dev_dbg(dev, "Hashing support is not enabled\n"); - return -EOPNOTSUPP; - } - memset(&cls_cfg, 0, sizeof(cls_cfg)); - for (i = 0; i < ARRAY_SIZE(hash_fields); i++) { + for (i = 0; i < ARRAY_SIZE(dist_fields); i++) { struct dpkg_extract *key = &cls_cfg.extracts[cls_cfg.num_extracts]; - if (!(flags & hash_fields[i].rxnfc_field)) - continue; + /* For Rx hashing key we set only the selected fields. + * For Rx flow classification key we set all supported fields + */ + if (type == DPAA2_ETH_RX_DIST_HASH) { + if (!(flags & dist_fields[i].rxnfc_field)) + continue; + rx_hash_fields |= dist_fields[i].rxnfc_field; + } if (cls_cfg.num_extracts >= DPKG_MAX_NUM_OF_EXTRACTS) { dev_err(dev, "error adding key extraction rule, too many rules?\n"); @@ -2083,12 +2205,10 @@ int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) } key->type = DPKG_EXTRACT_FROM_HDR; - key->extract.from_hdr.prot = hash_fields[i].cls_prot; + key->extract.from_hdr.prot = dist_fields[i].cls_prot; key->extract.from_hdr.type = DPKG_FULL_FIELD; - key->extract.from_hdr.field = hash_fields[i].cls_field; + key->extract.from_hdr.field = dist_fields[i].cls_field; cls_cfg.num_extracts++; - - rx_hash_fields |= hash_fields[i].rxnfc_field; } dma_mem = kzalloc(DPAA2_CLASSIFIER_DMA_SIZE, GFP_KERNEL); @@ -2098,38 +2218,73 @@ int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) err = dpni_prepare_key_cfg(&cls_cfg, dma_mem); if (err) { dev_err(dev, "dpni_prepare_key_cfg error %d\n", err); - goto err_prep_key; + goto free_key; } - memset(&dist_cfg, 0, sizeof(dist_cfg)); - /* Prepare for setting the rx dist */ - dist_cfg.key_cfg_iova = dma_map_single(dev, dma_mem, - DPAA2_CLASSIFIER_DMA_SIZE, - DMA_TO_DEVICE); - if (dma_mapping_error(dev, dist_cfg.key_cfg_iova)) { + key_iova = dma_map_single(dev, dma_mem, DPAA2_CLASSIFIER_DMA_SIZE, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, key_iova)) { dev_err(dev, "DMA mapping failed\n"); err = -ENOMEM; - goto err_dma_map; + goto free_key; } - dist_cfg.dist_size = dpaa2_eth_queue_count(priv); - dist_cfg.dist_mode = DPNI_DIST_MODE_HASH; + if (type == DPAA2_ETH_RX_DIST_HASH) { + if (dpaa2_eth_has_legacy_dist(priv)) + err = config_legacy_hash_key(priv, key_iova); + else + err = config_hash_key(priv, key_iova); + } else { + err = config_cls_key(priv, key_iova); + } - err = dpni_set_rx_tc_dist(priv->mc_io, 0, priv->mc_token, 0, &dist_cfg); - dma_unmap_single(dev, dist_cfg.key_cfg_iova, - DPAA2_CLASSIFIER_DMA_SIZE, DMA_TO_DEVICE); - if (err) - dev_err(dev, "dpni_set_rx_tc_dist() error %d\n", err); - else + dma_unmap_single(dev, key_iova, DPAA2_CLASSIFIER_DMA_SIZE, + DMA_TO_DEVICE); + if (!err && type == DPAA2_ETH_RX_DIST_HASH) priv->rx_hash_fields = rx_hash_fields; -err_dma_map: -err_prep_key: +free_key: kfree(dma_mem); return err; } +int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + + if (!dpaa2_eth_hash_enabled(priv)) + return -EOPNOTSUPP; + + return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_HASH, flags); +} + +static int dpaa2_eth_set_cls(struct dpaa2_eth_priv *priv) +{ + struct device *dev = priv->net_dev->dev.parent; + + /* Check if we actually support Rx flow classification */ + if (dpaa2_eth_has_legacy_dist(priv)) { + dev_dbg(dev, "Rx cls not supported by current MC version\n"); + return -EOPNOTSUPP; + } + + if (priv->dpni_attrs.options & DPNI_OPT_NO_FS || + !(priv->dpni_attrs.options & DPNI_OPT_HAS_KEY_MASKING)) { + dev_dbg(dev, "Rx cls disabled in DPNI options\n"); + return -EOPNOTSUPP; + } + + if (!dpaa2_eth_hash_enabled(priv)) { + dev_dbg(dev, "Rx cls disabled for single queue DPNIs\n"); + return -EOPNOTSUPP; + } + + priv->rx_cls_enabled = 1; + + return dpaa2_eth_set_dist_key(priv->net_dev, DPAA2_ETH_RX_DIST_CLS, 0); +} + /* Bind the DPNI to its needed objects and resources: buffer pool, DPIOs, * frame queues and channels */ @@ -2159,6 +2314,13 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) if (err && err != -EOPNOTSUPP) dev_err(dev, "Failed to configure hashing\n"); + /* Configure the flow classification key; it includes all + * supported header fields and cannot be modified at runtime + */ + err = dpaa2_eth_set_cls(priv); + if (err && err != -EOPNOTSUPP) + dev_err(dev, "Failed to configure Rx classification key\n"); + /* Configure handling of error frames */ err_cfg.errors = DPAA2_FAS_RX_ERR_MASK; err_cfg.set_frame_annotation = 1; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 93bc41265e5e..452a8e9c4f0e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -40,6 +40,11 @@ */ #define DPAA2_ETH_TAILDROP_THRESH (64 * 1024) +/* Maximum number of Tx confirmation frames to be processed + * in a single NAPI call + */ +#define DPAA2_ETH_TXCONF_PER_NAPI 256 + /* Buffer quota per queue. Must be large enough such that for minimum sized * frames taildrop kicks in before the bpool gets depleted, so we compute * how many 64B frames fit inside the taildrop threshold and add a margin @@ -290,13 +295,18 @@ struct dpaa2_eth_channel { struct dpaa2_eth_ch_stats stats; }; -struct dpaa2_eth_hash_fields { +struct dpaa2_eth_dist_fields { u64 rxnfc_field; enum net_prot cls_prot; int cls_field; int size; }; +struct dpaa2_eth_cls_rule { + struct ethtool_rx_flow_spec fs; + u8 in_use; +}; + /* Driver private data */ struct dpaa2_eth_priv { struct net_device *net_dev; @@ -340,6 +350,8 @@ struct dpaa2_eth_priv { /* enabled ethtool hashing bits */ u64 rx_hash_fields; + struct dpaa2_eth_cls_rule *cls_rules; + u8 rx_cls_enabled; }; #define DPAA2_RXH_SUPPORTED (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO \ @@ -367,6 +379,24 @@ static inline int dpaa2_eth_cmp_dpni_ver(struct dpaa2_eth_priv *priv, return priv->dpni_ver_major - ver_major; } +/* Minimum firmware version that supports a more flexible API + * for configuring the Rx flow hash key + */ +#define DPNI_RX_DIST_KEY_VER_MAJOR 7 +#define DPNI_RX_DIST_KEY_VER_MINOR 5 + +#define dpaa2_eth_has_legacy_dist(priv) \ + (dpaa2_eth_cmp_dpni_ver((priv), DPNI_RX_DIST_KEY_VER_MAJOR, \ + DPNI_RX_DIST_KEY_VER_MINOR) < 0) + +#define dpaa2_eth_fs_count(priv) \ + ((priv)->dpni_attrs.fs_entries) + +enum dpaa2_eth_rx_dist { + DPAA2_ETH_RX_DIST_HASH, + DPAA2_ETH_RX_DIST_CLS +}; + /* Hardware only sees DPAA2_ETH_RX_BUF_SIZE, but the skb built around * the buffer also needs space for its shared info struct, and we need * to allocate enough to accommodate hardware alignment restrictions @@ -410,5 +440,7 @@ static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv) } int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags); +int dpaa2_eth_cls_key_size(void); +int dpaa2_eth_cls_fld_off(int prot, int field); #endif /* __DPAA2_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index ce0d94d8a7d8..26bd5a2bd8ed 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -224,10 +224,310 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, *(data + i++) = cdan; } +static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask, + void *key, void *mask) +{ + int off; + + if (eth_mask->h_proto) { + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE); + *(__be16 *)(key + off) = eth_value->h_proto; + *(__be16 *)(mask + off) = eth_mask->h_proto; + } + + if (!is_zero_ether_addr(eth_mask->h_source)) { + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_SA); + ether_addr_copy(key + off, eth_value->h_source); + ether_addr_copy(mask + off, eth_mask->h_source); + } + + if (!is_zero_ether_addr(eth_mask->h_dest)) { + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA); + ether_addr_copy(key + off, eth_value->h_dest); + ether_addr_copy(mask + off, eth_mask->h_dest); + } + + return 0; +} + +static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value, + struct ethtool_usrip4_spec *uip_mask, + void *key, void *mask) +{ + int off; + u32 tmp_value, tmp_mask; + + if (uip_mask->tos || uip_mask->ip_ver) + return -EOPNOTSUPP; + + if (uip_mask->ip4src) { + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC); + *(__be32 *)(key + off) = uip_value->ip4src; + *(__be32 *)(mask + off) = uip_mask->ip4src; + } + + if (uip_mask->ip4dst) { + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST); + *(__be32 *)(key + off) = uip_value->ip4dst; + *(__be32 *)(mask + off) = uip_mask->ip4dst; + } + + if (uip_mask->proto) { + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO); + *(u8 *)(key + off) = uip_value->proto; + *(u8 *)(mask + off) = uip_mask->proto; + } + + if (uip_mask->l4_4_bytes) { + tmp_value = be32_to_cpu(uip_value->l4_4_bytes); + tmp_mask = be32_to_cpu(uip_mask->l4_4_bytes); + + off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC); + *(__be16 *)(key + off) = htons(tmp_value >> 16); + *(__be16 *)(mask + off) = htons(tmp_mask >> 16); + + off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST); + *(__be16 *)(key + off) = htons(tmp_value & 0xFFFF); + *(__be16 *)(mask + off) = htons(tmp_mask & 0xFFFF); + } + + /* Only apply the rule for IPv4 frames */ + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE); + *(__be16 *)(key + off) = htons(ETH_P_IP); + *(__be16 *)(mask + off) = htons(0xFFFF); + + return 0; +} + +static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value, + struct ethtool_tcpip4_spec *l4_mask, + void *key, void *mask, u8 l4_proto) +{ + int off; + + if (l4_mask->tos) + return -EOPNOTSUPP; + + if (l4_mask->ip4src) { + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC); + *(__be32 *)(key + off) = l4_value->ip4src; + *(__be32 *)(mask + off) = l4_mask->ip4src; + } + + if (l4_mask->ip4dst) { + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST); + *(__be32 *)(key + off) = l4_value->ip4dst; + *(__be32 *)(mask + off) = l4_mask->ip4dst; + } + + if (l4_mask->psrc) { + off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC); + *(__be16 *)(key + off) = l4_value->psrc; + *(__be16 *)(mask + off) = l4_mask->psrc; + } + + if (l4_mask->pdst) { + off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST); + *(__be16 *)(key + off) = l4_value->pdst; + *(__be16 *)(mask + off) = l4_mask->pdst; + } + + /* Only apply the rule for IPv4 frames with the specified L4 proto */ + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE); + *(__be16 *)(key + off) = htons(ETH_P_IP); + *(__be16 *)(mask + off) = htons(0xFFFF); + + off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO); + *(u8 *)(key + off) = l4_proto; + *(u8 *)(mask + off) = 0xFF; + + return 0; +} + +static int prep_ext_rule(struct ethtool_flow_ext *ext_value, + struct ethtool_flow_ext *ext_mask, + void *key, void *mask) +{ + int off; + + if (ext_mask->vlan_etype) + return -EOPNOTSUPP; + + if (ext_mask->vlan_tci) { + off = dpaa2_eth_cls_fld_off(NET_PROT_VLAN, NH_FLD_VLAN_TCI); + *(__be16 *)(key + off) = ext_value->vlan_tci; + *(__be16 *)(mask + off) = ext_mask->vlan_tci; + } + + return 0; +} + +static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value, + struct ethtool_flow_ext *ext_mask, + void *key, void *mask) +{ + int off; + + if (!is_zero_ether_addr(ext_mask->h_dest)) { + off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA); + ether_addr_copy(key + off, ext_value->h_dest); + ether_addr_copy(mask + off, ext_mask->h_dest); + } + + return 0; +} + +static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask) +{ + int err; + + switch (fs->flow_type & 0xFF) { + case ETHER_FLOW: + err = prep_eth_rule(&fs->h_u.ether_spec, &fs->m_u.ether_spec, + key, mask); + break; + case IP_USER_FLOW: + err = prep_uip_rule(&fs->h_u.usr_ip4_spec, + &fs->m_u.usr_ip4_spec, key, mask); + break; + case TCP_V4_FLOW: + err = prep_l4_rule(&fs->h_u.tcp_ip4_spec, &fs->m_u.tcp_ip4_spec, + key, mask, IPPROTO_TCP); + break; + case UDP_V4_FLOW: + err = prep_l4_rule(&fs->h_u.udp_ip4_spec, &fs->m_u.udp_ip4_spec, + key, mask, IPPROTO_UDP); + break; + case SCTP_V4_FLOW: + err = prep_l4_rule(&fs->h_u.sctp_ip4_spec, + &fs->m_u.sctp_ip4_spec, key, mask, + IPPROTO_SCTP); + break; + default: + return -EOPNOTSUPP; + } + + if (err) + return err; + + if (fs->flow_type & FLOW_EXT) { + err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask); + if (err) + return err; + } + + if (fs->flow_type & FLOW_MAC_EXT) { + err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask); + if (err) + return err; + } + + return 0; +} + +static int do_cls_rule(struct net_device *net_dev, + struct ethtool_rx_flow_spec *fs, + bool add) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + struct device *dev = net_dev->dev.parent; + struct dpni_rule_cfg rule_cfg = { 0 }; + struct dpni_fs_action_cfg fs_act = { 0 }; + dma_addr_t key_iova; + void *key_buf; + int err; + + if (fs->ring_cookie != RX_CLS_FLOW_DISC && + fs->ring_cookie >= dpaa2_eth_queue_count(priv)) + return -EINVAL; + + rule_cfg.key_size = dpaa2_eth_cls_key_size(); + + /* allocate twice the key size, for the actual key and for mask */ + key_buf = kzalloc(rule_cfg.key_size * 2, GFP_KERNEL); + if (!key_buf) + return -ENOMEM; + + /* Fill the key and mask memory areas */ + err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size); + if (err) + goto free_mem; + + key_iova = dma_map_single(dev, key_buf, rule_cfg.key_size * 2, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, key_iova)) { + err = -ENOMEM; + goto free_mem; + } + + rule_cfg.key_iova = key_iova; + rule_cfg.mask_iova = key_iova + rule_cfg.key_size; + + if (add) { + if (fs->ring_cookie == RX_CLS_FLOW_DISC) + fs_act.options |= DPNI_FS_OPT_DISCARD; + else + fs_act.flow_id = fs->ring_cookie; + err = dpni_add_fs_entry(priv->mc_io, 0, priv->mc_token, 0, + fs->location, &rule_cfg, &fs_act); + } else { + err = dpni_remove_fs_entry(priv->mc_io, 0, priv->mc_token, 0, + &rule_cfg); + } + + dma_unmap_single(dev, key_iova, rule_cfg.key_size * 2, DMA_TO_DEVICE); + +free_mem: + kfree(key_buf); + + return err; +} + +static int update_cls_rule(struct net_device *net_dev, + struct ethtool_rx_flow_spec *new_fs, + int location) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + struct dpaa2_eth_cls_rule *rule; + int err = -EINVAL; + + if (!priv->rx_cls_enabled) + return -EOPNOTSUPP; + + if (location >= dpaa2_eth_fs_count(priv)) + return -EINVAL; + + rule = &priv->cls_rules[location]; + + /* If a rule is present at the specified location, delete it. */ + if (rule->in_use) { + err = do_cls_rule(net_dev, &rule->fs, false); + if (err) + return err; + + rule->in_use = 0; + } + + /* If no new entry to add, return here */ + if (!new_fs) + return err; + + err = do_cls_rule(net_dev, new_fs, true); + if (err) + return err; + + rule->in_use = 1; + rule->fs = *new_fs; + + return 0; +} + static int dpaa2_eth_get_rxnfc(struct net_device *net_dev, struct ethtool_rxnfc *rxnfc, u32 *rule_locs) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int max_rules = dpaa2_eth_fs_count(priv); + int i, j = 0; switch (rxnfc->cmd) { case ETHTOOL_GRXFH: @@ -240,6 +540,31 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev, case ETHTOOL_GRXRINGS: rxnfc->data = dpaa2_eth_queue_count(priv); break; + case ETHTOOL_GRXCLSRLCNT: + rxnfc->rule_cnt = 0; + for (i = 0; i < max_rules; i++) + if (priv->cls_rules[i].in_use) + rxnfc->rule_cnt++; + rxnfc->data = max_rules; + break; + case ETHTOOL_GRXCLSRULE: + if (rxnfc->fs.location >= max_rules) + return -EINVAL; + if (!priv->cls_rules[rxnfc->fs.location].in_use) + return -EINVAL; + rxnfc->fs = priv->cls_rules[rxnfc->fs.location].fs; + break; + case ETHTOOL_GRXCLSRLALL: + for (i = 0; i < max_rules; i++) { + if (!priv->cls_rules[i].in_use) + continue; + if (j == rxnfc->rule_cnt) + return -EMSGSIZE; + rule_locs[j++] = i; + } + rxnfc->rule_cnt = j; + rxnfc->data = max_rules; + break; default: return -EOPNOTSUPP; } @@ -258,6 +583,12 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev, return -EOPNOTSUPP; err = dpaa2_eth_set_hash(net_dev, rxnfc->data); break; + case ETHTOOL_SRXCLSRLINS: + err = update_cls_rule(net_dev, &rxnfc->fs, rxnfc->fs.location); + break; + case ETHTOOL_SRXCLSRLDEL: + err = update_cls_rule(net_dev, NULL, rxnfc->fs.location); + break; default: err = -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c new file mode 100644 index 000000000000..84b942b1eccc --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016-2018 NXP + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/fsl/mc.h> + +#include "dpaa2-ptp.h" + +struct ptp_dpaa2_priv { + struct fsl_mc_device *ptp_mc_dev; + struct ptp_clock *clock; + struct ptp_clock_info caps; + u32 freq_comp; +}; + +/* PTP clock operations */ +static int ptp_dpaa2_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + struct ptp_dpaa2_priv *ptp_dpaa2 = + container_of(ptp, struct ptp_dpaa2_priv, caps); + struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev; + struct device *dev = &mc_dev->dev; + u64 adj; + u32 diff, tmr_add; + int neg_adj = 0; + int err = 0; + + if (ppb < 0) { + neg_adj = 1; + ppb = -ppb; + } + + tmr_add = ptp_dpaa2->freq_comp; + adj = tmr_add; + adj *= ppb; + diff = div_u64(adj, 1000000000ULL); + + tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; + + err = dprtc_set_freq_compensation(mc_dev->mc_io, 0, + mc_dev->mc_handle, tmr_add); + if (err) + dev_err(dev, "dprtc_set_freq_compensation err %d\n", err); + return err; +} + +static int ptp_dpaa2_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ptp_dpaa2_priv *ptp_dpaa2 = + container_of(ptp, struct ptp_dpaa2_priv, caps); + struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev; + struct device *dev = &mc_dev->dev; + s64 now; + int err = 0; + + err = dprtc_get_time(mc_dev->mc_io, 0, mc_dev->mc_handle, &now); + if (err) { + dev_err(dev, "dprtc_get_time err %d\n", err); + return err; + } + + now += delta; + + err = dprtc_set_time(mc_dev->mc_io, 0, mc_dev->mc_handle, now); + if (err) + dev_err(dev, "dprtc_set_time err %d\n", err); + return err; +} + +static int ptp_dpaa2_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct ptp_dpaa2_priv *ptp_dpaa2 = + container_of(ptp, struct ptp_dpaa2_priv, caps); + struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev; + struct device *dev = &mc_dev->dev; + u64 ns; + u32 remainder; + int err = 0; + + err = dprtc_get_time(mc_dev->mc_io, 0, mc_dev->mc_handle, &ns); + if (err) { + dev_err(dev, "dprtc_get_time err %d\n", err); + return err; + } + + ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder); + ts->tv_nsec = remainder; + return err; +} + +static int ptp_dpaa2_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ptp_dpaa2_priv *ptp_dpaa2 = + container_of(ptp, struct ptp_dpaa2_priv, caps); + struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev; + struct device *dev = &mc_dev->dev; + u64 ns; + int err = 0; + + ns = ts->tv_sec * 1000000000ULL; + ns += ts->tv_nsec; + + err = dprtc_set_time(mc_dev->mc_io, 0, mc_dev->mc_handle, ns); + if (err) + dev_err(dev, "dprtc_set_time err %d\n", err); + return err; +} + +static const struct ptp_clock_info ptp_dpaa2_caps = { + .owner = THIS_MODULE, + .name = "DPAA2 PTP Clock", + .max_adj = 512000, + .n_alarm = 2, + .n_ext_ts = 2, + .n_per_out = 3, + .n_pins = 0, + .pps = 1, + .adjfreq = ptp_dpaa2_adjfreq, + .adjtime = ptp_dpaa2_adjtime, + .gettime64 = ptp_dpaa2_gettime, + .settime64 = ptp_dpaa2_settime, +}; + +static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) +{ + struct device *dev = &mc_dev->dev; + struct ptp_dpaa2_priv *ptp_dpaa2; + u32 tmr_add = 0; + int err; + + ptp_dpaa2 = devm_kzalloc(dev, sizeof(*ptp_dpaa2), GFP_KERNEL); + if (!ptp_dpaa2) + return -ENOMEM; + + err = fsl_mc_portal_allocate(mc_dev, 0, &mc_dev->mc_io); + if (err) { + dev_err(dev, "fsl_mc_portal_allocate err %d\n", err); + goto err_exit; + } + + err = dprtc_open(mc_dev->mc_io, 0, mc_dev->obj_desc.id, + &mc_dev->mc_handle); + if (err) { + dev_err(dev, "dprtc_open err %d\n", err); + goto err_free_mcp; + } + + ptp_dpaa2->ptp_mc_dev = mc_dev; + + err = dprtc_get_freq_compensation(mc_dev->mc_io, 0, + mc_dev->mc_handle, &tmr_add); + if (err) { + dev_err(dev, "dprtc_get_freq_compensation err %d\n", err); + goto err_close; + } + + ptp_dpaa2->freq_comp = tmr_add; + ptp_dpaa2->caps = ptp_dpaa2_caps; + + ptp_dpaa2->clock = ptp_clock_register(&ptp_dpaa2->caps, dev); + if (IS_ERR(ptp_dpaa2->clock)) { + err = PTR_ERR(ptp_dpaa2->clock); + goto err_close; + } + + dpaa2_phc_index = ptp_clock_index(ptp_dpaa2->clock); + + dev_set_drvdata(dev, ptp_dpaa2); + + return 0; + +err_close: + dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); +err_free_mcp: + fsl_mc_portal_free(mc_dev->mc_io); +err_exit: + return err; +} + +static int dpaa2_ptp_remove(struct fsl_mc_device *mc_dev) +{ + struct ptp_dpaa2_priv *ptp_dpaa2; + struct device *dev = &mc_dev->dev; + + ptp_dpaa2 = dev_get_drvdata(dev); + ptp_clock_unregister(ptp_dpaa2->clock); + + dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); + fsl_mc_portal_free(mc_dev->mc_io); + + return 0; +} + +static const struct fsl_mc_device_id dpaa2_ptp_match_id_table[] = { + { + .vendor = FSL_MC_VENDOR_FREESCALE, + .obj_type = "dprtc", + }, + {} +}; +MODULE_DEVICE_TABLE(fslmc, dpaa2_ptp_match_id_table); + +static struct fsl_mc_driver dpaa2_ptp_drv = { + .driver = { + .name = KBUILD_MODNAME, + .owner = THIS_MODULE, + }, + .probe = dpaa2_ptp_probe, + .remove = dpaa2_ptp_remove, + .match_id_table = dpaa2_ptp_match_id_table, +}; + +module_fsl_mc_driver(dpaa2_ptp_drv); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("DPAA2 PTP Clock Driver"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h new file mode 100644 index 000000000000..ff2e177395d4 --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2018 NXP + */ + +#ifndef __RTC_H +#define __RTC_H + +#include "dprtc.h" +#include "dprtc-cmd.h" + +extern int dpaa2_phc_index; + +#endif diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 83698abce8b4..7b44d7d9b19a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h @@ -82,6 +82,9 @@ #define DPNI_CMDID_GET_OFFLOAD DPNI_CMD(0x26B) #define DPNI_CMDID_SET_OFFLOAD DPNI_CMD(0x26C) +#define DPNI_CMDID_SET_RX_FS_DIST DPNI_CMD(0x273) +#define DPNI_CMDID_SET_RX_HASH_DIST DPNI_CMD(0x274) + /* Macros for accessing command fields smaller than 1byte */ #define DPNI_MASK(field) \ GENMASK(DPNI_##field##_SHIFT + DPNI_##field##_SIZE - 1, \ @@ -515,4 +518,52 @@ struct dpni_rsp_get_api_version { __le16 minor; }; +#define DPNI_RX_FS_DIST_ENABLE_SHIFT 0 +#define DPNI_RX_FS_DIST_ENABLE_SIZE 1 +struct dpni_cmd_set_rx_fs_dist { + __le16 dist_size; + u8 enable; + u8 tc; + __le16 miss_flow_id; + __le16 pad; + __le64 key_cfg_iova; +}; + +#define DPNI_RX_HASH_DIST_ENABLE_SHIFT 0 +#define DPNI_RX_HASH_DIST_ENABLE_SIZE 1 +struct dpni_cmd_set_rx_hash_dist { + __le16 dist_size; + u8 enable; + u8 tc; + __le32 pad; + __le64 key_cfg_iova; +}; + +struct dpni_cmd_add_fs_entry { + /* cmd word 0 */ + __le16 options; + u8 tc_id; + u8 key_size; + __le16 index; + __le16 flow_id; + /* cmd word 1 */ + __le64 key_iova; + /* cmd word 2 */ + __le64 mask_iova; + /* cmd word 3 */ + __le64 flc; +}; + +struct dpni_cmd_remove_fs_entry { + /* cmd word 0 */ + __le16 pad0; + u8 tc_id; + u8 key_size; + __le32 pad1; + /* cmd word 1 */ + __le64 key_iova; + /* cmd word 2 */ + __le64 mask_iova; +}; + #endif /* _FSL_DPNI_CMD_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c index d6ac26797cec..220dfc806a24 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c @@ -1598,3 +1598,155 @@ int dpni_get_api_version(struct fsl_mc_io *mc_io, return 0; } + +/** + * dpni_set_rx_fs_dist() - Set Rx flow steering distribution + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPNI object + * @cfg: Distribution configuration + * + * If the FS is already enabled with a previous call the classification + * key will be changed but all the table rules are kept. If the + * existing rules do not match the key the results will not be + * predictable. It is the user responsibility to keep key integrity. + * If cfg.enable is set to 1 the command will create a flow steering table + * and will classify packets according to this table. The packets that + * miss all the table rules will be classified according to settings + * made in dpni_set_rx_hash_dist() + * If cfg.enable is set to 0 the command will clear flow steering table. + * The packets will be classified according to settings made in + * dpni_set_rx_hash_dist() + */ +int dpni_set_rx_fs_dist(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dpni_rx_dist_cfg *cfg) +{ + struct dpni_cmd_set_rx_fs_dist *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPNI_CMDID_SET_RX_FS_DIST, + cmd_flags, + token); + cmd_params = (struct dpni_cmd_set_rx_fs_dist *)cmd.params; + cmd_params->dist_size = cpu_to_le16(cfg->dist_size); + dpni_set_field(cmd_params->enable, RX_FS_DIST_ENABLE, cfg->enable); + cmd_params->tc = cfg->tc; + cmd_params->miss_flow_id = cpu_to_le16(cfg->fs_miss_flow_id); + cmd_params->key_cfg_iova = cpu_to_le64(cfg->key_cfg_iova); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} + +/** + * dpni_set_rx_hash_dist() - Set Rx hash distribution + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPNI object + * @cfg: Distribution configuration + * If cfg.enable is set to 1 the packets will be classified using a hash + * function based on the key received in cfg.key_cfg_iova parameter. + * If cfg.enable is set to 0 the packets will be sent to the default queue + */ +int dpni_set_rx_hash_dist(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dpni_rx_dist_cfg *cfg) +{ + struct dpni_cmd_set_rx_hash_dist *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPNI_CMDID_SET_RX_HASH_DIST, + cmd_flags, + token); + cmd_params = (struct dpni_cmd_set_rx_hash_dist *)cmd.params; + cmd_params->dist_size = cpu_to_le16(cfg->dist_size); + dpni_set_field(cmd_params->enable, RX_HASH_DIST_ENABLE, cfg->enable); + cmd_params->tc = cfg->tc; + cmd_params->key_cfg_iova = cpu_to_le64(cfg->key_cfg_iova); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} + +/** + * dpni_add_fs_entry() - Add Flow Steering entry for a specific traffic class + * (to select a flow ID) + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPNI object + * @tc_id: Traffic class selection (0-7) + * @index: Location in the FS table where to insert the entry. + * Only relevant if MASKING is enabled for FS + * classification on this DPNI, it is ignored for exact match. + * @cfg: Flow steering rule to add + * @action: Action to be taken as result of a classification hit + * + * Return: '0' on Success; Error code otherwise. + */ +int dpni_add_fs_entry(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u8 tc_id, + u16 index, + const struct dpni_rule_cfg *cfg, + const struct dpni_fs_action_cfg *action) +{ + struct dpni_cmd_add_fs_entry *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPNI_CMDID_ADD_FS_ENT, + cmd_flags, + token); + cmd_params = (struct dpni_cmd_add_fs_entry *)cmd.params; + cmd_params->tc_id = tc_id; + cmd_params->key_size = cfg->key_size; + cmd_params->index = cpu_to_le16(index); + cmd_params->key_iova = cpu_to_le64(cfg->key_iova); + cmd_params->mask_iova = cpu_to_le64(cfg->mask_iova); + cmd_params->options = cpu_to_le16(action->options); + cmd_params->flow_id = cpu_to_le16(action->flow_id); + cmd_params->flc = cpu_to_le64(action->flc); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} + +/** + * dpni_remove_fs_entry() - Remove Flow Steering entry from a specific + * traffic class + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPNI object + * @tc_id: Traffic class selection (0-7) + * @cfg: Flow steering rule to remove + * + * Return: '0' on Success; Error code otherwise. + */ +int dpni_remove_fs_entry(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u8 tc_id, + const struct dpni_rule_cfg *cfg) +{ + struct dpni_cmd_remove_fs_entry *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPNI_CMDID_REMOVE_FS_ENT, + cmd_flags, + token); + cmd_params = (struct dpni_cmd_remove_fs_entry *)cmd.params; + cmd_params->tc_id = tc_id; + cmd_params->key_size = cfg->key_size; + cmd_params->key_iova = cpu_to_le64(cfg->key_iova); + cmd_params->mask_iova = cpu_to_le64(cfg->mask_iova); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index b378a00c7c53..a521242e2353 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h @@ -629,6 +629,45 @@ int dpni_set_rx_tc_dist(struct fsl_mc_io *mc_io, const struct dpni_rx_tc_dist_cfg *cfg); /** + * When used for fs_miss_flow_id in function dpni_set_rx_dist, + * will signal to dpni to drop all unclassified frames + */ +#define DPNI_FS_MISS_DROP ((uint16_t)-1) + +/** + * struct dpni_rx_dist_cfg - Rx distribution configuration + * @dist_size: distribution size + * @key_cfg_iova: I/O virtual address of 256 bytes DMA-able memory filled with + * the extractions to be used for the distribution key by calling + * dpni_prepare_key_cfg(); relevant only when enable!=0 otherwise + * it can be '0' + * @enable: enable/disable the distribution. + * @tc: TC id for which distribution is set + * @fs_miss_flow_id: when packet misses all rules from flow steering table and + * hash is disabled it will be put into this queue id; use + * DPNI_FS_MISS_DROP to drop frames. The value of this field is + * used only when flow steering distribution is enabled and hash + * distribution is disabled + */ +struct dpni_rx_dist_cfg { + u16 dist_size; + u64 key_cfg_iova; + u8 enable; + u8 tc; + u16 fs_miss_flow_id; +}; + +int dpni_set_rx_fs_dist(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dpni_rx_dist_cfg *cfg); + +int dpni_set_rx_hash_dist(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dpni_rx_dist_cfg *cfg); + +/** * enum dpni_dest - DPNI destination types * @DPNI_DEST_NONE: Unassigned destination; The queue is set in parked mode and * does not generate FQDAN notifications; user is expected to @@ -816,6 +855,64 @@ struct dpni_rule_cfg { u8 key_size; }; +/** + * Discard matching traffic. If set, this takes precedence over any other + * configuration and matching traffic is always discarded. + */ + #define DPNI_FS_OPT_DISCARD 0x1 + +/** + * Set FLC value. If set, flc member of struct dpni_fs_action_cfg is used to + * override the FLC value set per queue. + * For more details check the Frame Descriptor section in the hardware + * documentation. + */ +#define DPNI_FS_OPT_SET_FLC 0x2 + +/** + * Indicates whether the 6 lowest significant bits of FLC are used for stash + * control. If set, the 6 least significant bits in value are interpreted as + * follows: + * - bits 0-1: indicates the number of 64 byte units of context that are + * stashed. FLC value is interpreted as a memory address in this case, + * excluding the 6 LS bits. + * - bits 2-3: indicates the number of 64 byte units of frame annotation + * to be stashed. Annotation is placed at FD[ADDR]. + * - bits 4-5: indicates the number of 64 byte units of frame data to be + * stashed. Frame data is placed at FD[ADDR] + FD[OFFSET]. + * This flag is ignored if DPNI_FS_OPT_SET_FLC is not specified. + */ +#define DPNI_FS_OPT_SET_STASH_CONTROL 0x4 + +/** + * struct dpni_fs_action_cfg - Action configuration for table look-up + * @flc: FLC value for traffic matching this rule. Please check the + * Frame Descriptor section in the hardware documentation for + * more information. + * @flow_id: Identifies the Rx queue used for matching traffic. Supported + * values are in range 0 to num_queue-1. + * @options: Any combination of DPNI_FS_OPT_ values. + */ +struct dpni_fs_action_cfg { + u64 flc; + u16 flow_id; + u16 options; +}; + +int dpni_add_fs_entry(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u8 tc_id, + u16 index, + const struct dpni_rule_cfg *cfg, + const struct dpni_fs_action_cfg *action); + +int dpni_remove_fs_entry(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u8 tc_id, + const struct dpni_rule_cfg *cfg); + int dpni_get_api_version(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 *major_ver, diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h new file mode 100644 index 000000000000..9af4ac71f347 --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016-2018 NXP + */ + +#ifndef _FSL_DPRTC_CMD_H +#define _FSL_DPRTC_CMD_H + +/* Command versioning */ +#define DPRTC_CMD_BASE_VERSION 1 +#define DPRTC_CMD_ID_OFFSET 4 + +#define DPRTC_CMD(id) (((id) << DPRTC_CMD_ID_OFFSET) | DPRTC_CMD_BASE_VERSION) + +/* Command IDs */ +#define DPRTC_CMDID_CLOSE DPRTC_CMD(0x800) +#define DPRTC_CMDID_OPEN DPRTC_CMD(0x810) + +#define DPRTC_CMDID_SET_FREQ_COMPENSATION DPRTC_CMD(0x1d1) +#define DPRTC_CMDID_GET_FREQ_COMPENSATION DPRTC_CMD(0x1d2) +#define DPRTC_CMDID_GET_TIME DPRTC_CMD(0x1d3) +#define DPRTC_CMDID_SET_TIME DPRTC_CMD(0x1d4) + +#pragma pack(push, 1) +struct dprtc_cmd_open { + __le32 dprtc_id; +}; + +struct dprtc_get_freq_compensation { + __le32 freq_compensation; +}; + +struct dprtc_time { + __le64 time; +}; + +#pragma pack(pop) + +#endif /* _FSL_DPRTC_CMD_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.c b/drivers/net/ethernet/freescale/dpaa2/dprtc.c new file mode 100644 index 000000000000..c13e09bc7b9d --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016-2018 NXP + */ + +#include <linux/fsl/mc.h> + +#include "dprtc.h" +#include "dprtc-cmd.h" + +/** + * dprtc_open() - Open a control session for the specified object. + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @dprtc_id: DPRTC unique ID + * @token: Returned token; use in subsequent API calls + * + * This function can be used to open a control session for an + * already created object; an object may have been declared in + * the DPL or by calling the dprtc_create function. + * This function returns a unique authentication token, + * associated with the specific object ID and the specific MC + * portal; this token must be used in all subsequent commands for + * this specific object + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_open(struct fsl_mc_io *mc_io, + u32 cmd_flags, + int dprtc_id, + u16 *token) +{ + struct dprtc_cmd_open *cmd_params; + struct fsl_mc_command cmd = { 0 }; + int err; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_OPEN, + cmd_flags, + 0); + cmd_params = (struct dprtc_cmd_open *)cmd.params; + cmd_params->dprtc_id = cpu_to_le32(dprtc_id); + + err = mc_send_command(mc_io, &cmd); + if (err) + return err; + + *token = mc_cmd_hdr_read_token(&cmd); + + return 0; +} + +/** + * dprtc_close() - Close the control session of the object + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRTC object + * + * After this function is called, no further operations are + * allowed on the object without opening a new control session. + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_close(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token) +{ + struct fsl_mc_command cmd = { 0 }; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_CLOSE, cmd_flags, + token); + + return mc_send_command(mc_io, &cmd); +} + +/** + * dprtc_set_freq_compensation() - Sets a new frequency compensation value. + * + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRTC object + * @freq_compensation: The new frequency compensation value to set. + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_set_freq_compensation(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u32 freq_compensation) +{ + struct dprtc_get_freq_compensation *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_FREQ_COMPENSATION, + cmd_flags, + token); + cmd_params = (struct dprtc_get_freq_compensation *)cmd.params; + cmd_params->freq_compensation = cpu_to_le32(freq_compensation); + + return mc_send_command(mc_io, &cmd); +} + +/** + * dprtc_get_freq_compensation() - Retrieves the frequency compensation value + * + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRTC object + * @freq_compensation: Frequency compensation value + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_get_freq_compensation(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u32 *freq_compensation) +{ + struct dprtc_get_freq_compensation *rsp_params; + struct fsl_mc_command cmd = { 0 }; + int err; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_FREQ_COMPENSATION, + cmd_flags, + token); + + err = mc_send_command(mc_io, &cmd); + if (err) + return err; + + rsp_params = (struct dprtc_get_freq_compensation *)cmd.params; + *freq_compensation = le32_to_cpu(rsp_params->freq_compensation); + + return 0; +} + +/** + * dprtc_get_time() - Returns the current RTC time. + * + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRTC object + * @time: Current RTC time. + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_get_time(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + uint64_t *time) +{ + struct dprtc_time *rsp_params; + struct fsl_mc_command cmd = { 0 }; + int err; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_TIME, + cmd_flags, + token); + + err = mc_send_command(mc_io, &cmd); + if (err) + return err; + + rsp_params = (struct dprtc_time *)cmd.params; + *time = le64_to_cpu(rsp_params->time); + + return 0; +} + +/** + * dprtc_set_time() - Updates current RTC time. + * + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRTC object + * @time: New RTC time. + * + * Return: '0' on Success; Error code otherwise. + */ +int dprtc_set_time(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + uint64_t time) +{ + struct dprtc_time *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_TIME, + cmd_flags, + token); + cmd_params = (struct dprtc_time *)cmd.params; + cmd_params->time = cpu_to_le64(time); + + return mc_send_command(mc_io, &cmd); +} diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.h b/drivers/net/ethernet/freescale/dpaa2/dprtc.h new file mode 100644 index 000000000000..fe19618d6cdf --- /dev/null +++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016-2018 NXP + */ + +#ifndef __FSL_DPRTC_H +#define __FSL_DPRTC_H + +/* Data Path Real Time Counter API + * Contains initialization APIs and runtime control APIs for RTC + */ + +struct fsl_mc_io; + +int dprtc_open(struct fsl_mc_io *mc_io, + u32 cmd_flags, + int dprtc_id, + u16 *token); + +int dprtc_close(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token); + +int dprtc_set_freq_compensation(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u32 freq_compensation); + +int dprtc_get_freq_compensation(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + u32 *freq_compensation); + +int dprtc_get_time(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + uint64_t *time); + +int dprtc_set_time(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + uint64_t time); + +#endif /* __FSL_DPRTC_H */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index ce74b7a46d07..a17cc973d9a3 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1158,7 +1158,7 @@ static void fec_enet_timeout_work(struct work_struct *work) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -1273,7 +1273,7 @@ skb_done: /* Since we have freed up a buffer, the ring is no longer full */ - if (netif_queue_stopped(ndev)) { + if (netif_tx_queue_stopped(nq)) { entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free >= txq->tx_wake_threshold) netif_tx_wake_queue(nq); @@ -1746,7 +1746,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -2240,7 +2240,7 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index a847b9c3b31a..d79e4e009d63 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -393,11 +393,7 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, */ /* get local capabilities */ - lcl_adv = 0; - if (phy_dev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phy_dev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phy_dev->advertising); /* get link partner capabilities */ rmt_adv = 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 0bd21a493016..3c8da1a18ba0 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3656,12 +3656,7 @@ static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv) if (phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - lcl_adv = 0; - if (phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; - + lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising); flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (flowctrl & FLOW_CTRL_TX) val |= MACCFG1_TX_FLOW; diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index a051e582d541..79d03f8ee7b1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -84,7 +84,7 @@ static void hnae_unmap_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) if (cb->type == DESC_TYPE_SKB) dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); - else + else if (cb->length) dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index f56855e63c96..28e907831b0e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -40,9 +40,9 @@ #define SKB_TMP_LEN(SKB) \ (((SKB)->transport_header - (SKB)->mac_header) + tcp_hdrlen(SKB)) -static void fill_v2_desc(struct hnae_ring *ring, void *priv, - int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu) +static void fill_v2_desc_hw(struct hnae_ring *ring, void *priv, int size, + int send_sz, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) { struct hnae_desc *desc = &ring->desc[ring->next_to_use]; struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; @@ -64,7 +64,7 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, desc_cb->type = type; desc->addr = cpu_to_le64(dma); - desc->tx.send_size = cpu_to_le16((u16)size); + desc->tx.send_size = cpu_to_le16((u16)send_sz); /* config bd buffer end */ hnae_set_bit(rrcfv, HNSV2_TXD_VLD_B, 1); @@ -133,6 +133,14 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, ring_ptr_move_fw(ring, next_to_use); } +static void fill_v2_desc(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) +{ + fill_v2_desc_hw(ring, priv, size, size, dma, frag_end, + buf_num, type, mtu); +} + static const struct acpi_device_id hns_enet_acpi_match[] = { { "HISI00C1", 0 }, { "HISI00C2", 0 }, @@ -289,15 +297,15 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv, /* when the frag size is bigger than hardware, split this frag */ for (k = 0; k < frag_buf_num; k++) - fill_v2_desc(ring, priv, - (k == frag_buf_num - 1) ? + fill_v2_desc_hw(ring, priv, k == 0 ? size : 0, + (k == frag_buf_num - 1) ? sizeoflast : BD_MAX_SEND_SIZE, - dma + BD_MAX_SEND_SIZE * k, - frag_end && (k == frag_buf_num - 1) ? 1 : 0, - buf_num, - (type == DESC_TYPE_SKB && !k) ? + dma + BD_MAX_SEND_SIZE * k, + frag_end && (k == frag_buf_num - 1) ? 1 : 0, + buf_num, + (type == DESC_TYPE_SKB && !k) ? DESC_TYPE_SKB : DESC_TYPE_PAGE, - mtu); + mtu); } netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, @@ -1495,21 +1503,6 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, return phy_mii_ioctl(phy_dev, ifr, cmd); } -/* use only for netconsole to poll with the device without interrupt */ -#ifdef CONFIG_NET_POLL_CONTROLLER -static void hns_nic_poll_controller(struct net_device *ndev) -{ - struct hns_nic_priv *priv = netdev_priv(ndev); - unsigned long flags; - int i; - - local_irq_save(flags); - for (i = 0; i < priv->ae_handle->q_num * 2; i++) - napi_schedule(&priv->ring_data[i].napi); - local_irq_restore(flags); -} -#endif - static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb, struct net_device *ndev) { @@ -1962,9 +1955,6 @@ static const struct net_device_ops hns_nic_netdev_ops = { .ndo_set_features = hns_nic_set_features, .ndo_fix_features = hns_nic_fix_features, .ndo_get_stats64 = hns_nic_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = hns_nic_poll_controller, -#endif .ndo_set_rx_mode = hns_nic_set_rx_mode, .ndo_select_queue = hns_nic_select_queue, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index be9dc08ccf67..038326cfda93 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -46,9 +46,6 @@ enum hclge_mbx_mac_vlan_subcode { HCLGE_MBX_MAC_VLAN_MC_MODIFY, /* modify MC mac addr */ HCLGE_MBX_MAC_VLAN_MC_ADD, /* add new MC mac addr */ HCLGE_MBX_MAC_VLAN_MC_REMOVE, /* remove MC mac addr */ - HCLGE_MBX_MAC_VLAN_MC_FUNC_MTA_ENABLE, /* config func MTA enable */ - HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ, /* read func MTA type */ - HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE, /* update MTA status */ }; /* below are per-VF vlan cfg subcodes */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 564afd4c1323..1b49c5d3340b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -51,6 +51,7 @@ #define HNAE3_KNIC_CLIENT_INITED_B 0x3 #define HNAE3_UNIC_CLIENT_INITED_B 0x4 #define HNAE3_ROCE_CLIENT_INITED_B 0x5 +#define HNAE3_DEV_SUPPORT_FD_B 0x6 #define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\ BIT(HNAE3_DEV_SUPPORT_ROCE_B)) @@ -61,6 +62,9 @@ #define hnae3_dev_dcb_supported(hdev) \ hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) +#define hnae3_dev_fd_supported(hdev) \ + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B) + #define ring_ptr_move_fw(ring, p) \ ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) #define ring_ptr_move_bw(ring, p) \ @@ -84,10 +88,11 @@ struct hnae3_queue { /*hnae3 loop mode*/ enum hnae3_loop { - HNAE3_MAC_INTER_LOOP_MAC, - HNAE3_MAC_INTER_LOOP_SERDES, - HNAE3_MAC_INTER_LOOP_PHY, - HNAE3_MAC_LOOP_NONE, + HNAE3_LOOP_APP, + HNAE3_LOOP_SERIAL_SERDES, + HNAE3_LOOP_PARALLEL_SERDES, + HNAE3_LOOP_PHY, + HNAE3_LOOP_NONE, }; enum hnae3_client_type { @@ -174,6 +179,7 @@ struct hnae3_ae_dev { struct list_head node; u32 flag; enum hnae3_dev_type dev_type; + enum hnae3_reset_type reset_type; void *priv; }; @@ -349,8 +355,6 @@ struct hnae3_ae_ops { const unsigned char *addr); int (*rm_mc_addr)(struct hnae3_handle *handle, const unsigned char *addr); - int (*update_mta_status)(struct hnae3_handle *handle); - void (*set_tso_stats)(struct hnae3_handle *handle, int enable); void (*update_stats)(struct hnae3_handle *handle, struct net_device_stats *net_stats); @@ -402,7 +406,7 @@ struct hnae3_ae_ops { void (*get_channels)(struct hnae3_handle *handle, struct ethtool_channels *ch); void (*get_tqps_and_rss_info)(struct hnae3_handle *h, - u16 *free_tqps, u16 *max_rss_size); + u16 *alloc_tqps, u16 *max_rss_size); int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num); void (*get_flowctrl_adv)(struct hnae3_handle *handle, u32 *flowctrl_adv); @@ -411,6 +415,20 @@ struct hnae3_ae_ops { void (*get_link_mode)(struct hnae3_handle *handle, unsigned long *supported, unsigned long *advertising); + int (*add_fd_entry)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); + int (*del_fd_entry)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); + void (*del_all_fd_entries)(struct hnae3_handle *handle, + bool clear_list); + int (*get_fd_rule_cnt)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); + int (*get_fd_rule_info)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); + int (*get_fd_all_rules)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd, u32 *rule_locs); + int (*restore_fd_rules)(struct hnae3_handle *handle); + void (*enable_fd)(struct hnae3_handle *handle, bool enable); }; struct hnae3_dcb_ops { @@ -478,10 +496,11 @@ struct hnae3_unic_private_info { struct hnae3_queue **tqp; /* array base of all TQPs of this instance */ }; -#define HNAE3_SUPPORT_MAC_LOOPBACK BIT(0) +#define HNAE3_SUPPORT_APP_LOOPBACK BIT(0) #define HNAE3_SUPPORT_PHY_LOOPBACK BIT(1) -#define HNAE3_SUPPORT_SERDES_LOOPBACK BIT(2) +#define HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK BIT(2) #define HNAE3_SUPPORT_VF BIT(3) +#define HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK BIT(4) struct hnae3_handle { struct hnae3_client *client; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 5a4773a9b4a5..e9d4564b8ce1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -21,6 +21,7 @@ static void hns3_clear_all_ring(struct hnae3_handle *h); static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h); +static void hns3_remove_hw_addr(struct net_device *netdev); static const char hns3_driver_name[] = "hns3"; const char hns3_driver_version[] = VERMAGIC_STRING; @@ -225,8 +226,6 @@ void hns3_set_vector_coalesce_tx_gl(struct hns3_enet_tqp_vector *tqp_vector, static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector, struct hns3_nic_priv *priv) { - struct hnae3_handle *h = priv->ae_handle; - /* initialize the configuration for interrupt coalescing. * 1. GL (Interrupt Gap Limiter) * 2. RL (Interrupt Rate Limiter) @@ -239,9 +238,6 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector, tqp_vector->tx_group.coal.int_gl = HNS3_INT_GL_50K; tqp_vector->rx_group.coal.int_gl = HNS3_INT_GL_50K; - /* Default: disable RL */ - h->kinfo.int_rl_setting = 0; - tqp_vector->int_adapt_down = HNS3_INT_ADAPT_DOWN_START; tqp_vector->rx_group.coal.flow_level = HNS3_FLOW_LOW; tqp_vector->tx_group.coal.flow_level = HNS3_FLOW_LOW; @@ -307,12 +303,12 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev) static u16 hns3_get_max_available_channels(struct hnae3_handle *h) { - u16 free_tqps, max_rss_size, max_tqps; + u16 alloc_tqps, max_rss_size, rss_size; - h->ae_algo->ops->get_tqps_and_rss_info(h, &free_tqps, &max_rss_size); - max_tqps = h->kinfo.num_tc * max_rss_size; + h->ae_algo->ops->get_tqps_and_rss_info(h, &alloc_tqps, &max_rss_size); + rss_size = alloc_tqps / h->kinfo.num_tc; - return min_t(u16, max_tqps, (free_tqps + h->kinfo.num_tqps)); + return min_t(u16, rss_size, max_rss_size); } static int hns3_nic_net_up(struct net_device *netdev) @@ -480,9 +476,6 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev) if (netdev->flags & IFF_MULTICAST) { if (__dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync)) netdev_err(netdev, "sync mc address fail\n"); - - if (h->ae_algo->ops->update_mta_status) - h->ae_algo->ops->update_mta_status(h); } } @@ -1290,6 +1283,13 @@ static int hns3_nic_set_features(struct net_device *netdev, return ret; } + if ((changed & NETIF_F_NTUPLE) && h->ae_algo->ops->enable_fd) { + if (features & NETIF_F_NTUPLE) + h->ae_algo->ops->enable_fd(h, true); + else + h->ae_algo->ops->enable_fd(h, false); + } + netdev->features = features; return 0; } @@ -1491,13 +1491,11 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) } ret = h->ae_algo->ops->set_mtu(h, new_mtu); - if (ret) { + if (ret) netdev_err(netdev, "failed to change MTU in hardware %d\n", ret); - return ret; - } - - netdev->mtu = new_mtu; + else + netdev->mtu = new_mtu; /* if the netdev was running earlier, bring it up again */ if (if_running && hns3_nic_net_open(netdev)) @@ -1629,6 +1627,13 @@ static void hns3_disable_sriov(struct pci_dev *pdev) pci_disable_sriov(pdev); } +static void hns3_get_dev_capability(struct pci_dev *pdev, + struct hnae3_ae_dev *ae_dev) +{ + if (pdev->revision >= 0x21) + hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B, 1); +} + /* hns3_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in hns3_pci_tbl @@ -1654,6 +1659,8 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ae_dev->pdev = pdev; ae_dev->flag = ent->driver_data; ae_dev->dev_type = HNAE3_DEV_KNIC; + ae_dev->reset_type = HNAE3_NONE_RESET; + hns3_get_dev_capability(pdev, ae_dev); pci_set_drvdata(pdev, ae_dev); hnae3_register_ae_dev(ae_dev); @@ -1740,7 +1747,7 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; @@ -1752,24 +1759,30 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC; netdev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC; netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC; - if (pdev->revision != 0x20) + if (pdev->revision >= 0x21) { netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + if (!(h->flags & HNAE3_SUPPORT_VF)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + } + } } static int hns3_alloc_buffer(struct hns3_enet_ring *ring, @@ -2187,18 +2200,18 @@ static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb) napi_gro_receive(&ring->tqp_vector->napi, skb); } -static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring, - struct hns3_desc *desc, u32 l234info) +static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring, + struct hns3_desc *desc, u32 l234info, + u16 *vlan_tag) { struct pci_dev *pdev = ring->tqp->handle->pdev; - u16 vlan_tag; if (pdev->revision == 0x20) { - vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); - if (!(vlan_tag & VLAN_VID_MASK)) - vlan_tag = le16_to_cpu(desc->rx.vlan_tag); + *vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); + if (!(*vlan_tag & VLAN_VID_MASK)) + *vlan_tag = le16_to_cpu(desc->rx.vlan_tag); - return vlan_tag; + return (*vlan_tag != 0); } #define HNS3_STRP_OUTER_VLAN 0x1 @@ -2207,17 +2220,14 @@ static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring, switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M, HNS3_RXD_STRP_TAGP_S)) { case HNS3_STRP_OUTER_VLAN: - vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); - break; + *vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); + return true; case HNS3_STRP_INNER_VLAN: - vlan_tag = le16_to_cpu(desc->rx.vlan_tag); - break; + *vlan_tag = le16_to_cpu(desc->rx.vlan_tag); + return true; default: - vlan_tag = 0; - break; + return false; } - - return vlan_tag; } static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, @@ -2319,8 +2329,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { u16 vlan_tag; - vlan_tag = hns3_parse_vlan_tag(ring, desc, l234info); - if (vlan_tag & VLAN_VID_MASK) + if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); @@ -3140,13 +3149,23 @@ static void hns3_init_mac_addr(struct net_device *netdev, bool init) } -static void hns3_uninit_mac_addr(struct net_device *netdev) +static int hns3_restore_fd_rules(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); + int ret = 0; - if (h->ae_algo->ops->rm_uc_addr) - h->ae_algo->ops->rm_uc_addr(h, netdev->dev_addr); + if (h->ae_algo->ops->restore_fd_rules) + ret = h->ae_algo->ops->restore_fd_rules(h); + + return ret; +} + +static void hns3_del_all_fd_rules(struct net_device *netdev, bool clear_list) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (h->ae_algo->ops->del_all_fd_entries) + h->ae_algo->ops->del_all_fd_entries(h, clear_list); } static void hns3_nic_set_priv_ops(struct net_device *netdev) @@ -3166,12 +3185,14 @@ static void hns3_nic_set_priv_ops(struct net_device *netdev) static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; + u16 alloc_tqps, max_rss_size; struct hns3_nic_priv *priv; struct net_device *netdev; int ret; - netdev = alloc_etherdev_mq(sizeof(struct hns3_nic_priv), - hns3_get_max_available_channels(handle)); + handle->ae_algo->ops->get_tqps_and_rss_info(handle, &alloc_tqps, + &max_rss_size); + netdev = alloc_etherdev_mq(sizeof(struct hns3_nic_priv), alloc_tqps); if (!netdev) return -ENOMEM; @@ -3260,9 +3281,13 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) struct hns3_nic_priv *priv = netdev_priv(netdev); int ret; + hns3_remove_hw_addr(netdev); + if (netdev->reg_state != NETREG_UNINITIALIZED) unregister_netdev(netdev); + hns3_del_all_fd_rules(netdev, true); + hns3_force_clear_all_rx_ring(handle); ret = hns3_nic_uninit_vector_data(priv); @@ -3281,8 +3306,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) priv->ring_data = NULL; - hns3_uninit_mac_addr(netdev); - free_netdev(netdev); } @@ -3354,6 +3377,25 @@ static void hns3_recover_hw_addr(struct net_device *ndev) hns3_nic_mc_sync(ndev, ha->addr); } +static void hns3_remove_hw_addr(struct net_device *netdev) +{ + struct netdev_hw_addr_list *list; + struct netdev_hw_addr *ha, *tmp; + + hns3_nic_uc_unsync(netdev, netdev->dev_addr); + + /* go through and unsync uc_addr entries to the device */ + list = &netdev->uc; + list_for_each_entry_safe(ha, tmp, &list->list, list) + hns3_nic_uc_unsync(netdev, ha->addr); + + /* go through and unsync mc_addr entries to the device */ + list = &netdev->mc; + list_for_each_entry_safe(ha, tmp, &list->list, list) + if (ha->refcount > 1) + hns3_nic_mc_unsync(netdev, ha->addr); +} + static void hns3_clear_tx_ring(struct hns3_enet_ring *ring) { while (ring->next_to_clean != ring->next_to_use) { @@ -3490,6 +3532,31 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) return 0; } +static void hns3_store_coal(struct hns3_nic_priv *priv) +{ + /* ethtool only support setting and querying one coal + * configuation for now, so save the vector 0' coal + * configuation here in order to restore it. + */ + memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, + sizeof(struct hns3_enet_coalesce)); + memcpy(&priv->rx_coal, &priv->tqp_vector[0].rx_group.coal, + sizeof(struct hns3_enet_coalesce)); +} + +static void hns3_restore_coal(struct hns3_nic_priv *priv) +{ + u16 vector_num = priv->vector_num; + int i; + + for (i = 0; i < vector_num; i++) { + memcpy(&priv->tqp_vector[i].tx_group.coal, &priv->tx_coal, + sizeof(struct hns3_enet_coalesce)); + memcpy(&priv->tqp_vector[i].rx_group.coal, &priv->rx_coal, + sizeof(struct hns3_enet_coalesce)); + } +} + static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; @@ -3533,9 +3600,13 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) if (!(handle->flags & HNAE3_SUPPORT_VF)) hns3_restore_vlan(netdev); + hns3_restore_fd_rules(netdev); + /* Carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); + hns3_restore_coal(priv); + ret = hns3_nic_init_vector_data(priv); if (ret) return ret; @@ -3551,6 +3622,7 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev); struct net_device *netdev = handle->kinfo.netdev; struct hns3_nic_priv *priv = netdev_priv(netdev); int ret; @@ -3563,11 +3635,20 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) return ret; } + hns3_store_coal(priv); + ret = hns3_uninit_all_ring(priv); if (ret) netdev_err(netdev, "uninit ring error\n"); - hns3_uninit_mac_addr(netdev); + /* it is cumbersome for hardware to pick-and-choose entries for deletion + * from table space. Hence, for function reset software intervention is + * required to delete the entries + */ + if (hns3_dev_ongoing_func_reset(ae_dev)) { + hns3_remove_hw_addr(netdev); + hns3_del_all_fd_rules(netdev, false); + } return ret; } @@ -3597,24 +3678,7 @@ static int hns3_reset_notify(struct hnae3_handle *handle, return ret; } -static void hns3_restore_coal(struct hns3_nic_priv *priv, - struct hns3_enet_coalesce *tx, - struct hns3_enet_coalesce *rx) -{ - u16 vector_num = priv->vector_num; - int i; - - for (i = 0; i < vector_num; i++) { - memcpy(&priv->tqp_vector[i].tx_group.coal, tx, - sizeof(struct hns3_enet_coalesce)); - memcpy(&priv->tqp_vector[i].rx_group.coal, rx, - sizeof(struct hns3_enet_coalesce)); - } -} - -static int hns3_modify_tqp_num(struct net_device *netdev, u16 new_tqp_num, - struct hns3_enet_coalesce *tx, - struct hns3_enet_coalesce *rx) +static int hns3_modify_tqp_num(struct net_device *netdev, u16 new_tqp_num) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = hns3_get_handle(netdev); @@ -3632,7 +3696,7 @@ static int hns3_modify_tqp_num(struct net_device *netdev, u16 new_tqp_num, if (ret) goto err_alloc_vector; - hns3_restore_coal(priv, tx, rx); + hns3_restore_coal(priv); ret = hns3_nic_init_vector_data(priv); if (ret) @@ -3664,7 +3728,6 @@ int hns3_set_channels(struct net_device *netdev, struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = hns3_get_handle(netdev); struct hnae3_knic_private_info *kinfo = &h->kinfo; - struct hns3_enet_coalesce tx_coal, rx_coal; bool if_running = netif_running(netdev); u32 new_tqp_num = ch->combined_count; u16 org_tqp_num; @@ -3696,15 +3759,7 @@ int hns3_set_channels(struct net_device *netdev, goto open_netdev; } - /* Changing the tqp num may also change the vector num, - * ethtool only support setting and querying one coal - * configuation for now, so save the vector 0' coal - * configuation here in order to restore it. - */ - memcpy(&tx_coal, &priv->tqp_vector[0].tx_group.coal, - sizeof(struct hns3_enet_coalesce)); - memcpy(&rx_coal, &priv->tqp_vector[0].rx_group.coal, - sizeof(struct hns3_enet_coalesce)); + hns3_store_coal(priv); hns3_nic_dealloc_vector_data(priv); @@ -3712,10 +3767,9 @@ int hns3_set_channels(struct net_device *netdev, hns3_put_ring_config(priv); org_tqp_num = h->kinfo.num_tqps; - ret = hns3_modify_tqp_num(netdev, new_tqp_num, &tx_coal, &rx_coal); + ret = hns3_modify_tqp_num(netdev, new_tqp_num); if (ret) { - ret = hns3_modify_tqp_num(netdev, org_tqp_num, - &tx_coal, &rx_coal); + ret = hns3_modify_tqp_num(netdev, org_tqp_num); if (ret) { /* If revert to old tqp failed, fatal error occurred */ dev_err(&netdev->dev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 4a56c3d2204f..ac881e8fc05d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -543,6 +543,8 @@ struct hns3_nic_priv { /* Vxlan/Geneve information */ struct hns3_udp_tunnel udp_tnl[HNS3_UDP_TNL_MAX]; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct hns3_enet_coalesce tx_coal; + struct hns3_enet_coalesce rx_coal; }; union l3_hdr_info { @@ -583,6 +585,11 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) writel(value, reg_addr + reg); } +static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev) +{ + return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET)); +} + #define hns3_write_dev(a, reg, value) \ hns3_write_reg((a)->io_base, (reg), (value)) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 8803a8721c8e..7d79a074a214 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -53,7 +53,7 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT) -#define HNS3_SELF_TEST_TYPE_NUM 2 +#define HNS3_SELF_TEST_TYPE_NUM 3 #define HNS3_NIC_LB_TEST_PKT_NUM 1 #define HNS3_NIC_LB_TEST_RING_ID 0 #define HNS3_NIC_LB_TEST_PACKET_SIZE 128 @@ -78,8 +78,9 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) return -EOPNOTSUPP; switch (loop) { - case HNAE3_MAC_INTER_LOOP_SERDES: - case HNAE3_MAC_INTER_LOOP_MAC: + case HNAE3_LOOP_SERIAL_SERDES: + case HNAE3_LOOP_PARALLEL_SERDES: + case HNAE3_LOOP_APP: ret = h->ae_algo->ops->set_loopback(h, loop, en); break; default: @@ -286,13 +287,18 @@ static void hns3_self_test(struct net_device *ndev, if (eth_test->flags != ETH_TEST_FL_OFFLINE) return; - st_param[HNAE3_MAC_INTER_LOOP_MAC][0] = HNAE3_MAC_INTER_LOOP_MAC; - st_param[HNAE3_MAC_INTER_LOOP_MAC][1] = - h->flags & HNAE3_SUPPORT_MAC_LOOPBACK; + st_param[HNAE3_LOOP_APP][0] = HNAE3_LOOP_APP; + st_param[HNAE3_LOOP_APP][1] = + h->flags & HNAE3_SUPPORT_APP_LOOPBACK; - st_param[HNAE3_MAC_INTER_LOOP_SERDES][0] = HNAE3_MAC_INTER_LOOP_SERDES; - st_param[HNAE3_MAC_INTER_LOOP_SERDES][1] = - h->flags & HNAE3_SUPPORT_SERDES_LOOPBACK; + st_param[HNAE3_LOOP_SERIAL_SERDES][0] = HNAE3_LOOP_SERIAL_SERDES; + st_param[HNAE3_LOOP_SERIAL_SERDES][1] = + h->flags & HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK; + + st_param[HNAE3_LOOP_PARALLEL_SERDES][0] = + HNAE3_LOOP_PARALLEL_SERDES; + st_param[HNAE3_LOOP_PARALLEL_SERDES][1] = + h->flags & HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK; if (if_running) ndev->netdev_ops->ndo_stop(ndev); @@ -693,20 +699,33 @@ static int hns3_get_rxnfc(struct net_device *netdev, { struct hnae3_handle *h = hns3_get_handle(netdev); - if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_tuple) + if (!h->ae_algo || !h->ae_algo->ops) return -EOPNOTSUPP; switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = h->kinfo.rss_size; - break; + cmd->data = h->kinfo.num_tqps; + return 0; case ETHTOOL_GRXFH: - return h->ae_algo->ops->get_rss_tuple(h, cmd); + if (h->ae_algo->ops->get_rss_tuple) + return h->ae_algo->ops->get_rss_tuple(h, cmd); + return -EOPNOTSUPP; + case ETHTOOL_GRXCLSRLCNT: + if (h->ae_algo->ops->get_fd_rule_cnt) + return h->ae_algo->ops->get_fd_rule_cnt(h, cmd); + return -EOPNOTSUPP; + case ETHTOOL_GRXCLSRULE: + if (h->ae_algo->ops->get_fd_rule_info) + return h->ae_algo->ops->get_fd_rule_info(h, cmd); + return -EOPNOTSUPP; + case ETHTOOL_GRXCLSRLALL: + if (h->ae_algo->ops->get_fd_all_rules) + return h->ae_algo->ops->get_fd_all_rules(h, cmd, + rule_locs); + return -EOPNOTSUPP; default: return -EOPNOTSUPP; } - - return 0; } static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, @@ -789,12 +808,22 @@ static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); - if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss_tuple) + if (!h->ae_algo || !h->ae_algo->ops) return -EOPNOTSUPP; switch (cmd->cmd) { case ETHTOOL_SRXFH: - return h->ae_algo->ops->set_rss_tuple(h, cmd); + if (h->ae_algo->ops->set_rss_tuple) + return h->ae_algo->ops->set_rss_tuple(h, cmd); + return -EOPNOTSUPP; + case ETHTOOL_SRXCLSRLINS: + if (h->ae_algo->ops->add_fd_entry) + return h->ae_algo->ops->add_fd_entry(h, cmd); + return -EOPNOTSUPP; + case ETHTOOL_SRXCLSRLDEL: + if (h->ae_algo->ops->del_fd_entry) + return h->ae_algo->ops->del_fd_entry(h, cmd); + return -EOPNOTSUPP; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 821d4c2f84bd..1ccde67db770 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -175,21 +175,22 @@ enum hclge_opcode_type { HCLGE_OPC_MAC_VLAN_REMOVE = 0x1001, HCLGE_OPC_MAC_VLAN_TYPE_ID = 0x1002, HCLGE_OPC_MAC_VLAN_INSERT = 0x1003, + HCLGE_OPC_MAC_VLAN_ALLOCATE = 0x1004, HCLGE_OPC_MAC_ETHTYPE_ADD = 0x1010, HCLGE_OPC_MAC_ETHTYPE_REMOVE = 0x1011, - HCLGE_OPC_MAC_VLAN_MASK_SET = 0x1012, - - /* Multicast linear table commands */ - HCLGE_OPC_MTA_MAC_MODE_CFG = 0x1020, - HCLGE_OPC_MTA_MAC_FUNC_CFG = 0x1021, - HCLGE_OPC_MTA_TBL_ITEM_CFG = 0x1022, - HCLGE_OPC_MTA_TBL_ITEM_QUERY = 0x1023, /* VLAN commands */ HCLGE_OPC_VLAN_FILTER_CTRL = 0x1100, HCLGE_OPC_VLAN_FILTER_PF_CFG = 0x1101, HCLGE_OPC_VLAN_FILTER_VF_CFG = 0x1102, + /* Flow Director commands */ + HCLGE_OPC_FD_MODE_CTRL = 0x1200, + HCLGE_OPC_FD_GET_ALLOCATION = 0x1201, + HCLGE_OPC_FD_KEY_CONFIG = 0x1202, + HCLGE_OPC_FD_TCAM_OP = 0x1203, + HCLGE_OPC_FD_AD_OP = 0x1204, + /* MDIO command */ HCLGE_OPC_MDIO_CONFIG = 0x1900, @@ -395,6 +396,8 @@ struct hclge_pf_res_cmd { #define HCLGE_CFG_RSS_SIZE_M GENMASK(31, 24) #define HCLGE_CFG_SPEED_ABILITY_S 0 #define HCLGE_CFG_SPEED_ABILITY_M GENMASK(7, 0) +#define HCLGE_CFG_UMV_TBL_SPACE_S 16 +#define HCLGE_CFG_UMV_TBL_SPACE_M GENMASK(31, 16) struct hclge_cfg_param_cmd { __le32 offset; @@ -584,13 +587,12 @@ struct hclge_mac_vlan_tbl_entry_cmd { u8 rsv2[6]; }; -#define HCLGE_VLAN_MASK_EN_B 0 -struct hclge_mac_vlan_mask_entry_cmd { - u8 rsv0[2]; - u8 vlan_mask; - u8 rsv1; - u8 mac_mask[6]; - u8 rsv2[14]; +#define HCLGE_UMV_SPC_ALC_B 0 +struct hclge_umv_spc_alc_cmd { + u8 allocate; + u8 rsv1[3]; + __le32 space_size; + u8 rsv2[16]; }; #define HCLGE_MAC_MGR_MASK_VLAN_B BIT(0) @@ -615,30 +617,6 @@ struct hclge_mac_mgr_tbl_entry_cmd { u8 rsv3[2]; }; -#define HCLGE_CFG_MTA_MAC_SEL_S 0 -#define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) -#define HCLGE_CFG_MTA_MAC_EN_B 7 -struct hclge_mta_filter_mode_cmd { - u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ - u8 rsv[23]; -}; - -#define HCLGE_CFG_FUNC_MTA_ACCEPT_B 0 -struct hclge_cfg_func_mta_filter_cmd { - u8 accept; /* Only used lowest 1 bit */ - u8 function_id; - u8 rsv[22]; -}; - -#define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0 -#define HCLGE_CFG_MTA_ITEM_IDX_S 0 -#define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) -struct hclge_cfg_func_mta_item_cmd { - __le16 item_idx; /* Only used lowest 12 bit */ - u8 accept; /* Only used lowest 1 bit */ - u8 rsv[21]; -}; - struct hclge_mac_vlan_add_cmd { __le16 flags; __le16 mac_addr_hi16; @@ -778,6 +756,7 @@ struct hclge_reset_cmd { }; #define HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B BIT(0) +#define HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B BIT(2) #define HCLGE_CMD_SERDES_DONE_B BIT(0) #define HCLGE_CMD_SERDES_SUCCESS_B BIT(1) struct hclge_serdes_lb_cmd { @@ -818,6 +797,76 @@ struct hclge_set_led_state_cmd { u8 rsv2[20]; }; +struct hclge_get_fd_mode_cmd { + u8 mode; + u8 enable; + u8 rsv[22]; +}; + +struct hclge_get_fd_allocation_cmd { + __le32 stage1_entry_num; + __le32 stage2_entry_num; + __le16 stage1_counter_num; + __le16 stage2_counter_num; + u8 rsv[12]; +}; + +struct hclge_set_fd_key_config_cmd { + u8 stage; + u8 key_select; + u8 inner_sipv6_word_en; + u8 inner_dipv6_word_en; + u8 outer_sipv6_word_en; + u8 outer_dipv6_word_en; + u8 rsv1[2]; + __le32 tuple_mask; + __le32 meta_data_mask; + u8 rsv2[8]; +}; + +#define HCLGE_FD_EPORT_SW_EN_B 0 +struct hclge_fd_tcam_config_1_cmd { + u8 stage; + u8 xy_sel; + u8 port_info; + u8 rsv1[1]; + __le32 index; + u8 entry_vld; + u8 rsv2[7]; + u8 tcam_data[8]; +}; + +struct hclge_fd_tcam_config_2_cmd { + u8 tcam_data[24]; +}; + +struct hclge_fd_tcam_config_3_cmd { + u8 tcam_data[20]; + u8 rsv[4]; +}; + +#define HCLGE_FD_AD_DROP_B 0 +#define HCLGE_FD_AD_DIRECT_QID_B 1 +#define HCLGE_FD_AD_QID_S 2 +#define HCLGE_FD_AD_QID_M GENMASK(12, 2) +#define HCLGE_FD_AD_USE_COUNTER_B 12 +#define HCLGE_FD_AD_COUNTER_NUM_S 13 +#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(20, 13) +#define HCLGE_FD_AD_NXT_STEP_B 20 +#define HCLGE_FD_AD_NXT_KEY_S 21 +#define HCLGE_FD_AD_NXT_KEY_M GENMASK(26, 21) +#define HCLGE_FD_AD_WR_RULE_ID_B 0 +#define HCLGE_FD_AD_RULE_ID_S 1 +#define HCLGE_FD_AD_RULE_ID_M GENMASK(13, 1) + +struct hclge_fd_ad_config_cmd { + u8 stage; + u8 rsv1[3]; + __le32 index; + __le64 ad_data; + u8 rsv2[8]; +}; + int hclge_cmd_init(struct hclge_dev *hdev); static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 92f19384e258..e72f724123d7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -184,7 +184,9 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) if (ret) return ret; - hclge_tm_schd_info_update(hdev, num_tc); + ret = hclge_tm_schd_info_update(hdev, num_tc); + if (ret) + return ret; ret = hclge_ieee_ets_to_tm_info(hdev, ets); if (ret) @@ -310,7 +312,9 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc) return -EINVAL; } - hclge_tm_schd_info_update(hdev, tc); + ret = hclge_tm_schd_info_update(hdev, tc); + if (ret) + return ret; ret = hclge_tm_prio_tc_info_update(hdev, prio_tc); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 2de5a0061dc9..ca1a93664d0e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -25,12 +25,11 @@ #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) -static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, - enum hclge_mta_dmac_sel_type mta_mac_sel, - bool enable); static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu); static int hclge_init_vlan_config(struct hclge_dev *hdev); static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev); +static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, + u16 *allocated_size, bool is_alloc); static struct hnae3_ae_algo ae_algo; @@ -49,8 +48,9 @@ static const struct pci_device_id ae_algo_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl); static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = { - "Mac Loopback test", - "Serdes Loopback test", + "App Loopback test", + "Serdes serial Loopback test", + "Serdes parallel Loopback test", "Phy Loopback test" }; @@ -475,7 +475,10 @@ static void hclge_update_stats(struct hnae3_handle *handle, static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) { -#define HCLGE_LOOPBACK_TEST_FLAGS 0x7 +#define HCLGE_LOOPBACK_TEST_FLAGS (HNAE3_SUPPORT_APP_LOOPBACK |\ + HNAE3_SUPPORT_PHY_LOOPBACK |\ + HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK |\ + HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK) struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -489,15 +492,17 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) if (stringset == ETH_SS_TEST) { /* clear loopback bit flags at first */ handle->flags = (handle->flags & (~HCLGE_LOOPBACK_TEST_FLAGS)); - if (hdev->hw.mac.speed == HCLGE_MAC_SPEED_10M || + if (hdev->pdev->revision >= 0x21 || + hdev->hw.mac.speed == HCLGE_MAC_SPEED_10M || hdev->hw.mac.speed == HCLGE_MAC_SPEED_100M || hdev->hw.mac.speed == HCLGE_MAC_SPEED_1G) { count += 1; - handle->flags |= HNAE3_SUPPORT_MAC_LOOPBACK; + handle->flags |= HNAE3_SUPPORT_APP_LOOPBACK; } - count++; - handle->flags |= HNAE3_SUPPORT_SERDES_LOOPBACK; + count += 2; + handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK; + handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK; } else if (stringset == ETH_SS_STATS) { count = ARRAY_SIZE(g_mac_stats_string) + hclge_tqps_get_sset_count(handle, stringset); @@ -521,21 +526,27 @@ static void hclge_get_strings(struct hnae3_handle *handle, p); p = hclge_tqps_get_strings(handle, p); } else if (stringset == ETH_SS_TEST) { - if (handle->flags & HNAE3_SUPPORT_MAC_LOOPBACK) { + if (handle->flags & HNAE3_SUPPORT_APP_LOOPBACK) { memcpy(p, - hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_MAC], + hns3_nic_test_strs[HNAE3_LOOP_APP], ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - if (handle->flags & HNAE3_SUPPORT_SERDES_LOOPBACK) { + if (handle->flags & HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK) { memcpy(p, - hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_SERDES], + hns3_nic_test_strs[HNAE3_LOOP_SERIAL_SERDES], + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + if (handle->flags & HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK) { + memcpy(p, + hns3_nic_test_strs[HNAE3_LOOP_PARALLEL_SERDES], ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } if (handle->flags & HNAE3_SUPPORT_PHY_LOOPBACK) { memcpy(p, - hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_PHY], + hns3_nic_test_strs[HNAE3_LOOP_PHY], ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } @@ -766,6 +777,11 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]), HCLGE_CFG_SPEED_ABILITY_M, HCLGE_CFG_SPEED_ABILITY_S); + cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_UMV_TBL_SPACE_M, + HCLGE_CFG_UMV_TBL_SPACE_S); + if (!cfg->umv_space) + cfg->umv_space = HCLGE_DEFAULT_UMV_SPACE_PER_PF; } /* hclge_get_cfg: query the static parameter from flash @@ -844,6 +860,7 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->tm_info.num_pg = 1; hdev->tc_max = cfg.tc_num; hdev->tm_info.hw_pfc_map = 0; + hdev->wanted_umv_size = cfg.umv_space; ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed); if (ret) { @@ -1344,11 +1361,13 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev, static int hclge_rx_buffer_calc(struct hclge_dev *hdev, struct hclge_pkt_buf_alloc *buf_alloc) { - u32 rx_all = hdev->pkt_buf_size; +#define HCLGE_BUF_SIZE_UNIT 128 + u32 rx_all = hdev->pkt_buf_size, aligned_mps; int no_pfc_priv_num, pfc_priv_num; struct hclge_priv_buf *priv; int i; + aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT); rx_all -= hclge_get_tx_buff_alloced(buf_alloc); /* When DCB is not supported, rx private @@ -1367,13 +1386,13 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev, if (hdev->hw_tc_map & BIT(i)) { priv->enable = 1; if (hdev->tm_info.hw_pfc_map & BIT(i)) { - priv->wl.low = hdev->mps; - priv->wl.high = priv->wl.low + hdev->mps; + priv->wl.low = aligned_mps; + priv->wl.high = priv->wl.low + aligned_mps; priv->buf_size = priv->wl.high + HCLGE_DEFAULT_DV; } else { priv->wl.low = 0; - priv->wl.high = 2 * hdev->mps; + priv->wl.high = 2 * aligned_mps; priv->buf_size = priv->wl.high; } } else { @@ -1405,11 +1424,11 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev, if (hdev->tm_info.hw_pfc_map & BIT(i)) { priv->wl.low = 128; - priv->wl.high = priv->wl.low + hdev->mps; + priv->wl.high = priv->wl.low + aligned_mps; priv->buf_size = priv->wl.high + HCLGE_DEFAULT_DV; } else { priv->wl.low = 0; - priv->wl.high = hdev->mps; + priv->wl.high = aligned_mps; priv->buf_size = priv->wl.high; } } @@ -1925,40 +1944,13 @@ static int hclge_get_autoneg(struct hnae3_handle *handle) return hdev->hw.mac.autoneg; } -static int hclge_set_default_mac_vlan_mask(struct hclge_dev *hdev, - bool mask_vlan, - u8 *mac_mask) -{ - struct hclge_mac_vlan_mask_entry_cmd *req; - struct hclge_desc desc; - int status; - - req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false); - - hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B, - mask_vlan ? 1 : 0); - ether_addr_copy(req->mac_mask, mac_mask); - - status = hclge_cmd_send(&hdev->hw, &desc, 1); - if (status) - dev_err(&hdev->pdev->dev, - "Config mac_vlan_mask failed for cmd_send, ret =%d\n", - status); - - return status; -} - static int hclge_mac_init(struct hclge_dev *hdev) { struct hnae3_handle *handle = &hdev->vport[0].nic; struct net_device *netdev = handle->kinfo.netdev; struct hclge_mac *mac = &hdev->hw.mac; - u8 mac_mask[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; - struct hclge_vport *vport; int mtu; int ret; - int i; hdev->hw.mac.duplex = HCLGE_MAC_FULL; ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, @@ -1971,39 +1963,6 @@ static int hclge_mac_init(struct hclge_dev *hdev) mac->link = 0; - /* Initialize the MTA table work mode */ - hdev->enable_mta = true; - hdev->mta_mac_sel_type = HCLGE_MAC_ADDR_47_36; - - ret = hclge_set_mta_filter_mode(hdev, - hdev->mta_mac_sel_type, - hdev->enable_mta); - if (ret) { - dev_err(&hdev->pdev->dev, "set mta filter mode failed %d\n", - ret); - return ret; - } - - for (i = 0; i < hdev->num_alloc_vport; i++) { - vport = &hdev->vport[i]; - vport->accept_mta_mc = false; - - memset(vport->mta_shadow, 0, sizeof(vport->mta_shadow)); - ret = hclge_cfg_func_mta_filter(hdev, vport->vport_id, false); - if (ret) { - dev_err(&hdev->pdev->dev, - "set mta filter mode fail ret=%d\n", ret); - return ret; - } - } - - ret = hclge_set_default_mac_vlan_mask(hdev, true, mac_mask); - if (ret) { - dev_err(&hdev->pdev->dev, - "set default mac_vlan_mask fail ret=%d\n", ret); - return ret; - } - if (netdev) mtu = netdev->mtu; else @@ -2499,8 +2458,13 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev) static void hclge_reset(struct hclge_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hnae3_handle *handle; + /* Initialize ae_dev reset status as well, in case enet layer wants to + * know if device is undergoing reset + */ + ae_dev->reset_type = hdev->reset_type; /* perform reset of the stack & ae device for a client */ handle = &hdev->vport[0].nic; rtnl_lock(); @@ -2521,6 +2485,7 @@ static void hclge_reset(struct hclge_dev *hdev) hclge_notify_client(hdev, HNAE3_UP_CLIENT); handle->last_reset_time = jiffies; rtnl_unlock(); + ae_dev->reset_type = HNAE3_NONE_RESET; } static void hclge_reset_event(struct hnae3_handle *handle) @@ -3314,6 +3279,1281 @@ static void hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, hclge_cmd_set_promisc_mode(hdev, ¶m); } +static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode) +{ + struct hclge_get_fd_mode_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_MODE_CTRL, true); + + req = (struct hclge_get_fd_mode_cmd *)desc.data; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "get fd mode fail, ret=%d\n", ret); + return ret; + } + + *fd_mode = req->mode; + + return ret; +} + +static int hclge_get_fd_allocation(struct hclge_dev *hdev, + u32 *stage1_entry_num, + u32 *stage2_entry_num, + u16 *stage1_counter_num, + u16 *stage2_counter_num) +{ + struct hclge_get_fd_allocation_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_GET_ALLOCATION, true); + + req = (struct hclge_get_fd_allocation_cmd *)desc.data; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "query fd allocation fail, ret=%d\n", + ret); + return ret; + } + + *stage1_entry_num = le32_to_cpu(req->stage1_entry_num); + *stage2_entry_num = le32_to_cpu(req->stage2_entry_num); + *stage1_counter_num = le16_to_cpu(req->stage1_counter_num); + *stage2_counter_num = le16_to_cpu(req->stage2_counter_num); + + return ret; +} + +static int hclge_set_fd_key_config(struct hclge_dev *hdev, int stage_num) +{ + struct hclge_set_fd_key_config_cmd *req; + struct hclge_fd_key_cfg *stage; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_KEY_CONFIG, false); + + req = (struct hclge_set_fd_key_config_cmd *)desc.data; + stage = &hdev->fd_cfg.key_cfg[stage_num]; + req->stage = stage_num; + req->key_select = stage->key_sel; + req->inner_sipv6_word_en = stage->inner_sipv6_word_en; + req->inner_dipv6_word_en = stage->inner_dipv6_word_en; + req->outer_sipv6_word_en = stage->outer_sipv6_word_en; + req->outer_dipv6_word_en = stage->outer_dipv6_word_en; + req->tuple_mask = cpu_to_le32(~stage->tuple_active); + req->meta_data_mask = cpu_to_le32(~stage->meta_data_active); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, "set fd key fail, ret=%d\n", ret); + + return ret; +} + +static int hclge_init_fd_config(struct hclge_dev *hdev) +{ +#define LOW_2_WORDS 0x03 + struct hclge_fd_key_cfg *key_cfg; + int ret; + + if (!hnae3_dev_fd_supported(hdev)) + return 0; + + ret = hclge_get_fd_mode(hdev, &hdev->fd_cfg.fd_mode); + if (ret) + return ret; + + switch (hdev->fd_cfg.fd_mode) { + case HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1: + hdev->fd_cfg.max_key_length = MAX_KEY_LENGTH; + break; + case HCLGE_FD_MODE_DEPTH_4K_WIDTH_200B_STAGE_1: + hdev->fd_cfg.max_key_length = MAX_KEY_LENGTH / 2; + break; + default: + dev_err(&hdev->pdev->dev, + "Unsupported flow director mode %d\n", + hdev->fd_cfg.fd_mode); + return -EOPNOTSUPP; + } + + hdev->fd_cfg.fd_en = true; + hdev->fd_cfg.proto_support = + TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW | + UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW; + key_cfg = &hdev->fd_cfg.key_cfg[HCLGE_FD_STAGE_1]; + key_cfg->key_sel = HCLGE_FD_KEY_BASE_ON_TUPLE, + key_cfg->inner_sipv6_word_en = LOW_2_WORDS; + key_cfg->inner_dipv6_word_en = LOW_2_WORDS; + key_cfg->outer_sipv6_word_en = 0; + key_cfg->outer_dipv6_word_en = 0; + + key_cfg->tuple_active = BIT(INNER_VLAN_TAG_FST) | BIT(INNER_ETH_TYPE) | + BIT(INNER_IP_PROTO) | BIT(INNER_IP_TOS) | + BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) | + BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); + + /* If use max 400bit key, we can support tuples for ether type */ + if (hdev->fd_cfg.max_key_length == MAX_KEY_LENGTH) { + hdev->fd_cfg.proto_support |= ETHER_FLOW; + key_cfg->tuple_active |= + BIT(INNER_DST_MAC) | BIT(INNER_SRC_MAC); + } + + /* roce_type is used to filter roce frames + * dst_vport is used to specify the rule + */ + key_cfg->meta_data_active = BIT(ROCE_TYPE) | BIT(DST_VPORT); + + ret = hclge_get_fd_allocation(hdev, + &hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1], + &hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_2], + &hdev->fd_cfg.cnt_num[HCLGE_FD_STAGE_1], + &hdev->fd_cfg.cnt_num[HCLGE_FD_STAGE_2]); + if (ret) + return ret; + + return hclge_set_fd_key_config(hdev, HCLGE_FD_STAGE_1); +} + +static int hclge_fd_tcam_config(struct hclge_dev *hdev, u8 stage, bool sel_x, + int loc, u8 *key, bool is_add) +{ + struct hclge_fd_tcam_config_1_cmd *req1; + struct hclge_fd_tcam_config_2_cmd *req2; + struct hclge_fd_tcam_config_3_cmd *req3; + struct hclge_desc desc[3]; + int ret; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, false); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_FD_TCAM_OP, false); + desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_FD_TCAM_OP, false); + + req1 = (struct hclge_fd_tcam_config_1_cmd *)desc[0].data; + req2 = (struct hclge_fd_tcam_config_2_cmd *)desc[1].data; + req3 = (struct hclge_fd_tcam_config_3_cmd *)desc[2].data; + + req1->stage = stage; + req1->xy_sel = sel_x ? 1 : 0; + hnae3_set_bit(req1->port_info, HCLGE_FD_EPORT_SW_EN_B, 0); + req1->index = cpu_to_le32(loc); + req1->entry_vld = sel_x ? is_add : 0; + + if (key) { + memcpy(req1->tcam_data, &key[0], sizeof(req1->tcam_data)); + memcpy(req2->tcam_data, &key[sizeof(req1->tcam_data)], + sizeof(req2->tcam_data)); + memcpy(req3->tcam_data, &key[sizeof(req1->tcam_data) + + sizeof(req2->tcam_data)], sizeof(req3->tcam_data)); + } + + ret = hclge_cmd_send(&hdev->hw, desc, 3); + if (ret) + dev_err(&hdev->pdev->dev, + "config tcam key fail, ret=%d\n", + ret); + + return ret; +} + +static int hclge_fd_ad_config(struct hclge_dev *hdev, u8 stage, int loc, + struct hclge_fd_ad_data *action) +{ + struct hclge_fd_ad_config_cmd *req; + struct hclge_desc desc; + u64 ad_data = 0; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_AD_OP, false); + + req = (struct hclge_fd_ad_config_cmd *)desc.data; + req->index = cpu_to_le32(loc); + req->stage = stage; + + hnae3_set_bit(ad_data, HCLGE_FD_AD_WR_RULE_ID_B, + action->write_rule_id_to_bd); + hnae3_set_field(ad_data, HCLGE_FD_AD_RULE_ID_M, HCLGE_FD_AD_RULE_ID_S, + action->rule_id); + ad_data <<= 32; + hnae3_set_bit(ad_data, HCLGE_FD_AD_DROP_B, action->drop_packet); + hnae3_set_bit(ad_data, HCLGE_FD_AD_DIRECT_QID_B, + action->forward_to_direct_queue); + hnae3_set_field(ad_data, HCLGE_FD_AD_QID_M, HCLGE_FD_AD_QID_S, + action->queue_id); + hnae3_set_bit(ad_data, HCLGE_FD_AD_USE_COUNTER_B, action->use_counter); + hnae3_set_field(ad_data, HCLGE_FD_AD_COUNTER_NUM_M, + HCLGE_FD_AD_COUNTER_NUM_S, action->counter_id); + hnae3_set_bit(ad_data, HCLGE_FD_AD_NXT_STEP_B, action->use_next_stage); + hnae3_set_field(ad_data, HCLGE_FD_AD_NXT_KEY_M, HCLGE_FD_AD_NXT_KEY_S, + action->counter_id); + + req->ad_data = cpu_to_le64(ad_data); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, "fd ad config fail, ret=%d\n", ret); + + return ret; +} + +static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y, + struct hclge_fd_rule *rule) +{ + u16 tmp_x_s, tmp_y_s; + u32 tmp_x_l, tmp_y_l; + int i; + + if (rule->unused_tuple & tuple_bit) + return true; + + switch (tuple_bit) { + case 0: + return false; + case BIT(INNER_DST_MAC): + for (i = 0; i < 6; i++) { + calc_x(key_x[5 - i], rule->tuples.dst_mac[i], + rule->tuples_mask.dst_mac[i]); + calc_y(key_y[5 - i], rule->tuples.dst_mac[i], + rule->tuples_mask.dst_mac[i]); + } + + return true; + case BIT(INNER_SRC_MAC): + for (i = 0; i < 6; i++) { + calc_x(key_x[5 - i], rule->tuples.src_mac[i], + rule->tuples.src_mac[i]); + calc_y(key_y[5 - i], rule->tuples.src_mac[i], + rule->tuples.src_mac[i]); + } + + return true; + case BIT(INNER_VLAN_TAG_FST): + calc_x(tmp_x_s, rule->tuples.vlan_tag1, + rule->tuples_mask.vlan_tag1); + calc_y(tmp_y_s, rule->tuples.vlan_tag1, + rule->tuples_mask.vlan_tag1); + *(__le16 *)key_x = cpu_to_le16(tmp_x_s); + *(__le16 *)key_y = cpu_to_le16(tmp_y_s); + + return true; + case BIT(INNER_ETH_TYPE): + calc_x(tmp_x_s, rule->tuples.ether_proto, + rule->tuples_mask.ether_proto); + calc_y(tmp_y_s, rule->tuples.ether_proto, + rule->tuples_mask.ether_proto); + *(__le16 *)key_x = cpu_to_le16(tmp_x_s); + *(__le16 *)key_y = cpu_to_le16(tmp_y_s); + + return true; + case BIT(INNER_IP_TOS): + calc_x(*key_x, rule->tuples.ip_tos, rule->tuples_mask.ip_tos); + calc_y(*key_y, rule->tuples.ip_tos, rule->tuples_mask.ip_tos); + + return true; + case BIT(INNER_IP_PROTO): + calc_x(*key_x, rule->tuples.ip_proto, + rule->tuples_mask.ip_proto); + calc_y(*key_y, rule->tuples.ip_proto, + rule->tuples_mask.ip_proto); + + return true; + case BIT(INNER_SRC_IP): + calc_x(tmp_x_l, rule->tuples.src_ip[3], + rule->tuples_mask.src_ip[3]); + calc_y(tmp_y_l, rule->tuples.src_ip[3], + rule->tuples_mask.src_ip[3]); + *(__le32 *)key_x = cpu_to_le32(tmp_x_l); + *(__le32 *)key_y = cpu_to_le32(tmp_y_l); + + return true; + case BIT(INNER_DST_IP): + calc_x(tmp_x_l, rule->tuples.dst_ip[3], + rule->tuples_mask.dst_ip[3]); + calc_y(tmp_y_l, rule->tuples.dst_ip[3], + rule->tuples_mask.dst_ip[3]); + *(__le32 *)key_x = cpu_to_le32(tmp_x_l); + *(__le32 *)key_y = cpu_to_le32(tmp_y_l); + + return true; + case BIT(INNER_SRC_PORT): + calc_x(tmp_x_s, rule->tuples.src_port, + rule->tuples_mask.src_port); + calc_y(tmp_y_s, rule->tuples.src_port, + rule->tuples_mask.src_port); + *(__le16 *)key_x = cpu_to_le16(tmp_x_s); + *(__le16 *)key_y = cpu_to_le16(tmp_y_s); + + return true; + case BIT(INNER_DST_PORT): + calc_x(tmp_x_s, rule->tuples.dst_port, + rule->tuples_mask.dst_port); + calc_y(tmp_y_s, rule->tuples.dst_port, + rule->tuples_mask.dst_port); + *(__le16 *)key_x = cpu_to_le16(tmp_x_s); + *(__le16 *)key_y = cpu_to_le16(tmp_y_s); + + return true; + default: + return false; + } +} + +static u32 hclge_get_port_number(enum HLCGE_PORT_TYPE port_type, u8 pf_id, + u8 vf_id, u8 network_port_id) +{ + u32 port_number = 0; + + if (port_type == HOST_PORT) { + hnae3_set_field(port_number, HCLGE_PF_ID_M, HCLGE_PF_ID_S, + pf_id); + hnae3_set_field(port_number, HCLGE_VF_ID_M, HCLGE_VF_ID_S, + vf_id); + hnae3_set_bit(port_number, HCLGE_PORT_TYPE_B, HOST_PORT); + } else { + hnae3_set_field(port_number, HCLGE_NETWORK_PORT_ID_M, + HCLGE_NETWORK_PORT_ID_S, network_port_id); + hnae3_set_bit(port_number, HCLGE_PORT_TYPE_B, NETWORK_PORT); + } + + return port_number; +} + +static void hclge_fd_convert_meta_data(struct hclge_fd_key_cfg *key_cfg, + __le32 *key_x, __le32 *key_y, + struct hclge_fd_rule *rule) +{ + u32 tuple_bit, meta_data = 0, tmp_x, tmp_y, port_number; + u8 cur_pos = 0, tuple_size, shift_bits; + int i; + + for (i = 0; i < MAX_META_DATA; i++) { + tuple_size = meta_data_key_info[i].key_length; + tuple_bit = key_cfg->meta_data_active & BIT(i); + + switch (tuple_bit) { + case BIT(ROCE_TYPE): + hnae3_set_bit(meta_data, cur_pos, NIC_PACKET); + cur_pos += tuple_size; + break; + case BIT(DST_VPORT): + port_number = hclge_get_port_number(HOST_PORT, 0, + rule->vf_id, 0); + hnae3_set_field(meta_data, + GENMASK(cur_pos + tuple_size, cur_pos), + cur_pos, port_number); + cur_pos += tuple_size; + break; + default: + break; + } + } + + calc_x(tmp_x, meta_data, 0xFFFFFFFF); + calc_y(tmp_y, meta_data, 0xFFFFFFFF); + shift_bits = sizeof(meta_data) * 8 - cur_pos; + + *key_x = cpu_to_le32(tmp_x << shift_bits); + *key_y = cpu_to_le32(tmp_y << shift_bits); +} + +/* A complete key is combined with meta data key and tuple key. + * Meta data key is stored at the MSB region, and tuple key is stored at + * the LSB region, unused bits will be filled 0. + */ +static int hclge_config_key(struct hclge_dev *hdev, u8 stage, + struct hclge_fd_rule *rule) +{ + struct hclge_fd_key_cfg *key_cfg = &hdev->fd_cfg.key_cfg[stage]; + u8 key_x[MAX_KEY_BYTES], key_y[MAX_KEY_BYTES]; + u8 *cur_key_x, *cur_key_y; + int i, ret, tuple_size; + u8 meta_data_region; + + memset(key_x, 0, sizeof(key_x)); + memset(key_y, 0, sizeof(key_y)); + cur_key_x = key_x; + cur_key_y = key_y; + + for (i = 0 ; i < MAX_TUPLE; i++) { + bool tuple_valid; + u32 check_tuple; + + tuple_size = tuple_key_info[i].key_length / 8; + check_tuple = key_cfg->tuple_active & BIT(i); + + tuple_valid = hclge_fd_convert_tuple(check_tuple, cur_key_x, + cur_key_y, rule); + if (tuple_valid) { + cur_key_x += tuple_size; + cur_key_y += tuple_size; + } + } + + meta_data_region = hdev->fd_cfg.max_key_length / 8 - + MAX_META_DATA_LENGTH / 8; + + hclge_fd_convert_meta_data(key_cfg, + (__le32 *)(key_x + meta_data_region), + (__le32 *)(key_y + meta_data_region), + rule); + + ret = hclge_fd_tcam_config(hdev, stage, false, rule->location, key_y, + true); + if (ret) { + dev_err(&hdev->pdev->dev, + "fd key_y config fail, loc=%d, ret=%d\n", + rule->queue_id, ret); + return ret; + } + + ret = hclge_fd_tcam_config(hdev, stage, true, rule->location, key_x, + true); + if (ret) + dev_err(&hdev->pdev->dev, + "fd key_x config fail, loc=%d, ret=%d\n", + rule->queue_id, ret); + return ret; +} + +static int hclge_config_action(struct hclge_dev *hdev, u8 stage, + struct hclge_fd_rule *rule) +{ + struct hclge_fd_ad_data ad_data; + + ad_data.ad_id = rule->location; + + if (rule->action == HCLGE_FD_ACTION_DROP_PACKET) { + ad_data.drop_packet = true; + ad_data.forward_to_direct_queue = false; + ad_data.queue_id = 0; + } else { + ad_data.drop_packet = false; + ad_data.forward_to_direct_queue = true; + ad_data.queue_id = rule->queue_id; + } + + ad_data.use_counter = false; + ad_data.counter_id = 0; + + ad_data.use_next_stage = false; + ad_data.next_input_key = 0; + + ad_data.write_rule_id_to_bd = true; + ad_data.rule_id = rule->location; + + return hclge_fd_ad_config(hdev, stage, ad_data.ad_id, &ad_data); +} + +static int hclge_fd_check_spec(struct hclge_dev *hdev, + struct ethtool_rx_flow_spec *fs, u32 *unused) +{ + struct ethtool_tcpip4_spec *tcp_ip4_spec; + struct ethtool_usrip4_spec *usr_ip4_spec; + struct ethtool_tcpip6_spec *tcp_ip6_spec; + struct ethtool_usrip6_spec *usr_ip6_spec; + struct ethhdr *ether_spec; + + if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) + return -EINVAL; + + if (!(fs->flow_type & hdev->fd_cfg.proto_support)) + return -EOPNOTSUPP; + + if ((fs->flow_type & FLOW_EXT) && + (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) { + dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n"); + return -EOPNOTSUPP; + } + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { + case SCTP_V4_FLOW: + case TCP_V4_FLOW: + case UDP_V4_FLOW: + tcp_ip4_spec = &fs->h_u.tcp_ip4_spec; + *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC); + + if (!tcp_ip4_spec->ip4src) + *unused |= BIT(INNER_SRC_IP); + + if (!tcp_ip4_spec->ip4dst) + *unused |= BIT(INNER_DST_IP); + + if (!tcp_ip4_spec->psrc) + *unused |= BIT(INNER_SRC_PORT); + + if (!tcp_ip4_spec->pdst) + *unused |= BIT(INNER_DST_PORT); + + if (!tcp_ip4_spec->tos) + *unused |= BIT(INNER_IP_TOS); + + break; + case IP_USER_FLOW: + usr_ip4_spec = &fs->h_u.usr_ip4_spec; + *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); + + if (!usr_ip4_spec->ip4src) + *unused |= BIT(INNER_SRC_IP); + + if (!usr_ip4_spec->ip4dst) + *unused |= BIT(INNER_DST_IP); + + if (!usr_ip4_spec->tos) + *unused |= BIT(INNER_IP_TOS); + + if (!usr_ip4_spec->proto) + *unused |= BIT(INNER_IP_PROTO); + + if (usr_ip4_spec->l4_4_bytes) + return -EOPNOTSUPP; + + if (usr_ip4_spec->ip_ver != ETH_RX_NFC_IP4) + return -EOPNOTSUPP; + + break; + case SCTP_V6_FLOW: + case TCP_V6_FLOW: + case UDP_V6_FLOW: + tcp_ip6_spec = &fs->h_u.tcp_ip6_spec; + *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_IP_TOS); + + if (!tcp_ip6_spec->ip6src[0] && !tcp_ip6_spec->ip6src[1] && + !tcp_ip6_spec->ip6src[2] && !tcp_ip6_spec->ip6src[3]) + *unused |= BIT(INNER_SRC_IP); + + if (!tcp_ip6_spec->ip6dst[0] && !tcp_ip6_spec->ip6dst[1] && + !tcp_ip6_spec->ip6dst[2] && !tcp_ip6_spec->ip6dst[3]) + *unused |= BIT(INNER_DST_IP); + + if (!tcp_ip6_spec->psrc) + *unused |= BIT(INNER_SRC_PORT); + + if (!tcp_ip6_spec->pdst) + *unused |= BIT(INNER_DST_PORT); + + if (tcp_ip6_spec->tclass) + return -EOPNOTSUPP; + + break; + case IPV6_USER_FLOW: + usr_ip6_spec = &fs->h_u.usr_ip6_spec; + *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) | + BIT(INNER_DST_PORT); + + if (!usr_ip6_spec->ip6src[0] && !usr_ip6_spec->ip6src[1] && + !usr_ip6_spec->ip6src[2] && !usr_ip6_spec->ip6src[3]) + *unused |= BIT(INNER_SRC_IP); + + if (!usr_ip6_spec->ip6dst[0] && !usr_ip6_spec->ip6dst[1] && + !usr_ip6_spec->ip6dst[2] && !usr_ip6_spec->ip6dst[3]) + *unused |= BIT(INNER_DST_IP); + + if (!usr_ip6_spec->l4_proto) + *unused |= BIT(INNER_IP_PROTO); + + if (usr_ip6_spec->tclass) + return -EOPNOTSUPP; + + if (usr_ip6_spec->l4_4_bytes) + return -EOPNOTSUPP; + + break; + case ETHER_FLOW: + ether_spec = &fs->h_u.ether_spec; + *unused |= BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) | + BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT) | + BIT(INNER_IP_TOS) | BIT(INNER_IP_PROTO); + + if (is_zero_ether_addr(ether_spec->h_source)) + *unused |= BIT(INNER_SRC_MAC); + + if (is_zero_ether_addr(ether_spec->h_dest)) + *unused |= BIT(INNER_DST_MAC); + + if (!ether_spec->h_proto) + *unused |= BIT(INNER_ETH_TYPE); + + break; + default: + return -EOPNOTSUPP; + } + + if ((fs->flow_type & FLOW_EXT)) { + if (fs->h_ext.vlan_etype) + return -EOPNOTSUPP; + if (!fs->h_ext.vlan_tci) + *unused |= BIT(INNER_VLAN_TAG_FST); + + if (fs->m_ext.vlan_tci) { + if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID) + return -EINVAL; + } + } else { + *unused |= BIT(INNER_VLAN_TAG_FST); + } + + if (fs->flow_type & FLOW_MAC_EXT) { + if (!(hdev->fd_cfg.proto_support & ETHER_FLOW)) + return -EOPNOTSUPP; + + if (is_zero_ether_addr(fs->h_ext.h_dest)) + *unused |= BIT(INNER_DST_MAC); + else + *unused &= ~(BIT(INNER_DST_MAC)); + } + + return 0; +} + +static bool hclge_fd_rule_exist(struct hclge_dev *hdev, u16 location) +{ + struct hclge_fd_rule *rule = NULL; + struct hlist_node *node2; + + hlist_for_each_entry_safe(rule, node2, &hdev->fd_rule_list, rule_node) { + if (rule->location >= location) + break; + } + + return rule && rule->location == location; +} + +static int hclge_fd_update_rule_list(struct hclge_dev *hdev, + struct hclge_fd_rule *new_rule, + u16 location, + bool is_add) +{ + struct hclge_fd_rule *rule = NULL, *parent = NULL; + struct hlist_node *node2; + + if (is_add && !new_rule) + return -EINVAL; + + hlist_for_each_entry_safe(rule, node2, + &hdev->fd_rule_list, rule_node) { + if (rule->location >= location) + break; + parent = rule; + } + + if (rule && rule->location == location) { + hlist_del(&rule->rule_node); + kfree(rule); + hdev->hclge_fd_rule_num--; + + if (!is_add) + return 0; + + } else if (!is_add) { + dev_err(&hdev->pdev->dev, + "delete fail, rule %d is inexistent\n", + location); + return -EINVAL; + } + + INIT_HLIST_NODE(&new_rule->rule_node); + + if (parent) + hlist_add_behind(&new_rule->rule_node, &parent->rule_node); + else + hlist_add_head(&new_rule->rule_node, &hdev->fd_rule_list); + + hdev->hclge_fd_rule_num++; + + return 0; +} + +static int hclge_fd_get_tuple(struct hclge_dev *hdev, + struct ethtool_rx_flow_spec *fs, + struct hclge_fd_rule *rule) +{ + u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT); + + switch (flow_type) { + case SCTP_V4_FLOW: + case TCP_V4_FLOW: + case UDP_V4_FLOW: + rule->tuples.src_ip[3] = + be32_to_cpu(fs->h_u.tcp_ip4_spec.ip4src); + rule->tuples_mask.src_ip[3] = + be32_to_cpu(fs->m_u.tcp_ip4_spec.ip4src); + + rule->tuples.dst_ip[3] = + be32_to_cpu(fs->h_u.tcp_ip4_spec.ip4dst); + rule->tuples_mask.dst_ip[3] = + be32_to_cpu(fs->m_u.tcp_ip4_spec.ip4dst); + + rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip4_spec.psrc); + rule->tuples_mask.src_port = + be16_to_cpu(fs->m_u.tcp_ip4_spec.psrc); + + rule->tuples.dst_port = be16_to_cpu(fs->h_u.tcp_ip4_spec.pdst); + rule->tuples_mask.dst_port = + be16_to_cpu(fs->m_u.tcp_ip4_spec.pdst); + + rule->tuples.ip_tos = fs->h_u.tcp_ip4_spec.tos; + rule->tuples_mask.ip_tos = fs->m_u.tcp_ip4_spec.tos; + + rule->tuples.ether_proto = ETH_P_IP; + rule->tuples_mask.ether_proto = 0xFFFF; + + break; + case IP_USER_FLOW: + rule->tuples.src_ip[3] = + be32_to_cpu(fs->h_u.usr_ip4_spec.ip4src); + rule->tuples_mask.src_ip[3] = + be32_to_cpu(fs->m_u.usr_ip4_spec.ip4src); + + rule->tuples.dst_ip[3] = + be32_to_cpu(fs->h_u.usr_ip4_spec.ip4dst); + rule->tuples_mask.dst_ip[3] = + be32_to_cpu(fs->m_u.usr_ip4_spec.ip4dst); + + rule->tuples.ip_tos = fs->h_u.usr_ip4_spec.tos; + rule->tuples_mask.ip_tos = fs->m_u.usr_ip4_spec.tos; + + rule->tuples.ip_proto = fs->h_u.usr_ip4_spec.proto; + rule->tuples_mask.ip_proto = fs->m_u.usr_ip4_spec.proto; + + rule->tuples.ether_proto = ETH_P_IP; + rule->tuples_mask.ether_proto = 0xFFFF; + + break; + case SCTP_V6_FLOW: + case TCP_V6_FLOW: + case UDP_V6_FLOW: + be32_to_cpu_array(rule->tuples.src_ip, + fs->h_u.tcp_ip6_spec.ip6src, 4); + be32_to_cpu_array(rule->tuples_mask.src_ip, + fs->m_u.tcp_ip6_spec.ip6src, 4); + + be32_to_cpu_array(rule->tuples.dst_ip, + fs->h_u.tcp_ip6_spec.ip6dst, 4); + be32_to_cpu_array(rule->tuples_mask.dst_ip, + fs->m_u.tcp_ip6_spec.ip6dst, 4); + + rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.psrc); + rule->tuples_mask.src_port = + be16_to_cpu(fs->m_u.tcp_ip6_spec.psrc); + + rule->tuples.dst_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.pdst); + rule->tuples_mask.dst_port = + be16_to_cpu(fs->m_u.tcp_ip6_spec.pdst); + + rule->tuples.ether_proto = ETH_P_IPV6; + rule->tuples_mask.ether_proto = 0xFFFF; + + break; + case IPV6_USER_FLOW: + be32_to_cpu_array(rule->tuples.src_ip, + fs->h_u.usr_ip6_spec.ip6src, 4); + be32_to_cpu_array(rule->tuples_mask.src_ip, + fs->m_u.usr_ip6_spec.ip6src, 4); + + be32_to_cpu_array(rule->tuples.dst_ip, + fs->h_u.usr_ip6_spec.ip6dst, 4); + be32_to_cpu_array(rule->tuples_mask.dst_ip, + fs->m_u.usr_ip6_spec.ip6dst, 4); + + rule->tuples.ip_proto = fs->h_u.usr_ip6_spec.l4_proto; + rule->tuples_mask.ip_proto = fs->m_u.usr_ip6_spec.l4_proto; + + rule->tuples.ether_proto = ETH_P_IPV6; + rule->tuples_mask.ether_proto = 0xFFFF; + + break; + case ETHER_FLOW: + ether_addr_copy(rule->tuples.src_mac, + fs->h_u.ether_spec.h_source); + ether_addr_copy(rule->tuples_mask.src_mac, + fs->m_u.ether_spec.h_source); + + ether_addr_copy(rule->tuples.dst_mac, + fs->h_u.ether_spec.h_dest); + ether_addr_copy(rule->tuples_mask.dst_mac, + fs->m_u.ether_spec.h_dest); + + rule->tuples.ether_proto = + be16_to_cpu(fs->h_u.ether_spec.h_proto); + rule->tuples_mask.ether_proto = + be16_to_cpu(fs->m_u.ether_spec.h_proto); + + break; + default: + return -EOPNOTSUPP; + } + + switch (flow_type) { + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + rule->tuples.ip_proto = IPPROTO_SCTP; + rule->tuples_mask.ip_proto = 0xFF; + break; + case TCP_V4_FLOW: + case TCP_V6_FLOW: + rule->tuples.ip_proto = IPPROTO_TCP; + rule->tuples_mask.ip_proto = 0xFF; + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + rule->tuples.ip_proto = IPPROTO_UDP; + rule->tuples_mask.ip_proto = 0xFF; + break; + default: + break; + } + + if ((fs->flow_type & FLOW_EXT)) { + rule->tuples.vlan_tag1 = be16_to_cpu(fs->h_ext.vlan_tci); + rule->tuples_mask.vlan_tag1 = be16_to_cpu(fs->m_ext.vlan_tci); + } + + if (fs->flow_type & FLOW_MAC_EXT) { + ether_addr_copy(rule->tuples.dst_mac, fs->h_ext.h_dest); + ether_addr_copy(rule->tuples_mask.dst_mac, fs->m_ext.h_dest); + } + + return 0; +} + +static int hclge_add_fd_entry(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u16 dst_vport_id = 0, q_index = 0; + struct ethtool_rx_flow_spec *fs; + struct hclge_fd_rule *rule; + u32 unused = 0; + u8 action; + int ret; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + if (!hdev->fd_cfg.fd_en) { + dev_warn(&hdev->pdev->dev, + "Please enable flow director first\n"); + return -EOPNOTSUPP; + } + + fs = (struct ethtool_rx_flow_spec *)&cmd->fs; + + ret = hclge_fd_check_spec(hdev, fs, &unused); + if (ret) { + dev_err(&hdev->pdev->dev, "Check fd spec failed\n"); + return ret; + } + + if (fs->ring_cookie == RX_CLS_FLOW_DISC) { + action = HCLGE_FD_ACTION_DROP_PACKET; + } else { + u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie); + u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie); + u16 tqps; + + dst_vport_id = vf ? hdev->vport[vf].vport_id : vport->vport_id; + tqps = vf ? hdev->vport[vf].alloc_tqps : vport->alloc_tqps; + + if (ring >= tqps) { + dev_err(&hdev->pdev->dev, + "Error: queue id (%d) > max tqp num (%d)\n", + ring, tqps - 1); + return -EINVAL; + } + + if (vf > hdev->num_req_vfs) { + dev_err(&hdev->pdev->dev, + "Error: vf id (%d) > max vf num (%d)\n", + vf, hdev->num_req_vfs); + return -EINVAL; + } + + action = HCLGE_FD_ACTION_ACCEPT_PACKET; + q_index = ring; + } + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return -ENOMEM; + + ret = hclge_fd_get_tuple(hdev, fs, rule); + if (ret) + goto free_rule; + + rule->flow_type = fs->flow_type; + + rule->location = fs->location; + rule->unused_tuple = unused; + rule->vf_id = dst_vport_id; + rule->queue_id = q_index; + rule->action = action; + + ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule); + if (ret) + goto free_rule; + + ret = hclge_config_key(hdev, HCLGE_FD_STAGE_1, rule); + if (ret) + goto free_rule; + + ret = hclge_fd_update_rule_list(hdev, rule, fs->location, true); + if (ret) + goto free_rule; + + return ret; + +free_rule: + kfree(rule); + return ret; +} + +static int hclge_del_fd_entry(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct ethtool_rx_flow_spec *fs; + int ret; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + fs = (struct ethtool_rx_flow_spec *)&cmd->fs; + + if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) + return -EINVAL; + + if (!hclge_fd_rule_exist(hdev, fs->location)) { + dev_err(&hdev->pdev->dev, + "Delete fail, rule %d is inexistent\n", + fs->location); + return -ENOENT; + } + + ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, + fs->location, NULL, false); + if (ret) + return ret; + + return hclge_fd_update_rule_list(hdev, NULL, fs->location, + false); +} + +static void hclge_del_all_fd_entries(struct hnae3_handle *handle, + bool clear_list) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_fd_rule *rule; + struct hlist_node *node; + + if (!hnae3_dev_fd_supported(hdev)) + return; + + if (clear_list) { + hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, + rule_node) { + hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, + rule->location, NULL, false); + hlist_del(&rule->rule_node); + kfree(rule); + hdev->hclge_fd_rule_num--; + } + } else { + hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, + rule_node) + hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, + rule->location, NULL, false); + } +} + +static int hclge_restore_fd_entries(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_fd_rule *rule; + struct hlist_node *node; + int ret; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) { + ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule); + if (!ret) + ret = hclge_config_key(hdev, HCLGE_FD_STAGE_1, rule); + + if (ret) { + dev_warn(&hdev->pdev->dev, + "Restore rule %d failed, remove it\n", + rule->location); + hlist_del(&rule->rule_node); + kfree(rule); + hdev->hclge_fd_rule_num--; + } + } + return 0; +} + +static int hclge_get_fd_rule_cnt(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + cmd->rule_cnt = hdev->hclge_fd_rule_num; + cmd->data = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]; + + return 0; +} + +static int hclge_get_fd_rule_info(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_fd_rule *rule = NULL; + struct hclge_dev *hdev = vport->back; + struct ethtool_rx_flow_spec *fs; + struct hlist_node *node2; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + fs = (struct ethtool_rx_flow_spec *)&cmd->fs; + + hlist_for_each_entry_safe(rule, node2, &hdev->fd_rule_list, rule_node) { + if (rule->location >= fs->location) + break; + } + + if (!rule || fs->location != rule->location) + return -ENOENT; + + fs->flow_type = rule->flow_type; + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { + case SCTP_V4_FLOW: + case TCP_V4_FLOW: + case UDP_V4_FLOW: + fs->h_u.tcp_ip4_spec.ip4src = + cpu_to_be32(rule->tuples.src_ip[3]); + fs->m_u.tcp_ip4_spec.ip4src = + rule->unused_tuple & BIT(INNER_SRC_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.src_ip[3]); + + fs->h_u.tcp_ip4_spec.ip4dst = + cpu_to_be32(rule->tuples.dst_ip[3]); + fs->m_u.tcp_ip4_spec.ip4dst = + rule->unused_tuple & BIT(INNER_DST_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.dst_ip[3]); + + fs->h_u.tcp_ip4_spec.psrc = cpu_to_be16(rule->tuples.src_port); + fs->m_u.tcp_ip4_spec.psrc = + rule->unused_tuple & BIT(INNER_SRC_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.src_port); + + fs->h_u.tcp_ip4_spec.pdst = cpu_to_be16(rule->tuples.dst_port); + fs->m_u.tcp_ip4_spec.pdst = + rule->unused_tuple & BIT(INNER_DST_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.dst_port); + + fs->h_u.tcp_ip4_spec.tos = rule->tuples.ip_tos; + fs->m_u.tcp_ip4_spec.tos = + rule->unused_tuple & BIT(INNER_IP_TOS) ? + 0 : rule->tuples_mask.ip_tos; + + break; + case IP_USER_FLOW: + fs->h_u.usr_ip4_spec.ip4src = + cpu_to_be32(rule->tuples.src_ip[3]); + fs->m_u.tcp_ip4_spec.ip4src = + rule->unused_tuple & BIT(INNER_SRC_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.src_ip[3]); + + fs->h_u.usr_ip4_spec.ip4dst = + cpu_to_be32(rule->tuples.dst_ip[3]); + fs->m_u.usr_ip4_spec.ip4dst = + rule->unused_tuple & BIT(INNER_DST_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.dst_ip[3]); + + fs->h_u.usr_ip4_spec.tos = rule->tuples.ip_tos; + fs->m_u.usr_ip4_spec.tos = + rule->unused_tuple & BIT(INNER_IP_TOS) ? + 0 : rule->tuples_mask.ip_tos; + + fs->h_u.usr_ip4_spec.proto = rule->tuples.ip_proto; + fs->m_u.usr_ip4_spec.proto = + rule->unused_tuple & BIT(INNER_IP_PROTO) ? + 0 : rule->tuples_mask.ip_proto; + + fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + + break; + case SCTP_V6_FLOW: + case TCP_V6_FLOW: + case UDP_V6_FLOW: + cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6src, + rule->tuples.src_ip, 4); + if (rule->unused_tuple & BIT(INNER_SRC_IP)) + memset(fs->m_u.tcp_ip6_spec.ip6src, 0, sizeof(int) * 4); + else + cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6src, + rule->tuples_mask.src_ip, 4); + + cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6dst, + rule->tuples.dst_ip, 4); + if (rule->unused_tuple & BIT(INNER_DST_IP)) + memset(fs->m_u.tcp_ip6_spec.ip6dst, 0, sizeof(int) * 4); + else + cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6dst, + rule->tuples_mask.dst_ip, 4); + + fs->h_u.tcp_ip6_spec.psrc = cpu_to_be16(rule->tuples.src_port); + fs->m_u.tcp_ip6_spec.psrc = + rule->unused_tuple & BIT(INNER_SRC_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.src_port); + + fs->h_u.tcp_ip6_spec.pdst = cpu_to_be16(rule->tuples.dst_port); + fs->m_u.tcp_ip6_spec.pdst = + rule->unused_tuple & BIT(INNER_DST_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.dst_port); + + break; + case IPV6_USER_FLOW: + cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6src, + rule->tuples.src_ip, 4); + if (rule->unused_tuple & BIT(INNER_SRC_IP)) + memset(fs->m_u.usr_ip6_spec.ip6src, 0, sizeof(int) * 4); + else + cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6src, + rule->tuples_mask.src_ip, 4); + + cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6dst, + rule->tuples.dst_ip, 4); + if (rule->unused_tuple & BIT(INNER_DST_IP)) + memset(fs->m_u.usr_ip6_spec.ip6dst, 0, sizeof(int) * 4); + else + cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6dst, + rule->tuples_mask.dst_ip, 4); + + fs->h_u.usr_ip6_spec.l4_proto = rule->tuples.ip_proto; + fs->m_u.usr_ip6_spec.l4_proto = + rule->unused_tuple & BIT(INNER_IP_PROTO) ? + 0 : rule->tuples_mask.ip_proto; + + break; + case ETHER_FLOW: + ether_addr_copy(fs->h_u.ether_spec.h_source, + rule->tuples.src_mac); + if (rule->unused_tuple & BIT(INNER_SRC_MAC)) + eth_zero_addr(fs->m_u.ether_spec.h_source); + else + ether_addr_copy(fs->m_u.ether_spec.h_source, + rule->tuples_mask.src_mac); + + ether_addr_copy(fs->h_u.ether_spec.h_dest, + rule->tuples.dst_mac); + if (rule->unused_tuple & BIT(INNER_DST_MAC)) + eth_zero_addr(fs->m_u.ether_spec.h_dest); + else + ether_addr_copy(fs->m_u.ether_spec.h_dest, + rule->tuples_mask.dst_mac); + + fs->h_u.ether_spec.h_proto = + cpu_to_be16(rule->tuples.ether_proto); + fs->m_u.ether_spec.h_proto = + rule->unused_tuple & BIT(INNER_ETH_TYPE) ? + 0 : cpu_to_be16(rule->tuples_mask.ether_proto); + + break; + default: + return -EOPNOTSUPP; + } + + if (fs->flow_type & FLOW_EXT) { + fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1); + fs->m_ext.vlan_tci = + rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ? + cpu_to_be16(VLAN_VID_MASK) : + cpu_to_be16(rule->tuples_mask.vlan_tag1); + } + + if (fs->flow_type & FLOW_MAC_EXT) { + ether_addr_copy(fs->h_ext.h_dest, rule->tuples.dst_mac); + if (rule->unused_tuple & BIT(INNER_DST_MAC)) + eth_zero_addr(fs->m_u.ether_spec.h_dest); + else + ether_addr_copy(fs->m_u.ether_spec.h_dest, + rule->tuples_mask.dst_mac); + } + + if (rule->action == HCLGE_FD_ACTION_DROP_PACKET) { + fs->ring_cookie = RX_CLS_FLOW_DISC; + } else { + u64 vf_id; + + fs->ring_cookie = rule->queue_id; + vf_id = rule->vf_id; + vf_id <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; + fs->ring_cookie |= vf_id; + } + + return 0; +} + +static int hclge_get_all_rules(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd, u32 *rule_locs) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_fd_rule *rule; + struct hlist_node *node2; + int cnt = 0; + + if (!hnae3_dev_fd_supported(hdev)) + return -EOPNOTSUPP; + + cmd->data = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]; + + hlist_for_each_entry_safe(rule, node2, + &hdev->fd_rule_list, rule_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + + rule_locs[cnt] = rule->location; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + hdev->fd_cfg.fd_en = enable; + if (!enable) + hclge_del_all_fd_entries(handle, false); + else + hclge_restore_fd_entries(handle); +} + static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { struct hclge_desc desc; @@ -3345,7 +4585,7 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) "mac enable fail, ret =%d.\n", ret); } -static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en) +static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) { struct hclge_config_mac_mode_cmd *req; struct hclge_desc desc; @@ -3381,22 +4621,37 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en) return ret; } -static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en) +static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en, + enum hnae3_loop loop_mode) { #define HCLGE_SERDES_RETRY_MS 10 #define HCLGE_SERDES_RETRY_NUM 100 struct hclge_serdes_lb_cmd *req; struct hclge_desc desc; int ret, i = 0; + u8 loop_mode_b; req = (struct hclge_serdes_lb_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, false); + switch (loop_mode) { + case HNAE3_LOOP_SERIAL_SERDES: + loop_mode_b = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; + break; + case HNAE3_LOOP_PARALLEL_SERDES: + loop_mode_b = HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B; + break; + default: + dev_err(&hdev->pdev->dev, + "unsupported serdes loopback mode %d\n", loop_mode); + return -ENOTSUPP; + } + if (en) { - req->enable = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; - req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; + req->enable = loop_mode_b; + req->mask = loop_mode_b; } else { - req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; + req->mask = loop_mode_b; } ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -3459,11 +4714,12 @@ static int hclge_set_loopback(struct hnae3_handle *handle, int i, ret; switch (loop_mode) { - case HNAE3_MAC_INTER_LOOP_MAC: - ret = hclge_set_mac_loopback(hdev, en); + case HNAE3_LOOP_APP: + ret = hclge_set_app_loopback(hdev, en); break; - case HNAE3_MAC_INTER_LOOP_SERDES: - ret = hclge_set_serdes_loopback(hdev, en); + case HNAE3_LOOP_SERIAL_SERDES: + case HNAE3_LOOP_PARALLEL_SERDES: + ret = hclge_set_serdes_loopback(hdev, en, loop_mode); break; default: ret = -ENOTSUPP; @@ -3667,174 +4923,6 @@ static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); } -static u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, - const u8 *addr) -{ - u16 high_val = addr[1] | (addr[0] << 8); - struct hclge_dev *hdev = vport->back; - u32 rsh = 4 - hdev->mta_mac_sel_type; - u16 ret_val = (high_val >> rsh) & 0xfff; - - return ret_val; -} - -static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, - enum hclge_mta_dmac_sel_type mta_mac_sel, - bool enable) -{ - struct hclge_mta_filter_mode_cmd *req; - struct hclge_desc desc; - int ret; - - req = (struct hclge_mta_filter_mode_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); - - hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, - enable); - hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M, - HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "Config mat filter mode failed for cmd_send, ret =%d.\n", - ret); - - return ret; -} - -int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, - u8 func_id, - bool enable) -{ - struct hclge_cfg_func_mta_filter_cmd *req; - struct hclge_desc desc; - int ret; - - req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); - - hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, - enable); - req->function_id = func_id; - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "Config func_id enable failed for cmd_send, ret =%d.\n", - ret); - - return ret; -} - -static int hclge_set_mta_table_item(struct hclge_vport *vport, - u16 idx, - bool enable) -{ - struct hclge_dev *hdev = vport->back; - struct hclge_cfg_func_mta_item_cmd *req; - struct hclge_desc desc; - u16 item_idx = 0; - int ret; - - req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); - hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); - - hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, - HCLGE_CFG_MTA_ITEM_IDX_S, idx); - req->item_idx = cpu_to_le16(item_idx); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, - "Config mta table item failed for cmd_send, ret =%d.\n", - ret); - return ret; - } - - if (enable) - set_bit(idx, vport->mta_shadow); - else - clear_bit(idx, vport->mta_shadow); - - return 0; -} - -static int hclge_update_mta_status(struct hnae3_handle *handle) -{ - unsigned long mta_status[BITS_TO_LONGS(HCLGE_MTA_TBL_SIZE)]; - struct hclge_vport *vport = hclge_get_vport(handle); - struct net_device *netdev = handle->kinfo.netdev; - struct netdev_hw_addr *ha; - u16 tbl_idx; - - memset(mta_status, 0, sizeof(mta_status)); - - /* update mta_status from mc addr list */ - netdev_for_each_mc_addr(ha, netdev) { - tbl_idx = hclge_get_mac_addr_to_mta_index(vport, ha->addr); - set_bit(tbl_idx, mta_status); - } - - return hclge_update_mta_status_common(vport, mta_status, - 0, HCLGE_MTA_TBL_SIZE, true); -} - -int hclge_update_mta_status_common(struct hclge_vport *vport, - unsigned long *status, - u16 idx, - u16 count, - bool update_filter) -{ - struct hclge_dev *hdev = vport->back; - u16 update_max = idx + count; - u16 check_max; - int ret = 0; - bool used; - u16 i; - - /* setup mta check range */ - if (update_filter) { - i = 0; - check_max = HCLGE_MTA_TBL_SIZE; - } else { - i = idx; - check_max = update_max; - } - - used = false; - /* check and update all mta item */ - for (; i < check_max; i++) { - /* ignore unused item */ - if (!test_bit(i, vport->mta_shadow)) - continue; - - /* if i in update range then update it */ - if (i >= idx && i < update_max) - if (!test_bit(i - idx, status)) - hclge_set_mta_table_item(vport, i, false); - - if (!used && test_bit(i, vport->mta_shadow)) - used = true; - } - - /* no longer use mta, disable it */ - if (vport->accept_mta_mc && update_filter && !used) { - ret = hclge_cfg_func_mta_filter(hdev, - vport->vport_id, - false); - if (ret) - dev_err(&hdev->pdev->dev, - "disable func mta filter fail ret=%d\n", - ret); - else - vport->accept_mta_mc = false; - } - - return ret; -} - static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, struct hclge_mac_vlan_tbl_entry_cmd *req) { @@ -3958,6 +5046,118 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, return cfg_status; } +static int hclge_init_umv_space(struct hclge_dev *hdev) +{ + u16 allocated_size = 0; + int ret; + + ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size, + true); + if (ret) + return ret; + + if (allocated_size < hdev->wanted_umv_size) + dev_warn(&hdev->pdev->dev, + "Alloc umv space failed, want %d, get %d\n", + hdev->wanted_umv_size, allocated_size); + + mutex_init(&hdev->umv_mutex); + hdev->max_umv_size = allocated_size; + hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_req_vfs + 2); + hdev->share_umv_size = hdev->priv_umv_size + + hdev->max_umv_size % (hdev->num_req_vfs + 2); + + return 0; +} + +static int hclge_uninit_umv_space(struct hclge_dev *hdev) +{ + int ret; + + if (hdev->max_umv_size > 0) { + ret = hclge_set_umv_space(hdev, hdev->max_umv_size, NULL, + false); + if (ret) + return ret; + hdev->max_umv_size = 0; + } + mutex_destroy(&hdev->umv_mutex); + + return 0; +} + +static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, + u16 *allocated_size, bool is_alloc) +{ + struct hclge_umv_spc_alc_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_umv_spc_alc_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ALLOCATE, false); + hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, !is_alloc); + req->space_size = cpu_to_le32(space_size); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "%s umv space failed for cmd_send, ret =%d\n", + is_alloc ? "allocate" : "free", ret); + return ret; + } + + if (is_alloc && allocated_size) + *allocated_size = le32_to_cpu(desc.data[1]); + + return 0; +} + +static void hclge_reset_umv_space(struct hclge_dev *hdev) +{ + struct hclge_vport *vport; + int i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + vport = &hdev->vport[i]; + vport->used_umv_num = 0; + } + + mutex_lock(&hdev->umv_mutex); + hdev->share_umv_size = hdev->priv_umv_size + + hdev->max_umv_size % (hdev->num_req_vfs + 2); + mutex_unlock(&hdev->umv_mutex); +} + +static bool hclge_is_umv_space_full(struct hclge_vport *vport) +{ + struct hclge_dev *hdev = vport->back; + bool is_full; + + mutex_lock(&hdev->umv_mutex); + is_full = (vport->used_umv_num >= hdev->priv_umv_size && + hdev->share_umv_size == 0); + mutex_unlock(&hdev->umv_mutex); + + return is_full; +} + +static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free) +{ + struct hclge_dev *hdev = vport->back; + + mutex_lock(&hdev->umv_mutex); + if (is_free) { + if (vport->used_umv_num > hdev->priv_umv_size) + hdev->share_umv_size++; + vport->used_umv_num--; + } else { + if (vport->used_umv_num >= hdev->priv_umv_size) + hdev->share_umv_size--; + vport->used_umv_num++; + } + mutex_unlock(&hdev->umv_mutex); +} + static int hclge_add_uc_addr(struct hnae3_handle *handle, const unsigned char *addr) { @@ -4003,8 +5203,19 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, * is not allowed in the mac vlan table. */ ret = hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false); - if (ret == -ENOENT) - return hclge_add_mac_vlan_tbl(vport, &req, NULL); + if (ret == -ENOENT) { + if (!hclge_is_umv_space_full(vport)) { + ret = hclge_add_mac_vlan_tbl(vport, &req, NULL); + if (!ret) + hclge_update_umv_space(vport, false); + return ret; + } + + dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n", + hdev->priv_umv_size); + + return -ENOSPC; + } /* check if we just hit the duplicate */ if (!ret) @@ -4047,6 +5258,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr); ret = hclge_remove_mac_vlan_tbl(vport, &req); + if (!ret) + hclge_update_umv_space(vport, true); return ret; } @@ -4065,7 +5278,6 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_mac_vlan_tbl_entry_cmd req; struct hclge_desc desc[3]; - u16 tbl_idx; int status; /* mac addr check */ @@ -4095,25 +5307,8 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, status = hclge_add_mac_vlan_tbl(vport, &req, desc); } - /* If mc mac vlan table is full, use MTA table */ - if (status == -ENOSPC) { - if (!vport->accept_mta_mc) { - status = hclge_cfg_func_mta_filter(hdev, - vport->vport_id, - true); - if (status) { - dev_err(&hdev->pdev->dev, - "set mta filter mode fail ret=%d\n", - status); - return status; - } - vport->accept_mta_mc = true; - } - - /* Set MTA table for this MAC address */ - tbl_idx = hclge_get_mac_addr_to_mta_index(vport, addr); - status = hclge_set_mta_table_item(vport, tbl_idx, true); - } + if (status == -ENOSPC) + dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); return status; } @@ -4328,7 +5523,7 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, } static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, - bool filter_en) + u8 fe_type, bool filter_en) { struct hclge_vlan_filter_ctrl_cmd *req; struct hclge_desc desc; @@ -4338,7 +5533,7 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; - req->vlan_fe = filter_en; + req->vlan_fe = filter_en ? fe_type : 0; ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) @@ -4350,13 +5545,30 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, #define HCLGE_FILTER_TYPE_VF 0 #define HCLGE_FILTER_TYPE_PORT 1 +#define HCLGE_FILTER_FE_EGRESS_V1_B BIT(0) +#define HCLGE_FILTER_FE_NIC_INGRESS_B BIT(0) +#define HCLGE_FILTER_FE_NIC_EGRESS_B BIT(1) +#define HCLGE_FILTER_FE_ROCE_INGRESS_B BIT(2) +#define HCLGE_FILTER_FE_ROCE_EGRESS_B BIT(3) +#define HCLGE_FILTER_FE_EGRESS (HCLGE_FILTER_FE_NIC_EGRESS_B \ + | HCLGE_FILTER_FE_ROCE_EGRESS_B) +#define HCLGE_FILTER_FE_INGRESS (HCLGE_FILTER_FE_NIC_INGRESS_B \ + | HCLGE_FILTER_FE_ROCE_INGRESS_B) static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, enable); + if (hdev->pdev->revision >= 0x21) { + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS, enable); + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, + HCLGE_FILTER_FE_INGRESS, enable); + } else { + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS_V1_B, enable); + } } static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, @@ -4658,13 +5870,23 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) int ret; int i; - ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, true); - if (ret) - return ret; + if (hdev->pdev->revision >= 0x21) { + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS, true); + if (ret) + return ret; - ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, true); - if (ret) - return ret; + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, + HCLGE_FILTER_FE_INGRESS, true); + if (ret) + return ret; + } else { + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS_V1_B, + true); + if (ret) + return ret; + } hdev->vlan_type_cfg.rx_in_fst_vlan_type = HCLGE_DEF_VLAN_TYPE; hdev->vlan_type_cfg.rx_in_sec_vlan_type = HCLGE_DEF_VLAN_TYPE; @@ -4976,11 +6198,7 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) if (!phydev->link || !phydev->autoneg) return 0; - if (phydev->advertising & ADVERTISED_Pause) - local_advertising = ADVERTISE_PAUSE_CAP; - - if (phydev->advertising & ADVERTISED_Asym_Pause) - local_advertising |= ADVERTISE_PAUSE_ASYM; + local_advertising = ethtool_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) remote_advertising = LPA_PAUSE_CAP; @@ -5439,6 +6657,12 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) } } + ret = hclge_init_umv_space(hdev); + if (ret) { + dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret); + goto err_msi_irq_uninit; + } + ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); @@ -5476,6 +6700,13 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) goto err_mdiobus_unreg; } + ret = hclge_init_fd_config(hdev); + if (ret) { + dev_err(&pdev->dev, + "fd table init fail, ret=%d\n", ret); + goto err_mdiobus_unreg; + } + hclge_dcb_ops_set(hdev); timer_setup(&hdev->service_timer, hclge_service_timer, 0); @@ -5552,6 +6783,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + hclge_reset_umv_space(hdev); + ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); @@ -5582,6 +6815,13 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = hclge_init_fd_config(hdev); + if (ret) { + dev_err(&pdev->dev, + "fd table init fail, ret=%d\n", ret); + return ret; + } + dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@ -5598,6 +6838,8 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) if (mac->phydev) mdiobus_unregister(mac->mdio_bus); + hclge_uninit_umv_space(hdev); + /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); synchronize_irq(hdev->misc_vector.vector_irq); @@ -5629,18 +6871,12 @@ static void hclge_get_channels(struct hnae3_handle *handle, } static void hclge_get_tqps_and_rss_info(struct hnae3_handle *handle, - u16 *free_tqps, u16 *max_rss_size) + u16 *alloc_tqps, u16 *max_rss_size) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - u16 temp_tqps = 0; - int i; - for (i = 0; i < hdev->num_tqps; i++) { - if (!hdev->htqp[i].alloced) - temp_tqps++; - } - *free_tqps = temp_tqps; + *alloc_tqps = vport->alloc_tqps; *max_rss_size = hdev->rss_size_max; } @@ -6002,7 +7238,6 @@ static const struct hnae3_ae_ops hclge_ops = { .rm_uc_addr = hclge_rm_uc_addr, .add_mc_addr = hclge_add_mc_addr, .rm_mc_addr = hclge_rm_mc_addr, - .update_mta_status = hclge_update_mta_status, .set_autoneg = hclge_set_autoneg, .get_autoneg = hclge_get_autoneg, .get_pauseparam = hclge_get_pauseparam, @@ -6027,6 +7262,14 @@ static const struct hnae3_ae_ops hclge_ops = { .get_regs = hclge_get_regs, .set_led_id = hclge_set_led_id, .get_link_mode = hclge_get_link_mode, + .add_fd_entry = hclge_add_fd_entry, + .del_fd_entry = hclge_del_fd_entry, + .del_all_fd_entries = hclge_del_all_fd_entries, + .get_fd_rule_cnt = hclge_get_fd_rule_cnt, + .get_fd_rule_info = hclge_get_fd_rule_info, + .get_fd_all_rules = hclge_get_all_rules, + .restore_fd_rules = hclge_restore_fd_entries, + .enable_fd = hclge_enable_fd, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 7841b830a716..e3dfd654eca9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -14,6 +14,8 @@ #define HCLGE_MOD_VERSION "1.0" #define HCLGE_DRIVER_NAME "hclge" +#define HCLGE_MAX_PF_NUM 8 + #define HCLGE_INVALID_VPORT 0xffff #define HCLGE_PF_CFG_BLOCK_SIZE 32 @@ -53,7 +55,9 @@ #define HCLGE_RSS_TC_SIZE_6 64 #define HCLGE_RSS_TC_SIZE_7 128 -#define HCLGE_MTA_TBL_SIZE 4096 +#define HCLGE_UMV_TBL_SIZE 3072 +#define HCLGE_DEFAULT_UMV_SPACE_PER_PF \ + (HCLGE_UMV_TBL_SIZE / HCLGE_MAX_PF_NUM) #define HCLGE_TQP_RESET_TRY_TIMES 10 @@ -79,6 +83,19 @@ #define HCLGE_VF_NUM_PER_CMD 64 #define HCLGE_VF_NUM_PER_BYTE 8 +enum HLCGE_PORT_TYPE { + HOST_PORT, + NETWORK_PORT +}; + +#define HCLGE_PF_ID_S 0 +#define HCLGE_PF_ID_M GENMASK(2, 0) +#define HCLGE_VF_ID_S 3 +#define HCLGE_VF_ID_M GENMASK(10, 3) +#define HCLGE_PORT_TYPE_B 11 +#define HCLGE_NETWORK_PORT_ID_S 0 +#define HCLGE_NETWORK_PORT_ID_M GENMASK(3, 0) + /* Reset related Registers */ #define HCLGE_MISC_RESET_STS_REG 0x20700 #define HCLGE_MISC_VECTOR_INT_STS 0x20800 @@ -149,13 +166,6 @@ enum HCLGE_MAC_DUPLEX { HCLGE_MAC_FULL }; -enum hclge_mta_dmac_sel_type { - HCLGE_MAC_ADDR_47_36, - HCLGE_MAC_ADDR_46_35, - HCLGE_MAC_ADDR_45_34, - HCLGE_MAC_ADDR_44_33, -}; - struct hclge_mac { u8 phy_addr; u8 flag; @@ -238,6 +248,7 @@ struct hclge_cfg { u8 default_speed; u32 numa_node_map; u8 speed_ability; + u16 umv_space; }; struct hclge_tm_info { @@ -359,6 +370,221 @@ struct hclge_vlan_type_cfg { u16 tx_in_vlan_type; }; +enum HCLGE_FD_MODE { + HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1, + HCLGE_FD_MODE_DEPTH_1K_WIDTH_400B_STAGE_2, + HCLGE_FD_MODE_DEPTH_4K_WIDTH_200B_STAGE_1, + HCLGE_FD_MODE_DEPTH_2K_WIDTH_200B_STAGE_2, +}; + +enum HCLGE_FD_KEY_TYPE { + HCLGE_FD_KEY_BASE_ON_PTYPE, + HCLGE_FD_KEY_BASE_ON_TUPLE, +}; + +enum HCLGE_FD_STAGE { + HCLGE_FD_STAGE_1, + HCLGE_FD_STAGE_2, +}; + +/* OUTER_XXX indicates tuples in tunnel header of tunnel packet + * INNER_XXX indicate tuples in tunneled header of tunnel packet or + * tuples of non-tunnel packet + */ +enum HCLGE_FD_TUPLE { + OUTER_DST_MAC, + OUTER_SRC_MAC, + OUTER_VLAN_TAG_FST, + OUTER_VLAN_TAG_SEC, + OUTER_ETH_TYPE, + OUTER_L2_RSV, + OUTER_IP_TOS, + OUTER_IP_PROTO, + OUTER_SRC_IP, + OUTER_DST_IP, + OUTER_L3_RSV, + OUTER_SRC_PORT, + OUTER_DST_PORT, + OUTER_L4_RSV, + OUTER_TUN_VNI, + OUTER_TUN_FLOW_ID, + INNER_DST_MAC, + INNER_SRC_MAC, + INNER_VLAN_TAG_FST, + INNER_VLAN_TAG_SEC, + INNER_ETH_TYPE, + INNER_L2_RSV, + INNER_IP_TOS, + INNER_IP_PROTO, + INNER_SRC_IP, + INNER_DST_IP, + INNER_L3_RSV, + INNER_SRC_PORT, + INNER_DST_PORT, + INNER_L4_RSV, + MAX_TUPLE, +}; + +enum HCLGE_FD_META_DATA { + PACKET_TYPE_ID, + IP_FRAGEMENT, + ROCE_TYPE, + NEXT_KEY, + VLAN_NUMBER, + SRC_VPORT, + DST_VPORT, + TUNNEL_PACKET, + MAX_META_DATA, +}; + +struct key_info { + u8 key_type; + u8 key_length; +}; + +static const struct key_info meta_data_key_info[] = { + { PACKET_TYPE_ID, 6}, + { IP_FRAGEMENT, 1}, + { ROCE_TYPE, 1}, + { NEXT_KEY, 5}, + { VLAN_NUMBER, 2}, + { SRC_VPORT, 12}, + { DST_VPORT, 12}, + { TUNNEL_PACKET, 1}, +}; + +static const struct key_info tuple_key_info[] = { + { OUTER_DST_MAC, 48}, + { OUTER_SRC_MAC, 48}, + { OUTER_VLAN_TAG_FST, 16}, + { OUTER_VLAN_TAG_SEC, 16}, + { OUTER_ETH_TYPE, 16}, + { OUTER_L2_RSV, 16}, + { OUTER_IP_TOS, 8}, + { OUTER_IP_PROTO, 8}, + { OUTER_SRC_IP, 32}, + { OUTER_DST_IP, 32}, + { OUTER_L3_RSV, 16}, + { OUTER_SRC_PORT, 16}, + { OUTER_DST_PORT, 16}, + { OUTER_L4_RSV, 32}, + { OUTER_TUN_VNI, 24}, + { OUTER_TUN_FLOW_ID, 8}, + { INNER_DST_MAC, 48}, + { INNER_SRC_MAC, 48}, + { INNER_VLAN_TAG_FST, 16}, + { INNER_VLAN_TAG_SEC, 16}, + { INNER_ETH_TYPE, 16}, + { INNER_L2_RSV, 16}, + { INNER_IP_TOS, 8}, + { INNER_IP_PROTO, 8}, + { INNER_SRC_IP, 32}, + { INNER_DST_IP, 32}, + { INNER_L3_RSV, 16}, + { INNER_SRC_PORT, 16}, + { INNER_DST_PORT, 16}, + { INNER_L4_RSV, 32}, +}; + +#define MAX_KEY_LENGTH 400 +#define MAX_KEY_DWORDS DIV_ROUND_UP(MAX_KEY_LENGTH / 8, 4) +#define MAX_KEY_BYTES (MAX_KEY_DWORDS * 4) +#define MAX_META_DATA_LENGTH 32 + +enum HCLGE_FD_PACKET_TYPE { + NIC_PACKET, + ROCE_PACKET, +}; + +enum HCLGE_FD_ACTION { + HCLGE_FD_ACTION_ACCEPT_PACKET, + HCLGE_FD_ACTION_DROP_PACKET, +}; + +struct hclge_fd_key_cfg { + u8 key_sel; + u8 inner_sipv6_word_en; + u8 inner_dipv6_word_en; + u8 outer_sipv6_word_en; + u8 outer_dipv6_word_en; + u32 tuple_active; + u32 meta_data_active; +}; + +struct hclge_fd_cfg { + u8 fd_mode; + u8 fd_en; + u16 max_key_length; + u32 proto_support; + u32 rule_num[2]; /* rule entry number */ + u16 cnt_num[2]; /* rule hit counter number */ + struct hclge_fd_key_cfg key_cfg[2]; +}; + +struct hclge_fd_rule_tuples { + u8 src_mac[6]; + u8 dst_mac[6]; + u32 src_ip[4]; + u32 dst_ip[4]; + u16 src_port; + u16 dst_port; + u16 vlan_tag1; + u16 ether_proto; + u8 ip_tos; + u8 ip_proto; +}; + +struct hclge_fd_rule { + struct hlist_node rule_node; + struct hclge_fd_rule_tuples tuples; + struct hclge_fd_rule_tuples tuples_mask; + u32 unused_tuple; + u32 flow_type; + u8 action; + u16 vf_id; + u16 queue_id; + u16 location; +}; + +struct hclge_fd_ad_data { + u16 ad_id; + u8 drop_packet; + u8 forward_to_direct_queue; + u16 queue_id; + u8 use_counter; + u8 counter_id; + u8 use_next_stage; + u8 write_rule_id_to_bd; + u8 next_input_key; + u16 rule_id; +}; + +/* For each bit of TCAM entry, it uses a pair of 'x' and + * 'y' to indicate which value to match, like below: + * ---------------------------------- + * | bit x | bit y | search value | + * ---------------------------------- + * | 0 | 0 | always hit | + * ---------------------------------- + * | 1 | 0 | match '0' | + * ---------------------------------- + * | 0 | 1 | match '1' | + * ---------------------------------- + * | 1 | 1 | invalid | + * ---------------------------------- + * Then for input key(k) and mask(v), we can calculate the value by + * the formulae: + * x = (~k) & v + * y = (k ^ ~v) & k + */ +#define calc_x(x, k, v) ((x) = (~(k) & (v))) +#define calc_y(y, k, v) \ + do { \ + const typeof(k) _k_ = (k); \ + const typeof(v) _v_ = (v); \ + (y) = (_k_ ^ ~_v_) & (_k_); \ + } while (0) + #define HCLGE_VPORT_NUM 256 struct hclge_dev { struct pci_dev *pdev; @@ -442,12 +668,22 @@ struct hclge_dev { u32 pkt_buf_size; /* Total pf buf size for tx/rx */ u32 mps; /* Max packet size */ - enum hclge_mta_dmac_sel_type mta_mac_sel_type; - bool enable_mta; /* Multicast filter enable */ - struct hclge_vlan_type_cfg vlan_type_cfg; unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)]; + + struct hclge_fd_cfg fd_cfg; + struct hlist_head fd_rule_list; + u16 hclge_fd_rule_num; + + u16 wanted_umv_size; + /* max available unicast mac vlan space */ + u16 max_umv_size; + /* private unicast mac vlan space, it's same for PF and its VFs */ + u16 priv_umv_size; + /* unicast mac vlan space shared by PF and its VFs */ + u16 share_umv_size; + struct mutex umv_mutex; /* protect share_umv_size */ }; /* VPort level vlan tag configuration for TX direction */ @@ -500,13 +736,12 @@ struct hclge_vport { struct hclge_tx_vtag_cfg txvlan_cfg; struct hclge_rx_vtag_cfg rxvlan_cfg; + u16 used_umv_num; + int vport_id; struct hclge_dev *back; /* Back reference to associated dev */ struct hnae3_handle nic; struct hnae3_handle roce; - - bool accept_mta_mc; /* whether to accept mta filter multicast */ - unsigned long mta_shadow[BITS_TO_LONGS(HCLGE_MTA_TBL_SIZE)]; }; void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, @@ -521,15 +756,6 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, int hclge_rm_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr); -int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, - u8 func_id, - bool enable); -int hclge_update_mta_status_common(struct hclge_vport *vport, - unsigned long *status, - u16 idx, - u16 count, - bool update_filter); - struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle); int hclge_bind_ring_with_vector(struct hclge_vport *vport, int vector_id, bool en, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index f34851c91eb3..04462a347a94 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -233,43 +233,6 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, return 0; } -static int hclge_set_vf_mc_mta_status(struct hclge_vport *vport, - u8 *msg, u8 idx, bool is_end) -{ -#define HCLGE_MTA_STATUS_MSG_SIZE 13 -#define HCLGE_MTA_STATUS_MSG_BITS \ - (HCLGE_MTA_STATUS_MSG_SIZE * BITS_PER_BYTE) -#define HCLGE_MTA_STATUS_MSG_END_BITS \ - (HCLGE_MTA_TBL_SIZE % HCLGE_MTA_STATUS_MSG_BITS) - unsigned long status[BITS_TO_LONGS(HCLGE_MTA_STATUS_MSG_BITS)]; - u16 tbl_cnt; - u16 tbl_idx; - u8 msg_ofs; - u8 msg_bit; - - tbl_cnt = is_end ? HCLGE_MTA_STATUS_MSG_END_BITS : - HCLGE_MTA_STATUS_MSG_BITS; - - /* set msg field */ - msg_ofs = 0; - msg_bit = 0; - memset(status, 0, sizeof(status)); - for (tbl_idx = 0; tbl_idx < tbl_cnt; tbl_idx++) { - if (msg[msg_ofs] & BIT(msg_bit)) - set_bit(tbl_idx, status); - - msg_bit++; - if (msg_bit == BITS_PER_BYTE) { - msg_bit = 0; - msg_ofs++; - } - } - - return hclge_update_mta_status_common(vport, - status, idx * HCLGE_MTA_STATUS_MSG_BITS, - tbl_cnt, is_end); -} - static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req, bool gen_resp) @@ -284,27 +247,6 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, status = hclge_add_mc_addr_common(vport, mac_addr); } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_REMOVE) { status = hclge_rm_mc_addr_common(vport, mac_addr); - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_FUNC_MTA_ENABLE) { - u8 func_id = vport->vport_id; - bool enable = mbx_req->msg[2]; - - status = hclge_cfg_func_mta_filter(hdev, func_id, enable); - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ) { - resp_data = hdev->mta_mac_sel_type; - resp_len = sizeof(u8); - gen_resp = true; - status = 0; - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE) { - /* mta status update msg format - * msg[2.6 : 2.0] msg index - * msg[2.7] msg is end - * msg[15 : 3] mta status bits[103 : 0] - */ - bool is_end = (mbx_req->msg[2] & 0x80) ? true : false; - - status = hclge_set_vf_mc_mta_status(vport, &mbx_req->msg[3], - mbx_req->msg[2] & 0x7F, - is_end); } else { dev_err(&hdev->pdev->dev, "failed to set mcast mac addr, unknown subcode %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 00bb39451bc5..aa5cb9834d73 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -193,6 +193,7 @@ static int hclge_pause_param_cfg(struct hclge_dev *hdev, const u8 *addr, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, false); ether_addr_copy(pause_param->mac_addr, addr); + ether_addr_copy(pause_param->mac_addr_extra, addr); pause_param->pause_trans_gap = pause_trans_gap; pause_param->pause_trans_time = cpu_to_le16(pause_trans_time); @@ -1279,10 +1280,15 @@ int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc) return 0; } -void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) +int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) { u8 i, bit_map = 0; + for (i = 0; i < hdev->num_alloc_vport; i++) { + if (num_tc > hdev->vport[i].alloc_tqps) + return -EINVAL; + } + hdev->tm_info.num_tc = num_tc; for (i = 0; i < hdev->tm_info.num_tc; i++) @@ -1296,6 +1302,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) hdev->hw_tc_map = bit_map; hclge_tm_schd_info_init(hdev); + + return 0; } int hclge_tm_init_hw(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index dd4c194747c1..25eef13a3e14 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -106,6 +106,10 @@ struct hclge_cfg_pause_param_cmd { u8 pause_trans_gap; u8 rsvd; __le16 pause_trans_time; + u8 rsvd1[6]; + /* extra mac address to do double check for pause frame */ + u8 mac_addr_extra[ETH_ALEN]; + u16 rsvd2; }; struct hclge_pfc_stats_cmd { @@ -128,7 +132,7 @@ int hclge_tm_schd_init(struct hclge_dev *hdev); int hclge_pause_setup_hw(struct hclge_dev *hdev); int hclge_tm_schd_mode_hw(struct hclge_dev *hdev); int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc); -void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); +int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_map_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 978193123c71..ca4a9f790917 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -746,126 +746,6 @@ static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle) } } -static int hclgevf_cfg_func_mta_type(struct hclgevf_dev *hdev) -{ - u8 resp_msg = HCLGEVF_MTA_TYPE_SEL_MAX; - int ret; - - ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ, - NULL, 0, true, &resp_msg, sizeof(u8)); - - if (ret) { - dev_err(&hdev->pdev->dev, - "Read mta type fail, ret=%d.\n", ret); - return ret; - } - - if (resp_msg > HCLGEVF_MTA_TYPE_SEL_MAX) { - dev_err(&hdev->pdev->dev, - "Read mta type invalid, resp=%d.\n", resp_msg); - return -EINVAL; - } - - hdev->mta_mac_sel_type = resp_msg; - - return 0; -} - -static u16 hclgevf_get_mac_addr_to_mta_index(struct hclgevf_dev *hdev, - const u8 *addr) -{ - u32 rsh = HCLGEVF_MTA_TYPE_SEL_MAX - hdev->mta_mac_sel_type; - u16 high_val = addr[1] | (addr[0] << 8); - - return (high_val >> rsh) & 0xfff; -} - -static int hclgevf_do_update_mta_status(struct hclgevf_dev *hdev, - unsigned long *status) -{ -#define HCLGEVF_MTA_STATUS_MSG_SIZE 13 -#define HCLGEVF_MTA_STATUS_MSG_BITS \ - (HCLGEVF_MTA_STATUS_MSG_SIZE * BITS_PER_BYTE) -#define HCLGEVF_MTA_STATUS_MSG_END_BITS \ - (HCLGEVF_MTA_TBL_SIZE % HCLGEVF_MTA_STATUS_MSG_BITS) - u16 tbl_cnt; - u16 tbl_idx; - u8 msg_cnt; - u8 msg_idx; - int ret; - - msg_cnt = DIV_ROUND_UP(HCLGEVF_MTA_TBL_SIZE, - HCLGEVF_MTA_STATUS_MSG_BITS); - tbl_idx = 0; - msg_idx = 0; - while (msg_cnt--) { - u8 msg[HCLGEVF_MTA_STATUS_MSG_SIZE + 1]; - u8 *p = &msg[1]; - u8 msg_ofs; - u8 msg_bit; - - memset(msg, 0, sizeof(msg)); - - /* set index field */ - msg[0] = 0x7F & msg_idx; - - /* set end flag field */ - if (msg_cnt == 0) { - msg[0] |= 0x80; - tbl_cnt = HCLGEVF_MTA_STATUS_MSG_END_BITS; - } else { - tbl_cnt = HCLGEVF_MTA_STATUS_MSG_BITS; - } - - /* set status field */ - msg_ofs = 0; - msg_bit = 0; - while (tbl_cnt--) { - if (test_bit(tbl_idx, status)) - p[msg_ofs] |= BIT(msg_bit); - - tbl_idx++; - - msg_bit++; - if (msg_bit == BITS_PER_BYTE) { - msg_bit = 0; - msg_ofs++; - } - } - - ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE, - msg, sizeof(msg), false, NULL, 0); - if (ret) - break; - - msg_idx++; - } - - return ret; -} - -static int hclgevf_update_mta_status(struct hnae3_handle *handle) -{ - unsigned long mta_status[BITS_TO_LONGS(HCLGEVF_MTA_TBL_SIZE)]; - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct net_device *netdev = hdev->nic.kinfo.netdev; - struct netdev_hw_addr *ha; - u16 tbl_idx; - - /* clear status */ - memset(mta_status, 0, sizeof(mta_status)); - - /* update status from mc addr list */ - netdev_for_each_mc_addr(ha, netdev) { - tbl_idx = hclgevf_get_mac_addr_to_mta_index(hdev, ha->addr); - set_bit(tbl_idx, mta_status); - } - - return hclgevf_do_update_mta_status(hdev, mta_status); -} - static void hclgevf_get_mac_addr(struct hnae3_handle *handle, u8 *p) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); @@ -1871,14 +1751,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) goto err_config; } - /* Initialize mta type for this VF */ - ret = hclgevf_cfg_func_mta_type(hdev); - if (ret) { - dev_err(&hdev->pdev->dev, - "failed(%d) to initialize MTA type\n", ret); - goto err_config; - } - /* Initialize RSS for this VF */ ret = hclgevf_rss_init_hw(hdev); if (ret) { @@ -1975,11 +1847,11 @@ static void hclgevf_get_channels(struct hnae3_handle *handle, } static void hclgevf_get_tqps_and_rss_info(struct hnae3_handle *handle, - u16 *free_tqps, u16 *max_rss_size) + u16 *alloc_tqps, u16 *max_rss_size) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - *free_tqps = 0; + *alloc_tqps = hdev->num_tqps; *max_rss_size = hdev->rss_size_max; } @@ -2038,7 +1910,6 @@ static const struct hnae3_ae_ops hclgevf_ops = { .rm_uc_addr = hclgevf_rm_uc_addr, .add_mc_addr = hclgevf_add_mc_addr, .rm_mc_addr = hclgevf_rm_mc_addr, - .update_mta_status = hclgevf_update_mta_status, .get_stats = hclgevf_get_stats, .update_stats = hclgevf_update_stats, .get_strings = hclgevf_get_strings, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 2af01f107c63..cf5fbf793c5e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -47,9 +47,6 @@ #define HCLGEVF_RSS_CFG_TBL_NUM \ (HCLGEVF_RSS_IND_TBL_SIZE / HCLGEVF_RSS_CFG_TBL_SIZE) -#define HCLGEVF_MTA_TBL_SIZE 4096 -#define HCLGEVF_MTA_TYPE_SEL_MAX 4 - /* states of hclgevf device & tasks */ enum hclgevf_states { /* device states */ @@ -157,8 +154,6 @@ struct hclgevf_dev { u16 *vector_status; int *vector_irq; - bool accept_mta_mc; /* whether to accept mta filter multicast */ - u8 mta_mac_sel_type; bool mbx_event_pending; struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */ struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 09e9da10b786..4a8f82938ed5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -789,23 +789,6 @@ static void hinic_get_stats64(struct net_device *netdev, stats->tx_errors = nic_tx_stats->tx_dropped; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void hinic_netpoll(struct net_device *netdev) -{ - struct hinic_dev *nic_dev = netdev_priv(netdev); - int i, num_qps; - - num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); - for (i = 0; i < num_qps; i++) { - struct hinic_txq *txq = &nic_dev->txqs[i]; - struct hinic_rxq *rxq = &nic_dev->rxqs[i]; - - napi_schedule(&txq->napi); - napi_schedule(&rxq->napi); - } -} -#endif - static const struct net_device_ops hinic_netdev_ops = { .ndo_open = hinic_open, .ndo_stop = hinic_close, @@ -818,9 +801,6 @@ static const struct net_device_ops hinic_netdev_ops = { .ndo_start_xmit = hinic_xmit_frame, .ndo_tx_timeout = hinic_tx_timeout, .ndo_get_stats64 = hinic_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = hinic_netpoll, -#endif }; static void netdev_features_init(struct net_device *netdev) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index aa0b89777e74..3baabdc89726 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -920,17 +920,6 @@ static int ehea_poll(struct napi_struct *napi, int budget) return rx; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ehea_netpoll(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - int i; - - for (i = 0; i < port->num_def_qps; i++) - napi_schedule(&port->port_res[i].napi); -} -#endif - static irqreturn_t ehea_recv_irq_handler(int irq, void *param) { struct ehea_port_res *pr = param; @@ -2952,9 +2941,6 @@ static const struct net_device_ops ehea_netdev_ops = { .ndo_open = ehea_open, .ndo_stop = ehea_stop, .ndo_start_xmit = ehea_start_xmit, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ehea_netpoll, -#endif .ndo_get_stats64 = ehea_get_stats64, .ndo_set_mac_address = ehea_set_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a8369addfe68..7893beffcc71 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2207,19 +2207,6 @@ restart_poll: return frames_processed; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ibmvnic_netpoll_controller(struct net_device *dev) -{ - struct ibmvnic_adapter *adapter = netdev_priv(dev); - int i; - - replenish_pools(netdev_priv(dev)); - for (i = 0; i < adapter->req_rx_queues; i++) - ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq, - adapter->rx_scrq[i]); -} -#endif - static int wait_for_reset(struct ibmvnic_adapter *adapter) { int rc, ret; @@ -2292,9 +2279,6 @@ static const struct net_device_ops ibmvnic_netdev_ops = { .ndo_set_mac_address = ibmvnic_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = ibmvnic_tx_timeout, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ibmvnic_netpoll_controller, -#endif .ndo_change_mtu = ibmvnic_change_mtu, .ndo_features_check = ibmvnic_features_check, }; @@ -2364,8 +2348,13 @@ static void ibmvnic_get_ringparam(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; - ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; + if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { + ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; + ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; + } else { + ring->rx_max_pending = IBMVNIC_MAX_QUEUE_SZ; + ring->tx_max_pending = IBMVNIC_MAX_QUEUE_SZ; + } ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; ring->rx_pending = adapter->req_rx_add_entries_per_subcrq; @@ -2378,21 +2367,23 @@ static int ibmvnic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int ret; - if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq || - ring->tx_pending > adapter->max_tx_entries_per_subcrq) { - netdev_err(netdev, "Invalid request.\n"); - netdev_err(netdev, "Max tx buffers = %llu\n", - adapter->max_rx_add_entries_per_subcrq); - netdev_err(netdev, "Max rx buffers = %llu\n", - adapter->max_tx_entries_per_subcrq); - return -EINVAL; - } - + ret = 0; adapter->desired.rx_entries = ring->rx_pending; adapter->desired.tx_entries = ring->tx_pending; - return wait_for_reset(adapter); + ret = wait_for_reset(adapter); + + if (!ret && + (adapter->req_rx_add_entries_per_subcrq != ring->rx_pending || + adapter->req_tx_entries_per_subcrq != ring->tx_pending)) + netdev_info(netdev, + "Could not match full ringsize request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", + ring->rx_pending, ring->tx_pending, + adapter->req_rx_add_entries_per_subcrq, + adapter->req_tx_entries_per_subcrq); + return ret; } static void ibmvnic_get_channels(struct net_device *netdev, @@ -2400,8 +2391,14 @@ static void ibmvnic_get_channels(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - channels->max_rx = adapter->max_rx_queues; - channels->max_tx = adapter->max_tx_queues; + if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { + channels->max_rx = adapter->max_rx_queues; + channels->max_tx = adapter->max_tx_queues; + } else { + channels->max_rx = IBMVNIC_MAX_QUEUES; + channels->max_tx = IBMVNIC_MAX_QUEUES; + } + channels->max_other = 0; channels->max_combined = 0; channels->rx_count = adapter->req_rx_queues; @@ -2414,11 +2411,23 @@ static int ibmvnic_set_channels(struct net_device *netdev, struct ethtool_channels *channels) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int ret; + ret = 0; adapter->desired.rx_queues = channels->rx_count; adapter->desired.tx_queues = channels->tx_count; - return wait_for_reset(adapter); + ret = wait_for_reset(adapter); + + if (!ret && + (adapter->req_rx_queues != channels->rx_count || + adapter->req_tx_queues != channels->tx_count)) + netdev_info(netdev, + "Could not match full channels request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", + channels->rx_count, channels->tx_count, + adapter->req_rx_queues, adapter->req_tx_queues); + return ret; + } static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -2426,32 +2435,43 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) struct ibmvnic_adapter *adapter = netdev_priv(dev); int i; - if (stringset != ETH_SS_STATS) - return; + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); + i++, data += ETH_GSTRING_LEN) + memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); - for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) - memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); + for (i = 0; i < adapter->req_tx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); + data += ETH_GSTRING_LEN; - for (i = 0; i < adapter->req_tx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, + "tx%d_dropped_packets", i); + data += ETH_GSTRING_LEN; + } - snprintf(data, ETH_GSTRING_LEN, "tx%d_dropped_packets", i); - data += ETH_GSTRING_LEN; - } + for (i = 0; i < adapter->req_rx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); + data += ETH_GSTRING_LEN; - for (i = 0; i < adapter->req_rx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); + data += ETH_GSTRING_LEN; + } + break; - snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); - data += ETH_GSTRING_LEN; + case ETH_SS_PRIV_FLAGS: + for (i = 0; i < ARRAY_SIZE(ibmvnic_priv_flags); i++) + strcpy(data + i * ETH_GSTRING_LEN, + ibmvnic_priv_flags[i]); + break; + default: + return; } } @@ -2464,6 +2484,8 @@ static int ibmvnic_get_sset_count(struct net_device *dev, int sset) return ARRAY_SIZE(ibmvnic_stats) + adapter->req_tx_queues * NUM_TX_STATS + adapter->req_rx_queues * NUM_RX_STATS; + case ETH_SS_PRIV_FLAGS: + return ARRAY_SIZE(ibmvnic_priv_flags); default: return -EOPNOTSUPP; } @@ -2514,6 +2536,25 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, } } +static u32 ibmvnic_get_priv_flags(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + return adapter->priv_flags; +} + +static int ibmvnic_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + bool which_maxes = !!(flags & IBMVNIC_USE_SERVER_MAXES); + + if (which_maxes) + adapter->priv_flags |= IBMVNIC_USE_SERVER_MAXES; + else + adapter->priv_flags &= ~IBMVNIC_USE_SERVER_MAXES; + + return 0; +} static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_drvinfo = ibmvnic_get_drvinfo, .get_msglevel = ibmvnic_get_msglevel, @@ -2527,6 +2568,8 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_sset_count = ibmvnic_get_sset_count, .get_ethtool_stats = ibmvnic_get_ethtool_stats, .get_link_ksettings = ibmvnic_get_link_ksettings, + .get_priv_flags = ibmvnic_get_priv_flags, + .set_priv_flags = ibmvnic_set_priv_flags, }; /* Routines for managing CRQs/sCRQs */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index f06eec145ca6..18103b811d4d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -39,7 +39,8 @@ #define IBMVNIC_RX_WEIGHT 16 /* when changing this, update IBMVNIC_IO_ENTITLEMENT_DEFAULT */ #define IBMVNIC_BUFFS_PER_POOL 100 -#define IBMVNIC_MAX_QUEUES 10 +#define IBMVNIC_MAX_QUEUES 16 +#define IBMVNIC_MAX_QUEUE_SZ 4096 #define IBMVNIC_TSO_BUF_SZ 65536 #define IBMVNIC_TSO_BUFS 64 @@ -48,6 +49,11 @@ #define IBMVNIC_MAX_LTB_SIZE ((1 << (MAX_ORDER - 1)) * PAGE_SIZE) #define IBMVNIC_BUFFER_HLEN 500 +static const char ibmvnic_priv_flags[][ETH_GSTRING_LEN] = { +#define IBMVNIC_USE_SERVER_MAXES 0x1 + "use-server-maxes" +}; + struct ibmvnic_login_buffer { __be32 len; __be32 version; @@ -969,6 +975,7 @@ struct ibmvnic_adapter { struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl; dma_addr_t ip_offload_ctrl_tok; u32 msg_enable; + u32 priv_flags; /* Vital Product Data (VPD) */ struct ibmvnic_vpd *vpd; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 56b911a5dd8b..a20d1cf058ad 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -132,8 +132,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n", (unsigned long int)nd->vlan_features); } - dev_info(&pf->pdev->dev, " active_vlans is %s\n", - vsi->active_vlans ? "<valid>" : "<null>"); dev_info(&pf->pdev->dev, " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index f4bb2779f03a..81b0e1f8d14b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4256,7 +4256,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) vf->link_forced = true; vf->link_up = true; pfe.event_data.link_event.link_status = true; - pfe.event_data.link_event.link_speed = I40E_LINK_SPEED_40GB; + pfe.event_data.link_event.link_speed = VIRTCHNL_LINK_SPEED_40GB; break; case IFLA_VF_LINK_STATE_DISABLE: vf->link_forced = true; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a512f7521841..272d76b733aa 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -342,7 +342,7 @@ struct iavf_adapter { struct iavf_channel_config ch_config; u8 num_tc; struct list_head cloud_filter_list; - /* lock to protest access to the cloud filter list */ + /* lock to protect access to the cloud filter list */ spinlock_t cloud_filter_list_lock; u16 num_cloud_filters; }; diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 4058673fd853..e5d6f684437e 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -13,5 +13,7 @@ ice-y := ice_main.o \ ice_nvm.o \ ice_switch.o \ ice_sched.o \ + ice_lib.o \ ice_txrx.o \ ice_ethtool.o +ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 9cf233d085d8..4c4b5717a627 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -28,6 +28,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_bridge.h> +#include <linux/avf/virtchnl.h> #include <net/ipv6.h> #include "ice_devids.h" #include "ice_type.h" @@ -35,17 +36,20 @@ #include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_virtchnl_pf.h" +#include "ice_sriov.h" extern const char ice_drv_ver[]; #define ICE_BAR0 0 #define ICE_DFLT_NUM_DESC 128 -#define ICE_MIN_NUM_DESC 8 -#define ICE_MAX_NUM_DESC 8160 #define ICE_REQ_DESC_MULTIPLE 32 +#define ICE_MIN_NUM_DESC ICE_REQ_DESC_MULTIPLE +#define ICE_MAX_NUM_DESC 8160 #define ICE_DFLT_TRAFFIC_CLASS BIT(0) #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) #define ICE_ETHTOOL_FWVER_LEN 32 #define ICE_AQ_LEN 64 +#define ICE_MBXQ_LEN 64 #define ICE_MIN_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_MAX_VSI_ALLOC 130 @@ -63,6 +67,14 @@ extern const char ice_drv_ver[]; #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 +#define ICE_MAX_VF_COUNT 256 +#define ICE_MAX_QS_PER_VF 256 +#define ICE_MIN_QS_PER_VF 1 +#define ICE_DFLT_QS_PER_VF 4 +#define ICE_MAX_BASE_QS_PER_VF 16 +#define ICE_MAX_INTR_PER_VF 65 +#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) +#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -124,7 +136,7 @@ enum ice_state { __ICE_DOWN, __ICE_NEEDS_RESTART, __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ - __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */ + __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ __ICE_GLOBR_REQ, /* set by driver and peers */ @@ -133,9 +145,21 @@ enum ice_state { __ICE_EMPR_RECV, /* set by OICR handler */ __ICE_SUSPENDED, /* set on module remove path */ __ICE_RESET_FAILED, /* set by reset/rebuild */ + /* When checking for the PF to be in a nominal operating state, the + * bits that are grouped at the beginning of the list need to be + * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will + * be checked. If you need to add a bit into consideration for nominal + * operating state, it must be added before + * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position + * without appropriate consideration. + */ + __ICE_STATE_NOMINAL_CHECK_BITS, __ICE_ADMINQ_EVENT_PENDING, + __ICE_MAILBOXQ_EVENT_PENDING, __ICE_MDD_EVENT_PENDING, + __ICE_VFLR_EVENT_PENDING, __ICE_FLTR_OVERFLOW_PROMISC, + __ICE_VF_DIS, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, __ICE_SERVICE_DIS, @@ -172,7 +196,8 @@ struct ice_vsi { u32 rx_buf_failed; u32 rx_page_failed; int num_q_vectors; - int base_vector; + int sw_base_vector; /* Irq base for OS reserved vectors */ + int hw_base_vector; /* HW (absolute) index of a vector */ enum ice_vsi_type type; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ @@ -180,6 +205,8 @@ struct ice_vsi { /* Interrupt thresholds */ u16 work_lmt; + s16 vf_id; /* VF ID for SR-IOV VSIs */ + /* RSS config */ u16 rss_table_size; /* HW RSS table size */ u16 rss_size; /* Allocated RSS queues */ @@ -229,21 +256,39 @@ struct ice_q_vector { u8 num_ring_tx; /* total number of tx rings in vector */ u8 num_ring_rx; /* total number of rx rings in vector */ char name[ICE_INT_NAME_STR_LEN]; + /* in usecs, need to use ice_intrl_to_usecs_reg() before writing this + * value to the device + */ + u8 intrl; } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { ICE_FLAG_MSIX_ENA, ICE_FLAG_FLTR_SYNC, ICE_FLAG_RSS_ENA, + ICE_FLAG_SRIOV_ENA, + ICE_FLAG_SRIOV_CAPABLE, ICE_PF_FLAGS_NBITS /* must be last */ }; struct ice_pf { struct pci_dev *pdev; + + /* OS reserved IRQ details */ struct msix_entry *msix_entries; - struct ice_res_tracker *irq_tracker; + struct ice_res_tracker *sw_irq_tracker; + + /* HW reserved Interrupts for this PF */ + struct ice_res_tracker *hw_irq_tracker; + struct ice_vsi **vsi; /* VSIs created by the driver */ struct ice_sw *first_sw; /* first switch created by firmware */ + /* Virtchnl/SR-IOV config info */ + struct ice_vf *vf; + int num_alloc_vfs; /* actual number of VFs allocated */ + u16 num_vfs_supported; /* num VFs supported for this PF */ + u16 num_vf_qps; /* num queue pairs per VF */ + u16 num_vf_msix; /* num vectors per VF */ DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS); DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS); @@ -256,9 +301,11 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ u32 msg_enable; u32 hw_csum_rx_error; - u32 oicr_idx; /* Other interrupt cause vector index */ + u32 sw_oicr_idx; /* Other interrupt cause SW vector index */ + u32 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ + u32 hw_oicr_idx; /* Other interrupt cause vector HW index */ + u32 num_avail_hw_msix; /* remaining HW MSIX vectors left unclaimed */ u32 num_lan_msix; /* Total MSIX vectors for base driver */ - u32 num_avail_msix; /* remaining MSIX vectors left unclaimed */ u16 num_lan_tx; /* num lan tx queues setup */ u16 num_lan_rx; /* num lan rx queues setup */ u16 q_left_tx; /* remaining num tx queues left unclaimed */ @@ -293,8 +340,8 @@ struct ice_netdev_priv { static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi, struct ice_q_vector *q_vector) { - u32 vector = (vsi && q_vector) ? vsi->base_vector + q_vector->v_idx : - ((struct ice_pf *)hw->back)->oicr_idx; + u32 vector = (vsi && q_vector) ? vsi->hw_base_vector + q_vector->v_idx : + ((struct ice_pf *)hw->back)->hw_oicr_idx; int itr = ICE_ITR_NONE; u32 val; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index f8dfd675486c..6653555f55dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -87,6 +87,8 @@ struct ice_aqc_list_caps { /* Device/Function buffer entry, repeated per reported capability */ struct ice_aqc_list_caps_elem { __le16 cap; +#define ICE_AQC_CAPS_SRIOV 0x0012 +#define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 #define ICE_AQC_CAPS_RSS 0x0040 #define ICE_AQC_CAPS_RXQS 0x0041 @@ -736,6 +738,10 @@ struct ice_aqc_add_elem { struct ice_aqc_txsched_elem_data generic[1]; }; +struct ice_aqc_get_elem { + struct ice_aqc_txsched_elem_data generic[1]; +}; + struct ice_aqc_get_topo_elem { struct ice_aqc_txsched_topo_grp_info_hdr hdr; struct ice_aqc_txsched_elem_data @@ -1071,6 +1077,19 @@ struct ice_aqc_nvm { __le32 addr_low; }; +/** + * Send to PF command (indirect 0x0801) id is only used by PF + * + * Send to VF command (indirect 0x0802) id is only used by PF + * + */ +struct ice_aqc_pf_vf_msg { + __le32 id; + u32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { #define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) @@ -1328,6 +1347,7 @@ struct ice_aq_desc { struct ice_aqc_query_txsched_res query_sched_res; struct ice_aqc_add_move_delete_elem add_move_delete_elem; struct ice_aqc_nvm nvm; + struct ice_aqc_pf_vf_msg virt; struct ice_aqc_get_set_rss_lut get_set_rss_lut; struct ice_aqc_get_set_rss_key get_set_rss_key; struct ice_aqc_add_txqs add_txqs; @@ -1409,6 +1429,7 @@ enum ice_adminq_opc { /* transmit scheduler commands */ ice_aqc_opc_get_dflt_topo = 0x0400, ice_aqc_opc_add_sched_elems = 0x0401, + ice_aqc_opc_get_sched_elems = 0x0404, ice_aqc_opc_suspend_sched_elems = 0x0409, ice_aqc_opc_resume_sched_elems = 0x040A, ice_aqc_opc_delete_sched_elems = 0x040F, @@ -1424,6 +1445,10 @@ enum ice_adminq_opc { /* NVM commands */ ice_aqc_opc_nvm_read = 0x0701, + /* PF/VF mailbox commands */ + ice_mbx_opc_send_msg_to_pf = 0x0801, + ice_mbx_opc_send_msg_to_vf = 0x0802, + /* RSS commands */ ice_aqc_opc_set_rss_key = 0x0B02, ice_aqc_opc_set_rss_lut = 0x0B03, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 0847dbf9d42f..c52f450f2c0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -422,7 +422,7 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), lst_itr); } } - + ice_rm_all_sw_replay_rule_info(hw); devm_kfree(ice_hw_to_dev(hw), sw->recp_list); devm_kfree(ice_hw_to_dev(hw), sw); } @@ -598,6 +598,39 @@ void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) } /** + * ice_get_itr_intrl_gran - determine int/intrl granularity + * @hw: pointer to the hw struct + * + * Determines the itr/intrl granularities based on the maximum aggregate + * bandwidth according to the device's configuration during power-on. + */ +static enum ice_status ice_get_itr_intrl_gran(struct ice_hw *hw) +{ + u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) & + GL_PWR_MODE_CTL_CAR_MAX_BW_M) >> + GL_PWR_MODE_CTL_CAR_MAX_BW_S; + + switch (max_agg_bw) { + case ICE_MAX_AGG_BW_200G: + case ICE_MAX_AGG_BW_100G: + case ICE_MAX_AGG_BW_50G: + hw->itr_gran = ICE_ITR_GRAN_ABOVE_25; + hw->intrl_gran = ICE_INTRL_GRAN_ABOVE_25; + break; + case ICE_MAX_AGG_BW_25G: + hw->itr_gran = ICE_ITR_GRAN_MAX_25; + hw->intrl_gran = ICE_INTRL_GRAN_MAX_25; + break; + default: + ice_debug(hw, ICE_DBG_INIT, + "Failed to determine itr/intrl granularity\n"); + return ICE_ERR_CFG; + } + + return 0; +} + +/** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ @@ -621,11 +654,9 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) return status; - /* set these values to minimum allowed */ - hw->itr_gran_200 = ICE_ITR_GRAN_MIN_200; - hw->itr_gran_100 = ICE_ITR_GRAN_MIN_100; - hw->itr_gran_50 = ICE_ITR_GRAN_MIN_50; - hw->itr_gran_25 = ICE_ITR_GRAN_MIN_25; + status = ice_get_itr_intrl_gran(hw); + if (status) + return status; status = ice_init_all_ctrlq(hw); if (status) @@ -1375,6 +1406,28 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, u16 cap = le16_to_cpu(cap_resp->cap); switch (cap) { + case ICE_AQC_CAPS_SRIOV: + caps->sr_iov_1_1 = (number == 1); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: SR-IOV = %d\n", caps->sr_iov_1_1); + break; + case ICE_AQC_CAPS_VF: + if (dev_p) { + dev_p->num_vfs_exposed = number; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs exposed = %d\n", + dev_p->num_vfs_exposed); + } else if (func_p) { + func_p->num_allocd_vfs = number; + func_p->vf_base_id = logical_id; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs allocated = %d\n", + func_p->num_allocd_vfs); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VF base_id = %d\n", + func_p->vf_base_id); + } + break; case ICE_AQC_CAPS_VSI: if (dev_p) { dev_p->num_vsi_allocd_to_host = number; @@ -1451,7 +1504,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, * @hw: pointer to the hw struct * @buf: a virtual buffer to hold the capabilities * @buf_size: Size of the virtual buffer - * @data_size: Size of the returned data, or buf size needed if AQ err==ENOMEM + * @cap_count: cap count needed if AQ err==ENOMEM * @opc: capabilities type to discover - pass in the command opcode * @cd: pointer to command details structure or NULL * @@ -1459,7 +1512,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, * the firmware. */ static enum ice_status -ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u16 *data_size, +ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { struct ice_aqc_list_caps *cmd; @@ -1477,59 +1530,77 @@ ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u16 *data_size, status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); if (!status) ice_parse_caps(hw, buf, le32_to_cpu(cmd->count), opc); - *data_size = le16_to_cpu(desc.datalen); - + else if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOMEM) + *cap_count = + DIV_ROUND_UP(le16_to_cpu(desc.datalen), + sizeof(struct ice_aqc_list_caps_elem)); return status; } /** - * ice_get_caps - get info about the HW + * ice_discover_caps - get info about the HW * @hw: pointer to the hardware structure + * @opc: capabilities type to discover - pass in the command opcode */ -enum ice_status ice_get_caps(struct ice_hw *hw) +static enum ice_status ice_discover_caps(struct ice_hw *hw, + enum ice_adminq_opc opc) { enum ice_status status; - u16 data_size = 0; + u32 cap_count; u16 cbuf_len; u8 retries; /* The driver doesn't know how many capabilities the device will return * so the buffer size required isn't known ahead of time. The driver * starts with cbuf_len and if this turns out to be insufficient, the - * device returns ICE_AQ_RC_ENOMEM and also the buffer size it needs. - * The driver then allocates the buffer of this size and retries the - * operation. So it follows that the retry count is 2. + * device returns ICE_AQ_RC_ENOMEM and also the cap_count it needs. + * The driver then allocates the buffer based on the count and retries + * the operation. So it follows that the retry count is 2. */ #define ICE_GET_CAP_BUF_COUNT 40 #define ICE_GET_CAP_RETRY_COUNT 2 - cbuf_len = ICE_GET_CAP_BUF_COUNT * - sizeof(struct ice_aqc_list_caps_elem); - + cap_count = ICE_GET_CAP_BUF_COUNT; retries = ICE_GET_CAP_RETRY_COUNT; do { void *cbuf; + cbuf_len = (u16)(cap_count * + sizeof(struct ice_aqc_list_caps_elem)); cbuf = devm_kzalloc(ice_hw_to_dev(hw), cbuf_len, GFP_KERNEL); if (!cbuf) return ICE_ERR_NO_MEMORY; - status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &data_size, - ice_aqc_opc_list_func_caps, NULL); + status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &cap_count, + opc, NULL); devm_kfree(ice_hw_to_dev(hw), cbuf); if (!status || hw->adminq.sq_last_status != ICE_AQ_RC_ENOMEM) break; /* If ENOMEM is returned, try again with bigger buffer */ - cbuf_len = data_size; } while (--retries); return status; } /** + * ice_get_caps - get info about the HW + * @hw: pointer to the hardware structure + */ +enum ice_status ice_get_caps(struct ice_hw *hw) +{ + enum ice_status status; + + status = ice_discover_caps(hw, ice_aqc_opc_list_dev_caps); + if (!status) + status = ice_discover_caps(hw, ice_aqc_opc_list_func_caps); + + return status; +} + +/** * ice_aq_manage_mac_write - manage MAC address write command * @hw: pointer to the hw struct * @mac_addr: MAC address to be written as LAA/LAA+WoL/Port address @@ -1722,8 +1793,7 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, * ice_update_link_info - update status of the HW network link * @pi: port info structure of the interested logical port */ -static enum ice_status -ice_update_link_info(struct ice_port_info *pi) +enum ice_status ice_update_link_info(struct ice_port_info *pi) { struct ice_aqc_get_phy_caps_data *pcaps; struct ice_phy_info *phy_info; @@ -2037,7 +2107,7 @@ ice_aq_get_set_rss_lut_exit: /** * ice_aq_get_rss_lut * @hw: pointer to the hardware structure - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @lut_type: LUT table type * @lut: pointer to the LUT buffer provided by the caller * @lut_size: size of the LUT buffer @@ -2045,17 +2115,20 @@ ice_aq_get_set_rss_lut_exit: * get the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, - u16 lut_size) +ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, + u8 *lut, u16 lut_size) { - return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0, - false); + if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), + lut_type, lut, lut_size, 0, false); } /** * ice_aq_set_rss_lut * @hw: pointer to the hardware structure - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @lut_type: LUT table type * @lut: pointer to the LUT buffer provided by the caller * @lut_size: size of the LUT buffer @@ -2063,11 +2136,14 @@ ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, * set the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, - u16 lut_size) +ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, + u8 *lut, u16 lut_size) { - return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0, - true); + if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), + lut_type, lut, lut_size, 0, true); } /** @@ -2108,31 +2184,39 @@ ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, /** * ice_aq_get_rss_key * @hw: pointer to the hw struct - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @key: pointer to key info struct * * get the RSS key per VSI */ enum ice_status -ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *key) { - return __ice_aq_get_set_rss_key(hw, vsi_id, key, false); + if (!ice_is_vsi_valid(hw, vsi_handle) || !key) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), + key, false); } /** * ice_aq_set_rss_key * @hw: pointer to the hw struct - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @keys: pointer to key info struct * * set the RSS key per VSI */ enum ice_status -ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys) { - return __ice_aq_get_set_rss_key(hw, vsi_id, keys, true); + if (!ice_is_vsi_valid(hw, vsi_handle) || !keys) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), + keys, true); } /** @@ -2203,6 +2287,8 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, * @num_qgrps: number of groups in the list * @qg_list: the list of groups to disable * @buf_size: the total size of the qg_list buffer in bytes + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * Disable LAN Tx queue (0x0C31) @@ -2210,6 +2296,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, static enum ice_status ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *qg_list, u16 buf_size, + enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { struct ice_aqc_dis_txqs *cmd; @@ -2219,14 +2306,45 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, cmd = &desc.params.dis_txqs; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs); - if (!qg_list) + /* qg_list can be NULL only in VM/VF reset flow */ + if (!qg_list && !rst_src) return ICE_ERR_PARAM; if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS) return ICE_ERR_PARAM; - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + cmd->num_entries = num_qgrps; + cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) & + ICE_AQC_Q_DIS_TIMEOUT_M); + + switch (rst_src) { + case ICE_VM_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET; + cmd->vmvf_and_timeout |= + cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_VF_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET; + /* In this case, FW expects vmvf_num to be absolute VF id */ + cmd->vmvf_and_timeout |= + cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) & + ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_NO_RESET: + default: + break; + } + + /* If no queue group info, we are in a reset flow. Issue the AQ */ + if (!qg_list) + goto do_aq; + + /* set RD bit to indicate that command buffer is provided by the driver + * and it needs to be read by the firmware + */ + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + for (i = 0; i < num_qgrps; ++i) { /* Calculate the size taken up by the queue IDs in this group */ sz += qg_list[i].num_qs * sizeof(qg_list[i].q_id); @@ -2242,6 +2360,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, if (buf_size != sz) return ICE_ERR_PARAM; +do_aq: return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd); } @@ -2471,7 +2590,7 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /** * ice_ena_vsi_txq * @pi: port information structure - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * @tc: tc number * @num_qgrps: Number of added queue groups * @buf: list of queue groups to be added @@ -2481,7 +2600,7 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) * This function adds one lan q */ enum ice_status -ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, +ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd) { @@ -2498,15 +2617,19 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, hw = pi->hw; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + mutex_lock(&pi->sched_lock); /* find a parent node */ - parent = ice_sched_get_free_qparent(pi, vsi_id, tc, + parent = ice_sched_get_free_qparent(pi, vsi_handle, tc, ICE_SCHED_NODE_OWNER_LAN); if (!parent) { status = ICE_ERR_PARAM; goto ena_txq_exit; } + buf->parent_teid = parent->info.node_teid; node.parent_teid = parent->info.node_teid; /* Mark that the values in the "generic" section as valid. The default @@ -2544,13 +2667,16 @@ ena_txq_exit: * @num_queues: number of queues * @q_ids: pointer to the q_id array * @q_teids: pointer to queue node teids + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * This function removes queues and their corresponding nodes in SW DB */ enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cd) + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cd) { enum ice_status status = ICE_ERR_DOES_NOT_EXIST; struct ice_aqc_dis_txq_item qg_list; @@ -2559,6 +2685,15 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return ICE_ERR_CFG; + /* if queue is disabled already yet the disable queue command has to be + * sent to complete the VF reset, then call ice_aq_dis_lan_txq without + * any queue information + */ + + if (!num_queues && rst_src) + return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src, vmvf_num, + NULL); + mutex_lock(&pi->sched_lock); for (i = 0; i < num_queues; i++) { @@ -2571,7 +2706,8 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, qg_list.num_qs = 1; qg_list.q_id[0] = cpu_to_le16(q_ids[i]); status = ice_aq_dis_lan_txq(pi->hw, 1, &qg_list, - sizeof(qg_list), cd); + sizeof(qg_list), rst_src, vmvf_num, + cd); if (status) break; @@ -2584,7 +2720,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, /** * ice_cfg_vsi_qs - configure the new/exisiting VSI queues * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_bitmap: TC bitmap * @maxqs: max queues array per TC * @owner: lan or rdma @@ -2592,7 +2728,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, * This function adds/updates the VSI queues per TC. */ static enum ice_status -ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *maxqs, u8 owner) { enum ice_status status = 0; @@ -2601,6 +2737,9 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return ICE_ERR_CFG; + if (!ice_is_vsi_valid(pi->hw, vsi_handle)) + return ICE_ERR_PARAM; + mutex_lock(&pi->sched_lock); for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { @@ -2608,7 +2747,7 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, if (!ice_sched_get_tc_node(pi, i)) continue; - status = ice_sched_cfg_vsi(pi, vsi_id, i, maxqs[i], owner, + status = ice_sched_cfg_vsi(pi, vsi_handle, i, maxqs[i], owner, ice_is_tc_ena(tc_bitmap, i)); if (status) break; @@ -2621,16 +2760,140 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, /** * ice_cfg_vsi_lan - configure VSI lan queues * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_bitmap: TC bitmap * @max_lanqs: max lan queues array per TC * * This function adds/updates the VSI lan queues per TC. */ enum ice_status -ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs) { - return ice_cfg_vsi_qs(pi, vsi_id, tc_bitmap, max_lanqs, + return ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, max_lanqs, ICE_SCHED_NODE_OWNER_LAN); } + +/** + * ice_replay_pre_init - replay pre initialization + * @hw: pointer to the hw struct + * + * Initializes required config data for VSI, FD, ACL, and RSS before replay. + */ +static enum ice_status ice_replay_pre_init(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + /* Delete old entries from replay filter list head if there is any */ + ice_rm_all_sw_replay_rule_info(hw); + /* In start of replay, move entries into replay_rules list, it + * will allow adding rules entries back to filt_rules list, + * which is operational list. + */ + for (i = 0; i < ICE_SW_LKUP_LAST; i++) + list_replace_init(&sw->recp_list[i].filt_rules, + &sw->recp_list[i].filt_replay_rules); + + return 0; +} + +/** + * ice_replay_vsi - replay VSI configuration + * @hw: pointer to the hw struct + * @vsi_handle: driver VSI handle + * + * Restore all VSI configuration after reset. It is required to call this + * function with main VSI first. + */ +enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle) +{ + enum ice_status status; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + /* Replay pre-initialization if there is any */ + if (vsi_handle == ICE_MAIN_VSI_HANDLE) { + status = ice_replay_pre_init(hw); + if (status) + return status; + } + + /* Replay per VSI all filters */ + status = ice_replay_vsi_all_fltr(hw, vsi_handle); + return status; +} + +/** + * ice_replay_post - post replay configuration cleanup + * @hw: pointer to the hw struct + * + * Post replay cleanup. + */ +void ice_replay_post(struct ice_hw *hw) +{ + /* Delete old entries from replay filter list head */ + ice_rm_all_sw_replay_rule_info(hw); +} + +/** + * ice_stat_update40 - read 40 bit stat from the chip and update stat values + * @hw: ptr to the hardware info + * @hireg: high 32 bit HW register to read from + * @loreg: low 32 bit HW register to read from + * @prev_stat_loaded: bool to specify if previous stats are loaded + * @prev_stat: ptr to previous loaded stat value + * @cur_stat: ptr to current stat value + */ +void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, + bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat) +{ + u64 new_data; + + new_data = rd32(hw, loreg); + new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; + + /* device stats are not reset at PFR, they likely will not be zeroed + * when the driver starts. So save the first values read and use them as + * offsets to be subtracted from the raw values in order to report stats + * that count from zero. + */ + if (!prev_stat_loaded) + *prev_stat = new_data; + if (new_data >= *prev_stat) + *cur_stat = new_data - *prev_stat; + else + /* to manage the potential roll-over */ + *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; + *cur_stat &= 0xFFFFFFFFFFULL; +} + +/** + * ice_stat_update32 - read 32 bit stat from the chip and update stat values + * @hw: ptr to the hardware info + * @reg: HW register to read from + * @prev_stat_loaded: bool to specify if previous stats are loaded + * @prev_stat: ptr to previous loaded stat value + * @cur_stat: ptr to current stat value + */ +void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat) +{ + u32 new_data; + + new_data = rd32(hw, reg); + + /* device stats are not reset at PFR, they likely will not be zeroed + * when the driver starts. So save the first values read and use them as + * offsets to be subtracted from the raw values in order to report stats + * that count from zero. + */ + if (!prev_stat_loaded) + *prev_stat = new_data; + if (new_data >= *prev_stat) + *cur_stat = new_data - *prev_stat; + else + /* to manage the potential roll-over */ + *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; +} diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index aac2d6cadaaf..1900681289a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -7,6 +7,7 @@ #include "ice.h" #include "ice_type.h" #include "ice_switch.h" +#include <linux/avf/virtchnl.h> void ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf, u16 buf_len); @@ -21,6 +22,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending); enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up); +enum ice_status ice_update_link_info(struct ice_port_info *pi); enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, enum ice_aq_res_access_type access, u32 timeout); @@ -37,17 +39,18 @@ ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, +ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, u16 lut_size); enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, +ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, u16 lut_size); enum ice_status -ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); enum ice_status -ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); + bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); @@ -87,13 +90,20 @@ ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, struct ice_sq_cd *cd); enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cmd_details); + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cmd_details); enum ice_status -ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs); enum ice_status -ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, +ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); +void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); +void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, + bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 1fe026a65d75..84c967294eaf 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -33,6 +33,36 @@ static void ice_adminq_init_regs(struct ice_hw *hw) } /** + * ice_mailbox_init_regs - Initialize Mailbox registers + * @hw: pointer to the hardware structure + * + * This assumes the alloc_sq and alloc_rq functions have already been called + */ +static void ice_mailbox_init_regs(struct ice_hw *hw) +{ + struct ice_ctl_q_info *cq = &hw->mailboxq; + + /* set head and tail registers in our local struct */ + cq->sq.head = PF_MBX_ATQH; + cq->sq.tail = PF_MBX_ATQT; + cq->sq.len = PF_MBX_ATQLEN; + cq->sq.bah = PF_MBX_ATQBAH; + cq->sq.bal = PF_MBX_ATQBAL; + cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M; + cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M; + cq->sq.head_mask = PF_MBX_ATQH_ATQH_M; + + cq->rq.head = PF_MBX_ARQH; + cq->rq.tail = PF_MBX_ARQT; + cq->rq.len = PF_MBX_ARQLEN; + cq->rq.bah = PF_MBX_ARQBAH; + cq->rq.bal = PF_MBX_ARQBAL; + cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M; + cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M; + cq->rq.head_mask = PF_MBX_ARQH_ARQH_M; +} + +/** * ice_check_sq_alive * @hw: pointer to the hw struct * @cq: pointer to the specific Control queue @@ -518,22 +548,31 @@ shutdown_sq_out: /** * ice_aq_ver_check - Check the reported AQ API version. - * @fw_branch: The "branch" of FW, typically describes the device type - * @fw_major: The major version of the FW API - * @fw_minor: The minor version increment of the FW API + * @hw: pointer to the hardware structure * * Checks if the driver should load on a given AQ API version. * * Return: 'true' iff the driver should attempt to load. 'false' otherwise. */ -static bool ice_aq_ver_check(u8 fw_branch, u8 fw_major, u8 fw_minor) +static bool ice_aq_ver_check(struct ice_hw *hw) { - if (fw_branch != EXP_FW_API_VER_BRANCH) - return false; - if (fw_major != EXP_FW_API_VER_MAJOR) - return false; - if (fw_minor != EXP_FW_API_VER_MINOR) + if (hw->api_maj_ver > EXP_FW_API_VER_MAJOR) { + /* Major API version is newer than expected, don't load */ + dev_warn(ice_hw_to_dev(hw), + "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); return false; + } else if (hw->api_maj_ver == EXP_FW_API_VER_MAJOR) { + if (hw->api_min_ver > (EXP_FW_API_VER_MINOR + 2)) + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); + else if ((hw->api_min_ver + 2) < EXP_FW_API_VER_MINOR) + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + } else { + /* Major API version is older than expected, log a warning */ + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + } return true; } @@ -588,8 +627,7 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) if (status) goto init_ctrlq_free_rq; - if (!ice_aq_ver_check(hw->api_branch, hw->api_maj_ver, - hw->api_min_ver)) { + if (!ice_aq_ver_check(hw)) { status = ICE_ERR_FW_API_VER; goto init_ctrlq_free_rq; } @@ -597,11 +635,11 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) return 0; init_ctrlq_free_rq: - if (cq->rq.head) { + if (cq->rq.count) { ice_shutdown_rq(hw, cq); mutex_destroy(&cq->rq_lock); } - if (cq->sq.head) { + if (cq->sq.count) { ice_shutdown_sq(hw, cq); mutex_destroy(&cq->sq_lock); } @@ -631,6 +669,10 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) ice_adminq_init_regs(hw); cq = &hw->adminq; break; + case ICE_CTL_Q_MAILBOX: + ice_mailbox_init_regs(hw); + cq = &hw->mailboxq; + break; default: return ICE_ERR_PARAM; } @@ -688,7 +730,12 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) if (ret_code) return ret_code; - return ice_init_check_adminq(hw); + ret_code = ice_init_check_adminq(hw); + if (ret_code) + return ret_code; + + /* Init Mailbox queue */ + return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** @@ -706,15 +753,18 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) if (ice_check_sq_alive(hw, cq)) ice_aq_q_shutdown(hw, true); break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + break; default: return; } - if (cq->sq.head) { + if (cq->sq.count) { ice_shutdown_sq(hw, cq); mutex_destroy(&cq->sq_lock); } - if (cq->rq.head) { + if (cq->rq.count) { ice_shutdown_rq(hw, cq); mutex_destroy(&cq->rq_lock); } @@ -728,6 +778,8 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { /* Shutdown FW admin queue */ ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + /* Shutdown PF-VF Mailbox */ + ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** @@ -850,7 +902,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use); if (cd) - memcpy(details, cd, sizeof(*details)); + *details = *cd; else memset(details, 0, sizeof(*details)); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index ea02b89243e2..437f832fd7c4 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -8,6 +8,7 @@ /* Maximum buffer lengths for all control queue types */ #define ICE_AQ_MAX_BUF_LEN 4096 +#define ICE_MBXQ_MAX_BUF_LEN 4096 #define ICE_CTL_Q_DESC(R, i) \ (&(((struct ice_aq_desc *)((R).desc_buf.va))[i])) @@ -28,6 +29,7 @@ enum ice_ctl_q { ICE_CTL_Q_UNKNOWN = 0, ICE_CTL_Q_ADMIN, + ICE_CTL_Q_MAILBOX, }; /* Control Queue default settings */ diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 0e14d7215a6e..a6f0a5c0c305 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -5,15 +5,11 @@ #define _ICE_DEVIDS_H_ /* Device IDs */ -/* Intel(R) Ethernet Controller C810 for backplane */ +/* Intel(R) Ethernet Controller E810-C for backplane */ #define ICE_DEV_ID_C810_BACKPLANE 0x1591 -/* Intel(R) Ethernet Controller C810 for QSFP */ +/* Intel(R) Ethernet Controller E810-C for QSFP */ #define ICE_DEV_ID_C810_QSFP 0x1592 -/* Intel(R) Ethernet Controller C810 for SFP */ +/* Intel(R) Ethernet Controller E810-C for SFP */ #define ICE_DEV_ID_C810_SFP 0x1593 -/* Intel(R) Ethernet Controller C810/X557-AT 10GBASE-T */ -#define ICE_DEV_ID_C810_10G_BASE_T 0x1594 -/* Intel(R) Ethernet Controller C810 1GbE */ -#define ICE_DEV_ID_C810_SGMII 0x1595 #endif /* _ICE_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index db2c502ae932..96923580f2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1198,9 +1198,11 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) ring->tx_max_pending = ICE_MAX_NUM_DESC; ring->rx_pending = vsi->rx_rings[0]->count; ring->tx_pending = vsi->tx_rings[0]->count; - ring->rx_mini_pending = ICE_MIN_NUM_DESC; + + /* Rx mini and jumbo rings are not supported */ ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; + ring->rx_mini_pending = 0; ring->rx_jumbo_pending = 0; } @@ -1218,14 +1220,23 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) ring->tx_pending < ICE_MIN_NUM_DESC || ring->rx_pending > ICE_MAX_NUM_DESC || ring->rx_pending < ICE_MIN_NUM_DESC) { - netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d]\n", + netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n", ring->tx_pending, ring->rx_pending, - ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC); + ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC, + ICE_REQ_DESC_MULTIPLE); return -EINVAL; } new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); + if (new_tx_cnt != ring->tx_pending) + netdev_info(netdev, + "Requested Tx descriptor count rounded up to %d\n", + new_tx_cnt); new_rx_cnt = ALIGN(ring->rx_pending, ICE_REQ_DESC_MULTIPLE); + if (new_rx_cnt != ring->rx_pending) + netdev_info(netdev, + "Requested Rx descriptor count rounded up to %d\n", + new_rx_cnt); /* if nothing to do return success */ if (new_tx_cnt == vsi->tx_rings[0]->count && diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 88f11498804b..a6679a9bfd3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -29,6 +29,22 @@ #define PF_FW_ATQLEN_ATQCRIT_M BIT(30) #define PF_FW_ATQLEN_ATQENABLE_M BIT(31) #define PF_FW_ATQT 0x00080400 +#define PF_MBX_ARQBAH 0x0022E400 +#define PF_MBX_ARQBAL 0x0022E380 +#define PF_MBX_ARQH 0x0022E500 +#define PF_MBX_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN 0x0022E480 +#define PF_MBX_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN_ARQENABLE_M BIT(31) +#define PF_MBX_ARQT 0x0022E580 +#define PF_MBX_ATQBAH 0x0022E180 +#define PF_MBX_ATQBAL 0x0022E100 +#define PF_MBX_ATQH 0x0022E280 +#define PF_MBX_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN 0x0022E200 +#define PF_MBX_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN_ATQENABLE_M BIT(31) +#define PF_MBX_ATQT 0x0022E300 #define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) @@ -74,10 +90,16 @@ #define GLGEN_RTRIG_CORER_M BIT(0) #define GLGEN_RTRIG_GLOBR_M BIT(1) #define GLGEN_STAT 0x000B612C +#define GLGEN_VFLRSTAT(_i) (0x00093A04 + ((_i) * 4)) #define PFGEN_CTRL 0x00091000 #define PFGEN_CTRL_PFSWR_M BIT(0) #define PFGEN_STATE 0x00088000 #define PRTGEN_STATUS 0x000B8100 +#define VFGEN_RSTAT(_VF) (0x00074000 + ((_VF) * 4)) +#define VPGEN_VFRSTAT(_VF) (0x00090800 + ((_VF) * 4)) +#define VPGEN_VFRSTAT_VFRD_M BIT(0) +#define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4)) +#define VPGEN_VFRTRIG_VFSWR_M BIT(0) #define PFHMC_ERRORDATA 0x00520500 #define PFHMC_ERRORINFO 0x00520400 #define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) @@ -88,11 +110,25 @@ #define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) #define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) #define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) +#define GLINT_RATE(_INT) (0x0015A000 + ((_INT) * 4)) +#define GLINT_RATE_INTRL_ENA_M BIT(6) +#define GLINT_VECT2FUNC(_INT) (0x00162000 + ((_INT) * 4)) +#define GLINT_VECT2FUNC_VF_NUM_S 0 +#define GLINT_VECT2FUNC_VF_NUM_M ICE_M(0xFF, 0) +#define GLINT_VECT2FUNC_PF_NUM_S 12 +#define GLINT_VECT2FUNC_PF_NUM_M ICE_M(0x7, 12) +#define GLINT_VECT2FUNC_IS_PF_S 16 +#define GLINT_VECT2FUNC_IS_PF_M BIT(16) #define PFINT_FW_CTL 0x0016C800 #define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_FW_CTL_ITR_INDX_S 11 #define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, 11) #define PFINT_FW_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_MBX_CTL 0x0016B280 +#define PFINT_MBX_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_MBX_CTL_ITR_INDX_S 11 +#define PFINT_MBX_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_MBX_CTL_CAUSE_ENA_M BIT(30) #define PFINT_OICR 0x0016CA00 #define PFINT_OICR_ECC_ERR_M BIT(16) #define PFINT_OICR_MAL_DETECT_M BIT(19) @@ -100,6 +136,7 @@ #define PFINT_OICR_PCI_EXCEPTION_M BIT(21) #define PFINT_OICR_HMC_ERR_M BIT(26) #define PFINT_OICR_PE_CRITERR_M BIT(28) +#define PFINT_OICR_VFLR_M BIT(29) #define PFINT_OICR_CTL 0x0016CA80 #define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_OICR_CTL_ITR_INDX_S 11 @@ -114,6 +151,12 @@ #define QINT_TQCTL_MSIX_INDX_S 0 #define QINT_TQCTL_ITR_INDX_S 11 #define QINT_TQCTL_CAUSE_ENA_M BIT(30) +#define VPINT_ALLOC(_VF) (0x001D1000 + ((_VF) * 4)) +#define VPINT_ALLOC_FIRST_S 0 +#define VPINT_ALLOC_FIRST_M ICE_M(0x7FF, 0) +#define VPINT_ALLOC_LAST_S 12 +#define VPINT_ALLOC_LAST_M ICE_M(0x7FF, 12) +#define VPINT_ALLOC_VALID_M BIT(31) #define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) #define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) #define QRX_CTRL_MAX_INDEX 2047 @@ -126,6 +169,20 @@ #define QRX_TAIL_MAX_INDEX 2047 #define QRX_TAIL_TAIL_S 0 #define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0) +#define VPLAN_RX_QBASE(_VF) (0x00072000 + ((_VF) * 4)) +#define VPLAN_RX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_RX_QBASE_VFFIRSTQ_M ICE_M(0x7FF, 0) +#define VPLAN_RX_QBASE_VFNUMQ_S 16 +#define VPLAN_RX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_RXQ_MAPENA(_VF) (0x00073000 + ((_VF) * 4)) +#define VPLAN_RXQ_MAPENA_RX_ENA_M BIT(0) +#define VPLAN_TX_QBASE(_VF) (0x001D1800 + ((_VF) * 4)) +#define VPLAN_TX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_TX_QBASE_VFFIRSTQ_M ICE_M(0x3FFF, 0) +#define VPLAN_TX_QBASE_VFNUMQ_S 16 +#define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4)) +#define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0) #define GL_MDET_RX 0x00294C00 #define GL_MDET_RX_QNUM_S 0 #define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) @@ -162,6 +219,14 @@ #define PF_MDET_TX_PQM_VALID_M BIT(0) #define PF_MDET_TX_TCLAN 0x000FC000 #define PF_MDET_TX_TCLAN_VALID_M BIT(0) +#define VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4)) +#define VP_MDET_RX_VALID_M BIT(0) +#define VP_MDET_TX_PQM(_VF) (0x002D2000 + ((_VF) * 4)) +#define VP_MDET_TX_PQM_VALID_M BIT(0) +#define VP_MDET_TX_TCLAN(_VF) (0x000FB800 + ((_VF) * 4)) +#define VP_MDET_TX_TCLAN_VALID_M BIT(0) +#define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4)) +#define VP_MDET_TX_TDPU_VALID_M BIT(0) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 @@ -173,6 +238,12 @@ #define PF_FUNC_RID 0x0009E880 #define PF_FUNC_RID_FUNC_NUM_S 0 #define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) +#define PF_PCI_CIAA 0x0009E580 +#define PF_PCI_CIAA_VF_NUM_S 12 +#define PF_PCI_CIAD 0x0009E500 +#define GL_PWR_MODE_CTL 0x000B820C +#define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 +#define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) #define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) #define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) #define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) @@ -250,5 +321,8 @@ #define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define VSIQF_HKEY_MAX_INDEX 12 +#define VSIQF_HLUT_MAX_INDEX 15 +#define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) +#define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 94504023d86e..7d2a66739e3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -418,6 +418,7 @@ struct ice_tlan_ctx { u8 pf_num; u16 vmvf_num; u8 vmvf_type; +#define ICE_TLAN_CTX_VMVF_TYPE_VF 0 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ 1 #define ICE_TLAN_CTX_VMVF_TYPE_PF 2 u16 src_vsi; @@ -473,4 +474,16 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) { return ice_ptype_lkup[ptype]; } + +#define ICE_LINK_SPEED_UNKNOWN 0 +#define ICE_LINK_SPEED_10MBPS 10 +#define ICE_LINK_SPEED_100MBPS 100 +#define ICE_LINK_SPEED_1000MBPS 1000 +#define ICE_LINK_SPEED_2500MBPS 2500 +#define ICE_LINK_SPEED_5000MBPS 5000 +#define ICE_LINK_SPEED_10000MBPS 10000 +#define ICE_LINK_SPEED_20000MBPS 20000 +#define ICE_LINK_SPEED_25000MBPS 25000 +#define ICE_LINK_SPEED_40000MBPS 40000 + #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c new file mode 100644 index 000000000000..49f1940772ed --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -0,0 +1,2619 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +/** + * ice_setup_rx_ctx - Configure a receive ring context + * @ring: The Rx ring to configure + * + * Configure the Rx descriptor ring in RLAN context. + */ +static int ice_setup_rx_ctx(struct ice_ring *ring) +{ + struct ice_vsi *vsi = ring->vsi; + struct ice_hw *hw = &vsi->back->hw; + u32 rxdid = ICE_RXDID_FLEX_NIC; + struct ice_rlan_ctx rlan_ctx; + u32 regval; + u16 pf_q; + int err; + + /* what is RX queue number in global space of 2K Rx queues */ + pf_q = vsi->rxq_map[ring->q_index]; + + /* clear the context structure first */ + memset(&rlan_ctx, 0, sizeof(rlan_ctx)); + + rlan_ctx.base = ring->dma >> 7; + + rlan_ctx.qlen = ring->count; + + /* Receive Packet Data Buffer Size. + * The Packet Data Buffer Size is defined in 128 byte units. + */ + rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + + /* use 32 byte descriptors */ + rlan_ctx.dsize = 1; + + /* Strip the Ethernet CRC bytes before the packet is posted to host + * memory. + */ + rlan_ctx.crcstrip = 1; + + /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ + rlan_ctx.l2tsel = 1; + + rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; + + /* This controls whether VLAN is stripped from inner headers + * The VLAN in the inner L2 header is stripped to the receive + * descriptor if enabled by this flag. + */ + rlan_ctx.showiv = 0; + + /* Max packet size for this queue - must not be set to a larger value + * than 5 x DBUF + */ + rlan_ctx.rxmax = min_t(u16, vsi->max_frame, + ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len); + + /* Rx queue threshold in units of 64 */ + rlan_ctx.lrxqthresh = 1; + + /* Enable Flexible Descriptors in the queue context which + * allows this driver to select a specific receive descriptor format + */ + if (vsi->type != ICE_VSI_VF) { + regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); + regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & + QRXFLXP_CNTXT_RXDID_IDX_M; + + /* increasing context priority to pick up profile id; + * default is 0x01; setting to 0x03 to ensure profile + * is programming if prev context is of same priority + */ + regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & + QRXFLXP_CNTXT_RXDID_PRIO_M; + + wr32(hw, QRXFLXP_CNTXT(pf_q), regval); + } + + /* Absolute queue number out of 2K needs to be passed */ + err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); + if (err) { + dev_err(&vsi->back->pdev->dev, + "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", + pf_q, err); + return -EIO; + } + + if (vsi->type == ICE_VSI_VF) + return 0; + + /* init queue specific tail register */ + ring->tail = hw->hw_addr + QRX_TAIL(pf_q); + writel(0, ring->tail); + ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); + + return 0; +} + +/** + * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance + * @ring: The Tx ring to configure + * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized + * @pf_q: queue index in the PF space + * + * Configure the Tx descriptor ring in TLAN context. + */ +static void +ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) +{ + struct ice_vsi *vsi = ring->vsi; + struct ice_hw *hw = &vsi->back->hw; + + tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S; + + tlan_ctx->port_num = vsi->port_info->lport; + + /* Transmit Queue Length */ + tlan_ctx->qlen = ring->count; + + /* PF number */ + tlan_ctx->pf_num = hw->pf_id; + + /* queue belongs to a specific VSI type + * VF / VM index should be programmed per vmvf_type setting: + * for vmvf_type = VF, it is VF number between 0-256 + * for vmvf_type = VM, it is VM number between 0-767 + * for PF or EMP this field should be set to zero + */ + switch (vsi->type) { + case ICE_VSI_PF: + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; + break; + case ICE_VSI_VF: + /* Firmware expects vmvf_num to be absolute VF id */ + tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id; + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; + break; + default: + return; + } + + /* make sure the context is associated with the right VSI */ + tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx); + + tlan_ctx->tso_ena = ICE_TX_LEGACY; + tlan_ctx->tso_qnum = pf_q; + + /* Legacy or Advanced Host Interface: + * 0: Advanced Host Interface + * 1: Legacy Host Interface + */ + tlan_ctx->legacy_int = ICE_TX_LEGACY; +} + +/** + * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled + * @pf: the PF being configured + * @pf_q: the PF queue + * @ena: enable or disable state of the queue + * + * This routine will wait for the given Rx queue of the PF to reach the + * enabled or disabled state. + * Returns -ETIMEDOUT in case of failing to reach the requested state after + * multiple retries; else will return 0 in case of success. + */ +static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) +{ + int i; + + for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) { + u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q)); + + if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) + break; + + usleep_range(10, 20); + } + if (i >= ICE_Q_WAIT_RETRY_LIMIT) + return -ETIMEDOUT; + + return 0; +} + +/** + * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings + * @vsi: the VSI being configured + * @ena: start or stop the Rx rings + */ +static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int i, j, ret = 0; + + for (i = 0; i < vsi->num_rxq; i++) { + int pf_q = vsi->rxq_map[i]; + u32 rx_reg; + + for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) { + rx_reg = rd32(hw, QRX_CTRL(pf_q)); + if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) == + ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) + continue; + + /* turn on/off the queue */ + if (ena) + rx_reg |= QRX_CTRL_QENA_REQ_M; + else + rx_reg &= ~QRX_CTRL_QENA_REQ_M; + wr32(hw, QRX_CTRL(pf_q), rx_reg); + + /* wait for the change to finish */ + ret = ice_pf_rxq_wait(pf, pf_q, ena); + if (ret) { + dev_err(&pf->pdev->dev, + "VSI idx %d Rx ring %d %sable timeout\n", + vsi->idx, pf_q, (ena ? "en" : "dis")); + break; + } + } + + return ret; +} + +/** + * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the VSI + * @vsi: VSI pointer + * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. + * + * On error: returns error code (negative) + * On success: returns 0 + */ +static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors) +{ + struct ice_pf *pf = vsi->back; + + /* allocate memory for both Tx and Rx ring pointers */ + vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, + sizeof(struct ice_ring *), GFP_KERNEL); + if (!vsi->tx_rings) + goto err_txrings; + + vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, + sizeof(struct ice_ring *), GFP_KERNEL); + if (!vsi->rx_rings) + goto err_rxrings; + + if (alloc_qvectors) { + /* allocate memory for q_vector pointers */ + vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, + vsi->num_q_vectors, + sizeof(struct ice_q_vector *), + GFP_KERNEL); + if (!vsi->q_vectors) + goto err_vectors; + } + + return 0; + +err_vectors: + devm_kfree(&pf->pdev->dev, vsi->rx_rings); +err_rxrings: + devm_kfree(&pf->pdev->dev, vsi->tx_rings); +err_txrings: + return -ENOMEM; +} + +/** + * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + */ +static void ice_vsi_set_num_qs(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + + switch (vsi->type) { + case ICE_VSI_PF: + vsi->alloc_txq = pf->num_lan_tx; + vsi->alloc_rxq = pf->num_lan_rx; + vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE); + vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); + break; + case ICE_VSI_VF: + vsi->alloc_txq = pf->num_vf_qps; + vsi->alloc_rxq = pf->num_vf_qps; + /* pf->num_vf_msix includes (VF miscellaneous vector + + * data queue interrupts). Since vsi->num_q_vectors is number + * of queues vectors, subtract 1 from the original vector + * count + */ + vsi->num_q_vectors = pf->num_vf_msix - 1; + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } +} + +/** + * ice_get_free_slot - get the next non-NULL location index in array + * @array: array to search + * @size: size of the array + * @curr: last known occupied index to be used as a search hint + * + * void * is being used to keep the functionality generic. This lets us use this + * function on any array of pointers. + */ +static int ice_get_free_slot(void *array, int size, int curr) +{ + int **tmp_array = (int **)array; + int next; + + if (curr < (size - 1) && !tmp_array[curr + 1]) { + next = curr + 1; + } else { + int i = 0; + + while ((i < size) && (tmp_array[i])) + i++; + if (i == size) + next = ICE_NO_VSI; + else + next = i; + } + return next; +} + +/** + * ice_vsi_delete - delete a VSI from the switch + * @vsi: pointer to VSI being removed + */ +void ice_vsi_delete(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_vsi_ctx ctxt; + enum ice_status status; + + if (vsi->type == ICE_VSI_VF) + ctxt.vf_num = vsi->vf_id; + ctxt.vsi_num = vsi->vsi_num; + + memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); + + status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL); + if (status) + dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", + vsi->vsi_num); +} + +/** + * ice_vsi_free_arrays - clean up VSI resources + * @vsi: pointer to VSI being cleared + * @free_qvectors: bool to specify if q_vectors should be deallocated + */ +static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors) +{ + struct ice_pf *pf = vsi->back; + + /* free the ring and vector containers */ + if (free_qvectors && vsi->q_vectors) { + devm_kfree(&pf->pdev->dev, vsi->q_vectors); + vsi->q_vectors = NULL; + } + if (vsi->tx_rings) { + devm_kfree(&pf->pdev->dev, vsi->tx_rings); + vsi->tx_rings = NULL; + } + if (vsi->rx_rings) { + devm_kfree(&pf->pdev->dev, vsi->rx_rings); + vsi->rx_rings = NULL; + } +} + +/** + * ice_vsi_clear - clean up and deallocate the provided VSI + * @vsi: pointer to VSI being cleared + * + * This deallocates the VSI's queue resources, removes it from the PF's + * VSI array if necessary, and deallocates the VSI + * + * Returns 0 on success, negative on failure + */ +int ice_vsi_clear(struct ice_vsi *vsi) +{ + struct ice_pf *pf = NULL; + + if (!vsi) + return 0; + + if (!vsi->back) + return -EINVAL; + + pf = vsi->back; + + if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { + dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n", + vsi->idx); + return -EINVAL; + } + + mutex_lock(&pf->sw_mutex); + /* updates the PF for this cleared VSI */ + + pf->vsi[vsi->idx] = NULL; + if (vsi->idx < pf->next_vsi) + pf->next_vsi = vsi->idx; + + ice_vsi_free_arrays(vsi, true); + mutex_unlock(&pf->sw_mutex); + devm_kfree(&pf->pdev->dev, vsi); + + return 0; +} + +/** + * ice_msix_clean_rings - MSIX mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a q_vector + */ +irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) +{ + struct ice_q_vector *q_vector = (struct ice_q_vector *)data; + + if (!q_vector->tx.ring && !q_vector->rx.ring) + return IRQ_HANDLED; + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ice_vsi_alloc - Allocates the next available struct VSI in the PF + * @pf: board private structure + * @type: type of VSI + * + * returns a pointer to a VSI on success, NULL on failure. + */ +static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type) +{ + struct ice_vsi *vsi = NULL; + + /* Need to protect the allocation of the VSIs at the PF level */ + mutex_lock(&pf->sw_mutex); + + /* If we have already allocated our maximum number of VSIs, + * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index + * is available to be populated + */ + if (pf->next_vsi == ICE_NO_VSI) { + dev_dbg(&pf->pdev->dev, "out of VSI slots!\n"); + goto unlock_pf; + } + + vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL); + if (!vsi) + goto unlock_pf; + + vsi->type = type; + vsi->back = pf; + set_bit(__ICE_DOWN, vsi->state); + vsi->idx = pf->next_vsi; + vsi->work_lmt = ICE_DFLT_IRQ_WORK; + + ice_vsi_set_num_qs(vsi); + + switch (vsi->type) { + case ICE_VSI_PF: + if (ice_vsi_alloc_arrays(vsi, true)) + goto err_rings; + + /* Setup default MSIX irq handler for VSI */ + vsi->irq_handler = ice_msix_clean_rings; + break; + case ICE_VSI_VF: + if (ice_vsi_alloc_arrays(vsi, true)) + goto err_rings; + break; + default: + dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); + goto unlock_pf; + } + + /* fill VSI slot in the PF struct */ + pf->vsi[pf->next_vsi] = vsi; + + /* prepare pf->next_vsi for next use */ + pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, + pf->next_vsi); + goto unlock_pf; + +err_rings: + devm_kfree(&pf->pdev->dev, vsi); + vsi = NULL; +unlock_pf: + mutex_unlock(&pf->sw_mutex); + return vsi; +} + +/** + * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI + * @vsi: the VSI getting queues + * + * Return 0 on success and a negative value on error + */ +static int ice_vsi_get_qs_contig(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int offset, ret = 0; + + mutex_lock(&pf->avail_q_mutex); + /* look for contiguous block of queues for Tx */ + offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS, + 0, vsi->alloc_txq, 0); + if (offset < ICE_MAX_TXQS) { + int i; + + bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq); + for (i = 0; i < vsi->alloc_txq; i++) + vsi->txq_map[i] = i + offset; + } else { + ret = -ENOMEM; + vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER; + } + + /* look for contiguous block of queues for Rx */ + offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS, + 0, vsi->alloc_rxq, 0); + if (offset < ICE_MAX_RXQS) { + int i; + + bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq); + for (i = 0; i < vsi->alloc_rxq; i++) + vsi->rxq_map[i] = i + offset; + } else { + ret = -ENOMEM; + vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER; + } + mutex_unlock(&pf->avail_q_mutex); + + return ret; +} + +/** + * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI + * @vsi: the VSI getting queues + * + * Return 0 on success and a negative value on error + */ +static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i, index = 0; + + mutex_lock(&pf->avail_q_mutex); + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) { + for (i = 0; i < vsi->alloc_txq; i++) { + index = find_next_zero_bit(pf->avail_txqs, + ICE_MAX_TXQS, index); + if (index < ICE_MAX_TXQS) { + set_bit(index, pf->avail_txqs); + vsi->txq_map[i] = index; + } else { + goto err_scatter_tx; + } + } + } + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) { + for (i = 0; i < vsi->alloc_rxq; i++) { + index = find_next_zero_bit(pf->avail_rxqs, + ICE_MAX_RXQS, index); + if (index < ICE_MAX_RXQS) { + set_bit(index, pf->avail_rxqs); + vsi->rxq_map[i] = index; + } else { + goto err_scatter_rx; + } + } + } + + mutex_unlock(&pf->avail_q_mutex); + return 0; + +err_scatter_rx: + /* unflag any queues we have grabbed (i is failed position) */ + for (index = 0; index < i; index++) { + clear_bit(vsi->rxq_map[index], pf->avail_rxqs); + vsi->rxq_map[index] = 0; + } + i = vsi->alloc_txq; +err_scatter_tx: + /* i is either position of failed attempt or vsi->alloc_txq */ + for (index = 0; index < i; index++) { + clear_bit(vsi->txq_map[index], pf->avail_txqs); + vsi->txq_map[index] = 0; + } + + mutex_unlock(&pf->avail_q_mutex); + return -ENOMEM; +} + +/** + * ice_vsi_get_qs - Assign queues from PF to VSI + * @vsi: the VSI to assign queues to + * + * Returns 0 on success and a negative value on error + */ +static int ice_vsi_get_qs(struct ice_vsi *vsi) +{ + int ret = 0; + + vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG; + vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG; + + /* NOTE: ice_vsi_get_qs_contig() will set the Rx/Tx mapping + * modes individually to scatter if assigning contiguous queues + * to Rx or Tx fails + */ + ret = ice_vsi_get_qs_contig(vsi); + if (ret < 0) { + if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) + vsi->alloc_txq = max_t(u16, vsi->alloc_txq, + ICE_MAX_SCATTER_TXQS); + if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) + vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq, + ICE_MAX_SCATTER_RXQS); + ret = ice_vsi_get_qs_scatter(vsi); + } + + return ret; +} + +/** + * ice_vsi_put_qs - Release queues from VSI to PF + * @vsi: the VSI that is going to release queues + */ +void ice_vsi_put_qs(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i; + + mutex_lock(&pf->avail_q_mutex); + + for (i = 0; i < vsi->alloc_txq; i++) { + clear_bit(vsi->txq_map[i], pf->avail_txqs); + vsi->txq_map[i] = ICE_INVAL_Q_INDEX; + } + + for (i = 0; i < vsi->alloc_rxq; i++) { + clear_bit(vsi->rxq_map[i], pf->avail_rxqs); + vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; + } + + mutex_unlock(&pf->avail_q_mutex); +} + +/** + * ice_rss_clean - Delete RSS related VSI structures that hold user inputs + * @vsi: the VSI being removed + */ +static void ice_rss_clean(struct ice_vsi *vsi) +{ + struct ice_pf *pf; + + pf = vsi->back; + + if (vsi->rss_hkey_user) + devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user); + if (vsi->rss_lut_user) + devm_kfree(&pf->pdev->dev, vsi->rss_lut_user); +} + +/** + * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type + * @vsi: the VSI being configured + */ +static void ice_vsi_set_rss_params(struct ice_vsi *vsi) +{ + struct ice_hw_common_caps *cap; + struct ice_pf *pf = vsi->back; + + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + vsi->rss_size = 1; + return; + } + + cap = &pf->hw.func_caps.common_cap; + switch (vsi->type) { + case ICE_VSI_PF: + /* PF VSI will inherit RSS instance of PF */ + vsi->rss_table_size = cap->rss_table_size; + vsi->rss_size = min_t(int, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table + * For VSI_LUT, LUT size should be set to 64 bytes + */ + vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_size = min_t(int, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + break; + default: + dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } +} + +/** + * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI + * @ctxt: the VSI context being set + * + * This initializes a default VSI context for all sections except the Queues. + */ +static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) +{ + u32 table = 0; + + memset(&ctxt->info, 0, sizeof(ctxt->info)); + /* VSI's should be allocated from shared pool */ + ctxt->alloc_from_pool = true; + /* Src pruning enabled by default */ + ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; + /* Traffic from VSI can be sent to LAN */ + ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; + /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy + * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all + * packets untagged/tagged. + */ + ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & + ICE_AQ_VSI_VLAN_MODE_M) >> + ICE_AQ_VSI_VLAN_MODE_S); + /* Have 1:1 UP mapping for both ingress/egress tables */ + table |= ICE_UP_TABLE_TRANSLATE(0, 0); + table |= ICE_UP_TABLE_TRANSLATE(1, 1); + table |= ICE_UP_TABLE_TRANSLATE(2, 2); + table |= ICE_UP_TABLE_TRANSLATE(3, 3); + table |= ICE_UP_TABLE_TRANSLATE(4, 4); + table |= ICE_UP_TABLE_TRANSLATE(5, 5); + table |= ICE_UP_TABLE_TRANSLATE(6, 6); + table |= ICE_UP_TABLE_TRANSLATE(7, 7); + ctxt->info.ingress_table = cpu_to_le32(table); + ctxt->info.egress_table = cpu_to_le32(table); + /* Have 1:1 UP mapping for outer to inner UP table */ + ctxt->info.outer_up_table = cpu_to_le32(table); + /* No Outer tag support outer_tag_flags remains to zero */ +} + +/** + * ice_vsi_setup_q_map - Setup a VSI queue map + * @vsi: the VSI being configured + * @ctxt: VSI context structure + */ +static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) +{ + u16 offset = 0, qmap = 0, numq_tc; + u16 pow = 0, max_rss = 0, qcount; + u16 qcount_tx = vsi->alloc_txq; + u16 qcount_rx = vsi->alloc_rxq; + bool ena_tc0 = false; + int i; + + /* at least TC0 should be enabled by default */ + if (vsi->tc_cfg.numtc) { + if (!(vsi->tc_cfg.ena_tc & BIT(0))) + ena_tc0 = true; + } else { + ena_tc0 = true; + } + + if (ena_tc0) { + vsi->tc_cfg.numtc++; + vsi->tc_cfg.ena_tc |= 1; + } + + numq_tc = qcount_rx / vsi->tc_cfg.numtc; + + /* TC mapping is a function of the number of Rx queues assigned to the + * VSI for each traffic class and the offset of these queues. + * The first 10 bits are for queue offset for TC0, next 4 bits for no:of + * queues allocated to TC0. No:of queues is a power-of-2. + * + * If TC is not enabled, the queue offset is set to 0, and allocate one + * queue, this way, traffic for the given TC will be sent to the default + * queue. + * + * Setup number and offset of Rx queues for all TCs for the VSI + */ + + qcount = numq_tc; + /* qcount will change if RSS is enabled */ + if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { + if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) { + if (vsi->type == ICE_VSI_PF) + max_rss = ICE_MAX_LG_RSS_QS; + else + max_rss = ICE_MAX_SMALL_RSS_QS; + qcount = min_t(int, numq_tc, max_rss); + qcount = min_t(int, qcount, vsi->rss_size); + } + } + + /* find the (rounded up) power-of-2 of qcount */ + pow = order_base_2(qcount); + + for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) { + /* TC is not enabled */ + vsi->tc_cfg.tc_info[i].qoffset = 0; + vsi->tc_cfg.tc_info[i].qcount = 1; + ctxt->info.tc_mapping[i] = 0; + continue; + } + + /* TC is enabled */ + vsi->tc_cfg.tc_info[i].qoffset = offset; + vsi->tc_cfg.tc_info[i].qcount = qcount; + + qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & + ICE_AQ_VSI_TC_Q_OFFSET_M) | + ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & + ICE_AQ_VSI_TC_Q_NUM_M); + offset += qcount; + ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); + } + + vsi->num_txq = qcount_tx; + vsi->num_rxq = offset; + + if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { + dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); + /* since there is a chance that num_rxq could have been changed + * in the above for loop, make num_txq equal to num_rxq. + */ + vsi->num_txq = vsi->num_rxq; + } + + /* Rx queue mapping */ + ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); + /* q_mapping buffer holds the info for the first queue allocated for + * this VSI in the PF space and also the number of queues associated + * with this VSI. + */ + ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); + ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq); +} + +/** + * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI + * @ctxt: the VSI context being set + * @vsi: the VSI being configured + */ +static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) +{ + u8 lut_type, hash_type; + + switch (vsi->type) { + case ICE_VSI_PF: + /* PF VSI will inherit RSS instance of PF */ + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table which is a VSI LUT type */ + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + return; + } + + ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & + ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | + ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & + ICE_AQ_VSI_Q_OPT_RSS_HASH_M); +} + +/** + * ice_vsi_init - Create and initialize a VSI + * @vsi: the VSI being configured + * + * This initializes a VSI context depending on the VSI type to be added and + * passes it down to the add_vsi aq command to create a new VSI. + */ +static int ice_vsi_init(struct ice_vsi *vsi) +{ + struct ice_vsi_ctx ctxt = { 0 }; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int ret = 0; + + switch (vsi->type) { + case ICE_VSI_PF: + ctxt.flags = ICE_AQ_VSI_TYPE_PF; + break; + case ICE_VSI_VF: + ctxt.flags = ICE_AQ_VSI_TYPE_VF; + /* VF number here is the absolute VF number (0-255) */ + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id; + break; + default: + return -ENODEV; + } + + ice_set_dflt_vsi_ctx(&ctxt); + /* if the switch is in VEB mode, allow VSI loopback */ + if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB) + ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + + /* Set LUT type and HASH type if RSS is enabled */ + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_set_rss_vsi_ctx(&ctxt, vsi); + + ctxt.info.sw_id = vsi->port_info->sw_id; + ice_vsi_setup_q_map(vsi, &ctxt); + + ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Add VSI failed, err %d\n", ret); + return -EIO; + } + + /* keep context for update VSI operations */ + vsi->info = ctxt.info; + + /* record VSI number returned */ + vsi->vsi_num = ctxt.vsi_num; + + return ret; +} + +/** + * ice_free_q_vector - Free memory allocated for a specific interrupt vector + * @vsi: VSI having the memory freed + * @v_idx: index of the vector to be freed + */ +static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) +{ + struct ice_q_vector *q_vector; + struct ice_ring *ring; + + if (!vsi->q_vectors[v_idx]) { + dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n", + v_idx); + return; + } + q_vector = vsi->q_vectors[v_idx]; + + ice_for_each_ring(ring, q_vector->tx) + ring->q_vector = NULL; + ice_for_each_ring(ring, q_vector->rx) + ring->q_vector = NULL; + + /* only VSI with an associated netdev is set up with NAPI */ + if (vsi->netdev) + netif_napi_del(&q_vector->napi); + + devm_kfree(&vsi->back->pdev->dev, q_vector); + vsi->q_vectors[v_idx] = NULL; +} + +/** + * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors + * @vsi: the VSI having memory freed + */ +void ice_vsi_free_q_vectors(struct ice_vsi *vsi) +{ + int v_idx; + + for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) + ice_free_q_vector(vsi, v_idx); +} + +/** + * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector + * @vsi: the VSI being configured + * @v_idx: index of the vector in the VSI struct + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + */ +static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) +{ + struct ice_pf *pf = vsi->back; + struct ice_q_vector *q_vector; + + /* allocate q_vector */ + q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + q_vector->vsi = vsi; + q_vector->v_idx = v_idx; + if (vsi->type == ICE_VSI_VF) + goto out; + /* only set affinity_mask if the CPU is online */ + if (cpu_online(v_idx)) + cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + + /* This will not be called in the driver load path because the netdev + * will not be created yet. All other cases with register the NAPI + * handler here (i.e. resume, reset/rebuild, etc.) + */ + if (vsi->netdev) + netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, + NAPI_POLL_WEIGHT); + +out: + /* tie q_vector and VSI together */ + vsi->q_vectors[v_idx] = q_vector; + + return 0; +} + +/** + * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors + * @vsi: the VSI being configured + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + */ +static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int v_idx = 0, num_q_vectors; + int err; + + if (vsi->q_vectors[0]) { + dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n", + vsi->vsi_num); + return -EEXIST; + } + + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + num_q_vectors = vsi->num_q_vectors; + } else { + err = -EINVAL; + goto err_out; + } + + for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { + err = ice_vsi_alloc_q_vector(vsi, v_idx); + if (err) + goto err_out; + } + + return 0; + +err_out: + while (v_idx--) + ice_free_q_vector(vsi, v_idx); + + dev_err(&pf->pdev->dev, + "Failed to allocate %d q_vector for VSI %d, ret=%d\n", + vsi->num_q_vectors, vsi->vsi_num, err); + vsi->num_q_vectors = 0; + return err; +} + +/** + * ice_vsi_setup_vector_base - Set up the base vector for the given VSI + * @vsi: ptr to the VSI + * + * This should only be called after ice_vsi_alloc() which allocates the + * corresponding SW VSI structure and initializes num_queue_pairs for the + * newly allocated VSI. + * + * Returns 0 on success or negative on failure + */ +static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int num_q_vectors = 0; + + if (vsi->sw_base_vector || vsi->hw_base_vector) { + dev_dbg(&pf->pdev->dev, "VSI %d has non-zero HW base vector %d or SW base vector %d\n", + vsi->vsi_num, vsi->hw_base_vector, vsi->sw_base_vector); + return -EEXIST; + } + + if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + return -ENOENT; + + switch (vsi->type) { + case ICE_VSI_PF: + num_q_vectors = vsi->num_q_vectors; + /* reserve slots from OS requested IRQs */ + vsi->sw_base_vector = ice_get_res(pf, pf->sw_irq_tracker, + num_q_vectors, vsi->idx); + if (vsi->sw_base_vector < 0) { + dev_err(&pf->pdev->dev, + "Failed to get tracking for %d SW vectors for VSI %d, err=%d\n", + num_q_vectors, vsi->vsi_num, + vsi->sw_base_vector); + return -ENOENT; + } + pf->num_avail_sw_msix -= num_q_vectors; + + /* reserve slots from HW interrupts */ + vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, + num_q_vectors, vsi->idx); + break; + case ICE_VSI_VF: + /* take VF misc vector and data vectors into account */ + num_q_vectors = pf->num_vf_msix; + /* For VF VSI, reserve slots only from HW interrupts */ + vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, + num_q_vectors, vsi->idx); + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } + + if (vsi->hw_base_vector < 0) { + dev_err(&pf->pdev->dev, + "Failed to get tracking for %d HW vectors for VSI %d, err=%d\n", + num_q_vectors, vsi->vsi_num, vsi->hw_base_vector); + if (vsi->type != ICE_VSI_VF) { + ice_free_res(vsi->back->sw_irq_tracker, + vsi->sw_base_vector, vsi->idx); + pf->num_avail_sw_msix += num_q_vectors; + } + return -ENOENT; + } + + pf->num_avail_hw_msix -= num_q_vectors; + + return 0; +} + +/** + * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI + * @vsi: the VSI having rings deallocated + */ +static void ice_vsi_clear_rings(struct ice_vsi *vsi) +{ + int i; + + if (vsi->tx_rings) { + for (i = 0; i < vsi->alloc_txq; i++) { + if (vsi->tx_rings[i]) { + kfree_rcu(vsi->tx_rings[i], rcu); + vsi->tx_rings[i] = NULL; + } + } + } + if (vsi->rx_rings) { + for (i = 0; i < vsi->alloc_rxq; i++) { + if (vsi->rx_rings[i]) { + kfree_rcu(vsi->rx_rings[i], rcu); + vsi->rx_rings[i] = NULL; + } + } + } +} + +/** + * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI + * @vsi: VSI which is having rings allocated + */ +static int ice_vsi_alloc_rings(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i; + + /* Allocate tx_rings */ + for (i = 0; i < vsi->alloc_txq; i++) { + struct ice_ring *ring; + + /* allocate with kzalloc(), free with kfree_rcu() */ + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + + if (!ring) + goto err_out; + + ring->q_index = i; + ring->reg_idx = vsi->txq_map[i]; + ring->ring_active = false; + ring->vsi = vsi; + ring->dev = &pf->pdev->dev; + ring->count = vsi->num_desc; + vsi->tx_rings[i] = ring; + } + + /* Allocate rx_rings */ + for (i = 0; i < vsi->alloc_rxq; i++) { + struct ice_ring *ring; + + /* allocate with kzalloc(), free with kfree_rcu() */ + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_out; + + ring->q_index = i; + ring->reg_idx = vsi->rxq_map[i]; + ring->ring_active = false; + ring->vsi = vsi; + ring->netdev = vsi->netdev; + ring->dev = &pf->pdev->dev; + ring->count = vsi->num_desc; + vsi->rx_rings[i] = ring; + } + + return 0; + +err_out: + ice_vsi_clear_rings(vsi); + return -ENOMEM; +} + +/** + * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors + * @vsi: the VSI being configured + * + * This function maps descriptor rings to the queue-specific vectors allotted + * through the MSI-X enabling code. On a constrained vector budget, we map Tx + * and Rx rings to the vector as "efficiently" as possible. + */ +static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) +{ + int q_vectors = vsi->num_q_vectors; + int tx_rings_rem, rx_rings_rem; + int v_id; + + /* initially assigning remaining rings count to VSIs num queue value */ + tx_rings_rem = vsi->num_txq; + rx_rings_rem = vsi->num_rxq; + + for (v_id = 0; v_id < q_vectors; v_id++) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_id]; + int tx_rings_per_v, rx_rings_per_v, q_id, q_base; + + /* Tx rings mapping to vector */ + tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); + q_vector->num_ring_tx = tx_rings_per_v; + q_vector->tx.ring = NULL; + q_vector->tx.itr_idx = ICE_TX_ITR; + q_base = vsi->num_txq - tx_rings_rem; + + for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { + struct ice_ring *tx_ring = vsi->tx_rings[q_id]; + + tx_ring->q_vector = q_vector; + tx_ring->next = q_vector->tx.ring; + q_vector->tx.ring = tx_ring; + } + tx_rings_rem -= tx_rings_per_v; + + /* Rx rings mapping to vector */ + rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); + q_vector->num_ring_rx = rx_rings_per_v; + q_vector->rx.ring = NULL; + q_vector->rx.itr_idx = ICE_RX_ITR; + q_base = vsi->num_rxq - rx_rings_rem; + + for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { + struct ice_ring *rx_ring = vsi->rx_rings[q_id]; + + rx_ring->q_vector = q_vector; + rx_ring->next = q_vector->rx.ring; + q_vector->rx.ring = rx_ring; + } + rx_rings_rem -= rx_rings_per_v; + } +} + +/** + * ice_vsi_manage_rss_lut - disable/enable RSS + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is an enable or disable request + * + * In the event of disable request for RSS, this function will zero out RSS + * LUT, while in the event of enable request for RSS, it will reconfigure RSS + * LUT. + */ +int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) +{ + int err = 0; + u8 *lut; + + lut = devm_kzalloc(&vsi->back->pdev->dev, vsi->rss_table_size, + GFP_KERNEL); + if (!lut) + return -ENOMEM; + + if (ena) { + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + ice_fill_rss_lut(lut, vsi->rss_table_size, + vsi->rss_size); + } + + err = ice_set_rss(vsi, NULL, lut, vsi->rss_table_size); + devm_kfree(&vsi->back->pdev->dev, lut); + return err; +} + +/** + * ice_vsi_cfg_rss_lut_key - Configure RSS params for a VSI + * @vsi: VSI to be configured + */ +static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) +{ + u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE]; + struct ice_aqc_get_set_rss_keys *key; + struct ice_pf *pf = vsi->back; + enum ice_status status; + int err = 0; + u8 *lut; + + vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq); + + lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); + + status = ice_aq_set_rss_lut(&pf->hw, vsi->idx, vsi->rss_lut_type, lut, + vsi->rss_table_size); + + if (status) { + dev_err(&vsi->back->pdev->dev, + "set_rss_lut failed, error %d\n", status); + err = -EIO; + goto ice_vsi_cfg_rss_exit; + } + + key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto ice_vsi_cfg_rss_exit; + } + + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + else + netdev_rss_key_fill((void *)seed, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + memcpy(&key->standard_rss_key, seed, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + + status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key); + + if (status) { + dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n", + status); + err = -EIO; + } + + devm_kfree(&pf->pdev->dev, key); +ice_vsi_cfg_rss_exit: + devm_kfree(&pf->pdev->dev, lut); + return err; +} + +/** + * ice_add_mac_to_list - Add a mac address filter entry to the list + * @vsi: the VSI to be forwarded to + * @add_list: pointer to the list which contains MAC filter entries + * @macaddr: the MAC address to be added. + * + * Adds mac address filter entry to the temp list + * + * Returns 0 on success or ENOMEM on failure. + */ +int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr) +{ + struct ice_fltr_list_entry *tmp; + struct ice_pf *pf = vsi->back; + + tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + + tmp->fltr_info.flag = ICE_FLTR_TX; + tmp->fltr_info.src_id = ICE_SRC_ID_VSI; + tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC; + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.vsi_handle = vsi->idx; + ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr); + + INIT_LIST_HEAD(&tmp->list_entry); + list_add(&tmp->list_entry, add_list); + + return 0; +} + +/** + * ice_update_eth_stats - Update VSI-specific ethernet statistics counters + * @vsi: the VSI to be updated + */ +void ice_update_eth_stats(struct ice_vsi *vsi) +{ + struct ice_eth_stats *prev_es, *cur_es; + struct ice_hw *hw = &vsi->back->hw; + u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ + + prev_es = &vsi->eth_stats_prev; + cur_es = &vsi->eth_stats; + + ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_bytes, + &cur_es->rx_bytes); + + ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_unicast, + &cur_es->rx_unicast); + + ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_multicast, + &cur_es->rx_multicast); + + ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_broadcast, + &cur_es->rx_broadcast); + + ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_discards, &cur_es->rx_discards); + + ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_bytes, + &cur_es->tx_bytes); + + ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_unicast, + &cur_es->tx_unicast); + + ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_multicast, + &cur_es->tx_multicast); + + ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_broadcast, + &cur_es->tx_broadcast); + + ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_errors, &cur_es->tx_errors); + + vsi->stat_offsets_loaded = true; +} + +/** + * ice_free_fltr_list - free filter lists helper + * @dev: pointer to the device struct + * @h: pointer to the list head to be freed + * + * Helper function to free filter lists previously created using + * ice_add_mac_to_list + */ +void ice_free_fltr_list(struct device *dev, struct list_head *h) +{ + struct ice_fltr_list_entry *e, *tmp; + + list_for_each_entry_safe(e, tmp, h, list_entry) { + list_del(&e->list_entry); + devm_kfree(dev, e); + } +} + +/** + * ice_vsi_add_vlan - Add VSI membership for given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be added + */ +int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid) +{ + struct ice_fltr_list_entry *tmp; + struct ice_pf *pf = vsi->back; + LIST_HEAD(tmp_add_list); + enum ice_status status; + int err = 0; + + tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.flag = ICE_FLTR_TX; + tmp->fltr_info.src_id = ICE_SRC_ID_VSI; + tmp->fltr_info.vsi_handle = vsi->idx; + tmp->fltr_info.l_data.vlan.vlan_id = vid; + + INIT_LIST_HEAD(&tmp->list_entry); + list_add(&tmp->list_entry, &tmp_add_list); + + status = ice_add_vlan(&pf->hw, &tmp_add_list); + if (status) { + err = -ENODEV; + dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n", + vid, vsi->vsi_num); + } + + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return err; +} + +/** + * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be removed + * + * Returns 0 on success and negative on failure + */ +int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) +{ + struct ice_fltr_list_entry *list; + struct ice_pf *pf = vsi->back; + LIST_HEAD(tmp_add_list); + int status = 0; + + list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); + if (!list) + return -ENOMEM; + + list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; + list->fltr_info.vsi_handle = vsi->idx; + list->fltr_info.fltr_act = ICE_FWD_TO_VSI; + list->fltr_info.l_data.vlan.vlan_id = vid; + list->fltr_info.flag = ICE_FLTR_TX; + list->fltr_info.src_id = ICE_SRC_ID_VSI; + + INIT_LIST_HEAD(&list->list_entry); + list_add(&list->list_entry, &tmp_add_list); + + if (ice_remove_vlan(&pf->hw, &tmp_add_list)) { + dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", + vid, vsi->vsi_num); + status = -EIO; + } + + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; +} + +/** + * ice_vsi_cfg_rxqs - Configure the VSI for Rx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Rx VSI for operation. + */ +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) +{ + int err = 0; + u16 i; + + if (vsi->type == ICE_VSI_VF) + goto setup_rings; + + if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN) + vsi->max_frame = vsi->netdev->mtu + + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + else + vsi->max_frame = ICE_RXBUF_2048; + + vsi->rx_buf_len = ICE_RXBUF_2048; +setup_rings: + /* set up individual rings */ + for (i = 0; i < vsi->num_rxq && !err; i++) + err = ice_setup_rx_ctx(vsi->rx_rings[i]); + + if (err) { + dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n"); + return -EIO; + } + return err; +} + +/** + * ice_vsi_cfg_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +int ice_vsi_cfg_txqs(struct ice_vsi *vsi) +{ + struct ice_aqc_add_tx_qgrp *qg_buf; + struct ice_aqc_add_txqs_perq *txq; + struct ice_pf *pf = vsi->back; + enum ice_status status; + u16 buf_len, i, pf_q; + int err = 0, tc = 0; + u8 num_q_grps; + + buf_len = sizeof(struct ice_aqc_add_tx_qgrp); + qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); + if (!qg_buf) + return -ENOMEM; + + if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) { + err = -EINVAL; + goto err_cfg_txqs; + } + qg_buf->num_txqs = 1; + num_q_grps = 1; + + /* set up and configure the Tx queues */ + ice_for_each_txq(vsi, i) { + struct ice_tlan_ctx tlan_ctx = { 0 }; + + pf_q = vsi->txq_map[i]; + ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q); + /* copy context contents into the qg_buf */ + qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); + ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, + ice_tlan_ctx_info); + + /* init queue specific tail reg. It is referred as transmit + * comm scheduler queue doorbell. + */ + vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); + status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, + num_q_grps, qg_buf, buf_len, NULL); + if (status) { + dev_err(&vsi->back->pdev->dev, + "Failed to set LAN Tx queue context, error: %d\n", + status); + err = -ENODEV; + goto err_cfg_txqs; + } + + /* Add Tx Queue TEID into the VSI Tx ring from the response + * This will complete configuring and enabling the queue. + */ + txq = &qg_buf->txqs[0]; + if (pf_q == le16_to_cpu(txq->txq_id)) + vsi->tx_rings[i]->txq_teid = + le32_to_cpu(txq->q_teid); + } +err_cfg_txqs: + devm_kfree(&pf->pdev->dev, qg_buf); + return err; +} + +/** + * ice_intrl_usec_to_reg - convert interrupt rate limit to register value + * @intrl: interrupt rate limit in usecs + * @gran: interrupt rate limit granularity in usecs + * + * This function converts a decimal interrupt rate limit in usecs to the format + * expected by firmware. + */ +static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) +{ + u32 val = intrl / gran; + + if (val) + return val | GLINT_RATE_INTRL_ENA_M; + return 0; +} + +/** + * ice_cfg_itr - configure the initial interrupt throttle values + * @hw: pointer to the HW structure + * @q_vector: interrupt vector that's being configured + * @vector: HW vector index to apply the interrupt throttling to + * + * Configure interrupt throttling values for the ring containers that are + * associated with the interrupt vector passed in. + */ +static void +ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector) +{ + u8 itr_gran = hw->itr_gran; + + if (q_vector->num_ring_rx) { + struct ice_ring_container *rc = &q_vector->rx; + + rc->itr = ITR_TO_REG(ICE_DFLT_RX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } + + if (q_vector->num_ring_tx) { + struct ice_ring_container *rc = &q_vector->tx; + + rc->itr = ITR_TO_REG(ICE_DFLT_TX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } +} + +/** + * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW + * @vsi: the VSI being configured + */ +void ice_vsi_cfg_msix(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + u16 vector = vsi->hw_base_vector; + struct ice_hw *hw = &pf->hw; + u32 txq = 0, rxq = 0; + int i, q; + + for (i = 0; i < vsi->num_q_vectors; i++, vector++) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + ice_cfg_itr(hw, q_vector, vector); + + wr32(hw, GLINT_RATE(vector), + ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); + + /* Both Transmit Queue Interrupt Cause Control register + * and Receive Queue Interrupt Cause control register + * expects MSIX_INDX field to be the vector index + * within the function space and not the absolute + * vector index across PF or across device. + * For SR-IOV VF VSIs queue vector index always starts + * with 1 since first vector index(0) is used for OICR + * in VF space. Since VMDq and other PF VSIs are within + * the PF function space, use the vector index that is + * tracked for this PF. + */ + for (q = 0; q < q_vector->num_ring_tx; q++) { + int itr_idx = q_vector->tx.itr_idx; + u32 val; + + if (vsi->type == ICE_VSI_VF) + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + ((i + 1) << QINT_TQCTL_MSIX_INDX_S); + else + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + (vector << QINT_TQCTL_MSIX_INDX_S); + wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); + txq++; + } + + for (q = 0; q < q_vector->num_ring_rx; q++) { + int itr_idx = q_vector->rx.itr_idx; + u32 val; + + if (vsi->type == ICE_VSI_VF) + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + ((i + 1) << QINT_RQCTL_MSIX_INDX_S); + else + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + (vector << QINT_RQCTL_MSIX_INDX_S); + wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); + rxq++; + } + } + + ice_flush(hw); +} + +/** + * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx + * @vsi: the VSI being changed + */ +int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + /* Here we are configuring the VSI to let the driver add VLAN tags by + * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag + * insertion happens in the Tx hot path, in ice_tx_map. + */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; + + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is a enable or disable request + */ +int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + /* Here we are configuring what the VSI should do with the VLAN tag in + * the Rx packet. We can either leave the tag in the packet or put it in + * the Rx descriptor. + */ + if (ena) { + /* Strip VLAN tag from Rx packet and put it in the desc */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; + } else { + /* Disable stripping. Leave tag in packet */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; + } + + /* Allow all packets untagged/tagged */ + ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; + + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", + ena, status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_start_rx_rings - start VSI's Rx rings + * @vsi: the VSI whose rings are to be started + * + * Returns 0 on success and a negative value on error + */ +int ice_vsi_start_rx_rings(struct ice_vsi *vsi) +{ + return ice_vsi_ctrl_rx_rings(vsi, true); +} + +/** + * ice_vsi_stop_rx_rings - stop VSI's Rx rings + * @vsi: the VSI + * + * Returns 0 on success and a negative value on error + */ +int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) +{ + return ice_vsi_ctrl_rx_rings(vsi, false); +} + +/** + * ice_vsi_stop_tx_rings - Disable Tx rings + * @vsi: the VSI being configured + * @rst_src: reset source + * @rel_vmvf_num: Relative id of VF/VM + */ +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u32 *q_teids, val; + u16 *q_ids, i; + int err = 0; + + if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) + return -EINVAL; + + q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids), + GFP_KERNEL); + if (!q_teids) + return -ENOMEM; + + q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids), + GFP_KERNEL); + if (!q_ids) { + err = -ENOMEM; + goto err_alloc_q_ids; + } + + /* set up the Tx queue list to be disabled */ + ice_for_each_txq(vsi, i) { + u16 v_idx; + + if (!vsi->tx_rings || !vsi->tx_rings[i]) { + err = -EINVAL; + goto err_out; + } + + q_ids[i] = vsi->txq_map[i]; + q_teids[i] = vsi->tx_rings[i]->txq_teid; + + /* clear cause_ena bit for disabled queues */ + val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx)); + val &= ~QINT_TQCTL_CAUSE_ENA_M; + wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val); + + /* software is expected to wait for 100 ns */ + ndelay(100); + + /* trigger a software interrupt for the vector associated to + * the queue to schedule NAPI handler + */ + v_idx = vsi->tx_rings[i]->q_vector->v_idx; + wr32(hw, GLINT_DYN_CTL(vsi->hw_base_vector + v_idx), + GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); + } + status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, + rst_src, rel_vmvf_num, NULL); + /* if the disable queue command was exercised during an active reset + * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as + * the reset operation disables queues at the hardware level anyway. + */ + if (status == ICE_ERR_RESET_ONGOING) { + dev_info(&pf->pdev->dev, + "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status) { + dev_err(&pf->pdev->dev, + "Failed to disable LAN Tx queues, error: %d\n", + status); + err = -ENODEV; + } + +err_out: + devm_kfree(&pf->pdev->dev, q_ids); + +err_alloc_q_ids: + devm_kfree(&pf->pdev->dev, q_teids); + + return err; +} + +/** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct device *dev; + int status; + + if (!vsi) + return -EINVAL; + + dev = &vsi->back->pdev->dev; + ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) { + ctxt->info.sec_flags |= + ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } else { + ctxt->info.sec_flags &= + ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n", + ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status, + vsi->back->hw.adminq.sq_last_status); + goto err_out; + } + + vsi->info.sec_flags = ctxt->info.sec_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + devm_kfree(dev, ctxt); + return 0; + +err_out: + devm_kfree(dev, ctxt); + return -EIO; +} + +/** + * ice_vsi_setup - Set up a VSI by a given type + * @pf: board private structure + * @pi: pointer to the port_info instance + * @type: VSI type + * @vf_id: defines VF id to which this VSI connects. This field is meant to be + * used only for ICE_VSI_VF VSI type. For other VSI types, should + * fill-in ICE_INVAL_VFID as input. + * + * This allocates the sw VSI structure and its queue resources. + * + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. + */ +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 vf_id) +{ + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct device *dev = &pf->pdev->dev; + struct ice_vsi *vsi; + int ret, i; + + vsi = ice_vsi_alloc(pf, type); + if (!vsi) { + dev_err(dev, "could not allocate VSI\n"); + return NULL; + } + + vsi->port_info = pi; + vsi->vsw = pf->first_sw; + if (vsi->type == ICE_VSI_VF) + vsi->vf_id = vf_id; + + if (ice_vsi_get_qs(vsi)) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_get_qs; + } + + /* set RSS capabilities */ + ice_vsi_set_rss_params(vsi); + + /* create the VSI */ + ret = ice_vsi_init(vsi); + if (ret) + goto unroll_get_qs; + + switch (vsi->type) { + case ICE_VSI_PF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto unroll_vsi_init; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto unroll_alloc_q_vector; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_vector_base; + + ice_vsi_map_rings_to_vectors(vsi); + + /* Do not exit if configuring RSS had an issue, at least + * receive traffic on first queue. Hence no need to capture + * return value + */ + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_vsi_cfg_rss_lut_key(vsi); + break; + case ICE_VSI_VF: + /* VF driver will take care of creating netdev for this type and + * map queues to vectors through Virtchnl, PF driver only + * creates a VSI and corresponding structures for bookkeeping + * purpose + */ + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto unroll_vsi_init; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + + /* Setup Vector base only during VF init phase or when VF asks + * for more vectors than assigned number. In all other cases, + * assign hw_base_vector to the value given earlier. + */ + if (test_bit(ICE_VF_STATE_CFG_INTR, pf->vf[vf_id].vf_states)) { + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto unroll_vector_base; + } else { + vsi->hw_base_vector = pf->vf[vf_id].first_vector_idx; + } + pf->q_left_tx -= vsi->alloc_txq; + pf->q_left_rx -= vsi->alloc_rxq; + break; + default: + /* if VSI type is not recognized, clean up the resources and + * exit + */ + goto unroll_vsi_init; + } + + ice_vsi_set_tc_cfg(vsi); + + /* configure VSI nodes based on number of queues and TC's */ + for (i = 0; i < vsi->tc_cfg.numtc; i++) + max_txqs[i] = vsi->num_txq; + + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n"); + goto unroll_vector_base; + } + + return vsi; + +unroll_vector_base: + /* reclaim SW interrupts back to the common pool */ + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + /* reclaim HW interrupt back to the common pool */ + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); + pf->num_avail_hw_msix += vsi->num_q_vectors; +unroll_alloc_q_vector: + ice_vsi_free_q_vectors(vsi); +unroll_vsi_init: + ice_vsi_delete(vsi); +unroll_get_qs: + ice_vsi_put_qs(vsi); + pf->q_left_tx += vsi->alloc_txq; + pf->q_left_rx += vsi->alloc_rxq; + ice_vsi_clear(vsi); + + return NULL; +} + +/** + * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW + * @vsi: the VSI being cleaned up + */ +static void ice_vsi_release_msix(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + u16 vector = vsi->hw_base_vector; + struct ice_hw *hw = &pf->hw; + u32 txq = 0; + u32 rxq = 0; + int i, q; + + for (i = 0; i < vsi->num_q_vectors; i++, vector++) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + wr32(hw, GLINT_ITR(ICE_IDX_ITR0, vector), 0); + wr32(hw, GLINT_ITR(ICE_IDX_ITR1, vector), 0); + for (q = 0; q < q_vector->num_ring_tx; q++) { + wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); + txq++; + } + + for (q = 0; q < q_vector->num_ring_rx; q++) { + wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0); + rxq++; + } + } + + ice_flush(hw); +} + +/** + * ice_vsi_free_irq - Free the IRQ association with the OS + * @vsi: the VSI being configured + */ +void ice_vsi_free_irq(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int base = vsi->sw_base_vector; + + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + int i; + + if (!vsi->q_vectors || !vsi->irqs_ready) + return; + + ice_vsi_release_msix(vsi); + if (vsi->type == ICE_VSI_VF) + return; + + vsi->irqs_ready = false; + for (i = 0; i < vsi->num_q_vectors; i++) { + u16 vector = i + base; + int irq_num; + + irq_num = pf->msix_entries[vector].vector; + + /* free only the irqs that were actually requested */ + if (!vsi->q_vectors[i] || + !(vsi->q_vectors[i]->num_ring_tx || + vsi->q_vectors[i]->num_ring_rx)) + continue; + + /* clear the affinity notifier in the IRQ descriptor */ + irq_set_affinity_notifier(irq_num, NULL); + + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(irq_num, NULL); + synchronize_irq(irq_num); + devm_free_irq(&pf->pdev->dev, irq_num, + vsi->q_vectors[i]); + } + } +} + +/** + * ice_vsi_free_tx_rings - Free Tx resources for VSI queues + * @vsi: the VSI having resources freed + */ +void ice_vsi_free_tx_rings(struct ice_vsi *vsi) +{ + int i; + + if (!vsi->tx_rings) + return; + + ice_for_each_txq(vsi, i) + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) + ice_free_tx_ring(vsi->tx_rings[i]); +} + +/** + * ice_vsi_free_rx_rings - Free Rx resources for VSI queues + * @vsi: the VSI having resources freed + */ +void ice_vsi_free_rx_rings(struct ice_vsi *vsi) +{ + int i; + + if (!vsi->rx_rings) + return; + + ice_for_each_rxq(vsi, i) + if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc) + ice_free_rx_ring(vsi->rx_rings[i]); +} + +/** + * ice_vsi_close - Shut down a VSI + * @vsi: the VSI being shut down + */ +void ice_vsi_close(struct ice_vsi *vsi) +{ + if (!test_and_set_bit(__ICE_DOWN, vsi->state)) + ice_down(vsi); + + ice_vsi_free_irq(vsi); + ice_vsi_free_tx_rings(vsi); + ice_vsi_free_rx_rings(vsi); +} + +/** + * ice_free_res - free a block of resources + * @res: pointer to the resource + * @index: starting index previously returned by ice_get_res + * @id: identifier to track owner + * + * Returns number of resources freed + */ +int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) +{ + int count = 0; + int i; + + if (!res || index >= res->num_entries) + return -EINVAL; + + id |= ICE_RES_VALID_BIT; + for (i = index; i < res->num_entries && res->list[i] == id; i++) { + res->list[i] = 0; + count++; + } + + return count; +} + +/** + * ice_search_res - Search the tracker for a block of resources + * @res: pointer to the resource + * @needed: size of the block needed + * @id: identifier to track owner + * + * Returns the base item index of the block, or -ENOMEM for error + */ +static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) +{ + int start = res->search_hint; + int end = start; + + if ((start + needed) > res->num_entries) + return -ENOMEM; + + id |= ICE_RES_VALID_BIT; + + do { + /* skip already allocated entries */ + if (res->list[end++] & ICE_RES_VALID_BIT) { + start = end; + if ((start + needed) > res->num_entries) + break; + } + + if (end == (start + needed)) { + int i = start; + + /* there was enough, so assign it to the requestor */ + while (i != end) + res->list[i++] = id; + + if (end == res->num_entries) + end = 0; + + res->search_hint = end; + return start; + } + } while (1); + + return -ENOMEM; +} + +/** + * ice_get_res - get a block of resources + * @pf: board private structure + * @res: pointer to the resource + * @needed: size of the block needed + * @id: identifier to track owner + * + * Returns the base item index of the block, or -ENOMEM for error + * The search_hint trick and lack of advanced fit-finding only works + * because we're highly likely to have all the same sized requests. + * Linear search time and any fragmentation should be minimal. + */ +int +ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) +{ + int ret; + + if (!res || !pf) + return -EINVAL; + + if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { + dev_err(&pf->pdev->dev, + "param err: needed=%d, num_entries = %d id=0x%04x\n", + needed, res->num_entries, id); + return -EINVAL; + } + + /* search based on search_hint */ + ret = ice_search_res(res, needed, id); + + if (ret < 0) { + /* previous search failed. Reset search hint and try again */ + res->search_hint = 0; + ret = ice_search_res(res, needed, id); + } + + return ret; +} + +/** + * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI + * @vsi: the VSI being un-configured + */ +void ice_vsi_dis_irq(struct ice_vsi *vsi) +{ + int base = vsi->sw_base_vector; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u32 val; + int i; + + /* disable interrupt causation from each queue */ + if (vsi->tx_rings) { + ice_for_each_txq(vsi, i) { + if (vsi->tx_rings[i]) { + u16 reg; + + reg = vsi->tx_rings[i]->reg_idx; + val = rd32(hw, QINT_TQCTL(reg)); + val &= ~QINT_TQCTL_CAUSE_ENA_M; + wr32(hw, QINT_TQCTL(reg), val); + } + } + } + + if (vsi->rx_rings) { + ice_for_each_rxq(vsi, i) { + if (vsi->rx_rings[i]) { + u16 reg; + + reg = vsi->rx_rings[i]->reg_idx; + val = rd32(hw, QINT_RQCTL(reg)); + val &= ~QINT_RQCTL_CAUSE_ENA_M; + wr32(hw, QINT_RQCTL(reg), val); + } + } + } + + /* disable each interrupt */ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + for (i = vsi->hw_base_vector; + i < (vsi->num_q_vectors + vsi->hw_base_vector); i++) + wr32(hw, GLINT_DYN_CTL(i), 0); + + ice_flush(hw); + for (i = 0; i < vsi->num_q_vectors; i++) + synchronize_irq(pf->msix_entries[i + base].vector); + } +} + +/** + * ice_vsi_release - Delete a VSI and free its resources + * @vsi: the VSI being removed + * + * Returns 0 on success or < 0 on error + */ +int ice_vsi_release(struct ice_vsi *vsi) +{ + struct ice_pf *pf; + struct ice_vf *vf; + + if (!vsi->back) + return -ENODEV; + pf = vsi->back; + vf = &pf->vf[vsi->vf_id]; + /* do not unregister and free netdevs while driver is in the reset + * recovery pending state. Since reset/rebuild happens through PF + * service task workqueue, its not a good idea to unregister netdev + * that is associated to the PF that is running the work queue items + * currently. This is done to avoid check_flush_dependency() warning + * on this wq + */ + if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + unregister_netdev(vsi->netdev); + free_netdev(vsi->netdev); + vsi->netdev = NULL; + } + + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_rss_clean(vsi); + + /* Disable VSI and free resources */ + ice_vsi_dis_irq(vsi); + ice_vsi_close(vsi); + + /* reclaim interrupt vectors back to PF */ + if (vsi->type != ICE_VSI_VF) { + /* reclaim SW interrupts back to the common pool */ + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, + vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + /* reclaim HW interrupts back to the common pool */ + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, + vsi->idx); + pf->num_avail_hw_msix += vsi->num_q_vectors; + } else if (test_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states)) { + /* Reclaim VF resources back only while freeing all VFs or + * vector reassignment is requested + */ + ice_free_res(vsi->back->hw_irq_tracker, vf->first_vector_idx, + vsi->idx); + pf->num_avail_hw_msix += pf->num_vf_msix; + } + + ice_remove_vsi_fltr(&pf->hw, vsi->idx); + ice_vsi_delete(vsi); + ice_vsi_free_q_vectors(vsi); + ice_vsi_clear_rings(vsi); + + ice_vsi_put_qs(vsi); + pf->q_left_tx += vsi->alloc_txq; + pf->q_left_rx += vsi->alloc_rxq; + + /* retain SW VSI data structure since it is needed to unregister and + * free VSI netdev when PF is not in reset recovery pending state,\ + * for ex: during rmmod. + */ + if (!ice_is_reset_in_progress(pf->state)) + ice_vsi_clear(vsi); + + return 0; +} + +/** + * ice_vsi_rebuild - Rebuild VSI after reset + * @vsi: VSI to be rebuild + * + * Returns 0 on success and negative value on failure + */ +int ice_vsi_rebuild(struct ice_vsi *vsi) +{ + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + int ret, i; + + if (!vsi) + return -EINVAL; + + ice_vsi_free_q_vectors(vsi); + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); + vsi->sw_base_vector = 0; + vsi->hw_base_vector = 0; + ice_vsi_clear_rings(vsi); + ice_vsi_free_arrays(vsi, false); + ice_vsi_set_num_qs(vsi); + + /* Initialize VSI struct elements and create VSI in FW */ + ret = ice_vsi_init(vsi); + if (ret < 0) + goto err_vsi; + + ret = ice_vsi_alloc_arrays(vsi, false); + if (ret < 0) + goto err_vsi; + + switch (vsi->type) { + case ICE_VSI_PF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto err_rings; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto err_vectors; + + ice_vsi_map_rings_to_vectors(vsi); + break; + case ICE_VSI_VF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto err_rings; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto err_vectors; + + vsi->back->q_left_tx -= vsi->alloc_txq; + vsi->back->q_left_rx -= vsi->alloc_rxq; + break; + default: + break; + } + + ice_vsi_set_tc_cfg(vsi); + + /* configure VSI nodes based on number of queues and TC's */ + for (i = 0; i < vsi->tc_cfg.numtc; i++) + max_txqs[i] = vsi->num_txq; + + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed VSI lan queue config\n"); + goto err_vectors; + } + return 0; + +err_vectors: + ice_vsi_free_q_vectors(vsi); +err_rings: + if (vsi->netdev) { + vsi->current_netdev_flags = 0; + unregister_netdev(vsi->netdev); + free_netdev(vsi->netdev); + vsi->netdev = NULL; + } +err_vsi: + ice_vsi_clear(vsi); + set_bit(__ICE_RESET_FAILED, vsi->back->state); + return ret; +} + +/** + * ice_is_reset_in_progress - check for a reset in progress + * @state: pf state field + */ +bool ice_is_reset_in_progress(unsigned long *state) +{ + return test_bit(__ICE_RESET_OICR_RECV, state) || + test_bit(__ICE_PFR_REQ, state) || + test_bit(__ICE_CORER_REQ, state) || + test_bit(__ICE_GLOBR_REQ, state); +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h new file mode 100644 index 000000000000..677db40338f5 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_LIB_H_ +#define _ICE_LIB_H_ + +#include "ice.h" + +int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr); + +void ice_free_fltr_list(struct device *dev, struct list_head *h); + +void ice_update_eth_stats(struct ice_vsi *vsi); + +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); + +int ice_vsi_cfg_txqs(struct ice_vsi *vsi); + +void ice_vsi_cfg_msix(struct ice_vsi *vsi); + +int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid); + +int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid); + +int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi); + +int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena); + +int ice_vsi_start_rx_rings(struct ice_vsi *vsi); + +int ice_vsi_stop_rx_rings(struct ice_vsi *vsi); + +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num); + +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); + +void ice_vsi_delete(struct ice_vsi *vsi); + +int ice_vsi_clear(struct ice_vsi *vsi); + +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 vf_id); + +int ice_vsi_release(struct ice_vsi *vsi); + +void ice_vsi_close(struct ice_vsi *vsi); + +int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); + +int +ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); + +int ice_vsi_rebuild(struct ice_vsi *vsi); + +bool ice_is_reset_in_progress(unsigned long *state); + +void ice_vsi_free_q_vectors(struct ice_vsi *vsi); + +void ice_vsi_put_qs(struct ice_vsi *vsi); + +void ice_vsi_dis_irq(struct ice_vsi *vsi); + +void ice_vsi_free_irq(struct ice_vsi *vsi); + +void ice_vsi_free_rx_rings(struct ice_vsi *vsi); + +void ice_vsi_free_tx_rings(struct ice_vsi *vsi); + +int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); + +int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); + +irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data); +#endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4f5fe6af6dac..8f61b375e768 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6,8 +6,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "ice.h" +#include "ice_lib.h" -#define DRV_VERSION "0.7.1-k" +#define DRV_VERSION "0.7.2-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY; @@ -31,7 +32,7 @@ static const struct net_device_ops ice_netdev_ops; static void ice_pf_dis_all_vsi(struct ice_pf *pf); static void ice_rebuild(struct ice_pf *pf); -static int ice_vsi_release(struct ice_vsi *vsi); + static void ice_vsi_release_all(struct ice_pf *pf); static void ice_update_vsi_stats(struct ice_vsi *vsi); static void ice_update_pf_stats(struct ice_pf *pf); @@ -94,7 +95,7 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) /* Trigger sw interrupt to revive the queue */ v_idx = tx_ring->q_vector->v_idx; wr32(&vsi->back->hw, - GLINT_DYN_CTL(vsi->base_vector + v_idx), + GLINT_DYN_CTL(vsi->hw_base_vector + v_idx), (itr << GLINT_DYN_CTL_ITR_INDX_S) | GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); @@ -112,171 +113,6 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) } /** - * ice_get_free_slot - get the next non-NULL location index in array - * @array: array to search - * @size: size of the array - * @curr: last known occupied index to be used as a search hint - * - * void * is being used to keep the functionality generic. This lets us use this - * function on any array of pointers. - */ -static int ice_get_free_slot(void *array, int size, int curr) -{ - int **tmp_array = (int **)array; - int next; - - if (curr < (size - 1) && !tmp_array[curr + 1]) { - next = curr + 1; - } else { - int i = 0; - - while ((i < size) && (tmp_array[i])) - i++; - if (i == size) - next = ICE_NO_VSI; - else - next = i; - } - return next; -} - -/** - * ice_search_res - Search the tracker for a block of resources - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * Returns the base item index of the block, or -ENOMEM for error - */ -static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) -{ - int start = res->search_hint; - int end = start; - - id |= ICE_RES_VALID_BIT; - - do { - /* skip already allocated entries */ - if (res->list[end++] & ICE_RES_VALID_BIT) { - start = end; - if ((start + needed) > res->num_entries) - break; - } - - if (end == (start + needed)) { - int i = start; - - /* there was enough, so assign it to the requestor */ - while (i != end) - res->list[i++] = id; - - if (end == res->num_entries) - end = 0; - - res->search_hint = end; - return start; - } - } while (1); - - return -ENOMEM; -} - -/** - * ice_get_res - get a block of resources - * @pf: board private structure - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or -ENOMEM for error - * The search_hint trick and lack of advanced fit-finding only works - * because we're highly likely to have all the same sized requests. - * Linear search time and any fragmentation should be minimal. - */ -static int -ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) -{ - int ret; - - if (!res || !pf) - return -EINVAL; - - if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { - dev_err(&pf->pdev->dev, - "param err: needed=%d, num_entries = %d id=0x%04x\n", - needed, res->num_entries, id); - return -EINVAL; - } - - /* search based on search_hint */ - ret = ice_search_res(res, needed, id); - - if (ret < 0) { - /* previous search failed. Reset search hint and try again */ - res->search_hint = 0; - ret = ice_search_res(res, needed, id); - } - - return ret; -} - -/** - * ice_free_res - free a block of resources - * @res: pointer to the resource - * @index: starting index previously returned by ice_get_res - * @id: identifier to track owner - * Returns number of resources freed - */ -static int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) -{ - int count = 0; - int i; - - if (!res || index >= res->num_entries) - return -EINVAL; - - id |= ICE_RES_VALID_BIT; - for (i = index; i < res->num_entries && res->list[i] == id; i++) { - res->list[i] = 0; - count++; - } - - return count; -} - -/** - * ice_add_mac_to_list - Add a mac address filter entry to the list - * @vsi: the VSI to be forwarded to - * @add_list: pointer to the list which contains MAC filter entries - * @macaddr: the MAC address to be added. - * - * Adds mac address filter entry to the temp list - * - * Returns 0 on success or ENOMEM on failure. - */ -static int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, - const u8 *macaddr) -{ - struct ice_fltr_list_entry *tmp; - struct ice_pf *pf = vsi->back; - - tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - - tmp->fltr_info.flag = ICE_FLTR_TX; - tmp->fltr_info.src = vsi->vsi_num; - tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC; - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr); - - INIT_LIST_HEAD(&tmp->list_entry); - list_add(&tmp->list_entry, add_list); - - return 0; -} - -/** * ice_add_mac_to_sync_list - creates list of mac addresses to be synced * @netdev: the net device on which the sync is happening * @addr: mac address to sync @@ -319,24 +155,6 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) } /** - * ice_free_fltr_list - free filter lists helper - * @dev: pointer to the device struct - * @h: pointer to the list head to be freed - * - * Helper function to free filter lists previously created using - * ice_add_mac_to_list - */ -static void ice_free_fltr_list(struct device *dev, struct list_head *h) -{ - struct ice_fltr_list_entry *e, *tmp; - - list_for_each_entry_safe(e, tmp, h, list_entry) { - list_del(&e->list_entry); - devm_kfree(dev, e); - } -} - -/** * ice_vsi_fltr_changed - check if filter state changed * @vsi: VSI to be checked * @@ -350,63 +168,6 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) } /** - * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI - * @vsi: VSI to enable or disable VLAN pruning on - * @ena: set to true to enable VLAN pruning and false to disable it - * - * returns 0 if VSI is updated, negative otherwise - */ -static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) -{ - struct ice_vsi_ctx *ctxt; - struct device *dev; - int status; - - if (!vsi) - return -EINVAL; - - dev = &vsi->back->pdev->dev; - ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - ctxt->info = vsi->info; - - if (ena) { - ctxt->info.sec_flags |= - ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; - ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } else { - ctxt->info.sec_flags &= - ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); - ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID | - ICE_AQ_VSI_PROP_SW_VALID); - ctxt->vsi_num = vsi->vsi_num; - status = ice_aq_update_vsi(&vsi->back->hw, ctxt, NULL); - if (status) { - netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI %d failed, err = %d, aq_err = %d\n", - ena ? "Ena" : "Dis", vsi->vsi_num, status, - vsi->back->hw.adminq.sq_last_status); - goto err_out; - } - - vsi->info.sec_flags = ctxt->info.sec_flags; - vsi->info.sw_flags2 = ctxt->info.sw_flags2; - - devm_kfree(dev, ctxt); - return 0; - -err_out: - devm_kfree(dev, ctxt); - return -EIO; -} - -/** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -492,7 +253,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags); if (vsi->current_netdev_flags & IFF_PROMISC) { /* Apply TX filter rule to get traffic from VMs */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true, + status = ice_cfg_dflt_vsi(hw, vsi->idx, true, ICE_FLTR_TX); if (status) { netdev_err(netdev, "Error setting default VSI %i tx rule\n", @@ -502,7 +263,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto out_promisc; } /* Apply RX filter rule to get traffic from wire */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true, + status = ice_cfg_dflt_vsi(hw, vsi->idx, true, ICE_FLTR_RX); if (status) { netdev_err(netdev, "Error setting default VSI %i rx rule\n", @@ -513,7 +274,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } } else { /* Clear TX filter rule to stop traffic from VMs */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false, + status = ice_cfg_dflt_vsi(hw, vsi->idx, false, ICE_FLTR_TX); if (status) { netdev_err(netdev, "Error clearing default VSI %i tx rule\n", @@ -522,8 +283,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) err = -EIO; goto out_promisc; } - /* Clear filter RX to remove traffic from wire */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false, + /* Clear RX filter to remove traffic from wire */ + status = ice_cfg_dflt_vsi(hw, vsi->idx, false, ICE_FLTR_RX); if (status) { netdev_err(netdev, "Error clearing default VSI %i rx rule\n", @@ -571,15 +332,6 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf) } /** - * ice_is_reset_recovery_pending - schedule a reset - * @state: pf state field - */ -static bool ice_is_reset_recovery_pending(unsigned long int *state) -{ - return test_bit(__ICE_RESET_RECOVERY_PENDING, state); -} - -/** * ice_prepare_for_reset - prep for the core to reset * @pf: board private structure * @@ -590,6 +342,10 @@ ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; + /* Notify VFs of impending reset */ + if (ice_check_sq_alive(hw, &hw->mailboxq)) + ice_vc_notify_reset(pf); + /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf); @@ -612,21 +368,17 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); WARN_ON(in_interrupt()); - /* PFR is a bit of a special case because it doesn't result in an OICR - * interrupt. Set pending bit here which otherwise gets set in the - * OICR handler. - */ - if (reset_type == ICE_RESET_PFR) - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - ice_prepare_for_reset(pf); /* trigger the reset */ if (ice_reset(hw, reset_type)) { dev_err(dev, "reset %d failed\n", reset_type); set_bit(__ICE_RESET_FAILED, pf->state); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_RESET_OICR_RECV, pf->state); clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); + clear_bit(__ICE_CORER_REQ, pf->state); + clear_bit(__ICE_GLOBR_REQ, pf->state); return; } @@ -637,8 +389,8 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; ice_rebuild(pf); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); } } @@ -653,14 +405,14 @@ static void ice_reset_subtask(struct ice_pf *pf) /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an * OICR interrupt. The OICR handler (ice_misc_intr) determines what type * of reset is pending and sets bits in pf->state indicating the reset - * type and __ICE_RESET_RECOVERY_PENDING. So, if the latter bit is set + * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set * prepare for pending reset if not already (for PF software-initiated * global resets the software should already be prepared for it as * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated * by firmware or software on other PFs, that bit is not set so prepare * for the reset now), poll for reset done, rebuild and return. */ - if (ice_is_reset_recovery_pending(pf->state)) { + if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) { clear_bit(__ICE_GLOBR_RECV, pf->state); clear_bit(__ICE_CORER_RECV, pf->state); if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) @@ -676,19 +428,22 @@ static void ice_reset_subtask(struct ice_pf *pf) /* clear bit to resume normal operations, but * ICE_NEEDS_RESTART bit is set incase rebuild failed */ - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_RESET_OICR_RECV, pf->state); clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); + clear_bit(__ICE_CORER_REQ, pf->state); + clear_bit(__ICE_GLOBR_REQ, pf->state); } return; } /* No pending resets to finish processing. Check for new resets */ - if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) + if (test_bit(__ICE_PFR_REQ, pf->state)) reset_type = ICE_RESET_PFR; - if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) + if (test_bit(__ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; - if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state)) + if (test_bit(__ICE_GLOBR_REQ, pf->state)) reset_type = ICE_RESET_GLOBR; /* If no valid reset type requested just return */ if (reset_type == ICE_RESET_INVAL) @@ -910,6 +665,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi) } } + ice_vc_notify_link_state(pf); + return 0; } @@ -960,6 +717,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) cq = &hw->adminq; qtype = "Admin"; break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + qtype = "Mailbox"; + break; default: dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n", q_type); @@ -1041,6 +802,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) dev_err(&pf->pdev->dev, "Could not handle link event\n"); break; + case ice_mbx_opc_send_msg_to_pf: + ice_vc_process_vf_msg(pf, &event); + break; case ice_aqc_opc_fw_logging: ice_output_fw_log(hw, &event.desc, event.msg_buf); break; @@ -1100,6 +864,28 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) } /** + * ice_clean_mailboxq_subtask - clean the MailboxQ rings + * @pf: board private structure + */ +static void ice_clean_mailboxq_subtask(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state)) + return; + + if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX)) + return; + + clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); + + if (ice_ctrlq_pending(hw, &hw->mailboxq)) + __ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX); + + ice_flush(hw); +} + +/** * ice_service_task_schedule - schedule the service task to wake up * @pf: board private structure * @@ -1165,6 +951,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; bool mdd_detected = false; u32 reg; + int i; if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state)) return; @@ -1254,6 +1041,51 @@ static void ice_handle_mdd_event(struct ice_pf *pf) } } + /* see if one of the VFs needs to be reset */ + for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + struct ice_vf *vf = &pf->vf[i]; + + reg = rd32(hw, VP_MDET_TX_PQM(i)); + if (reg & VP_MDET_TX_PQM_VALID_M) { + wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TCLAN(i)); + if (reg & VP_MDET_TX_TCLAN_VALID_M) { + wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TDPU(i)); + if (reg & VP_MDET_TX_TDPU_VALID_M) { + wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_RX(i)); + if (reg & VP_MDET_RX_VALID_M) { + wr32(hw, VP_MDET_RX(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", + i); + } + + if (vf->num_mdd_events > ICE_DFLT_NUM_MDD_EVENTS_ALLOWED) { + dev_info(&pf->pdev->dev, + "Too many MDD events on VF %d, disabled\n", i); + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + } + } + /* re-enable MDD interrupt cause */ clear_bit(__ICE_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, PFINT_OICR_ENA); @@ -1277,7 +1109,7 @@ static void ice_service_task(struct work_struct *work) ice_reset_subtask(pf); /* bail if a reset/recovery cycle is pending or rebuild failed */ - if (ice_is_reset_recovery_pending(pf->state) || + if (ice_is_reset_in_progress(pf->state) || test_bit(__ICE_SUSPENDED, pf->state) || test_bit(__ICE_NEEDS_RESTART, pf->state)) { ice_service_task_complete(pf); @@ -1287,8 +1119,10 @@ static void ice_service_task(struct work_struct *work) ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); ice_handle_mdd_event(pf); + ice_process_vflr_event(pf); ice_watchdog_subtask(pf); ice_clean_adminq_subtask(pf); + ice_clean_mailboxq_subtask(pf); /* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */ ice_service_task_complete(pf); @@ -1299,6 +1133,8 @@ static void ice_service_task(struct work_struct *work) */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || + test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) || test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -1313,6 +1149,10 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) hw->adminq.num_sq_entries = ICE_AQ_LEN; hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN; hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN; + hw->mailboxq.num_rq_entries = ICE_MBXQ_LEN; + hw->mailboxq.num_sq_entries = ICE_MBXQ_LEN; + hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN; + hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN; } /** @@ -1343,57 +1183,6 @@ static void ice_irq_affinity_notify(struct irq_affinity_notify *notify, static void ice_irq_affinity_release(struct kref __always_unused *ref) {} /** - * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI - * @vsi: the VSI being un-configured - */ -static void ice_vsi_dis_irq(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int base = vsi->base_vector; - u32 val; - int i; - - /* disable interrupt causation from each queue */ - if (vsi->tx_rings) { - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i]) { - u16 reg; - - reg = vsi->tx_rings[i]->reg_idx; - val = rd32(hw, QINT_TQCTL(reg)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(reg), val); - } - } - } - - if (vsi->rx_rings) { - ice_for_each_rxq(vsi, i) { - if (vsi->rx_rings[i]) { - u16 reg; - - reg = vsi->rx_rings[i]->reg_idx; - val = rd32(hw, QINT_RQCTL(reg)); - val &= ~QINT_RQCTL_CAUSE_ENA_M; - wr32(hw, QINT_RQCTL(reg), val); - } - } - } - - /* disable each interrupt */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - for (i = vsi->base_vector; - i < (vsi->num_q_vectors + vsi->base_vector); i++) - wr32(hw, GLINT_DYN_CTL(i), 0); - - ice_flush(hw); - for (i = 0; i < vsi->num_q_vectors; i++) - synchronize_irq(pf->msix_entries[i + base].vector); - } -} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -1414,26 +1203,6 @@ static int ice_vsi_ena_irq(struct ice_vsi *vsi) } /** - * ice_vsi_delete - delete a VSI from the switch - * @vsi: pointer to VSI being removed - */ -static void ice_vsi_delete(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_vsi_ctx ctxt; - enum ice_status status; - - ctxt.vsi_num = vsi->vsi_num; - - memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); - - status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL); - if (status) - dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", - vsi->vsi_num); -} - -/** * ice_vsi_req_irq_msix - get MSI-X vectors from the OS for the VSI * @vsi: the VSI being configured * @basename: name for the vector @@ -1442,7 +1211,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) { int q_vectors = vsi->num_q_vectors; struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; + int base = vsi->sw_base_vector; int rx_int_idx = 0; int tx_int_idx = 0; int vector, err; @@ -1501,471 +1270,6 @@ free_q_irqs: } /** - * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type - * @vsi: the VSI being configured - */ -static void ice_vsi_set_rss_params(struct ice_vsi *vsi) -{ - struct ice_hw_common_caps *cap; - struct ice_pf *pf = vsi->back; - - if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - vsi->rss_size = 1; - return; - } - - cap = &pf->hw.func_caps.common_cap; - switch (vsi->type) { - case ICE_VSI_PF: - /* PF VSI will inherit RSS instance of PF */ - vsi->rss_table_size = cap->rss_table_size; - vsi->rss_size = min_t(int, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; - break; - default: - dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); - break; - } -} - -/** - * ice_vsi_setup_q_map - Setup a VSI queue map - * @vsi: the VSI being configured - * @ctxt: VSI context structure - */ -static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) -{ - u16 offset = 0, qmap = 0, numq_tc; - u16 pow = 0, max_rss = 0, qcount; - u16 qcount_tx = vsi->alloc_txq; - u16 qcount_rx = vsi->alloc_rxq; - bool ena_tc0 = false; - int i; - - /* at least TC0 should be enabled by default */ - if (vsi->tc_cfg.numtc) { - if (!(vsi->tc_cfg.ena_tc & BIT(0))) - ena_tc0 = true; - } else { - ena_tc0 = true; - } - - if (ena_tc0) { - vsi->tc_cfg.numtc++; - vsi->tc_cfg.ena_tc |= 1; - } - - numq_tc = qcount_rx / vsi->tc_cfg.numtc; - - /* TC mapping is a function of the number of Rx queues assigned to the - * VSI for each traffic class and the offset of these queues. - * The first 10 bits are for queue offset for TC0, next 4 bits for no:of - * queues allocated to TC0. No:of queues is a power-of-2. - * - * If TC is not enabled, the queue offset is set to 0, and allocate one - * queue, this way, traffic for the given TC will be sent to the default - * queue. - * - * Setup number and offset of Rx queues for all TCs for the VSI - */ - - /* qcount will change if RSS is enabled */ - if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { - if (vsi->type == ICE_VSI_PF) - max_rss = ICE_MAX_LG_RSS_QS; - else - max_rss = ICE_MAX_SMALL_RSS_QS; - - qcount = min_t(int, numq_tc, max_rss); - qcount = min_t(int, qcount, vsi->rss_size); - } else { - qcount = numq_tc; - } - - /* find the (rounded up) power-of-2 of qcount */ - pow = order_base_2(qcount); - - for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { - if (!(vsi->tc_cfg.ena_tc & BIT(i))) { - /* TC is not enabled */ - vsi->tc_cfg.tc_info[i].qoffset = 0; - vsi->tc_cfg.tc_info[i].qcount = 1; - ctxt->info.tc_mapping[i] = 0; - continue; - } - - /* TC is enabled */ - vsi->tc_cfg.tc_info[i].qoffset = offset; - vsi->tc_cfg.tc_info[i].qcount = qcount; - - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); - offset += qcount; - ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); - } - - vsi->num_txq = qcount_tx; - vsi->num_rxq = offset; - - /* Rx queue mapping */ - ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); - /* q_mapping buffer holds the info for the first queue allocated for - * this VSI in the PF space and also the number of queues associated - * with this VSI. - */ - ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); - ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq); -} - -/** - * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI - * @ctxt: the VSI context being set - * - * This initializes a default VSI context for all sections except the Queues. - */ -static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) -{ - u32 table = 0; - - memset(&ctxt->info, 0, sizeof(ctxt->info)); - /* VSI's should be allocated from shared pool */ - ctxt->alloc_from_pool = true; - /* Src pruning enabled by default */ - ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; - /* Traffic from VSI can be sent to LAN */ - ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; - - /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy - * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all - * packets untagged/tagged. - */ - ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & - ICE_AQ_VSI_VLAN_MODE_M) >> - ICE_AQ_VSI_VLAN_MODE_S); - - /* Have 1:1 UP mapping for both ingress/egress tables */ - table |= ICE_UP_TABLE_TRANSLATE(0, 0); - table |= ICE_UP_TABLE_TRANSLATE(1, 1); - table |= ICE_UP_TABLE_TRANSLATE(2, 2); - table |= ICE_UP_TABLE_TRANSLATE(3, 3); - table |= ICE_UP_TABLE_TRANSLATE(4, 4); - table |= ICE_UP_TABLE_TRANSLATE(5, 5); - table |= ICE_UP_TABLE_TRANSLATE(6, 6); - table |= ICE_UP_TABLE_TRANSLATE(7, 7); - ctxt->info.ingress_table = cpu_to_le32(table); - ctxt->info.egress_table = cpu_to_le32(table); - /* Have 1:1 UP mapping for outer to inner UP table */ - ctxt->info.outer_up_table = cpu_to_le32(table); - /* No Outer tag support outer_tag_flags remains to zero */ -} - -/** - * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI - * @ctxt: the VSI context being set - * @vsi: the VSI being configured - */ -static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) -{ - u8 lut_type, hash_type; - - switch (vsi->type) { - case ICE_VSI_PF: - /* PF VSI will inherit RSS instance of PF */ - lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - return; - } - - ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); -} - -/** - * ice_vsi_init - Create and initialize a VSI - * @vsi: the VSI being configured - * - * This initializes a VSI context depending on the VSI type to be added and - * passes it down to the add_vsi aq command to create a new VSI. - */ -static int ice_vsi_init(struct ice_vsi *vsi) -{ - struct ice_vsi_ctx ctxt = { 0 }; - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int ret = 0; - - switch (vsi->type) { - case ICE_VSI_PF: - ctxt.flags = ICE_AQ_VSI_TYPE_PF; - break; - default: - return -ENODEV; - } - - ice_set_dflt_vsi_ctx(&ctxt); - /* if the switch is in VEB mode, allow VSI loopback */ - if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB) - ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; - - /* Set LUT type and HASH type if RSS is enabled */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_set_rss_vsi_ctx(&ctxt, vsi); - - ctxt.info.sw_id = vsi->port_info->sw_id; - ice_vsi_setup_q_map(vsi, &ctxt); - - ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL); - if (ret) { - dev_err(&pf->pdev->dev, - "Add VSI failed, err %d\n", ret); - return -EIO; - } - - /* keep context for update VSI operations */ - vsi->info = ctxt.info; - - /* record VSI number returned */ - vsi->vsi_num = ctxt.vsi_num; - - return ret; -} - -/** - * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW - * @vsi: the VSI being cleaned up - */ -static void ice_vsi_release_msix(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - u16 vector = vsi->base_vector; - struct ice_hw *hw = &pf->hw; - u32 txq = 0; - u32 rxq = 0; - int i, q; - - for (i = 0; i < vsi->num_q_vectors; i++, vector++) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), 0); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), 0); - for (q = 0; q < q_vector->num_ring_tx; q++) { - wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - txq++; - } - - for (q = 0; q < q_vector->num_ring_rx; q++) { - wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0); - rxq++; - } - } - - ice_flush(hw); -} - -/** - * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI - * @vsi: the VSI having rings deallocated - */ -static void ice_vsi_clear_rings(struct ice_vsi *vsi) -{ - int i; - - if (vsi->tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) { - if (vsi->tx_rings[i]) { - kfree_rcu(vsi->tx_rings[i], rcu); - vsi->tx_rings[i] = NULL; - } - } - } - if (vsi->rx_rings) { - for (i = 0; i < vsi->alloc_rxq; i++) { - if (vsi->rx_rings[i]) { - kfree_rcu(vsi->rx_rings[i], rcu); - vsi->rx_rings[i] = NULL; - } - } - } -} - -/** - * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI - * @vsi: VSI which is having rings allocated - */ -static int ice_vsi_alloc_rings(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int i; - - /* Allocate tx_rings */ - for (i = 0; i < vsi->alloc_txq; i++) { - struct ice_ring *ring; - - /* allocate with kzalloc(), free with kfree_rcu() */ - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - - if (!ring) - goto err_out; - - ring->q_index = i; - ring->reg_idx = vsi->txq_map[i]; - ring->ring_active = false; - ring->vsi = vsi; - ring->netdev = vsi->netdev; - ring->dev = &pf->pdev->dev; - ring->count = vsi->num_desc; - - vsi->tx_rings[i] = ring; - } - - /* Allocate rx_rings */ - for (i = 0; i < vsi->alloc_rxq; i++) { - struct ice_ring *ring; - - /* allocate with kzalloc(), free with kfree_rcu() */ - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_out; - - ring->q_index = i; - ring->reg_idx = vsi->rxq_map[i]; - ring->ring_active = false; - ring->vsi = vsi; - ring->netdev = vsi->netdev; - ring->dev = &pf->pdev->dev; - ring->count = vsi->num_desc; - vsi->rx_rings[i] = ring; - } - - return 0; - -err_out: - ice_vsi_clear_rings(vsi); - return -ENOMEM; -} - -/** - * ice_vsi_free_irq - Free the irq association with the OS - * @vsi: the VSI being configured - */ -static void ice_vsi_free_irq(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; - - if (!vsi->q_vectors || !vsi->irqs_ready) - return; - - vsi->irqs_ready = false; - for (i = 0; i < vsi->num_q_vectors; i++) { - u16 vector = i + base; - int irq_num; - - irq_num = pf->msix_entries[vector].vector; - - /* free only the irqs that were actually requested */ - if (!vsi->q_vectors[i] || - !(vsi->q_vectors[i]->num_ring_tx || - vsi->q_vectors[i]->num_ring_rx)) - continue; - - /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); - synchronize_irq(irq_num); - devm_free_irq(&pf->pdev->dev, irq_num, - vsi->q_vectors[i]); - } - ice_vsi_release_msix(vsi); - } -} - -/** - * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW - * @vsi: the VSI being configured - */ -static void ice_vsi_cfg_msix(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - u16 vector = vsi->base_vector; - struct ice_hw *hw = &pf->hw; - u32 txq = 0, rxq = 0; - int i, q, itr; - u8 itr_gran; - - for (i = 0; i < vsi->num_q_vectors; i++, vector++) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - itr_gran = hw->itr_gran_200; - - if (q_vector->num_ring_rx) { - q_vector->rx.itr = - ITR_TO_REG(vsi->rx_rings[rxq]->rx_itr_setting, - itr_gran); - q_vector->rx.latency_range = ICE_LOW_LATENCY; - } - - if (q_vector->num_ring_tx) { - q_vector->tx.itr = - ITR_TO_REG(vsi->tx_rings[txq]->tx_itr_setting, - itr_gran); - q_vector->tx.latency_range = ICE_LOW_LATENCY; - } - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), q_vector->rx.itr); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), q_vector->tx.itr); - - /* Both Transmit Queue Interrupt Cause Control register - * and Receive Queue Interrupt Cause control register - * expects MSIX_INDX field to be the vector index - * within the function space and not the absolute - * vector index across PF or across device. - * For SR-IOV VF VSIs queue vector index always starts - * with 1 since first vector index(0) is used for OICR - * in VF space. Since VMDq and other PF VSIs are withtin - * the PF function space, use the vector index thats - * tracked for this PF. - */ - for (q = 0; q < q_vector->num_ring_tx; q++) { - u32 val; - - itr = ICE_TX_ITR; - val = QINT_TQCTL_CAUSE_ENA_M | - (itr << QINT_TQCTL_ITR_INDX_S) | - (vector << QINT_TQCTL_MSIX_INDX_S); - wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); - txq++; - } - - for (q = 0; q < q_vector->num_ring_rx; q++) { - u32 val; - - itr = ICE_RX_ITR; - val = QINT_RQCTL_CAUSE_ENA_M | - (itr << QINT_RQCTL_ITR_INDX_S) | - (vector << QINT_RQCTL_MSIX_INDX_S); - wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); - rxq++; - } - } - - ice_flush(hw); -} - -/** * ice_ena_misc_vector - enable the non-queue interrupts * @pf: board private structure */ @@ -1982,13 +1286,14 @@ static void ice_ena_misc_vector(struct ice_pf *pf) PFINT_OICR_MAL_DETECT_M | PFINT_OICR_GRST_M | PFINT_OICR_PCI_EXCEPTION_M | + PFINT_OICR_VFLR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_CRITERR_M); wr32(hw, PFINT_OICR_ENA, val); /* SW_ITR_IDX = 0, but don't change INTENA */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx), GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M); } @@ -2005,6 +1310,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) u32 oicr, ena_mask; set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); + set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); @@ -2013,6 +1319,10 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) ena_mask &= ~PFINT_OICR_MAL_DETECT_M; set_bit(__ICE_MDD_EVENT_PENDING, pf->state); } + if (oicr & PFINT_OICR_VFLR_M) { + ena_mask &= ~PFINT_OICR_VFLR_M; + set_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + } if (oicr & PFINT_OICR_GRST_M) { u32 reset; @@ -2026,16 +1336,18 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) pf->corer_count++; else if (reset == ICE_RESET_GLOBR) pf->globr_count++; - else + else if (reset == ICE_RESET_EMPR) pf->empr_count++; + else + dev_dbg(&pf->pdev->dev, "Invalid reset type %d\n", + reset); /* If a reset cycle isn't already in progress, we set a bit in * pf->state so that the service task can start a reset/rebuild. * We also make note of which reset happened so that peer * devices/drivers can be informed. */ - if (!test_and_set_bit(__ICE_RESET_RECOVERY_PENDING, - pf->state)) { + if (!test_and_set_bit(__ICE_RESET_OICR_RECV, pf->state)) { if (reset == ICE_RESET_CORER) set_bit(__ICE_CORER_RECV, pf->state); else if (reset == ICE_RESET_GLOBR) @@ -2049,7 +1361,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) * is received and set back to false after the driver * has determined that the hardware is out of reset. * - * __ICE_RESET_RECOVERY_PENDING in pf->state indicates + * __ICE_RESET_OICR_RECV in pf->state indicates * that a post reset rebuild is required before the * driver is operational again. This is set above. * @@ -2097,208 +1409,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } /** - * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors - * @vsi: the VSI being configured - * - * This function maps descriptor rings to the queue-specific vectors allotted - * through the MSI-X enabling code. On a constrained vector budget, we map Tx - * and Rx rings to the vector as "efficiently" as possible. - */ -static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) -{ - int q_vectors = vsi->num_q_vectors; - int tx_rings_rem, rx_rings_rem; - int v_id; - - /* initially assigning remaining rings count to VSIs num queue value */ - tx_rings_rem = vsi->num_txq; - rx_rings_rem = vsi->num_rxq; - - for (v_id = 0; v_id < q_vectors; v_id++) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_id]; - int tx_rings_per_v, rx_rings_per_v, q_id, q_base; - - /* Tx rings mapping to vector */ - tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); - q_vector->num_ring_tx = tx_rings_per_v; - q_vector->tx.ring = NULL; - q_base = vsi->num_txq - tx_rings_rem; - - for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { - struct ice_ring *tx_ring = vsi->tx_rings[q_id]; - - tx_ring->q_vector = q_vector; - tx_ring->next = q_vector->tx.ring; - q_vector->tx.ring = tx_ring; - } - tx_rings_rem -= tx_rings_per_v; - - /* Rx rings mapping to vector */ - rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); - q_vector->num_ring_rx = rx_rings_per_v; - q_vector->rx.ring = NULL; - q_base = vsi->num_rxq - rx_rings_rem; - - for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { - struct ice_ring *rx_ring = vsi->rx_rings[q_id]; - - rx_ring->q_vector = q_vector; - rx_ring->next = q_vector->rx.ring; - q_vector->rx.ring = rx_ring; - } - rx_rings_rem -= rx_rings_per_v; - } -} - -/** - * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - - switch (vsi->type) { - case ICE_VSI_PF: - vsi->alloc_txq = pf->num_lan_tx; - vsi->alloc_rxq = pf->num_lan_rx; - vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE); - vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - break; - } -} - -/** - * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi - * @vsi: VSI pointer - * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. - * - * On error: returns error code (negative) - * On success: returns 0 - */ -static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors) -{ - struct ice_pf *pf = vsi->back; - - /* allocate memory for both Tx and Rx ring pointers */ - vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, - sizeof(struct ice_ring *), GFP_KERNEL); - if (!vsi->tx_rings) - goto err_txrings; - - vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, - sizeof(struct ice_ring *), GFP_KERNEL); - if (!vsi->rx_rings) - goto err_rxrings; - - if (alloc_qvectors) { - /* allocate memory for q_vector pointers */ - vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, - vsi->num_q_vectors, - sizeof(struct ice_q_vector *), - GFP_KERNEL); - if (!vsi->q_vectors) - goto err_vectors; - } - - return 0; - -err_vectors: - devm_kfree(&pf->pdev->dev, vsi->rx_rings); -err_rxrings: - devm_kfree(&pf->pdev->dev, vsi->tx_rings); -err_txrings: - return -ENOMEM; -} - -/** - * ice_msix_clean_rings - MSIX mode Interrupt Handler - * @irq: interrupt number - * @data: pointer to a q_vector - */ -static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) -{ - struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - - if (!q_vector->tx.ring && !q_vector->rx.ring) - return IRQ_HANDLED; - - napi_schedule(&q_vector->napi); - - return IRQ_HANDLED; -} - -/** - * ice_vsi_alloc - Allocates the next available struct vsi in the PF - * @pf: board private structure - * @type: type of VSI - * - * returns a pointer to a VSI on success, NULL on failure. - */ -static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type) -{ - struct ice_vsi *vsi = NULL; - - /* Need to protect the allocation of the VSIs at the PF level */ - mutex_lock(&pf->sw_mutex); - - /* If we have already allocated our maximum number of VSIs, - * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index - * is available to be populated - */ - if (pf->next_vsi == ICE_NO_VSI) { - dev_dbg(&pf->pdev->dev, "out of VSI slots!\n"); - goto unlock_pf; - } - - vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL); - if (!vsi) - goto unlock_pf; - - vsi->type = type; - vsi->back = pf; - set_bit(__ICE_DOWN, vsi->state); - vsi->idx = pf->next_vsi; - vsi->work_lmt = ICE_DFLT_IRQ_WORK; - - ice_vsi_set_num_qs(vsi); - - switch (vsi->type) { - case ICE_VSI_PF: - if (ice_vsi_alloc_arrays(vsi, true)) - goto err_rings; - - /* Setup default MSIX irq handler for VSI */ - vsi->irq_handler = ice_msix_clean_rings; - break; - default: - dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); - goto unlock_pf; - } - - /* fill VSI slot in the PF struct */ - pf->vsi[pf->next_vsi] = vsi; - - /* prepare pf->next_vsi for next use */ - pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, - pf->next_vsi); - goto unlock_pf; - -err_rings: - devm_kfree(&pf->pdev->dev, vsi); - vsi = NULL; -unlock_pf: - mutex_unlock(&pf->sw_mutex); - return vsi; -} - -/** * ice_free_irq_msix_misc - Unroll misc vector setup * @pf: board private structure */ @@ -2309,12 +1419,15 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) ice_flush(&pf->hw); if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) { - synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); + synchronize_irq(pf->msix_entries[pf->sw_oicr_idx].vector); devm_free_irq(&pf->pdev->dev, - pf->msix_entries[pf->oicr_idx].vector, pf); + pf->msix_entries[pf->sw_oicr_idx].vector, pf); } - ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + ice_free_res(pf->sw_irq_tracker, pf->sw_oicr_idx, ICE_RES_MISC_VEC_ID); + pf->num_avail_hw_msix += 1; + ice_free_res(pf->hw_irq_tracker, pf->hw_oicr_idx, ICE_RES_MISC_VEC_ID); } /** @@ -2341,42 +1454,61 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) * lost during reset. Note that this function is called only during * rebuild path and not while reset is in progress. */ - if (ice_is_reset_recovery_pending(pf->state)) + if (ice_is_reset_in_progress(pf->state)) goto skip_req_irq; - /* reserve one vector in irq_tracker for misc interrupts */ - oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); + /* reserve one vector in sw_irq_tracker for misc interrupts */ + oicr_idx = ice_get_res(pf, pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); if (oicr_idx < 0) return oicr_idx; - pf->oicr_idx = oicr_idx; + pf->num_avail_sw_msix -= 1; + pf->sw_oicr_idx = oicr_idx; + + /* reserve one vector in hw_irq_tracker for misc interrupts */ + oicr_idx = ice_get_res(pf, pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + if (oicr_idx < 0) { + ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + return oicr_idx; + } + pf->num_avail_hw_msix -= 1; + pf->hw_oicr_idx = oicr_idx; err = devm_request_irq(&pf->pdev->dev, - pf->msix_entries[pf->oicr_idx].vector, + pf->msix_entries[pf->sw_oicr_idx].vector, ice_misc_intr, 0, pf->int_name, pf); if (err) { dev_err(&pf->pdev->dev, "devm_request_irq for %s failed: %d\n", pf->int_name, err); - ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); + ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + ice_free_res(pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_hw_msix += 1; return err; } skip_req_irq: ice_ena_misc_vector(pf); - val = ((pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | + val = ((pf->hw_oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | PFINT_OICR_CTL_CAUSE_ENA_M); wr32(hw, PFINT_OICR_CTL, val); /* This enables Admin queue Interrupt causes */ - val = ((pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | + val = ((pf->hw_oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | PFINT_FW_CTL_CAUSE_ENA_M); wr32(hw, PFINT_FW_CTL, val); - itr_gran = hw->itr_gran_200; + /* This enables Mailbox queue Interrupt causes */ + val = ((pf->hw_oicr_idx & PFINT_MBX_CTL_MSIX_INDX_M) | + PFINT_MBX_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_MBX_CTL, val); + + itr_gran = hw->itr_gran; - wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx), + wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx), ITR_TO_REG(ICE_ITR_8K, itr_gran)); ice_flush(hw); @@ -2386,209 +1518,43 @@ skip_req_irq: } /** - * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI - * @vsi: the VSI getting queues - * - * Return 0 on success and a negative value on error - */ -static int ice_vsi_get_qs_contig(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int offset, ret = 0; - - mutex_lock(&pf->avail_q_mutex); - /* look for contiguous block of queues for tx */ - offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS, - 0, vsi->alloc_txq, 0); - if (offset < ICE_MAX_TXQS) { - int i; - - bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq); - for (i = 0; i < vsi->alloc_txq; i++) - vsi->txq_map[i] = i + offset; - } else { - ret = -ENOMEM; - vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER; - } - - /* look for contiguous block of queues for rx */ - offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS, - 0, vsi->alloc_rxq, 0); - if (offset < ICE_MAX_RXQS) { - int i; - - bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq); - for (i = 0; i < vsi->alloc_rxq; i++) - vsi->rxq_map[i] = i + offset; - } else { - ret = -ENOMEM; - vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER; - } - mutex_unlock(&pf->avail_q_mutex); - - return ret; -} - -/** - * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI - * @vsi: the VSI getting queues - * - * Return 0 on success and a negative value on error + * ice_napi_del - Remove NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be removed */ -static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi) +static void ice_napi_del(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; - int i, index = 0; - - mutex_lock(&pf->avail_q_mutex); - - if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) { - for (i = 0; i < vsi->alloc_txq; i++) { - index = find_next_zero_bit(pf->avail_txqs, - ICE_MAX_TXQS, index); - if (index < ICE_MAX_TXQS) { - set_bit(index, pf->avail_txqs); - vsi->txq_map[i] = index; - } else { - goto err_scatter_tx; - } - } - } - - if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) { - for (i = 0; i < vsi->alloc_rxq; i++) { - index = find_next_zero_bit(pf->avail_rxqs, - ICE_MAX_RXQS, index); - if (index < ICE_MAX_RXQS) { - set_bit(index, pf->avail_rxqs); - vsi->rxq_map[i] = index; - } else { - goto err_scatter_rx; - } - } - } - - mutex_unlock(&pf->avail_q_mutex); - return 0; + int v_idx; -err_scatter_rx: - /* unflag any queues we have grabbed (i is failed position) */ - for (index = 0; index < i; index++) { - clear_bit(vsi->rxq_map[index], pf->avail_rxqs); - vsi->rxq_map[index] = 0; - } - i = vsi->alloc_txq; -err_scatter_tx: - /* i is either position of failed attempt or vsi->alloc_txq */ - for (index = 0; index < i; index++) { - clear_bit(vsi->txq_map[index], pf->avail_txqs); - vsi->txq_map[index] = 0; - } + if (!vsi->netdev) + return; - mutex_unlock(&pf->avail_q_mutex); - return -ENOMEM; + for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) + netif_napi_del(&vsi->q_vectors[v_idx]->napi); } /** - * ice_vsi_get_qs - Assign queues from PF to VSI - * @vsi: the VSI to assign queues to + * ice_napi_add - register NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be registered * - * Returns 0 on success and a negative value on error + * This function is only called in the driver's load path. Registering the NAPI + * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, + * reset/rebuild, etc.) */ -static int ice_vsi_get_qs(struct ice_vsi *vsi) +static void ice_napi_add(struct ice_vsi *vsi) { - int ret = 0; - - vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG; - vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG; - - /* NOTE: ice_vsi_get_qs_contig() will set the rx/tx mapping - * modes individually to scatter if assigning contiguous queues - * to rx or tx fails - */ - ret = ice_vsi_get_qs_contig(vsi); - if (ret < 0) { - if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) - vsi->alloc_txq = max_t(u16, vsi->alloc_txq, - ICE_MAX_SCATTER_TXQS); - if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) - vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq, - ICE_MAX_SCATTER_RXQS); - ret = ice_vsi_get_qs_scatter(vsi); - } - - return ret; -} - -/** - * ice_vsi_put_qs - Release queues from VSI to PF - * @vsi: the VSI thats going to release queues - */ -static void ice_vsi_put_qs(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int i; - - mutex_lock(&pf->avail_q_mutex); - - for (i = 0; i < vsi->alloc_txq; i++) { - clear_bit(vsi->txq_map[i], pf->avail_txqs); - vsi->txq_map[i] = ICE_INVAL_Q_INDEX; - } - - for (i = 0; i < vsi->alloc_rxq; i++) { - clear_bit(vsi->rxq_map[i], pf->avail_rxqs); - vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; - } - - mutex_unlock(&pf->avail_q_mutex); -} - -/** - * ice_free_q_vector - Free memory allocated for a specific interrupt vector - * @vsi: VSI having the memory freed - * @v_idx: index of the vector to be freed - */ -static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) -{ - struct ice_q_vector *q_vector; - struct ice_ring *ring; + int v_idx; - if (!vsi->q_vectors[v_idx]) { - dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n", - v_idx); + if (!vsi->netdev) return; - } - q_vector = vsi->q_vectors[v_idx]; - - ice_for_each_ring(ring, q_vector->tx) - ring->q_vector = NULL; - ice_for_each_ring(ring, q_vector->rx) - ring->q_vector = NULL; - - /* only VSI with an associated netdev is set up with NAPI */ - if (vsi->netdev) - netif_napi_del(&q_vector->napi); - - devm_kfree(&vsi->back->pdev->dev, q_vector); - vsi->q_vectors[v_idx] = NULL; -} - -/** - * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors - * @vsi: the VSI having memory freed - */ -static void ice_vsi_free_q_vectors(struct ice_vsi *vsi) -{ - int v_idx; for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) - ice_free_q_vector(vsi, v_idx); + netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, + ice_napi_poll, NAPI_POLL_WEIGHT); } /** - * ice_cfg_netdev - Setup the netdev flags - * @vsi: the VSI being configured + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev * * Returns 0 on success, negative value on failure */ @@ -2601,6 +1567,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) struct ice_netdev_priv *np; struct net_device *netdev; u8 mac_addr[ETH_ALEN]; + int err; netdev = alloc_etherdev_mqs(sizeof(struct ice_netdev_priv), vsi->alloc_txq, vsi->alloc_rxq); @@ -2658,195 +1625,14 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = ICE_MAX_MTU; - return 0; -} - -/** - * ice_vsi_free_arrays - clean up vsi resources - * @vsi: pointer to VSI being cleared - * @free_qvectors: bool to specify if q_vectors should be deallocated - */ -static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors) -{ - struct ice_pf *pf = vsi->back; - - /* free the ring and vector containers */ - if (free_qvectors && vsi->q_vectors) { - devm_kfree(&pf->pdev->dev, vsi->q_vectors); - vsi->q_vectors = NULL; - } - if (vsi->tx_rings) { - devm_kfree(&pf->pdev->dev, vsi->tx_rings); - vsi->tx_rings = NULL; - } - if (vsi->rx_rings) { - devm_kfree(&pf->pdev->dev, vsi->rx_rings); - vsi->rx_rings = NULL; - } -} - -/** - * ice_vsi_clear - clean up and deallocate the provided vsi - * @vsi: pointer to VSI being cleared - * - * This deallocates the vsi's queue resources, removes it from the PF's - * VSI array if necessary, and deallocates the VSI - * - * Returns 0 on success, negative on failure - */ -static int ice_vsi_clear(struct ice_vsi *vsi) -{ - struct ice_pf *pf = NULL; - - if (!vsi) - return 0; - - if (!vsi->back) - return -EINVAL; - - pf = vsi->back; - - if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { - dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n", - vsi->idx); - return -EINVAL; - } - - mutex_lock(&pf->sw_mutex); - /* updates the PF for this cleared vsi */ - - pf->vsi[vsi->idx] = NULL; - if (vsi->idx < pf->next_vsi) - pf->next_vsi = vsi->idx; - - ice_vsi_free_arrays(vsi, true); - mutex_unlock(&pf->sw_mutex); - devm_kfree(&pf->pdev->dev, vsi); - - return 0; -} - -/** - * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector - * @vsi: the VSI being configured - * @v_idx: index of the vector in the vsi struct - * - * We allocate one q_vector. If allocation fails we return -ENOMEM. - */ -static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) -{ - struct ice_pf *pf = vsi->back; - struct ice_q_vector *q_vector; - - /* allocate q_vector */ - q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL); - if (!q_vector) - return -ENOMEM; - - q_vector->vsi = vsi; - q_vector->v_idx = v_idx; - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); - - if (vsi->netdev) - netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, - NAPI_POLL_WEIGHT); - /* tie q_vector and vsi together */ - vsi->q_vectors[v_idx] = q_vector; - - return 0; -} - -/** - * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors - * @vsi: the VSI being configured - * - * We allocate one q_vector per queue interrupt. If allocation fails we - * return -ENOMEM. - */ -static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int v_idx = 0, num_q_vectors; - int err; - - if (vsi->q_vectors[0]) { - dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n", - vsi->vsi_num); - return -EEXIST; - } - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - num_q_vectors = vsi->num_q_vectors; - } else { - err = -EINVAL; - goto err_out; - } - - for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - err = ice_vsi_alloc_q_vector(vsi, v_idx); - if (err) - goto err_out; - } - - return 0; - -err_out: - while (v_idx--) - ice_free_q_vector(vsi, v_idx); - - dev_err(&pf->pdev->dev, - "Failed to allocate %d q_vector for VSI %d, ret=%d\n", - vsi->num_q_vectors, vsi->vsi_num, err); - vsi->num_q_vectors = 0; - return err; -} - -/** - * ice_vsi_setup_vector_base - Set up the base vector for the given VSI - * @vsi: ptr to the VSI - * - * This should only be called after ice_vsi_alloc() which allocates the - * corresponding SW VSI structure and initializes num_queue_pairs for the - * newly allocated VSI. - * - * Returns 0 on success or negative on failure - */ -static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int num_q_vectors = 0; - - if (vsi->base_vector) { - dev_dbg(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n", - vsi->vsi_num, vsi->base_vector); - return -EEXIST; - } - - if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - return -ENOENT; - - switch (vsi->type) { - case ICE_VSI_PF: - num_q_vectors = vsi->num_q_vectors; - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - break; - } + err = register_netdev(vsi->netdev); + if (err) + return err; - if (num_q_vectors) - vsi->base_vector = ice_get_res(pf, pf->irq_tracker, - num_q_vectors, vsi->idx); + netif_carrier_off(vsi->netdev); - if (vsi->base_vector < 0) { - dev_err(&pf->pdev->dev, - "Failed to get tracking for %d vectors for VSI %d, err=%d\n", - num_q_vectors, vsi->vsi_num, vsi->base_vector); - return -ENOENT; - } + /* make sure transmit queues start off as stopped */ + netif_tx_stop_all_queues(vsi->netdev); return 0; } @@ -2866,275 +1652,6 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) } /** - * ice_vsi_cfg_rss - Configure RSS params for a VSI - * @vsi: VSI to be configured - */ -static int ice_vsi_cfg_rss(struct ice_vsi *vsi) -{ - u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE]; - struct ice_aqc_get_set_rss_keys *key; - struct ice_pf *pf = vsi->back; - enum ice_status status; - int err = 0; - u8 *lut; - - vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq); - - lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL); - if (!lut) - return -ENOMEM; - - if (vsi->rss_lut_user) - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); - else - ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); - - status = ice_aq_set_rss_lut(&pf->hw, vsi->vsi_num, vsi->rss_lut_type, - lut, vsi->rss_table_size); - - if (status) { - dev_err(&vsi->back->pdev->dev, - "set_rss_lut failed, error %d\n", status); - err = -EIO; - goto ice_vsi_cfg_rss_exit; - } - - key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL); - if (!key) { - err = -ENOMEM; - goto ice_vsi_cfg_rss_exit; - } - - if (vsi->rss_hkey_user) - memcpy(seed, vsi->rss_hkey_user, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - else - netdev_rss_key_fill((void *)seed, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - memcpy(&key->standard_rss_key, seed, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - - status = ice_aq_set_rss_key(&pf->hw, vsi->vsi_num, key); - - if (status) { - dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n", - status); - err = -EIO; - } - - devm_kfree(&pf->pdev->dev, key); -ice_vsi_cfg_rss_exit: - devm_kfree(&pf->pdev->dev, lut); - return err; -} - -/** - * ice_vsi_rebuild - Rebuild VSI after reset - * @vsi: vsi to be rebuild - * - * Returns 0 on success and negative value on failure - */ -static int ice_vsi_rebuild(struct ice_vsi *vsi) -{ - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - int ret, i; - - if (!vsi) - return -EINVAL; - - ice_vsi_free_q_vectors(vsi); - ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx); - vsi->base_vector = 0; - ice_vsi_clear_rings(vsi); - ice_vsi_free_arrays(vsi, false); - ice_vsi_set_num_qs(vsi); - - /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_init(vsi); - if (ret < 0) - goto err_vsi; - - ret = ice_vsi_alloc_arrays(vsi, false); - if (ret < 0) - goto err_vsi; - - switch (vsi->type) { - case ICE_VSI_PF: - /* fall through */ - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ice_vsi_map_rings_to_vectors(vsi); - break; - default: - break; - } - - ice_vsi_set_tc_cfg(vsi); - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; - - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num, - vsi->tc_cfg.ena_tc, max_txqs); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "Failed VSI lan queue config\n"); - goto err_vectors; - } - return 0; - -err_vectors: - ice_vsi_free_q_vectors(vsi); -err_rings: - if (vsi->netdev) { - vsi->current_netdev_flags = 0; - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_vsi: - ice_vsi_clear(vsi); - set_bit(__ICE_RESET_FAILED, vsi->back->state); - return ret; -} - -/** - * ice_vsi_setup - Set up a VSI by a given type - * @pf: board private structure - * @pi: pointer to the port_info instance - * @type: VSI type - * @vf_id: defines VF id to which this VSI connects. This field is meant to be - * used only for ICE_VSI_VF VSI type. For other VSI types, should - * fill-in ICE_INVAL_VFID as input. - * - * This allocates the sw VSI structure and its queue resources. - * - * Returns pointer to the successfully allocated and configured VSI sw struct on - * success, NULL on failure. - */ -static struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type type, u16 __always_unused vf_id) -{ - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - struct device *dev = &pf->pdev->dev; - struct ice_vsi *vsi; - int ret, i; - - vsi = ice_vsi_alloc(pf, type); - if (!vsi) { - dev_err(dev, "could not allocate VSI\n"); - return NULL; - } - - vsi->port_info = pi; - vsi->vsw = pf->first_sw; - - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto err_get_qs; - } - - /* set RSS capabilities */ - ice_vsi_set_rss_params(vsi); - - /* create the VSI */ - ret = ice_vsi_init(vsi); - if (ret) - goto err_vsi; - - switch (vsi->type) { - case ICE_VSI_PF: - ret = ice_cfg_netdev(vsi); - if (ret) - goto err_cfg_netdev; - - ret = register_netdev(vsi->netdev); - if (ret) - goto err_register_netdev; - - netif_carrier_off(vsi->netdev); - - /* make sure transmit queues start off as stopped */ - netif_tx_stop_all_queues(vsi->netdev); - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_msix; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_rings; - - ice_vsi_map_rings_to_vectors(vsi); - - /* Do not exit if configuring RSS had an issue, at least - * receive traffic on first queue. Hence no need to capture - * return value - */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_vsi_cfg_rss(vsi); - break; - default: - /* if vsi type is not recognized, clean up the resources and - * exit - */ - goto err_rings; - } - - ice_vsi_set_tc_cfg(vsi); - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; - - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num, - vsi->tc_cfg.ena_tc, max_txqs); - if (ret) { - dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n"); - goto err_rings; - } - - return vsi; - -err_rings: - ice_vsi_free_q_vectors(vsi); -err_msix: - if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(vsi->netdev); -err_register_netdev: - if (vsi->netdev) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_cfg_netdev: - ice_vsi_delete(vsi); -err_vsi: - ice_vsi_put_qs(vsi); -err_get_qs: - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; - ice_vsi_clear(vsi); - - return NULL; -} - -/** * ice_pf_vsi_setup - Set up a PF VSI * @pf: board private structure * @pi: pointer to the port_info instance @@ -3149,44 +1666,6 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) } /** - * ice_vsi_add_vlan - Add vsi membership for given vlan - * @vsi: the vsi being configured - * @vid: vlan id to be added - */ -static int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid) -{ - struct ice_fltr_list_entry *tmp; - struct ice_pf *pf = vsi->back; - LIST_HEAD(tmp_add_list); - enum ice_status status; - int err = 0; - - tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.flag = ICE_FLTR_TX; - tmp->fltr_info.src = vsi->vsi_num; - tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - tmp->fltr_info.l_data.vlan.vlan_id = vid; - - INIT_LIST_HEAD(&tmp->list_entry); - list_add(&tmp->list_entry, &tmp_add_list); - - status = ice_add_vlan(&pf->hw, &tmp_add_list); - if (status) { - err = -ENODEV; - dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n", - vid, vsi->vsi_num); - } - - ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); - return err; -} - -/** * ice_vlan_rx_add_vid - Add a vlan id filter to HW offload * @netdev: network interface to be adjusted * @proto: unused protocol @@ -3230,44 +1709,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, } /** - * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN - * @vsi: the VSI being configured - * @vid: VLAN id to be removed - * - * Returns 0 on success and negative on failure - */ -static int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) -{ - struct ice_fltr_list_entry *list; - struct ice_pf *pf = vsi->back; - LIST_HEAD(tmp_add_list); - int status = 0; - - list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); - if (!list) - return -ENOMEM; - - list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; - list->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - list->fltr_info.fltr_act = ICE_FWD_TO_VSI; - list->fltr_info.l_data.vlan.vlan_id = vid; - list->fltr_info.flag = ICE_FLTR_TX; - list->fltr_info.src = vsi->vsi_num; - - INIT_LIST_HEAD(&list->list_entry); - list_add(&list->list_entry, &tmp_add_list); - - if (ice_remove_vlan(&pf->hw, &tmp_add_list)) { - dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", - vid, vsi->vsi_num); - status = -EIO; - } - - ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); - return status; -} - -/** * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload * @netdev: network interface to be adjusted * @proto: unused protocol @@ -3314,7 +1755,7 @@ static int ice_setup_pf_sw(struct ice_pf *pf) struct ice_vsi *vsi; int status = 0; - if (ice_is_reset_recovery_pending(pf->state)) + if (ice_is_reset_in_progress(pf->state)) return -EBUSY; vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); @@ -3323,6 +1764,18 @@ static int ice_setup_pf_sw(struct ice_pf *pf) goto unroll_vsi_setup; } + status = ice_cfg_netdev(vsi); + if (status) { + status = -ENODEV; + goto unroll_vsi_setup; + } + + /* registering the NAPI handler requires both the queues and + * netdev to be created, which are done in ice_pf_vsi_setup() + * and ice_cfg_netdev() respectively + */ + ice_napi_add(vsi); + /* To add a MAC filter, first add the MAC to a list and then * pass the list to ice_add_mac. */ @@ -3331,7 +1784,7 @@ static int ice_setup_pf_sw(struct ice_pf *pf) status = ice_add_mac_to_list(vsi, &tmp_add_list, vsi->port_info->mac.perm_addr); if (status) - goto unroll_vsi_setup; + goto unroll_napi_add; /* VSI needs to receive broadcast traffic, so add the broadcast * MAC address to the list as well. @@ -3355,16 +1808,20 @@ static int ice_setup_pf_sw(struct ice_pf *pf) free_mac_list: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); -unroll_vsi_setup: +unroll_napi_add: if (vsi) { - ice_vsi_free_q_vectors(vsi); - if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(vsi->netdev); + ice_napi_del(vsi); if (vsi->netdev) { + if (vsi->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; } + } +unroll_vsi_setup: + if (vsi) { + ice_vsi_free_q_vectors(vsi); ice_vsi_delete(vsi); ice_vsi_put_qs(vsi); pf->q_left_tx += vsi->alloc_txq; @@ -3418,6 +1875,15 @@ static void ice_init_pf(struct ice_pf *pf) { bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS); set_bit(ICE_FLAG_MSIX_ENA, pf->flags); +#ifdef CONFIG_PCI_IOV + if (pf->hw.func_caps.common_cap.sr_iov_1_1) { + struct ice_hw *hw = &pf->hw; + + set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); + pf->num_vfs_supported = min_t(int, hw->func_caps.num_allocd_vfs, + ICE_MAX_VF_COUNT); + } +#endif /* CONFIG_PCI_IOV */ mutex_init(&pf->sw_mutex); mutex_init(&pf->avail_q_mutex); @@ -3460,6 +1926,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) /* reserve vectors for LAN traffic */ pf->num_lan_msix = min_t(int, num_online_cpus(), v_left); v_budget += pf->num_lan_msix; + v_left -= pf->num_lan_msix; pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget, sizeof(struct msix_entry), GFP_KERNEL); @@ -3487,10 +1954,11 @@ static int ice_ena_msix_range(struct ice_pf *pf) "not enough vectors. requested = %d, obtained = %d\n", v_budget, v_actual); if (v_actual >= (pf->num_lan_msix + 1)) { - pf->num_avail_msix = v_actual - (pf->num_lan_msix + 1); + pf->num_avail_sw_msix = v_actual - + (pf->num_lan_msix + 1); } else if (v_actual >= 2) { pf->num_lan_msix = 1; - pf->num_avail_msix = v_actual - 2; + pf->num_avail_sw_msix = v_actual - 2; } else { pci_disable_msix(pf->pdev); err = -ERANGE; @@ -3523,12 +1991,32 @@ static void ice_dis_msix(struct ice_pf *pf) } /** + * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme + * @pf: board private structure + */ +static void ice_clear_interrupt_scheme(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + ice_dis_msix(pf); + + if (pf->sw_irq_tracker) { + devm_kfree(&pf->pdev->dev, pf->sw_irq_tracker); + pf->sw_irq_tracker = NULL; + } + + if (pf->hw_irq_tracker) { + devm_kfree(&pf->pdev->dev, pf->hw_irq_tracker); + pf->hw_irq_tracker = NULL; + } +} + +/** * ice_init_interrupt_scheme - Determine proper interrupt scheme * @pf: board private structure to initialize */ static int ice_init_interrupt_scheme(struct ice_pf *pf) { - int vectors = 0; + int vectors = 0, hw_vectors = 0; ssize_t size; if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) @@ -3542,30 +2030,31 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) /* set up vector assignment tracking */ size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors); - pf->irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); - if (!pf->irq_tracker) { + pf->sw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); + if (!pf->sw_irq_tracker) { ice_dis_msix(pf); return -ENOMEM; } - pf->irq_tracker->num_entries = vectors; + /* populate SW interrupts pool with number of OS granted IRQs. */ + pf->num_avail_sw_msix = vectors; + pf->sw_irq_tracker->num_entries = vectors; - return 0; -} + /* set up HW vector assignment tracking */ + hw_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; + size = sizeof(struct ice_res_tracker) + (sizeof(u16) * hw_vectors); -/** - * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme - * @pf: board private structure - */ -static void ice_clear_interrupt_scheme(struct ice_pf *pf) -{ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_dis_msix(pf); - - if (pf->irq_tracker) { - devm_kfree(&pf->pdev->dev, pf->irq_tracker); - pf->irq_tracker = NULL; + pf->hw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); + if (!pf->hw_irq_tracker) { + ice_clear_interrupt_scheme(pf); + return -ENOMEM; } + + /* populate HW interrupts pool with number of HW supported irqs. */ + pf->num_avail_hw_msix = hw_vectors; + pf->hw_irq_tracker->num_entries = hw_vectors; + + return 0; } /** @@ -3750,6 +2239,7 @@ err_exit_unroll: static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); + int i; if (!pf) return; @@ -3757,8 +2247,15 @@ static void ice_remove(struct pci_dev *pdev) set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + ice_free_vfs(pf); ice_vsi_release_all(pf); ice_free_irq_msix_misc(pf); + ice_for_each_vsi(pf, i) { + if (!pf->vsi[i]) + continue; + ice_vsi_free_q_vectors(pf->vsi[i]); + } ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); @@ -3777,8 +2274,6 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_QSFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SGMII), 0 }, /* required last entry */ { 0, } }; @@ -3789,6 +2284,7 @@ static struct pci_driver ice_driver = { .id_table = ice_pci_tbl, .probe = ice_probe, .remove = ice_remove, + .sriov_configure = ice_sriov_configure, }; /** @@ -3866,7 +2362,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) } if (test_bit(__ICE_DOWN, pf->state) || - ice_is_reset_recovery_pending(pf->state)) { + ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't set mac %pM. device not ready\n", mac); return -EBUSY; @@ -4026,78 +2522,6 @@ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], } /** - * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx - * @vsi: the vsi being changed - */ -static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) -{ - struct device *dev = &vsi->back->pdev->dev; - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx ctxt = { 0 }; - enum ice_status status; - - /* Here we are configuring the VSI to let the driver add VLAN tags by - * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag - * insertion happens in the Tx hot path, in ice_tx_map. - */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - ctxt.vsi_num = vsi->vsi_num; - - status = ice_aq_update_vsi(hw, &ctxt, NULL); - if (status) { - dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", - status, hw->adminq.sq_last_status); - return -EIO; - } - - vsi->info.vlan_flags = ctxt.info.vlan_flags; - return 0; -} - -/** - * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx - * @vsi: the vsi being changed - * @ena: boolean value indicating if this is a enable or disable request - */ -static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) -{ - struct device *dev = &vsi->back->pdev->dev; - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx ctxt = { 0 }; - enum ice_status status; - - /* Here we are configuring what the VSI should do with the VLAN tag in - * the Rx packet. We can either leave the tag in the packet or put it in - * the Rx descriptor. - */ - if (ena) { - /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; - } else { - /* Disable stripping. Leave tag in packet */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; - } - - /* Allow all packets untagged/tagged */ - ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - ctxt.vsi_num = vsi->vsi_num; - - status = ice_aq_update_vsi(hw, &ctxt, NULL); - if (status) { - dev_err(dev, "update VSI for VALN strip failed, ena = %d err %d aq_err %d\n", - ena, status, hw->adminq.sq_last_status); - return -EIO; - } - - vsi->info.vlan_flags = ctxt.info.vlan_flags; - return 0; -} - -/** * ice_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting @@ -4109,6 +2533,12 @@ static int ice_set_features(struct net_device *netdev, struct ice_vsi *vsi = np->vsi; int ret = 0; + if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH)) + ret = ice_vsi_manage_rss_lut(vsi, true); + else if (!(features & NETIF_F_RXHASH) && + netdev->features & NETIF_F_RXHASH) + ret = ice_vsi_manage_rss_lut(vsi, false); + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) ret = ice_vsi_manage_vlan_stripping(vsi, true); @@ -4167,248 +2597,6 @@ static int ice_restore_vlan(struct ice_vsi *vsi) } /** - * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance - * @ring: The Tx ring to configure - * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized - * @pf_q: queue index in the PF space - * - * Configure the Tx descriptor ring in TLAN context. - */ -static void -ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) -{ - struct ice_vsi *vsi = ring->vsi; - struct ice_hw *hw = &vsi->back->hw; - - tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S; - - tlan_ctx->port_num = vsi->port_info->lport; - - /* Transmit Queue Length */ - tlan_ctx->qlen = ring->count; - - /* PF number */ - tlan_ctx->pf_num = hw->pf_id; - - /* queue belongs to a specific VSI type - * VF / VM index should be programmed per vmvf_type setting: - * for vmvf_type = VF, it is VF number between 0-256 - * for vmvf_type = VM, it is VM number between 0-767 - * for PF or EMP this field should be set to zero - */ - switch (vsi->type) { - case ICE_VSI_PF: - tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; - break; - default: - return; - } - - /* make sure the context is associated with the right VSI */ - tlan_ctx->src_vsi = vsi->vsi_num; - - tlan_ctx->tso_ena = ICE_TX_LEGACY; - tlan_ctx->tso_qnum = pf_q; - - /* Legacy or Advanced Host Interface: - * 0: Advanced Host Interface - * 1: Legacy Host Interface - */ - tlan_ctx->legacy_int = ICE_TX_LEGACY; -} - -/** - * ice_vsi_cfg_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -static int ice_vsi_cfg_txqs(struct ice_vsi *vsi) -{ - struct ice_aqc_add_tx_qgrp *qg_buf; - struct ice_aqc_add_txqs_perq *txq; - struct ice_pf *pf = vsi->back; - enum ice_status status; - u16 buf_len, i, pf_q; - int err = 0, tc = 0; - u8 num_q_grps; - - buf_len = sizeof(struct ice_aqc_add_tx_qgrp); - qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - - if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) { - err = -EINVAL; - goto err_cfg_txqs; - } - qg_buf->num_txqs = 1; - num_q_grps = 1; - - /* set up and configure the tx queues */ - ice_for_each_txq(vsi, i) { - struct ice_tlan_ctx tlan_ctx = { 0 }; - - pf_q = vsi->txq_map[i]; - ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q); - /* copy context contents into the qg_buf */ - qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); - - /* init queue specific tail reg. It is referred as transmit - * comm scheduler queue doorbell. - */ - vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); - status = ice_ena_vsi_txq(vsi->port_info, vsi->vsi_num, tc, - num_q_grps, qg_buf, buf_len, NULL); - if (status) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Tx queue context, error: %d\n", - status); - err = -ENODEV; - goto err_cfg_txqs; - } - - /* Add Tx Queue TEID into the VSI tx ring from the response - * This will complete configuring and enabling the queue. - */ - txq = &qg_buf->txqs[0]; - if (pf_q == le16_to_cpu(txq->txq_id)) - vsi->tx_rings[i]->txq_teid = - le32_to_cpu(txq->q_teid); - } -err_cfg_txqs: - devm_kfree(&pf->pdev->dev, qg_buf); - return err; -} - -/** - * ice_setup_rx_ctx - Configure a receive ring context - * @ring: The Rx ring to configure - * - * Configure the Rx descriptor ring in RLAN context. - */ -static int ice_setup_rx_ctx(struct ice_ring *ring) -{ - struct ice_vsi *vsi = ring->vsi; - struct ice_hw *hw = &vsi->back->hw; - u32 rxdid = ICE_RXDID_FLEX_NIC; - struct ice_rlan_ctx rlan_ctx; - u32 regval; - u16 pf_q; - int err; - - /* what is RX queue number in global space of 2K rx queues */ - pf_q = vsi->rxq_map[ring->q_index]; - - /* clear the context structure first */ - memset(&rlan_ctx, 0, sizeof(rlan_ctx)); - - rlan_ctx.base = ring->dma >> ICE_RLAN_BASE_S; - - rlan_ctx.qlen = ring->count; - - /* Receive Packet Data Buffer Size. - * The Packet Data Buffer Size is defined in 128 byte units. - */ - rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; - - /* use 32 byte descriptors */ - rlan_ctx.dsize = 1; - - /* Strip the Ethernet CRC bytes before the packet is posted to host - * memory. - */ - rlan_ctx.crcstrip = 1; - - /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ - rlan_ctx.l2tsel = 1; - - rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; - rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; - rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; - - /* This controls whether VLAN is stripped from inner headers - * The VLAN in the inner L2 header is stripped to the receive - * descriptor if enabled by this flag. - */ - rlan_ctx.showiv = 0; - - /* Max packet size for this queue - must not be set to a larger value - * than 5 x DBUF - */ - rlan_ctx.rxmax = min_t(u16, vsi->max_frame, - ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len); - - /* Rx queue threshold in units of 64 */ - rlan_ctx.lrxqthresh = 1; - - /* Enable Flexible Descriptors in the queue context which - * allows this driver to select a specific receive descriptor format - */ - regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - /* increasing context priority to pick up profile id; - * default is 0x01; setting to 0x03 to ensure profile - * is programming if prev context is of same priority - */ - regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; - - wr32(hw, QRXFLXP_CNTXT(pf_q), regval); - - /* Absolute queue number out of 2K needs to be passed */ - err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); - if (err) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", - pf_q, err); - return -EIO; - } - - /* init queue specific tail register */ - ring->tail = hw->hw_addr + QRX_TAIL(pf_q); - writel(0, ring->tail); - ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); - - return 0; -} - -/** - * ice_vsi_cfg_rxqs - Configure the VSI for Rx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Rx VSI for operation. - */ -static int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) -{ - int err = 0; - u16 i; - - if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN) - vsi->max_frame = vsi->netdev->mtu + - ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - else - vsi->max_frame = ICE_RXBUF_2048; - - vsi->rx_buf_len = ICE_RXBUF_2048; - /* set up individual rings */ - for (i = 0; i < vsi->num_rxq && !err; i++) - err = ice_setup_rx_ctx(vsi->rx_rings[i]); - - if (err) { - dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n"); - return -EIO; - } - return err; -} - -/** * ice_vsi_cfg - Setup the VSI * @vsi: the VSI being configured * @@ -4433,207 +2621,6 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) } /** - * ice_vsi_stop_tx_rings - Disable Tx rings - * @vsi: the VSI being configured - */ -static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - enum ice_status status; - u32 *q_teids, val; - u16 *q_ids, i; - int err = 0; - - if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) - return -EINVAL; - - q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids), - GFP_KERNEL); - if (!q_teids) - return -ENOMEM; - - q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids), - GFP_KERNEL); - if (!q_ids) { - err = -ENOMEM; - goto err_alloc_q_ids; - } - - /* set up the tx queue list to be disabled */ - ice_for_each_txq(vsi, i) { - u16 v_idx; - - if (!vsi->tx_rings || !vsi->tx_rings[i]) { - err = -EINVAL; - goto err_out; - } - - q_ids[i] = vsi->txq_map[i]; - q_teids[i] = vsi->tx_rings[i]->txq_teid; - - /* clear cause_ena bit for disabled queues */ - val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val); - - /* software is expected to wait for 100 ns */ - ndelay(100); - - /* trigger a software interrupt for the vector associated to - * the queue to schedule napi handler - */ - v_idx = vsi->tx_rings[i]->q_vector->v_idx; - wr32(hw, GLINT_DYN_CTL(vsi->base_vector + v_idx), - GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); - } - status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, - NULL); - /* if the disable queue command was exercised during an active reset - * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as - * the reset operation disables queues at the hardware level anyway. - */ - if (status == ICE_ERR_RESET_ONGOING) { - dev_dbg(&pf->pdev->dev, - "Reset in progress. LAN Tx queues already disabled\n"); - } else if (status) { - dev_err(&pf->pdev->dev, - "Failed to disable LAN Tx queues, error: %d\n", - status); - err = -ENODEV; - } - -err_out: - devm_kfree(&pf->pdev->dev, q_ids); - -err_alloc_q_ids: - devm_kfree(&pf->pdev->dev, q_teids); - - return err; -} - -/** - * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled - * @pf: the PF being configured - * @pf_q: the PF queue - * @ena: enable or disable state of the queue - * - * This routine will wait for the given Rx queue of the PF to reach the - * enabled or disabled state. - * Returns -ETIMEDOUT in case of failing to reach the requested state after - * multiple retries; else will return 0 in case of success. - */ -static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) -{ - int i; - - for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) { - u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q)); - - if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) - break; - - usleep_range(10, 20); - } - if (i >= ICE_Q_WAIT_RETRY_LIMIT) - return -ETIMEDOUT; - - return 0; -} - -/** - * ice_vsi_ctrl_rx_rings - Start or stop a VSI's rx rings - * @vsi: the VSI being configured - * @ena: start or stop the rx rings - */ -static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int i, j, ret = 0; - - for (i = 0; i < vsi->num_rxq; i++) { - int pf_q = vsi->rxq_map[i]; - u32 rx_reg; - - for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) { - rx_reg = rd32(hw, QRX_CTRL(pf_q)); - if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) == - ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1)) - break; - usleep_range(1000, 2000); - } - - /* Skip if the queue is already in the requested state */ - if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) - continue; - - /* turn on/off the queue */ - if (ena) - rx_reg |= QRX_CTRL_QENA_REQ_M; - else - rx_reg &= ~QRX_CTRL_QENA_REQ_M; - wr32(hw, QRX_CTRL(pf_q), rx_reg); - - /* wait for the change to finish */ - ret = ice_pf_rxq_wait(pf, pf_q, ena); - if (ret) { - dev_err(&pf->pdev->dev, - "VSI idx %d Rx ring %d %sable timeout\n", - vsi->idx, pf_q, (ena ? "en" : "dis")); - break; - } - } - - return ret; -} - -/** - * ice_vsi_start_rx_rings - start VSI's rx rings - * @vsi: the VSI whose rings are to be started - * - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_start_rx_rings(struct ice_vsi *vsi) -{ - return ice_vsi_ctrl_rx_rings(vsi, true); -} - -/** - * ice_vsi_stop_rx_rings - stop VSI's rx rings - * @vsi: the VSI - * - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) -{ - return ice_vsi_ctrl_rx_rings(vsi, false); -} - -/** - * ice_vsi_stop_tx_rx_rings - stop VSI's tx and rx rings - * @vsi: the VSI - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi) -{ - int err_tx, err_rx; - - err_tx = ice_vsi_stop_tx_rings(vsi); - if (err_tx) - dev_dbg(&vsi->back->pdev->dev, "Failed to disable Tx rings\n"); - - err_rx = ice_vsi_stop_rx_rings(vsi); - if (err_rx) - dev_dbg(&vsi->back->pdev->dev, "Failed to disable Rx rings\n"); - - if (err_tx || err_rx) - return -EIO; - - return 0; -} - -/** * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI * @vsi: the VSI being configured */ @@ -4730,122 +2717,6 @@ static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, } /** - * ice_stat_update40 - read 40 bit stat from the chip and update stat values - * @hw: ptr to the hardware info - * @hireg: high 32 bit HW register to read from - * @loreg: low 32 bit HW register to read from - * @prev_stat_loaded: bool to specify if previous stats are loaded - * @prev_stat: ptr to previous loaded stat value - * @cur_stat: ptr to current stat value - */ -static void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, - u64 *cur_stat) -{ - u64 new_data; - - new_data = rd32(hw, loreg); - new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; - - /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. - */ - if (!prev_stat_loaded) - *prev_stat = new_data; - if (likely(new_data >= *prev_stat)) - *cur_stat = new_data - *prev_stat; - else - /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; - *cur_stat &= 0xFFFFFFFFFFULL; -} - -/** - * ice_stat_update32 - read 32 bit stat from the chip and update stat values - * @hw: ptr to the hardware info - * @reg: HW register to read from - * @prev_stat_loaded: bool to specify if previous stats are loaded - * @prev_stat: ptr to previous loaded stat value - * @cur_stat: ptr to current stat value - */ -static void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, - u64 *prev_stat, u64 *cur_stat) -{ - u32 new_data; - - new_data = rd32(hw, reg); - - /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. - */ - if (!prev_stat_loaded) - *prev_stat = new_data; - if (likely(new_data >= *prev_stat)) - *cur_stat = new_data - *prev_stat; - else - /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; -} - -/** - * ice_update_eth_stats - Update VSI-specific ethernet statistics counters - * @vsi: the VSI to be updated - */ -static void ice_update_eth_stats(struct ice_vsi *vsi) -{ - struct ice_eth_stats *prev_es, *cur_es; - struct ice_hw *hw = &vsi->back->hw; - u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ - - prev_es = &vsi->eth_stats_prev; - cur_es = &vsi->eth_stats; - - ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_bytes, - &cur_es->rx_bytes); - - ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_unicast, - &cur_es->rx_unicast); - - ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_multicast, - &cur_es->rx_multicast); - - ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_broadcast, - &cur_es->rx_broadcast); - - ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, - &prev_es->rx_discards, &cur_es->rx_discards); - - ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_bytes, - &cur_es->tx_bytes); - - ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_unicast, - &cur_es->tx_unicast); - - ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_multicast, - &cur_es->tx_multicast); - - ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_broadcast, - &cur_es->tx_broadcast); - - ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, - &prev_es->tx_errors, &cur_es->tx_errors); - - vsi->stat_offsets_loaded = true; -} - -/** * ice_update_vsi_ring_stats - Update VSI stats counters * @vsi: the VSI to be updated */ @@ -5138,7 +3009,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, err; + int i, tx_err, rx_err; /* Caller of this function is expected to set the * vsi->state __ICE_DOWN bit @@ -5149,7 +3020,18 @@ int ice_down(struct ice_vsi *vsi) } ice_vsi_dis_irq(vsi); - err = ice_vsi_stop_tx_rx_rings(vsi); + tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0); + if (tx_err) + netdev_err(vsi->netdev, + "Failed stop Tx rings, VSI %d error %d\n", + vsi->vsi_num, tx_err); + + rx_err = ice_vsi_stop_rx_rings(vsi); + if (rx_err) + netdev_err(vsi->netdev, + "Failed stop Rx rings, VSI %d error %d\n", + vsi->vsi_num, rx_err); + ice_napi_disable_all(vsi); ice_for_each_txq(vsi, i) @@ -5158,10 +3040,14 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (err) - netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", + if (tx_err || rx_err) { + netdev_err(vsi->netdev, + "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); - return err; + return -EIO; + } + + return 0; } /** @@ -5181,6 +3067,7 @@ static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) } ice_for_each_txq(vsi, i) { + vsi->tx_rings[i]->netdev = vsi->netdev; err = ice_setup_tx_ring(vsi->tx_rings[i]); if (err) break; @@ -5206,6 +3093,7 @@ static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } ice_for_each_rxq(vsi, i) { + vsi->rx_rings[i]->netdev = vsi->netdev; err = ice_setup_rx_ring(vsi->rx_rings[i]); if (err) break; @@ -5233,38 +3121,6 @@ static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename) } /** - * ice_vsi_free_tx_rings - Free Tx resources for VSI queues - * @vsi: the VSI having resources freed - */ -static void ice_vsi_free_tx_rings(struct ice_vsi *vsi) -{ - int i; - - if (!vsi->tx_rings) - return; - - ice_for_each_txq(vsi, i) - if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) - ice_free_tx_ring(vsi->tx_rings[i]); -} - -/** - * ice_vsi_free_rx_rings - Free Rx resources for VSI queues - * @vsi: the VSI having resources freed - */ -static void ice_vsi_free_rx_rings(struct ice_vsi *vsi) -{ - int i; - - if (!vsi->rx_rings) - return; - - ice_for_each_rxq(vsi, i) - if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc) - ice_free_rx_ring(vsi->rx_rings[i]); -} - -/** * ice_vsi_open - Called when a network interface is made active * @vsi: the VSI to open * @@ -5325,92 +3181,6 @@ err_setup_tx: } /** - * ice_vsi_close - Shut down a VSI - * @vsi: the VSI being shut down - */ -static void ice_vsi_close(struct ice_vsi *vsi) -{ - if (!test_and_set_bit(__ICE_DOWN, vsi->state)) - ice_down(vsi); - - ice_vsi_free_irq(vsi); - ice_vsi_free_tx_rings(vsi); - ice_vsi_free_rx_rings(vsi); -} - -/** - * ice_rss_clean - Delete RSS related VSI structures that hold user inputs - * @vsi: the VSI being removed - */ -static void ice_rss_clean(struct ice_vsi *vsi) -{ - struct ice_pf *pf; - - pf = vsi->back; - - if (vsi->rss_hkey_user) - devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user); - if (vsi->rss_lut_user) - devm_kfree(&pf->pdev->dev, vsi->rss_lut_user); -} - -/** - * ice_vsi_release - Delete a VSI and free its resources - * @vsi: the VSI being removed - * - * Returns 0 on success or < 0 on error - */ -static int ice_vsi_release(struct ice_vsi *vsi) -{ - struct ice_pf *pf; - - if (!vsi->back) - return -ENODEV; - pf = vsi->back; - /* do not unregister and free netdevs while driver is in the reset - * recovery pending state. Since reset/rebuild happens through PF - * service task workqueue, its not a good idea to unregister netdev - * that is associated to the PF that is running the work queue items - * currently. This is done to avoid check_flush_dependency() warning - * on this wq - */ - if (vsi->netdev && !ice_is_reset_recovery_pending(pf->state)) { - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } - - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_rss_clean(vsi); - - /* Disable VSI and free resources */ - ice_vsi_dis_irq(vsi); - ice_vsi_close(vsi); - - /* reclaim interrupt vectors back to PF */ - ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_msix += vsi->num_q_vectors; - - ice_remove_vsi_fltr(&pf->hw, vsi->vsi_num); - ice_vsi_delete(vsi); - ice_vsi_free_q_vectors(vsi); - ice_vsi_clear_rings(vsi); - - ice_vsi_put_qs(vsi); - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; - - /* retain SW VSI data structure since it is needed to unregister and - * free VSI netdev when PF is not in reset recovery pending state,\ - * for ex: during rmmod. - */ - if (!ice_is_reset_recovery_pending(pf->state)) - ice_vsi_clear(vsi); - - return 0; -} - -/** * ice_vsi_release_all - Delete all VSIs * @pf: PF from which all VSIs are being removed */ @@ -5444,13 +3214,14 @@ static void ice_dis_vsi(struct ice_vsi *vsi) set_bit(__ICE_NEEDS_RESTART, vsi->state); - if (vsi->netdev && netif_running(vsi->netdev) && - vsi->type == ICE_VSI_PF) { - rtnl_lock(); - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - rtnl_unlock(); - } else { - ice_vsi_close(vsi); + if (vsi->type == ICE_VSI_PF && vsi->netdev) { + if (netif_running(vsi->netdev)) { + rtnl_lock(); + vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + rtnl_unlock(); + } else { + ice_vsi_close(vsi); + } } } @@ -5462,12 +3233,16 @@ static int ice_ena_vsi(struct ice_vsi *vsi) { int err = 0; - if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) - if (vsi->netdev && netif_running(vsi->netdev)) { + if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state) && + vsi->netdev) { + if (netif_running(vsi->netdev)) { rtnl_lock(); err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev); rtnl_unlock(); + } else { + err = ice_vsi_open(vsi); } + } return err; } @@ -5516,6 +3291,10 @@ static int ice_vsi_rebuild_all(struct ice_pf *pf) if (!pf->vsi[i]) continue; + /* VF VSI rebuild isn't supported yet */ + if (pf->vsi[i]->type == ICE_VSI_VF) + continue; + err = ice_vsi_rebuild(pf->vsi[i]); if (err) { dev_err(&pf->pdev->dev, @@ -5533,6 +3312,44 @@ static int ice_vsi_rebuild_all(struct ice_pf *pf) } /** + * ice_vsi_replay_all - replay all VSIs configuration in the PF + * @pf: the PF + */ +static int ice_vsi_replay_all(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + enum ice_status ret; + int i; + + /* loop through pf->vsi array and replay the VSI if found */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (!pf->vsi[i]) + continue; + + ret = ice_replay_vsi(hw, pf->vsi[i]->idx); + if (ret) { + dev_err(&pf->pdev->dev, + "VSI at index %d replay failed %d\n", + pf->vsi[i]->idx, ret); + return -EIO; + } + + /* Re-map HW VSI number, using VSI handle that has been + * previously validated in ice_replay_vsi() call above + */ + pf->vsi[i]->vsi_num = ice_get_hw_vsi_num(hw, pf->vsi[i]->idx); + + dev_info(&pf->pdev->dev, + "VSI at index %d filter replayed successfully - vsi_num %i\n", + pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + } + + /* Clean up replay filter after successful re-configuration */ + ice_replay_post(hw); + return 0; +} + +/** * ice_rebuild - rebuild after reset * @pf: pf to rebuild */ @@ -5572,16 +3389,26 @@ static void ice_rebuild(struct ice_pf *pf) if (err) goto err_sched_init_port; + /* reset search_hint of irq_trackers to 0 since interrupts are + * reclaimed and could be allocated from beginning during VSI rebuild + */ + pf->sw_irq_tracker->search_hint = 0; + pf->hw_irq_tracker->search_hint = 0; + err = ice_vsi_rebuild_all(pf); if (err) { dev_err(dev, "ice_vsi_rebuild_all failed\n"); goto err_vsi_rebuild; } - ret = ice_replay_all_fltr(&pf->hw); - if (ret) { + err = ice_update_link_info(hw->port_info); + if (err) + dev_err(&pf->pdev->dev, "Get link status error %d\n", err); + + /* Replay all VSIs Configuration, including filters after reset */ + if (ice_vsi_replay_all(pf)) { dev_err(&pf->pdev->dev, - "error replaying switch filter rules\n"); + "error replaying VSI configurations with switch filter rules\n"); goto err_vsi_rebuild; } @@ -5604,6 +3431,7 @@ static void ice_rebuild(struct ice_pf *pf) goto err_vsi_rebuild; } + ice_reset_all_vfs(pf, true); /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; @@ -5651,7 +3479,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) } /* if a reset is in progress, wait for some time for it to complete */ do { - if (ice_is_reset_recovery_pending(pf->state)) { + if (ice_is_reset_in_progress(pf->state)) { count++; usleep_range(1000, 2000); } else { @@ -5707,7 +3535,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) struct ice_aqc_get_set_rss_keys *buf = (struct ice_aqc_get_set_rss_keys *)seed; - status = ice_aq_set_rss_key(hw, vsi->vsi_num, buf); + status = ice_aq_set_rss_key(hw, vsi->idx, buf); if (status) { dev_err(&pf->pdev->dev, @@ -5718,8 +3546,8 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } if (lut) { - status = ice_aq_set_rss_lut(hw, vsi->vsi_num, - vsi->rss_lut_type, lut, lut_size); + status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type, + lut, lut_size); if (status) { dev_err(&pf->pdev->dev, "Cannot set RSS lut, err %d aq_err %d\n", @@ -5750,7 +3578,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) struct ice_aqc_get_set_rss_keys *buf = (struct ice_aqc_get_set_rss_keys *)seed; - status = ice_aq_get_rss_key(hw, vsi->vsi_num, buf); + status = ice_aq_get_rss_key(hw, vsi->idx, buf); if (status) { dev_err(&pf->pdev->dev, "Cannot get RSS key, err %d aq_err %d\n", @@ -5760,8 +3588,8 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } if (lut) { - status = ice_aq_get_rss_lut(hw, vsi->vsi_num, - vsi->rss_lut_type, lut, lut_size); + status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type, + lut, lut_size); if (status) { dev_err(&pf->pdev->dev, "Cannot get RSS lut, err %d aq_err %d\n", @@ -5823,9 +3651,9 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) else /* change from VEB to VEPA mode */ ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB; - ctxt.vsi_num = vsi->vsi_num; ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); - status = ice_aq_update_vsi(hw, &ctxt, NULL); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); if (status) { dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", bmode, status, hw->adminq.sq_last_status); @@ -5965,7 +3793,7 @@ static void ice_tx_timeout(struct net_device *netdev) if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) val = rd32(&pf->hw, GLINT_DYN_CTL(tx_ring->q_vector->v_idx + - tx_ring->vsi->base_vector - 1)); + tx_ring->vsi->hw_base_vector)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", vsi->vsi_num, hung_queue, tx_ring->next_to_clean, @@ -6112,6 +3940,12 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, + .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, + .ndo_set_vf_mac = ice_set_vf_mac, + .ndo_get_vf_config = ice_get_vf_cfg, + .ndo_set_vf_trust = ice_set_vf_trust, + .ndo_set_vf_vlan = ice_set_vf_port_vlan, + .ndo_set_vf_link_state = ice_set_vf_link_state, .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, .ndo_set_features = ice_set_features, diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 9b7b50554952..7cc8aa18a22b 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -85,6 +85,62 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid) } /** + * ice_aq_query_sched_elems - query scheduler elements + * @hw: pointer to the hw struct + * @elems_req: number of elements to query + * @buf: pointer to buffer + * @buf_size: buffer size in bytes + * @elems_ret: returns total number of elements returned + * @cd: pointer to command details structure or NULL + * + * Query scheduling elements (0x0404) + */ +static enum ice_status +ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, + struct ice_aqc_get_elem *buf, u16 buf_size, + u16 *elems_ret, struct ice_sq_cd *cd) +{ + struct ice_aqc_get_cfg_elem *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.get_update_elem; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sched_elems); + cmd->num_elem_req = cpu_to_le16(elems_req); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (!status && elems_ret) + *elems_ret = le16_to_cpu(cmd->num_elem_resp); + + return status; +} + +/** + * ice_sched_query_elem - query element information from hw + * @hw: pointer to the hw struct + * @node_teid: node teid to be queried + * @buf: buffer to element information + * + * This function queries HW element information + */ +static enum ice_status +ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, + struct ice_aqc_get_elem *buf) +{ + u16 buf_size, num_elem_ret = 0; + enum ice_status status; + + buf_size = sizeof(*buf); + memset(buf, 0, buf_size); + buf->generic[0].node_teid = cpu_to_le32(node_teid); + status = ice_aq_query_sched_elems(hw, 1, buf, buf_size, &num_elem_ret, + NULL); + if (status || num_elem_ret != 1) + ice_debug(hw, ICE_DBG_SCHED, "query element failed\n"); + return status; +} + +/** * ice_sched_add_node - Insert the Tx scheduler node in SW DB * @pi: port information structure * @layer: Scheduler layer of the node @@ -97,7 +153,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_aqc_txsched_elem_data *info) { struct ice_sched_node *parent; + struct ice_aqc_get_elem elem; struct ice_sched_node *node; + enum ice_status status; struct ice_hw *hw; if (!pi) @@ -115,6 +173,13 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, return ICE_ERR_PARAM; } + /* query the current node information from FW before additing it + * to the SW DB + */ + status = ice_sched_query_elem(hw, le32_to_cpu(info->node_teid), &elem); + if (status) + return status; + node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) return ICE_ERR_NO_MEMORY; @@ -133,7 +198,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, node->parent = parent; node->tx_sched_layer = layer; parent->children[parent->num_children++] = node; - memcpy(&node->info, info, sizeof(*info)); + memcpy(&node->info, &elem.generic[0], sizeof(node->info)); return 0; } @@ -534,9 +599,7 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, static void ice_sched_clear_tx_topo(struct ice_port_info *pi) { struct ice_sched_agg_info *agg_info; - struct ice_sched_vsi_info *vsi_elem; struct ice_sched_agg_info *atmp; - struct ice_sched_vsi_info *tmp; struct ice_hw *hw; if (!pi) @@ -555,13 +618,6 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi) } } - /* remove the vsi list */ - list_for_each_entry_safe(vsi_elem, tmp, &pi->vsi_info_list, - list_entry) { - list_del(&vsi_elem->list_entry); - devm_kfree(ice_hw_to_dev(hw), vsi_elem); - } - if (pi->root) { ice_free_sched_node(pi, pi->root); pi->root = NULL; @@ -612,31 +668,6 @@ void ice_sched_cleanup_all(struct ice_hw *hw) } /** - * ice_sched_create_vsi_info_entry - create an empty new VSI entry - * @pi: port information structure - * @vsi_id: VSI Id - * - * This function creates a new VSI entry and adds it to list - */ -static struct ice_sched_vsi_info * -ice_sched_create_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id) -{ - struct ice_sched_vsi_info *vsi_elem; - - if (!pi) - return NULL; - - vsi_elem = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*vsi_elem), - GFP_KERNEL); - if (!vsi_elem) - return NULL; - - list_add(&vsi_elem->list_entry, &pi->vsi_info_list); - vsi_elem->vsi_id = vsi_id; - return vsi_elem; -} - -/** * ice_sched_add_elems - add nodes to hw and SW DB * @pi: port information structure * @tc_node: pointer to the branch node @@ -1007,7 +1038,6 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) pi->port_state = ICE_SCHED_PORT_STATE_READY; mutex_init(&pi->sched_lock); INIT_LIST_HEAD(&pi->agg_list); - INIT_LIST_HEAD(&pi->vsi_info_list); err_init_port: if (status && pi->root) { @@ -1077,27 +1107,6 @@ sched_query_out: } /** - * ice_sched_get_vsi_info_entry - Get the vsi entry list for given vsi_id - * @pi: port information structure - * @vsi_id: vsi id - * - * This function retrieves the vsi list for the given vsi id - */ -static struct ice_sched_vsi_info * -ice_sched_get_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id) -{ - struct ice_sched_vsi_info *list_elem; - - if (!pi) - return NULL; - - list_for_each_entry(list_elem, &pi->vsi_info_list, list_entry) - if (list_elem->vsi_id == vsi_id) - return list_elem; - return NULL; -} - -/** * ice_sched_find_node_in_subtree - Find node in part of base node subtree * @hw: pointer to the hw struct * @base: pointer to the base node @@ -1133,30 +1142,28 @@ ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base, /** * ice_sched_get_free_qparent - Get a free lan or rdma q group node * @pi: port information structure - * @vsi_id: vsi id + * @vsi_handle: software VSI handle * @tc: branch number * @owner: lan or rdma * * This function retrieves a free lan or rdma q group node */ struct ice_sched_node * -ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, +ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner) { struct ice_sched_node *vsi_node, *qgrp_node = NULL; - struct ice_sched_vsi_info *list_elem; + struct ice_vsi_ctx *vsi_ctx; u16 max_children; u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); max_children = pi->hw->max_children[qgrp_layer]; - list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!list_elem) - goto lan_q_exit; - - vsi_node = list_elem->vsi_node[tc]; - + vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); + if (!vsi_ctx) + return NULL; + vsi_node = vsi_ctx->sched.vsi_node[tc]; /* validate invalid VSI id */ if (!vsi_node) goto lan_q_exit; @@ -1180,14 +1187,14 @@ lan_q_exit: * ice_sched_get_vsi_node - Get a VSI node based on VSI id * @hw: pointer to the hw struct * @tc_node: pointer to the TC node - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * * This function retrieves a VSI node for a given VSI id from a given * TC branch */ static struct ice_sched_node * ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node, - u16 vsi_id) + u16 vsi_handle) { struct ice_sched_node *node; u8 vsi_layer; @@ -1197,7 +1204,7 @@ ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node, /* Check whether it already exists */ while (node) { - if (node->vsi_id == vsi_id) + if (node->vsi_handle == vsi_handle) return node; node = node->sibling; } @@ -1236,7 +1243,7 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) /** * ice_sched_add_vsi_child_nodes - add VSI child nodes to tree * @pi: port information structure - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * @tc_node: pointer to the TC node * @num_nodes: pointer to the num nodes that needs to be added per layer * @owner: node owner (lan or rdma) @@ -1245,7 +1252,7 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) * lan and rdma separately. */ static enum ice_status -ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, +ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes, u8 owner) { @@ -1258,7 +1265,7 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); - parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + parent = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); for (i = vsil + 1; i <= qgl; i++) { if (!parent) return ICE_ERR_CFG; @@ -1371,7 +1378,7 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /** * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_node: pointer to TC node * @num_nodes: pointer to num nodes array * @@ -1379,7 +1386,7 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, * VSI, its parent and intermediate nodes in below layers */ static enum ice_status -ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, +ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *parent = tc_node; @@ -1413,7 +1420,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, return ICE_ERR_CFG; if (i == vsil) - parent->vsi_id = vsi_id; + parent->vsi_handle = vsi_handle; } return 0; @@ -1422,13 +1429,13 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, /** * ice_sched_add_vsi_to_topo - add a new VSI into tree * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * * This function adds a new VSI into scheduler tree */ static enum ice_status -ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) +ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) { u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; struct ice_sched_node *tc_node; @@ -1442,13 +1449,14 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) ice_sched_calc_vsi_support_nodes(hw, tc_node, num_nodes); /* add vsi supported nodes to tc subtree */ - return ice_sched_add_vsi_support_nodes(pi, vsi_id, tc_node, num_nodes); + return ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node, + num_nodes); } /** * ice_sched_update_vsi_child_nodes - update VSI child nodes * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * @new_numqs: new number of max queues * @owner: owner of this subtree @@ -1456,14 +1464,14 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) * This function updates the VSI child nodes based on the number of queues */ static enum ice_status -ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, - u16 new_numqs, u8 owner) +ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, + u8 tc, u16 new_numqs, u8 owner) { u16 prev_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; u16 new_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; struct ice_sched_node *vsi_node; struct ice_sched_node *tc_node; - struct ice_sched_vsi_info *vsi; + struct ice_vsi_ctx *vsi_ctx; enum ice_status status = 0; struct ice_hw *hw = pi->hw; u16 prev_numqs; @@ -1473,16 +1481,16 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, if (!tc_node) return ICE_ERR_CFG; - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); if (!vsi_node) return ICE_ERR_CFG; - vsi = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!vsi) - return ICE_ERR_CFG; + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; if (owner == ICE_SCHED_NODE_OWNER_LAN) - prev_numqs = vsi->max_lanq[tc]; + prev_numqs = vsi_ctx->sched.max_lanq[tc]; else return ICE_ERR_PARAM; @@ -1507,13 +1515,13 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++) new_num_nodes[i] -= prev_num_nodes[i]; - status = ice_sched_add_vsi_child_nodes(pi, vsi_id, tc_node, + status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node, new_num_nodes, owner); if (status) return status; } - vsi->max_lanq[tc] = new_numqs; + vsi_ctx->sched.max_lanq[tc] = new_numqs; return status; } @@ -1521,7 +1529,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, /** * ice_sched_cfg_vsi - configure the new/exisiting VSI * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * @maxqs: max number of queues * @owner: lan or rdma @@ -1532,25 +1540,21 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, * disabled then suspend the VSI if it is not already. */ enum ice_status -ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, +ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable) { struct ice_sched_node *vsi_node, *tc_node; - struct ice_sched_vsi_info *vsi; + struct ice_vsi_ctx *vsi_ctx; enum ice_status status = 0; struct ice_hw *hw = pi->hw; tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) return ICE_ERR_PARAM; - - vsi = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!vsi) - vsi = ice_sched_create_vsi_info_entry(pi, vsi_id); - if (!vsi) - return ICE_ERR_NO_MEMORY; - - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); /* suspend the VSI if tc is not enabled */ if (!enable) { @@ -1567,20 +1571,26 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, /* TC is enabled, if it is a new VSI then add it to the tree */ if (!vsi_node) { - status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc); + status = ice_sched_add_vsi_to_topo(pi, vsi_handle, tc); if (status) return status; - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); if (!vsi_node) return ICE_ERR_CFG; - vsi->vsi_node[tc] = vsi_node; + vsi_ctx->sched.vsi_node[tc] = vsi_node; vsi_node->in_use = true; + /* invalidate the max queues whenever VSI gets added first time + * into the scheduler tree (boot or after reset). We need to + * recreate the child nodes all the time in these cases. + */ + vsi_ctx->sched.max_lanq[tc] = 0; } /* update the VSI child nodes */ - status = ice_sched_update_vsi_child_nodes(pi, vsi_id, tc, maxqs, owner); + status = ice_sched_update_vsi_child_nodes(pi, vsi_handle, tc, maxqs, + owner); if (status) return status; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index badadcc120d3..5dc9cfa04c58 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -12,7 +12,6 @@ struct ice_sched_agg_vsi_info { struct list_head list_entry; DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS); - u16 vsi_id; }; struct ice_sched_agg_info { @@ -35,9 +34,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node); struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc); struct ice_sched_node * -ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, +ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner); enum ice_status -ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, +ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c new file mode 100644 index 000000000000..027eba4e13f8 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_adminq_cmd.h" +#include "ice_sriov.h" + +/** + * ice_aq_send_msg_to_vf + * @hw: pointer to the hardware structure + * @vfid: VF ID to send msg + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cd: pointer to command details + * + * Send message to VF driver (0x0802) using mailbox + * queue and asynchronously sending message via + * ice_sq_send_cmd() function + */ +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd) +{ + struct ice_aqc_pf_vf_msg *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf); + + cmd = &desc.params.virt; + cmd->id = cpu_to_le32(vfid); + + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + + if (msglen) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); +} + +/** + * ice_conv_link_speed_to_virtchnl + * @adv_link_support: determines the format of the returned link speed + * @link_speed: variable containing the link_speed to be converted + * + * Convert link speed supported by HW to link speed supported by virtchnl. + * If adv_link_support is true, then return link speed in Mbps. Else return + * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller + * needs to cast back to an enum virtchnl_link_speed in the case where + * adv_link_support is false, but when adv_link_support is true the caller can + * expect the speed in Mbps. + */ +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) +{ + u32 speed; + + if (adv_link_support) + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + speed = ICE_LINK_SPEED_10MBPS; + break; + case ICE_AQ_LINK_SPEED_100MB: + speed = ICE_LINK_SPEED_100MBPS; + break; + case ICE_AQ_LINK_SPEED_1000MB: + speed = ICE_LINK_SPEED_1000MBPS; + break; + case ICE_AQ_LINK_SPEED_2500MB: + speed = ICE_LINK_SPEED_2500MBPS; + break; + case ICE_AQ_LINK_SPEED_5GB: + speed = ICE_LINK_SPEED_5000MBPS; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = ICE_LINK_SPEED_10000MBPS; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = ICE_LINK_SPEED_20000MBPS; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = ICE_LINK_SPEED_25000MBPS; + break; + case ICE_AQ_LINK_SPEED_40GB: + speed = ICE_LINK_SPEED_40000MBPS; + break; + default: + speed = ICE_LINK_SPEED_UNKNOWN; + break; + } + else + /* Virtchnl speeds are not defined for every speed supported in + * the hardware. To maintain compatibility with older AVF + * drivers, while reporting the speed the new speed values are + * resolved to the closest known virtchnl speeds + */ + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + case ICE_AQ_LINK_SPEED_100MB: + speed = (u32)VIRTCHNL_LINK_SPEED_100MB; + break; + case ICE_AQ_LINK_SPEED_1000MB: + case ICE_AQ_LINK_SPEED_2500MB: + case ICE_AQ_LINK_SPEED_5GB: + speed = (u32)VIRTCHNL_LINK_SPEED_1GB; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = (u32)VIRTCHNL_LINK_SPEED_10GB; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = (u32)VIRTCHNL_LINK_SPEED_20GB; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = (u32)VIRTCHNL_LINK_SPEED_25GB; + break; + case ICE_AQ_LINK_SPEED_40GB: + /* fall through */ + speed = (u32)VIRTCHNL_LINK_SPEED_40GB; + break; + default: + speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; + break; + } + + return speed; +} diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h new file mode 100644 index 000000000000..3d78a0795138 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_SRIOV_H_ +#define _ICE_SRIOV_H_ + +#include "ice_common.h" + +#ifdef CONFIG_PCI_IOV +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd); + +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +#else /* CONFIG_PCI_IOV */ +static inline enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, + u16 __always_unused vfid, u32 __always_unused v_opcode, + u32 __always_unused v_retval, u8 __always_unused *msg, + u16 __always_unused msglen, + struct ice_sq_cd __always_unused *cd) +{ + return 0; +} + +static inline u32 +ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, + u16 __always_unused link_speed) +{ + return 0; +} + +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h index d2dae913d81e..f49f299ddf2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ b/drivers/net/ethernet/intel/ice/ice_status.h @@ -6,6 +6,9 @@ /* Error Codes */ enum ice_status { + ICE_SUCCESS = 0, + + /* Generic codes : Range -1..-49 */ ICE_ERR_PARAM = -1, ICE_ERR_NOT_IMPL = -2, ICE_ERR_NOT_READY = -3, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 65b4e1cca6be..33403f39f1b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -106,6 +106,7 @@ ice_init_def_sw_recp(struct ice_hw *hw) for (i = 0; i < ICE_SW_LKUP_LAST; i++) { recps[i].root_rid = i; INIT_LIST_HEAD(&recps[i].filt_rules); + INIT_LIST_HEAD(&recps[i].filt_replay_rules); mutex_init(&recps[i].filt_rule_lock); } @@ -186,6 +187,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, if (!vsi_ctx->alloc_from_pool) cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + cmd->vf_id = vsi_ctx->vf_num; cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags); @@ -247,7 +249,7 @@ ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, * * Update VSI context in the hardware (0x0211) */ -enum ice_status +static enum ice_status ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { @@ -277,72 +279,13 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** - * ice_update_fltr_vsi_map - update given filter VSI map - * @list_head: list for which filters needs to be updated - * @list_lock: filter lock which needs to be updated - * @old_vsi_num: old VSI HW id - * @new_vsi_num: new VSI HW id - * - * update the VSI map for a given filter list - */ -static void -ice_update_fltr_vsi_map(struct list_head *list_head, - struct mutex *list_lock, u16 old_vsi_num, - u16 new_vsi_num) -{ - struct ice_fltr_mgmt_list_entry *itr; - - mutex_lock(list_lock); - if (list_empty(list_head)) - goto exit_update_map; - - list_for_each_entry(itr, list_head, list_entry) { - if (itr->vsi_list_info && - test_bit(old_vsi_num, itr->vsi_list_info->vsi_map)) { - clear_bit(old_vsi_num, itr->vsi_list_info->vsi_map); - set_bit(new_vsi_num, itr->vsi_list_info->vsi_map); - } else if (itr->fltr_info.fltr_act == ICE_FWD_TO_VSI && - itr->fltr_info.fwd_id.vsi_id == old_vsi_num) { - itr->fltr_info.fwd_id.vsi_id = new_vsi_num; - itr->fltr_info.src = new_vsi_num; - } - } -exit_update_map: - mutex_unlock(list_lock); -} - -/** - * ice_update_all_fltr_vsi_map - update all filters VSI map - * @hw: pointer to the hardware structure - * @old_vsi_num: old VSI HW id - * @new_vsi_num: new VSI HW id - * - * update all filters VSI map - */ -static void -ice_update_all_fltr_vsi_map(struct ice_hw *hw, u16 old_vsi_num, u16 new_vsi_num) -{ - struct ice_switch_info *sw = hw->switch_info; - u8 i; - - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { - struct list_head *head = &sw->recp_list[i].filt_rules; - struct mutex *lock; /* Lock to protect filter rule list */ - - lock = &sw->recp_list[i].filt_rule_lock; - ice_update_fltr_vsi_map(head, lock, old_vsi_num, - new_vsi_num); - } -} - -/** * ice_is_vsi_valid - check whether the VSI is valid or not * @hw: pointer to the hw struct * @vsi_handle: VSI handle * * check whether the VSI is valid or not */ -static bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) { return vsi_handle < ICE_MAX_VSI && hw->vsi_ctx[vsi_handle]; } @@ -355,7 +298,7 @@ static bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) * return the hw VSI number * Caution: call this function only if VSI is valid (ice_is_vsi_valid) */ -static u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) +u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) { return hw->vsi_ctx[vsi_handle]->vsi_num; } @@ -367,7 +310,7 @@ static u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) * * return the VSI context entry for a given VSI handle */ -static struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) { return (vsi_handle >= ICE_MAX_VSI) ? NULL : hw->vsi_ctx[vsi_handle]; } @@ -440,12 +383,8 @@ ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx); } else { /* update with new HW VSI num */ - if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num) { - /* update all filter lists with new HW VSI num */ - ice_update_all_fltr_vsi_map(hw, tmp_vsi_ctx->vsi_num, - vsi_ctx->vsi_num); + if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num) tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num; - } } return status; @@ -477,6 +416,25 @@ ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, } /** + * ice_update_vsi + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle + * @vsi_ctx: pointer to a VSI context struct + * @cd: pointer to command details structure or NULL + * + * Update VSI context in the hardware + */ +enum ice_status +ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd) +{ + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); + return ice_aq_update_vsi(hw, vsi_ctx, cd); +} + +/** * ice_aq_alloc_free_vsi_list * @hw: pointer to the hw struct * @vsi_list_id: VSI list id returned or used for lookup @@ -698,6 +656,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, u8 *eth_hdr; u32 act = 0; __be16 *off; + u8 q_rgn; if (opc == ice_aqc_opc_remove_sw_rules) { s_rule->pdata.lkup_tx_rx.act = 0; @@ -716,7 +675,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, switch (f_info->fltr_act) { case ICE_FWD_TO_VSI: - act |= (f_info->fwd_id.vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & + act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | @@ -736,14 +695,19 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & ICE_SINGLE_ACT_Q_INDEX_M; break; + case ICE_DROP_PACKET: + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | + ICE_SINGLE_ACT_VALID_BIT; + break; case ICE_FWD_TO_QGRP: + q_rgn = f_info->qgrp_size > 0 ? + (u8)ilog2(f_info->qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->qgrp_size << ICE_SINGLE_ACT_Q_REGION_S) & + act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & ICE_SINGLE_ACT_Q_REGION_M; break; - case ICE_DROP_PACKET: - act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP; - break; default: return; } @@ -832,8 +796,8 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, enum ice_status status; u16 lg_act_size; u16 rules_size; - u16 vsi_info; u32 act; + u16 id; if (m_ent->fltr_info.lkup_type != ICE_SW_LKUP_MAC) return ICE_ERR_PARAM; @@ -859,12 +823,11 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /* First action VSI forwarding or VSI list forwarding depending on how * many VSIs */ - vsi_info = (m_ent->vsi_count > 1) ? - m_ent->fltr_info.fwd_id.vsi_list_id : - m_ent->fltr_info.fwd_id.vsi_id; + id = (m_ent->vsi_count > 1) ? m_ent->fltr_info.fwd_id.vsi_list_id : + m_ent->fltr_info.fwd_id.hw_vsi_id; act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT; - act |= (vsi_info << ICE_LG_ACT_VSI_LIST_ID_S) & + act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M; if (m_ent->vsi_count > 1) act |= ICE_LG_ACT_VSI_LIST; @@ -917,15 +880,15 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /** * ice_create_vsi_list_map * @hw: pointer to the hardware structure - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: num VSI in the array + * @vsi_handle_arr: array of VSI handles to set in the VSI mapping + * @num_vsi: number of VSI handles in the array * @vsi_list_id: VSI list id generated as part of allocate resource * * Helper function to create a new entry of VSI list id to VSI mapping * using the given VSI list id */ static struct ice_vsi_list_map_info * -ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id) { struct ice_switch_info *sw = hw->switch_info; @@ -937,9 +900,9 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, return NULL; v_map->vsi_list_id = vsi_list_id; - + v_map->ref_cnt = 1; for (i = 0; i < num_vsi; i++) - set_bit(vsi_array[i], v_map->vsi_map); + set_bit(vsi_handle_arr[i], v_map->vsi_map); list_add(&v_map->list_entry, &sw->vsi_list_map_head); return v_map; @@ -948,8 +911,8 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, /** * ice_update_vsi_list_rule * @hw: pointer to the hardware structure - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: num VSI in the array + * @vsi_handle_arr: array of VSI handles to form a VSI list + * @num_vsi: number of VSI handles in the array * @vsi_list_id: VSI list id generated as part of allocate resource * @remove: Boolean value to indicate if this is a remove action * @opc: switch rules population command type - pass in the command opcode @@ -959,7 +922,7 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, * using the given VSI list id */ static enum ice_status -ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id, bool remove, enum ice_adminq_opc opc, enum ice_sw_lkup_type lkup_type) { @@ -990,9 +953,15 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) return ICE_ERR_NO_MEMORY; - - for (i = 0; i < num_vsi; i++) - s_rule->pdata.vsi_list.vsi[i] = cpu_to_le16(vsi_array[i]); + for (i = 0; i < num_vsi; i++) { + if (!ice_is_vsi_valid(hw, vsi_handle_arr[i])) { + status = ICE_ERR_PARAM; + goto exit; + } + /* AQ call requires hw_vsi_id(s) */ + s_rule->pdata.vsi_list.vsi[i] = + cpu_to_le16(ice_get_hw_vsi_num(hw, vsi_handle_arr[i])); + } s_rule->type = cpu_to_le16(type); s_rule->pdata.vsi_list.number_vsi = cpu_to_le16(num_vsi); @@ -1000,6 +969,7 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opc, NULL); +exit: devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } @@ -1007,21 +977,16 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, /** * ice_create_vsi_list_rule - Creates and populates a VSI list rule * @hw: pointer to the hw struct - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: number of VSIs in the array + * @vsi_handle_arr: array of VSI handles to form a VSI list + * @num_vsi: number of VSI handles in the array * @vsi_list_id: stores the ID of the VSI list to be created * @lkup_type: switch rule filter's lookup type */ static enum ice_status -ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type) { enum ice_status status; - int i; - - for (i = 0; i < num_vsi; i++) - if (vsi_array[i] >= ICE_MAX_VSI) - return ICE_ERR_OUT_OF_RANGE; status = ice_aq_alloc_free_vsi_list(hw, vsi_list_id, lkup_type, ice_aqc_opc_alloc_res); @@ -1029,9 +994,9 @@ ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, return status; /* Update the newly created VSI list to include the specified VSIs */ - return ice_update_vsi_list_rule(hw, vsi_array, num_vsi, *vsi_list_id, - false, ice_aqc_opc_add_sw_rules, - lkup_type); + return ice_update_vsi_list_rule(hw, vsi_handle_arr, num_vsi, + *vsi_list_id, false, + ice_aqc_opc_add_sw_rules, lkup_type); } /** @@ -1217,15 +1182,15 @@ ice_add_update_vsi_list(struct ice_hw *hw, * new VSIs. */ struct ice_fltr_info tmp_fltr; - u16 vsi_id_arr[2]; + u16 vsi_handle_arr[2]; /* A rule already exists with the new VSI being added */ - if (cur_fltr->fwd_id.vsi_id == new_fltr->fwd_id.vsi_id) + if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id) return ICE_ERR_ALREADY_EXISTS; - vsi_id_arr[0] = cur_fltr->fwd_id.vsi_id; - vsi_id_arr[1] = new_fltr->fwd_id.vsi_id; - status = ice_create_vsi_list_rule(hw, &vsi_id_arr[0], 2, + vsi_handle_arr[0] = cur_fltr->vsi_handle; + vsi_handle_arr[1] = new_fltr->vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, &vsi_list_id, new_fltr->lkup_type); if (status) @@ -1245,7 +1210,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, cur_fltr->fwd_id.vsi_list_id = vsi_list_id; cur_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; m_entry->vsi_list_info = - ice_create_vsi_list_map(hw, &vsi_id_arr[0], 2, + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, vsi_list_id); /* If this entry was large action then the large action needs @@ -1257,11 +1222,11 @@ ice_add_update_vsi_list(struct ice_hw *hw, m_entry->sw_marker_id, m_entry->lg_act_idx); } else { - u16 vsi_id = new_fltr->fwd_id.vsi_id; + u16 vsi_handle = new_fltr->vsi_handle; enum ice_adminq_opc opcode; /* A rule already exists with the new VSI being added */ - if (test_bit(vsi_id, m_entry->vsi_list_info->vsi_map)) + if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) return 0; /* Update the previously created VSI list set with @@ -1270,12 +1235,12 @@ ice_add_update_vsi_list(struct ice_hw *hw, vsi_list_id = cur_fltr->fwd_id.vsi_list_id; opcode = ice_aqc_opc_update_sw_rules; - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, - false, opcode, + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, + vsi_list_id, false, opcode, new_fltr->lkup_type); /* update VSI list mapping info with new VSI id */ if (!status) - set_bit(vsi_id, m_entry->vsi_list_info->vsi_map); + set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map); } if (!status) m_entry->vsi_count++; @@ -1311,6 +1276,39 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) } /** + * ice_find_vsi_list_entry - Search VSI list map with VSI count 1 + * @hw: pointer to the hardware structure + * @recp_id: lookup type for which VSI lists needs to be searched + * @vsi_handle: VSI handle to be found in VSI list + * @vsi_list_id: VSI list id found containing vsi_handle + * + * Helper function to search a VSI list with single entry containing given VSI + * handle element. This can be extended further to search VSI list with more + * than 1 vsi_count. Returns pointer to VSI list entry if found. + */ +static struct ice_vsi_list_map_info * +ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, + u16 *vsi_list_id) +{ + struct ice_vsi_list_map_info *map_info = NULL; + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_itr; + struct list_head *list_head; + + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + 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; + return map_info; + } + } + } + return NULL; +} + +/** * ice_add_rule_internal - add rule for a given lookup type * @hw: pointer to the hardware structure * @recp_id: lookup type (recipe id) for which rule has to be added @@ -1328,6 +1326,11 @@ ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; mutex_lock(rule_lock); @@ -1335,7 +1338,7 @@ ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, if (new_fltr->flag & ICE_FLTR_RX) new_fltr->src = hw->port_info->lport; else if (new_fltr->flag & ICE_FLTR_TX) - new_fltr->src = f_entry->fltr_info.fwd_id.vsi_id; + new_fltr->src = f_entry->fltr_info.fwd_id.hw_vsi_id; m_entry = ice_find_rule_entry(hw, recp_id, new_fltr); if (!m_entry) { @@ -1388,12 +1391,12 @@ ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, /** * ice_rem_update_vsi_list * @hw: pointer to the hardware structure - * @vsi_id: ID of the VSI to remove + * @vsi_handle: VSI handle of the VSI to remove * @fm_list: filter management entry for which the VSI list management needs to * be done */ static enum ice_status -ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_id, +ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, struct ice_fltr_mgmt_list_entry *fm_list) { enum ice_sw_lkup_type lkup_type; @@ -1405,47 +1408,67 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_id, return ICE_ERR_PARAM; /* A rule with the VSI being removed does not exist */ - if (!test_bit(vsi_id, fm_list->vsi_list_info->vsi_map)) + if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) return ICE_ERR_DOES_NOT_EXIST; lkup_type = fm_list->fltr_info.lkup_type; vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id; - - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, true, + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, vsi_list_id, true, ice_aqc_opc_update_sw_rules, lkup_type); if (status) return status; fm_list->vsi_count--; - clear_bit(vsi_id, fm_list->vsi_list_info->vsi_map); + clear_bit(vsi_handle, fm_list->vsi_list_info->vsi_map); - if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) || - (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) { + if (fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) { + struct ice_fltr_info tmp_fltr_info = fm_list->fltr_info; struct ice_vsi_list_map_info *vsi_list_info = fm_list->vsi_list_info; - u16 rem_vsi_id; + u16 rem_vsi_handle; - rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, - ICE_MAX_VSI); - if (rem_vsi_id == ICE_MAX_VSI) + rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (!ice_is_vsi_valid(hw, rem_vsi_handle)) return ICE_ERR_OUT_OF_RANGE; - status = ice_update_vsi_list_rule(hw, &rem_vsi_id, 1, + /* Make sure VSI list is empty before removing it below */ + status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, vsi_list_id, true, ice_aqc_opc_update_sw_rules, lkup_type); if (status) return status; + tmp_fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + tmp_fltr_info.vsi_handle = rem_vsi_handle; + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr_info); + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n", + tmp_fltr_info.fwd_id.hw_vsi_id, status); + return status; + } + + fm_list->fltr_info = tmp_fltr_info; + } + + if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) || + (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) { + struct ice_vsi_list_map_info *vsi_list_info = + fm_list->vsi_list_info; + /* Remove the VSI list since it is no longer used */ status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); - if (status) + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to remove VSI list %d, error %d\n", + vsi_list_id, status); return status; - - /* Change the list entry action from VSI_LIST to VSI */ - fm_list->fltr_info.fltr_act = ICE_FWD_TO_VSI; - fm_list->fltr_info.fwd_id.vsi_id = rem_vsi_id; + } list_del(&vsi_list_info->list_entry); devm_kfree(ice_hw_to_dev(hw), vsi_list_info); @@ -1470,7 +1493,12 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; bool remove_rule = false; - u16 vsi_id; + u16 vsi_handle; + + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); rule_lock = &sw->recp_list[recp_id].filt_rule_lock; mutex_lock(rule_lock); @@ -1482,9 +1510,14 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) { remove_rule = true; + } else if (!list_elem->vsi_list_info) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; } else { - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - status = ice_rem_update_vsi_list(hw, vsi_id, list_elem); + if (list_elem->vsi_list_info->ref_cnt > 1) + list_elem->vsi_list_info->ref_cnt--; + vsi_handle = f_entry->fltr_info.vsi_handle; + status = ice_rem_update_vsi_list(hw, vsi_handle, list_elem); if (status) goto exit; /* if vsi count goes to zero after updating the vsi list */ @@ -1556,8 +1589,19 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry(m_list_itr, m_list, list_entry) { u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; + u16 vsi_handle; + u16 hw_vsi_id; m_list_itr->fltr_info.flag = ICE_FLTR_TX; + vsi_handle = m_list_itr->fltr_info.vsi_handle; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + m_list_itr->fltr_info.fwd_id.hw_vsi_id = hw_vsi_id; + /* update the src in case it is vsi num */ + if (m_list_itr->fltr_info.src_id != ICE_SRC_ID_VSI) + return ICE_ERR_PARAM; + m_list_itr->fltr_info.src = hw_vsi_id; if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || is_zero_ether_addr(add)) return ICE_ERR_PARAM; @@ -1676,57 +1720,145 @@ static enum ice_status ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { struct ice_switch_info *sw = hw->switch_info; - struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *v_list_itr; + struct ice_fltr_info *new_fltr, *cur_fltr; + enum ice_sw_lkup_type lkup_type; + u16 vsi_list_id = 0, vsi_handle; struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); new_fltr = &f_entry->fltr_info; + /* VLAN id should only be 12 bits */ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID) return ICE_ERR_PARAM; + if (new_fltr->src_id != ICE_SRC_ID_VSI) + return ICE_ERR_PARAM; + + new_fltr->src = new_fltr->fwd_id.hw_vsi_id; + lkup_type = new_fltr->lkup_type; + vsi_handle = new_fltr->vsi_handle; rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; mutex_lock(rule_lock); v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { - u16 vsi_id = ICE_VSI_INVAL_ID; - u16 vsi_list_id = 0; + struct ice_vsi_list_map_info *map_info = NULL; if (new_fltr->fltr_act == ICE_FWD_TO_VSI) { - enum ice_sw_lkup_type lkup_type = new_fltr->lkup_type; - - /* All VLAN pruning rules use a VSI list. - * Convert the action to forwarding to a VSI list. + /* All VLAN pruning rules use a VSI list. Check if + * there is already a VSI list containing VSI that we + * want to add. If found, use the same vsi_list_id for + * this new VLAN rule or else create a new list. */ - vsi_id = new_fltr->fwd_id.vsi_id; - status = ice_create_vsi_list_rule(hw, &vsi_id, 1, - &vsi_list_id, - lkup_type); - if (status) - goto exit; + map_info = ice_find_vsi_list_entry(hw, ICE_SW_LKUP_VLAN, + vsi_handle, + &vsi_list_id); + if (!map_info) { + status = ice_create_vsi_list_rule(hw, + &vsi_handle, + 1, + &vsi_list_id, + lkup_type); + if (status) + goto exit; + } + /* Convert the action to forwarding to a VSI list. */ new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; new_fltr->fwd_id.vsi_list_id = vsi_list_id; } status = ice_create_pkt_fwd_rule(hw, f_entry); - if (!status && vsi_id != ICE_VSI_INVAL_ID) { + if (!status) { v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { status = ICE_ERR_DOES_NOT_EXIST; goto exit; } - v_list_itr->vsi_list_info = - ice_create_vsi_list_map(hw, &vsi_id, 1, - vsi_list_id); + /* reuse VSI list for new rule and increment ref_cnt */ + if (map_info) { + v_list_itr->vsi_list_info = map_info; + map_info->ref_cnt++; + } else { + v_list_itr->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle, + 1, vsi_list_id); + } } + } else if (v_list_itr->vsi_list_info->ref_cnt == 1) { + /* Update existing VSI list to add new VSI id only if it used + * by one VLAN rule. + */ + cur_fltr = &v_list_itr->fltr_info; + status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr, + new_fltr); + } else { + /* If VLAN rule exists and VSI list being used by this rule is + * referenced by more than 1 VLAN rule. Then create a new VSI + * list appending previous VSI with new VSI and update existing + * VLAN rule to point to new VSI list id + */ + struct ice_fltr_info tmp_fltr; + u16 vsi_handle_arr[2]; + u16 cur_handle; - goto exit; - } + /* Current implementation only supports reusing VSI list with + * one VSI count. We should never hit below condition + */ + if (v_list_itr->vsi_count > 1 && + v_list_itr->vsi_list_info->ref_cnt > 1) { + ice_debug(hw, ICE_DBG_SW, + "Invalid configuration: Optimization to reuse VSI list with more than one VSI is not being done yet\n"); + status = ICE_ERR_CFG; + goto exit; + } + + cur_handle = + find_first_bit(v_list_itr->vsi_list_info->vsi_map, + ICE_MAX_VSI); + + /* A rule already exists with the new VSI being added */ + if (cur_handle == vsi_handle) { + status = ICE_ERR_ALREADY_EXISTS; + goto exit; + } + + vsi_handle_arr[0] = cur_handle; + vsi_handle_arr[1] = vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, + &vsi_list_id, lkup_type); + if (status) + goto exit; + + tmp_fltr = v_list_itr->fltr_info; + tmp_fltr.fltr_rule_id = v_list_itr->fltr_info.fltr_rule_id; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + /* Update the previous switch rule to a new VSI list which + * includes current VSI thats requested + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) + goto exit; + + /* before overriding VSI list map info. decrement ref_cnt of + * previous VSI list + */ + v_list_itr->vsi_list_info->ref_cnt--; - cur_fltr = &v_list_itr->fltr_info; - status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr, new_fltr); + /* now update to newly created list */ + v_list_itr->fltr_info.fwd_id.vsi_list_id = vsi_list_id; + v_list_itr->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, + vsi_list_id); + v_list_itr->vsi_count++; + } exit: mutex_unlock(rule_lock); @@ -1779,7 +1911,7 @@ ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) /** * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure - * @vsi_id: number of VSI to set as default + * @vsi_handle: VSI handle to set as default * @set: true to add the above mentioned switch rule, false to remove it * @direction: ICE_FLTR_RX or ICE_FLTR_TX * @@ -1787,13 +1919,18 @@ ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) * (represented by swid) */ enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) +ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) { struct ice_aqc_sw_rules_elem *s_rule; struct ice_fltr_info f_info; enum ice_adminq_opc opcode; enum ice_status status; u16 s_rule_size; + u16 hw_vsi_id; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE : ICE_SW_RULE_RX_TX_NO_HDR_SIZE; @@ -1806,15 +1943,17 @@ ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) f_info.lkup_type = ICE_SW_LKUP_DFLT; f_info.flag = direction; f_info.fltr_act = ICE_FWD_TO_VSI; - f_info.fwd_id.vsi_id = vsi_id; + f_info.fwd_id.hw_vsi_id = hw_vsi_id; if (f_info.flag & ICE_FLTR_RX) { f_info.src = hw->port_info->lport; + f_info.src_id = ICE_SRC_ID_LPORT; if (!set) f_info.fltr_rule_id = hw->port_info->dflt_rx_vsi_rule_id; } else if (f_info.flag & ICE_FLTR_TX) { - f_info.src = vsi_id; + f_info.src_id = ICE_SRC_ID_VSI; + f_info.src = hw_vsi_id; if (!set) f_info.fltr_rule_id = hw->port_info->dflt_tx_vsi_rule_id; @@ -1834,10 +1973,10 @@ ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) u16 index = le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); if (f_info.flag & ICE_FLTR_TX) { - hw->port_info->dflt_tx_vsi_num = vsi_id; + hw->port_info->dflt_tx_vsi_num = hw_vsi_id; hw->port_info->dflt_tx_vsi_rule_id = index; } else if (f_info.flag & ICE_FLTR_RX) { - hw->port_info->dflt_rx_vsi_num = vsi_id; + hw->port_info->dflt_rx_vsi_num = hw_vsi_id; hw->port_info->dflt_rx_vsi_rule_id = index; } } else { @@ -1871,12 +2010,12 @@ out: enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_fltr_list_entry *list_itr; + struct ice_fltr_list_entry *list_itr, *tmp; if (!m_list) return ICE_ERR_PARAM; - list_for_each_entry(list_itr, m_list, list_entry) { + list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; if (l_type != ICE_SW_LKUP_MAC) @@ -1898,12 +2037,12 @@ ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { - struct ice_fltr_list_entry *v_list_itr; + struct ice_fltr_list_entry *v_list_itr, *tmp; if (!v_list || !hw) return ICE_ERR_PARAM; - list_for_each_entry(v_list_itr, v_list, list_entry) { + list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) { enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; if (l_type != ICE_SW_LKUP_VLAN) @@ -1920,21 +2059,21 @@ ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) /** * ice_vsi_uses_fltr - Determine if given VSI uses specified filter * @fm_entry: filter entry to inspect - * @vsi_id: ID of VSI to compare with filter info + * @vsi_handle: VSI handle to compare with filter info */ static bool -ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_id) +ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) { return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && - fm_entry->fltr_info.fwd_id.vsi_id == vsi_id) || + fm_entry->fltr_info.vsi_handle == vsi_handle) || (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && - (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))); + (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); } /** * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from * @vsi_list_head: pointer to the list to add entry to * @fi: pointer to fltr_info of filter entry to copy & add * @@ -1945,7 +2084,7 @@ ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_id) * extract which VSI to remove the fltr from, and pass on that information. */ static enum ice_status -ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, +ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct list_head *vsi_list_head, struct ice_fltr_info *fi) { @@ -1966,7 +2105,8 @@ ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, * values. */ tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi_id; + tmp->fltr_info.vsi_handle = vsi_handle; + tmp->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); list_add(&tmp->list_entry, vsi_list_head); @@ -1976,9 +2116,9 @@ ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, /** * ice_add_to_vsi_fltr_list - Add VSI filters to the list * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from * @lkup_list_head: pointer to the list that has certain lookup type filters - * @vsi_list_head: pointer to the list pertaining to VSI with vsi_id + * @vsi_list_head: pointer to the list pertaining to VSI with vsi_handle * * Locates all filters in lkup_list_head that are used by the given VSI, * and adds COPIES of those entries to vsi_list_head (intended to be used @@ -1987,7 +2127,7 @@ ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, * deallocated by the caller when done with list. */ static enum ice_status -ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, +ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct list_head *lkup_list_head, struct list_head *vsi_list_head) { @@ -1995,17 +2135,17 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, enum ice_status status = 0; /* check to make sure VSI id is valid and within boundary */ - if (vsi_id >= ICE_MAX_VSI) + if (!ice_is_vsi_valid(hw, vsi_handle)) return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { struct ice_fltr_info *fi; fi = &fm_entry->fltr_info; - if (!ice_vsi_uses_fltr(fm_entry, vsi_id)) + if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle)) continue; - status = ice_add_entry_to_vsi_fltr_list(hw, vsi_id, + status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle, vsi_list_head, fi); if (status) return status; @@ -2016,11 +2156,11 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, /** * ice_remove_vsi_lkup_fltr - Remove lookup type filters for a VSI * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from * @lkup: switch rule filter lookup type */ static void -ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, +ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, enum ice_sw_lkup_type lkup) { struct ice_switch_info *sw = hw->switch_info; @@ -2035,7 +2175,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, rule_lock = &sw->recp_list[lkup].filt_rule_lock; rule_head = &sw->recp_list[lkup].filt_rules; mutex_lock(rule_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, rule_head, + status = ice_add_to_vsi_fltr_list(hw, vsi_handle, rule_head, &remove_list_head); mutex_unlock(rule_lock); if (status) @@ -2069,102 +2209,121 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, /** * ice_remove_vsi_fltr - Remove all filters for a VSI * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from */ -void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id) +void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle) { - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC_VLAN); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_VLAN); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_DFLT); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE_MAC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC_VLAN); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC_VLAN); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_VLAN); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_DFLT); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE_MAC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC_VLAN); } /** - * ice_replay_fltr - Replay all the filters stored by a specific list head + * ice_replay_vsi_fltr - Replay filters for requested VSI * @hw: pointer to the hardware structure - * @list_head: list for which filters needs to be replayed + * @vsi_handle: driver VSI handle * @recp_id: Recipe id for which rules need to be replayed + * @list_head: list for which filters need to be replayed + * + * Replays the filter of recipe recp_id for a VSI represented via vsi_handle. + * It is required to pass valid VSI handle. */ static enum ice_status -ice_replay_fltr(struct ice_hw *hw, u8 recp_id, struct list_head *list_head) +ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, + struct list_head *list_head) { struct ice_fltr_mgmt_list_entry *itr; - struct list_head l_head; enum ice_status status = 0; + u16 hw_vsi_id; if (list_empty(list_head)) return status; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - /* Move entries from the given list_head to a temporary l_head so that - * they can be replayed. Otherwise when trying to re-add the same - * filter, the function will return already exists - */ - list_replace_init(list_head, &l_head); - - /* Mark the given list_head empty by reinitializing it so filters - * could be added again by *handler - */ - list_for_each_entry(itr, &l_head, list_entry) { + list_for_each_entry(itr, list_head, list_entry) { struct ice_fltr_list_entry f_entry; f_entry.fltr_info = itr->fltr_info; - if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN) { + if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN && + itr->fltr_info.vsi_handle == vsi_handle) { + /* update the src in case it is vsi num */ + if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI) + f_entry.fltr_info.src = hw_vsi_id; status = ice_add_rule_internal(hw, recp_id, &f_entry); if (status) goto end; continue; } - - /* Add a filter per vsi separately */ - while (1) { - u16 vsi; - - vsi = find_first_bit(itr->vsi_list_info->vsi_map, - ICE_MAX_VSI); - if (vsi == ICE_MAX_VSI) - break; - - clear_bit(vsi, itr->vsi_list_info->vsi_map); - f_entry.fltr_info.fwd_id.vsi_id = vsi; - f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; - if (recp_id == ICE_SW_LKUP_VLAN) - status = ice_add_vlan_internal(hw, &f_entry); - else - status = ice_add_rule_internal(hw, recp_id, - &f_entry); - if (status) - goto end; - } + if (!itr->vsi_list_info || + !test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) + continue; + /* Clearing it so that the logic can add it back */ + clear_bit(vsi_handle, itr->vsi_list_info->vsi_map); + f_entry.fltr_info.vsi_handle = vsi_handle; + f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; + /* update the src in case it is vsi num */ + if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI) + f_entry.fltr_info.src = hw_vsi_id; + if (recp_id == ICE_SW_LKUP_VLAN) + status = ice_add_vlan_internal(hw, &f_entry); + else + status = ice_add_rule_internal(hw, recp_id, &f_entry); + if (status) + goto end; } end: - /* Clear the filter management list */ - ice_rem_sw_rule_info(hw, &l_head); return status; } /** - * ice_replay_all_fltr - replay all filters stored in bookkeeping lists + * ice_replay_vsi_all_fltr - replay all filters stored in bookkeeping lists * @hw: pointer to the hardware structure + * @vsi_handle: driver VSI handle * - * NOTE: This function does not clean up partially added filters on error. - * It is up to caller of the function to issue a reset or fail early. + * Replays filters for requested VSI via vsi_handle. */ -enum ice_status ice_replay_all_fltr(struct ice_hw *hw) +enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle) { struct ice_switch_info *sw = hw->switch_info; enum ice_status status = 0; u8 i; for (i = 0; i < ICE_SW_LKUP_LAST; i++) { - struct list_head *head = &sw->recp_list[i].filt_rules; + struct list_head *head; - status = ice_replay_fltr(hw, i, head); + head = &sw->recp_list[i].filt_replay_rules; + status = ice_replay_vsi_fltr(hw, vsi_handle, i, head); if (status) return status; } return status; } + +/** + * ice_rm_all_sw_replay_rule_info - deletes filter replay rules + * @hw: pointer to the hw struct + * + * Deletes the filter replay rules. + */ +void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + if (!sw) + return; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + if (!list_empty(&sw->recp_list[i].filt_replay_rules)) { + struct list_head *l_head; + + l_head = &sw->recp_list[i].filt_replay_rules; + ice_rem_sw_rule_info(hw, l_head); + } + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 646389ca1238..b88d96a1ef69 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -17,7 +17,9 @@ struct ice_vsi_ctx { u16 vsis_unallocated; u16 flags; struct ice_aqc_vsi_props info; + struct ice_sched_vsi_info sched; u8 alloc_from_pool; + u8 vf_num; }; enum ice_sw_fwd_act_type { @@ -42,6 +44,14 @@ enum ice_sw_lkup_type { ICE_SW_LKUP_LAST }; +/* type of filter src id */ +enum ice_src_id { + ICE_SRC_ID_UNKNOWN = 0, + ICE_SRC_ID_VSI, + ICE_SRC_ID_QUEUE, + ICE_SRC_ID_LPORT, +}; + struct ice_fltr_info { /* Look up information: how to look up packet */ enum ice_sw_lkup_type lkup_type; @@ -56,6 +66,7 @@ struct ice_fltr_info { /* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */ u16 src; + enum ice_src_id src_id; union { struct { @@ -77,7 +88,10 @@ struct ice_fltr_info { u16 ethertype; u8 mac_addr[ETH_ALEN]; /* optional */ } ethertype_mac; - } l_data; + } l_data; /* Make sure to zero out the memory of l_data before using + * it or only set the data associated with lookup match + * rest everything should be zero + */ /* Depending on filter action */ union { @@ -85,12 +99,16 @@ struct ice_fltr_info { * queue id in case of ICE_FWD_TO_QGRP. */ u16 q_id:11; - u16 vsi_id:10; + u16 hw_vsi_id:10; u16 vsi_list_id:10; } fwd_id; + /* Sw VSI handle */ + u16 vsi_handle; + /* Set to num_queues if action is ICE_FWD_TO_QGRP. This field - * determines the range of queues the packet needs to be forwarded to + * determines the range of queues the packet needs to be forwarded to. + * Note that qgrp_size must be set to a power of 2. */ u8 qgrp_size; @@ -109,6 +127,7 @@ struct ice_sw_recipe { /* List of type ice_fltr_mgmt_list_entry */ struct list_head filt_rules; + struct list_head filt_replay_rules; /* linked list of type recipe_list_entry */ struct list_head rg_list; @@ -129,6 +148,8 @@ struct ice_vsi_list_map_info { struct list_head list_entry; DECLARE_BITMAP(vsi_map, ICE_MAX_VSI); u16 vsi_list_id; + /* counter to track how many rules are reusing this VSI list */ + u16 ref_cnt; }; struct ice_fltr_list_entry { @@ -140,7 +161,8 @@ struct ice_fltr_list_entry { /* This defines an entry in the list that maintains MAC or VLAN membership * to HW list mapping, since multiple VSIs can subscribe to the same MAC or * VLAN. As an optimization the VSI list should be created only when a - * second VSI becomes a subscriber to the VLAN address. + * second VSI becomes a subscriber to the same MAC address. VSI lists are always + * used for VLAN membership. */ struct ice_fltr_mgmt_list_entry { /* back pointer to VSI list id to VSI list mapping */ @@ -158,28 +180,33 @@ struct ice_fltr_mgmt_list_entry { /* VSI related commands */ enum ice_status -ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - struct ice_sq_cd *cd); -enum ice_status ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); enum ice_status ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, bool keep_vsi_alloc, struct ice_sq_cd *cd); +enum ice_status +ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd); +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); +struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id); +void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction); - -enum ice_status ice_replay_all_fltr(struct ice_hw *hw); +ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction); enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); +u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); + +enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); +void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 839fd9ff6043..1d0f58bd389b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -104,10 +104,17 @@ enum ice_rx_dtype { #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 #define ICE_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define ICE_ITR_8K 0x003E +#define ICE_ITR_8K 125 +#define ICE_ITR_20K 50 +#define ICE_DFLT_TX_ITR ICE_ITR_20K +#define ICE_DFLT_RX_ITR ICE_ITR_20K +/* apply ITR granularity translation to program the register. itr_gran is either + * 2 or 4 usecs so we need to divide by 2 first then shift by that value + */ +#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> \ + ((itr_gran) / 2)) -/* apply ITR HW granularity translation to program the HW registers */ -#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> (itr_gran)) +#define ICE_DFLT_INTRL 0 /* Legacy or Advanced Mode Queue */ #define ICE_TX_ADVANCED 0 @@ -129,14 +136,6 @@ struct ice_ring { u16 q_index; /* Queue number of ring */ u32 txq_teid; /* Added Tx queue TEID */ - /* high bit set means dynamic, use accessor routines to read/write. - * hardware supports 2us/1us resolution for the ITR registers. - * these values always store the USER setting, and must be converted - * before programming to a register. - */ - u16 rx_itr_setting; - u16 tx_itr_setting; - u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -173,6 +172,7 @@ struct ice_ring_container { unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_pkts; /* total packets processed this int */ enum ice_latency_range latency_range; + int itr_idx; /* index in the interrupt vector */ u16 itr; }; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index e681804be4d4..12f9432abf11 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,9 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) return test_bit(tc, (unsigned long *)&bitmap); } +/* Driver always calls main vsi_handle first */ +#define ICE_MAIN_VSI_HANDLE 0 + /* debug masks - set these bits in hw->debug_mask to control output */ #define ICE_DBG_INIT BIT_ULL(1) #define ICE_DBG_LINK BIT_ULL(4) @@ -81,6 +84,7 @@ enum ice_media_type { enum ice_vsi_type { ICE_VSI_PF = 0, + ICE_VSI_VF, }; struct ice_link_status { @@ -100,6 +104,15 @@ struct ice_link_status { u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE]; }; +/* Different reset sources for which a disable queue AQ call has to be made in + * order to clean the TX scheduler as a part of the reset + */ +enum ice_disq_rst_src { + ICE_NO_RESET = 0, + ICE_VM_RESET, + ICE_VF_RESET, +}; + /* PHY info such as phy_type, etc... */ struct ice_phy_info { struct ice_link_status link_info; @@ -124,6 +137,9 @@ struct ice_hw_common_caps { /* Max MTU for function or device */ u16 max_mtu; + /* Virtualization support */ + u8 sr_iov_1_1; /* SR-IOV enabled */ + /* RSS related capabilities */ u16 rss_table_size; /* 512 for PFs and 64 for VFs */ u8 rss_table_entry_width; /* RSS Entry width in bits */ @@ -132,12 +148,15 @@ struct ice_hw_common_caps { /* Function specific capabilities */ struct ice_hw_func_caps { struct ice_hw_common_caps common_cap; + u32 num_allocd_vfs; /* Number of allocated VFs */ + u32 vf_base_id; /* Logical ID of the first VF */ u32 guaranteed_num_vsi; }; /* Device wide capabilities */ struct ice_hw_dev_caps { struct ice_hw_common_caps common_cap; + u32 num_vfs_exposed; /* Total number of VFs exposed */ u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ }; @@ -147,12 +166,18 @@ struct ice_mac_info { u8 perm_addr[ETH_ALEN]; }; -/* Various RESET request, These are not tied with HW reset types */ +/* Reset types used to determine which kind of reset was requested. These + * defines match what the RESET_TYPE field of the GLGEN_RSTAT register. + * ICE_RESET_PFR does not match any RESET_TYPE field in the GLGEN_RSTAT register + * because its reset source is different than the other types listed. + */ enum ice_reset_req { + ICE_RESET_POR = 0, ICE_RESET_INVAL = 0, - ICE_RESET_PFR = 1, - ICE_RESET_CORER = 2, - ICE_RESET_GLOBR = 3, + ICE_RESET_CORER = 1, + ICE_RESET_GLOBR = 2, + ICE_RESET_EMPR = 3, + ICE_RESET_PFR = 4, }; /* Bus parameters */ @@ -186,7 +211,7 @@ struct ice_sched_node { struct ice_sched_node **children; struct ice_aqc_txsched_elem_data info; u32 agg_id; /* aggregator group id */ - u16 vsi_id; + u16 vsi_handle; u8 in_use; /* suspended or in use */ u8 tx_sched_layer; /* Logical Layer (1-9) */ u8 num_children; @@ -245,8 +270,6 @@ struct ice_port_info { struct ice_mac_info mac; struct ice_phy_info phy; struct mutex sched_lock; /* protect access to TXSched tree */ - struct ice_sched_tx_policy sched_policy; - struct list_head vsi_info_list; struct list_head agg_list; /* lists all aggregator */ u8 lport; #define ICE_LPORT_MASK 0xff @@ -314,6 +337,7 @@ struct ice_hw { /* Control Queue info */ struct ice_ctl_q_info adminq; + struct ice_ctl_q_info mailboxq; u8 api_branch; /* API branch version */ u8 api_maj_ver; /* API major version */ @@ -326,16 +350,26 @@ struct ice_hw { u32 fw_build; /* firmware build number */ struct ice_fw_log_cfg fw_log; - /* minimum allowed value for different speeds */ -#define ICE_ITR_GRAN_MIN_200 1 -#define ICE_ITR_GRAN_MIN_100 1 -#define ICE_ITR_GRAN_MIN_50 2 -#define ICE_ITR_GRAN_MIN_25 4 + +/* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL + * register. Used for determining the itr/intrl granularity during + * initialization. + */ +#define ICE_MAX_AGG_BW_200G 0x0 +#define ICE_MAX_AGG_BW_100G 0X1 +#define ICE_MAX_AGG_BW_50G 0x2 +#define ICE_MAX_AGG_BW_25G 0x3 + /* ITR granularity for different speeds */ +#define ICE_ITR_GRAN_ABOVE_25 2 +#define ICE_ITR_GRAN_MAX_25 4 /* ITR granularity in 1 us */ - u8 itr_gran_200; - u8 itr_gran_100; - u8 itr_gran_50; - u8 itr_gran_25; + u8 itr_gran; + /* INTRL granularity for different speeds */ +#define ICE_INTRL_GRAN_ABOVE_25 4 +#define ICE_INTRL_GRAN_MAX_25 8 + /* INTRL granularity in 1 us */ + u8 intrl_gran; + u8 ucast_shared; /* true if VSIs can share unicast addr */ }; @@ -409,4 +443,7 @@ struct ice_hw_port_stats { #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 #define ICE_SR_WORDS_IN_1KB 512 +/* Hash redirection LUT for VSI - maximum array size */ +#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4) + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c new file mode 100644 index 000000000000..c25e486706f3 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -0,0 +1,2668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +/** + * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF + * @pf: pointer to the PF structure + * @v_opcode: operation code + * @v_retval: return value + * @msg: pointer to the msg buffer + * @msglen: msg length + */ +static void +ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf = pf->vf; + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++, vf++) { + /* Not all vfs are enabled so skip the ones that are not */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + continue; + + /* Ignore return value on purpose - a given VF may fail, but + * we need to keep going and send to all of them + */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg, + msglen, NULL); + } +} + +/** + * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_* + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + int ice_link_speed, bool link_up) +{ + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { + pfe->event_data.link_event_adv.link_status = link_up; + /* Speed in Mbps */ + pfe->event_data.link_event_adv.link_speed = + ice_conv_link_speed_to_virtchnl(true, ice_link_speed); + } else { + pfe->event_data.link_event.link_status = link_up; + /* Legacy method for virtchnl link speeds */ + pfe->event_data.link_event.link_speed = + (enum virtchnl_link_speed) + ice_conv_link_speed_to_virtchnl(false, ice_link_speed); + } +} + +/** + * ice_set_pfe_link_forced - Force the virtchnl_pf_event link speed/status + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + bool link_up) +{ + u16 link_speed; + + if (link_up) + link_speed = ICE_AQ_LINK_SPEED_40GB; + else + link_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + + ice_set_pfe_link(vf, pfe, link_speed, link_up); +} + +/** + * ice_vc_notify_vf_link_state - Inform a VF of link status + * @vf: pointer to the VF structure + * + * send a link status message to a single VF + */ +static void ice_vc_notify_vf_link_state(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + + hw = &pf->hw; + ls = &hw->port_info->phy.link_info; + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info & + ICE_AQ_LINK_UP); + + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); +} + +/** + * ice_get_vf_vector - get VF interrupt vector register offset + * @vf_msix: number of MSIx vector per VF on a PF + * @vf_id: VF identifier + * @i: index of MSIx vector + */ +static u32 ice_get_vf_vector(int vf_msix, int vf_id, int i) +{ + return ((i == 0) ? VFINT_DYN_CTLN(vf_id) : + VFINT_DYN_CTLN(((vf_msix - 1) * (vf_id)) + (i - 1))); +} + +/** + * ice_free_vf_res - Free a VF's resources + * @vf: pointer to the VF info + */ +static void ice_free_vf_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + int i, pf_vf_msix; + + /* First, disable VF's configuration API to prevent OS from + * accessing the VF's VSI after it's freed or invalidated. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* free vsi & disconnect it from the parent uplink */ + if (vf->lan_vsi_idx) { + ice_vsi_release(pf->vsi[vf->lan_vsi_idx]); + vf->lan_vsi_idx = 0; + vf->lan_vsi_num = 0; + vf->num_mac = 0; + } + + pf_vf_msix = pf->num_vf_msix; + /* Disable interrupts so that VF starts in a known state */ + for (i = 0; i < pf_vf_msix; i++) { + u32 reg_idx; + + reg_idx = ice_get_vf_vector(pf_vf_msix, vf->vf_id, i); + wr32(&pf->hw, reg_idx, VFINT_DYN_CTLN_CLEARPBA_M); + ice_flush(&pf->hw); + } + /* reset some of the state variables keeping track of the resources */ + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); +} + +/***********************enable_vf routines*****************************/ + +/** + * ice_dis_vf_mappings + * @vf: pointer to the VF structure + */ +static void ice_dis_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + + wr32(hw, VPINT_ALLOC(vf->vf_id), 0); + + first = vf->first_vector_idx; + last = first + pf->num_vf_msix - 1; + for (v = first; v <= last; v++) { + u32 reg; + + reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & + GLINT_VECT2FUNC_IS_PF_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); +} + +/** + * ice_free_vfs - Free all VFs + * @pf: pointer to the PF structure + */ +void ice_free_vfs(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int tmp, i; + + if (!pf->vf) + return; + + while (test_and_set_bit(__ICE_VF_DIS, pf->state)) + usleep_range(1000, 2000); + + /* Avoid wait time by stopping all VFs at the same time */ + for (i = 0; i < pf->num_alloc_vfs; i++) { + if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states)) + continue; + + /* stop rings without wait time */ + ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx], + ICE_NO_RESET, i); + ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]); + + clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); + } + + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + + tmp = pf->num_alloc_vfs; + pf->num_vf_qps = 0; + pf->num_alloc_vfs = 0; + for (i = 0; i < tmp; i++) { + if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + /* disable VF qp mappings */ + ice_dis_vf_mappings(&pf->vf[i]); + + /* Set this state so that assigned VF vectors can be + * reclaimed by PF for reuse in ice_vsi_release(). No + * need to clear this bit since pf->vf array is being + * freed anyways after this for loop + */ + set_bit(ICE_VF_STATE_CFG_INTR, pf->vf[i].vf_states); + ice_free_vf_res(&pf->vf[i]); + } + } + + devm_kfree(&pf->pdev->dev, pf->vf); + pf->vf = NULL; + + /* This check is for when the driver is unloaded while VFs are + * assigned. Setting the number of VFs to 0 through sysfs is caught + * before this function ever gets called. + */ + if (!pci_vfs_assigned(pf->pdev)) { + int vf_id; + + /* Acknowledge VFLR for all VFs. Without this, VFs will fail to + * work correctly when SR-IOV gets re-enabled. + */ + for (vf_id = 0; vf_id < tmp; vf_id++) { + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + } + } + clear_bit(__ICE_VF_DIS, pf->state); + clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); +} + +/** + * ice_trigger_vf_reset - Reset a VF on HW + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. + */ +static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + u32 reg, reg_idx, bit_idx; + struct ice_hw *hw; + int vf_abs_id, i; + + hw = &pf->hw; + vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* Inform VF that it is no longer active, as a warning */ + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * in ice_alloc_vf_res(), when it's safe again to access VF's VSI. + * It's normally disabled in ice_free_vf_res(), but it's safer + * to do it earlier to give some time to finish to any VF config + * functions that may still be running at this point. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* In the case of a VFLR, the HW has already reset the VF and we + * just need to clean up, so don't hit the VFRTRIG register. + */ + if (!is_vflr) { + /* reset VF using VPGEN_VFRTRIG reg */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg |= VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + } + /* clear the VFLR bit in GLGEN_VFLRSTAT */ + reg_idx = (vf_abs_id) / 32; + bit_idx = (vf_abs_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + ice_flush(hw); + + wr32(hw, PF_PCI_CIAA, + VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); + for (i = 0; i < 100; i++) { + reg = rd32(hw, PF_PCI_CIAD); + if ((reg & VF_TRANS_PENDING_M) != 0) + dev_err(&pf->pdev->dev, + "VF %d PCI transactions stuck\n", vf->vf_id); + udelay(1); + } +} + +/** + * ice_vsi_set_pvid - Set port VLAN id for the VSI + * @vsi: the VSI being changed + * @vid: the VLAN id to set as a PVID + */ +static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ICE_AQ_VSI_PVLAN_INSERT_PVID | + ICE_AQ_VSI_VLAN_EMOD_STR; + ctxt.info.pvid = cpu_to_le16(vid); + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_info(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.pvid = ctxt.info.pvid; + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_kill_pvid - Remove port VLAN id from the VSI + * @vsi: the VSI being changed + */ +static int ice_vsi_kill_pvid(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + + if (ice_vsi_manage_vlan_stripping(vsi, false)) { + dev_err(&pf->pdev->dev, "Error removing Port VLAN on VSI %i\n", + vsi->vsi_num); + return -ENODEV; + } + + vsi->info.pvid = 0; + return 0; +} + +/** + * ice_vf_vsi_setup - Set up a VF VSI + * @pf: board private structure + * @pi: pointer to the port_info instance + * @vf_id: defines VF id to which this VSI connects. + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi * +ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_VF, vf_id); +} + +/** + * ice_alloc_vsi_res - Setup VF VSI and its resources + * @vf: pointer to the VF structure + * + * Returns 0 on success, negative value on failure + */ +static int ice_alloc_vsi_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + LIST_HEAD(tmp_add_list); + u8 broadcast[ETH_ALEN]; + struct ice_vsi *vsi; + int status = 0; + + vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id); + + if (!vsi) { + dev_err(&pf->pdev->dev, "Failed to create VF VSI\n"); + return -ENOMEM; + } + + vf->lan_vsi_idx = vsi->idx; + vf->lan_vsi_num = vsi->vsi_num; + + /* first vector index is the VFs OICR index */ + vf->first_vector_idx = vsi->hw_base_vector; + /* Since hw_base_vector holds the vector where data queue interrupts + * starts, increment by 1 since VFs allocated vectors include OICR intr + * as well. + */ + vsi->hw_base_vector += 1; + + /* Check if port VLAN exist before, and restore it accordingly */ + if (vf->port_vlan_id) + ice_vsi_set_pvid(vsi, vf->port_vlan_id); + + eth_broadcast_addr(broadcast); + + status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); + if (status) + goto ice_alloc_vsi_res_exit; + + if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) { + status = ice_add_mac_to_list(vsi, &tmp_add_list, + vf->dflt_lan_addr.addr); + if (status) + goto ice_alloc_vsi_res_exit; + } + + status = ice_add_mac(&pf->hw, &tmp_add_list); + if (status) + dev_err(&pf->pdev->dev, "could not add mac filters\n"); + + /* Clear this bit after VF initialization since we shouldn't reclaim + * and reassign interrupts for synchronous or asynchronous VFR events. + * We don't want to reconfigure interrupts since AVF driver doesn't + * expect vector assignment to be changed unless there is a request for + * more vectors. + */ + clear_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states); +ice_alloc_vsi_res_exit: + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; +} + +/** + * ice_alloc_vf_res - Allocate VF resources + * @vf: pointer to the VF structure + */ +static int ice_alloc_vf_res(struct ice_vf *vf) +{ + int status; + + /* setup VF VSI and necessary resources */ + status = ice_alloc_vsi_res(vf); + if (status) + goto ice_alloc_vf_res_exit; + + if (vf->trusted) + set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + else + clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + + /* VF is now completely initialized */ + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + + return status; + +ice_alloc_vf_res_exit: + ice_free_vf_res(vf); + return status; +} + +/** + * ice_ena_vf_mappings + * @vf: pointer to the VF structure + * + * Enable VF vectors and queues allocation by writing the details into + * respective registers. + */ +static void ice_ena_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + int abs_vf_id; + u32 reg; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + first = vf->first_vector_idx; + last = (first + pf->num_vf_msix) - 1; + abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* VF Vector allocation */ + reg = (((first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) | + ((last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) | + VPINT_ALLOC_VALID_M); + wr32(hw, VPINT_ALLOC(vf->vf_id), reg); + + /* map the interrupts to its functions */ + for (v = first; v <= last; v++) { + reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & + GLINT_VECT2FUNC_VF_NUM_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + /* VF Tx queues allocation */ + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { + wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), + VPLAN_TXQ_MAPENA_TX_ENA_M); + /* set the VF PF Tx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & + VPLAN_TX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & + VPLAN_TX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + } + + /* VF Rx queues allocation */ + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { + wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), + VPLAN_RXQ_MAPENA_RX_ENA_M); + /* set the VF PF Rx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & + VPLAN_RX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & + VPLAN_RX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); + } +} + +/** + * ice_determine_res + * @pf: pointer to the PF structure + * @avail_res: available resources in the PF structure + * @max_res: maximum resources that can be given per VF + * @min_res: minimum resources that can be given per VF + * + * Returns non-zero value if resources (queues/vectors) are available or + * returns zero if PF cannot accommodate for all num_alloc_vfs. + */ +static int +ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res) +{ + bool checked_min_res = false; + int res; + + /* start by checking if PF can assign max number of resources for + * all num_alloc_vfs. + * if yes, return number per VF + * If no, divide by 2 and roundup, check again + * repeat the loop till we reach a point where even minimum resources + * are not available, in that case return 0 + */ + res = max_res; + while ((res >= min_res) && !checked_min_res) { + int num_all_res; + + num_all_res = pf->num_alloc_vfs * res; + if (num_all_res <= avail_res) + return res; + + if (res == min_res) + checked_min_res = true; + + res = DIV_ROUND_UP(res, 2); + } + return 0; +} + +/** + * ice_check_avail_res - check if vectors and queues are available + * @pf: pointer to the PF structure + * + * This function is where we calculate actual number of resources for VF VSIs, + * we don't reserve ahead of time during probe. Returns success if vectors and + * queues resources are available, otherwise returns error code + */ +static int ice_check_avail_res(struct ice_pf *pf) +{ + u16 num_msix, num_txq, num_rxq; + + if (!pf->num_alloc_vfs) + return -EINVAL; + + /* Grab from HW interrupts common pool + * Note: By the time the user decides it needs more vectors in a VF + * its already too late since one must decide this prior to creating the + * VF interface. So the best we can do is take a guess as to what the + * user might want. + * + * We have two policies for vector allocation: + * 1. if num_alloc_vfs is from 1 to 16, then we consider this as small + * number of NFV VFs used for NFV appliances, since this is a special + * case, we try to assign maximum vectors per VF (65) as much as + * possible, based on determine_resources algorithm. + * 2. if num_alloc_vfs is from 17 to 256, then its large number of + * regular VFs which are not used for any special purpose. Hence try to + * grab default interrupt vectors (5 as supported by AVF driver). + */ + if (pf->num_alloc_vfs <= 16) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_MAX_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else if (pf->num_alloc_vfs <= ICE_MAX_VF_COUNT) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_DFLT_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else { + dev_err(&pf->pdev->dev, + "Number of VFs %d exceeds max VF count %d\n", + pf->num_alloc_vfs, ICE_MAX_VF_COUNT); + return -EIO; + } + + if (!num_msix) + return -EIO; + + /* Grab from the common pool + * start by requesting Default queues (4 as supported by AVF driver), + * Note that, the main difference between queues and vectors is, latter + * can only be reserved at init time but queues can be requested by VF + * at runtime through Virtchnl, that is the reason we start by reserving + * few queues. + */ + num_txq = ice_determine_res(pf, pf->q_left_tx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + num_rxq = ice_determine_res(pf, pf->q_left_rx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + if (!num_txq || !num_rxq) + return -EIO; + + /* since AVF driver works with only queue pairs which means, it expects + * to have equal number of Rx and Tx queues, so take the minimum of + * available Tx or Rx queues + */ + pf->num_vf_qps = min_t(int, num_txq, num_rxq); + pf->num_vf_msix = num_msix; + + return 0; +} + +/** + * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset + * @vf: pointer to the VF structure + * + * Cleanup a VF after the hardware reset is finished. Expects the caller to + * have verified whether the reset is finished properly, and ensure the + * minimum amount of wait time has passed. Reallocate VF resources back to make + * VF state active + */ +static void ice_cleanup_and_realloc_vf(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + u32 reg; + + hw = &pf->hw; + + /* PF software completes the flow by notifying VF that reset flow is + * completed. This is done by enabling hardware by clearing the reset + * bit in the VPGEN_VFRTRIG reg and setting VFR_STATE in the VFGEN_RSTAT + * register to VFR completed (done at the end of this function) + * By doing this we allow HW to access VF memory at any point. If we + * did it any sooner, HW could access memory while it was being freed + * in ice_free_vf_res(), causing an IOMMU fault. + * + * On the other hand, this needs to be done ASAP, because the VF driver + * is waiting for this to happen and may report a timeout. It's + * harmless, but it gets logged into Guest OS kernel log, so best avoid + * it. + */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg &= ~VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + + /* reallocate VF resources to finish resetting the VSI state */ + if (!ice_alloc_vf_res(vf)) { + ice_ena_vf_mappings(vf); + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + vf->num_vlan = 0; + } + + /* Tell the VF driver the reset is done. This needs to be done only + * after VF has been fully initialized, because the VF driver may + * request resources immediately after setting this flag. + */ + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); +} + +/** + * ice_reset_all_vfs - reset all allocated VFs in one go + * @pf: pointer to the PF structure + * @is_vflr: true if VFLR was issued, false if not + * + * First, tell the hardware to reset each VF, then do all the waiting in one + * chunk, and finally finish restoring each VF after the wait. This is useful + * during PF routines which need to reset all VFs, as otherwise it must perform + * these resets in a serialized fashion. + * + * Returns true if any VFs were reset, and false otherwise. + */ +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) +{ + struct ice_hw *hw = &pf->hw; + int v, i; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!pf->num_alloc_vfs) + return false; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + /* Begin reset on all VFs at once */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_trigger_vf_reset(&pf->vf[v], is_vflr); + + /* Call Disable LAN Tx queue AQ call with VFR bit set and 0 + * queues to inform Firmware about VF reset. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_dis_vsi_txq(pf->vsi[0]->port_info, 0, NULL, NULL, + ICE_VF_RESET, v, NULL); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in + * sequence to make sure that it has completed. We'll keep track of + * the VFs using a simple iterator that increments once that VF has + * finished resetting. + */ + for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + usleep_range(10000, 20000); + + /* Check each VF in sequence */ + while (v < pf->num_alloc_vfs) { + struct ice_vf *vf = &pf->vf[v]; + u32 reg; + + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & VPGEN_VFRSTAT_VFRD_M)) + break; + + /* If the current VF has finished resetting, move on + * to the next VF in sequence. + */ + v++; + } + } + + /* Display a warning if at least one VF didn't manage to reset in + * time, but continue on with the operation. + */ + if (v < pf->num_alloc_vfs) + dev_warn(&pf->pdev->dev, "VF reset check timeout\n"); + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_free_vf_res(&pf->vf[v]); + + if (ice_check_avail_res(pf)) { + dev_err(&pf->pdev->dev, + "Cannot allocate VF resources, try with fewer number of VFs\n"); + return false; + } + + /* Finish the reset on each VF */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_cleanup_and_realloc_vf(&pf->vf[v]); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_reset_vf - Reset a particular VF + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Returns true if the VF is reset, false otherwise. + */ +static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw = &pf->hw; + bool rsd = false; + u32 reg; + int i; + + /* If the VFs have been disabled, this means something else is + * resetting the VF, so we shouldn't continue. + */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + ice_trigger_vf_reset(vf, is_vflr); + + if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET, + vf->vf_id); + ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]); + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + } else { + /* Call Disable LAN Tx queue AQ call even when queues are not + * enabled. This is needed for successful completiom of VFR + */ + ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0, + NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL); + } + + /* poll VPGEN_VFRSTAT reg to make sure + * that reset is complete + */ + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. + */ + usleep_range(10000, 20000); + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (reg & VPGEN_VFRSTAT_VFRD_M) { + rsd = true; + break; + } + } + + /* Display a warning if VF didn't manage to reset in time, but need to + * continue on with the operation. + */ + if (!rsd) + dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + vf->vf_id); + + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + ice_free_vf_res(vf); + + ice_cleanup_and_realloc_vf(vf); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_vc_notify_link_state - Inform all VFs on a PF of link status + * @pf: pointer to the PF structure + */ +void ice_vc_notify_link_state(struct ice_pf *pf) +{ + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++) + ice_vc_notify_vf_link_state(&pf->vf[i]); +} + +/** + * ice_vc_notify_reset - Send pending reset message to all VFs + * @pf: pointer to the PF structure + * + * indicate a pending reset to all VFs on a given PF + */ +void ice_vc_notify_reset(struct ice_pf *pf) +{ + struct virtchnl_pf_event pfe; + + if (!pf->num_alloc_vfs) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, ICE_SUCCESS, + (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); +} + +/** + * ice_vc_notify_vf_reset - Notify VF of a reset event + * @vf: pointer to the VF structure + */ +static void ice_vc_notify_vf_reset(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return; + + /* verify if the VF is in either init or active before proceeding */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, + (u8 *)&pfe, sizeof(pfe), NULL); +} + +/** + * ice_alloc_vfs - Allocate and set up VFs resources + * @pf: pointer to the PF structure + * @num_alloc_vfs: number of VFs to allocate + */ +static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vfs; + int i, ret; + + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ + wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx), + ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); + + ice_flush(hw); + + ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); + if (ret) { + pf->num_alloc_vfs = 0; + goto err_unroll_intr; + } + /* allocate memory */ + vfs = devm_kcalloc(&pf->pdev->dev, num_alloc_vfs, sizeof(*vfs), + GFP_KERNEL); + if (!vfs) { + ret = -ENOMEM; + goto err_unroll_sriov; + } + pf->vf = vfs; + + /* apply default profile */ + for (i = 0; i < num_alloc_vfs; i++) { + vfs[i].pf = pf; + vfs[i].vf_sw_id = pf->first_sw; + vfs[i].vf_id = i; + + /* assign default capabilities */ + set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); + vfs[i].spoofchk = true; + + /* Set this state so that PF driver does VF vector assignment */ + set_bit(ICE_VF_STATE_CFG_INTR, vfs[i].vf_states); + } + pf->num_alloc_vfs = num_alloc_vfs; + + /* VF resources get allocated during reset */ + if (!ice_reset_all_vfs(pf, false)) + goto err_unroll_sriov; + + goto err_unroll_intr; + +err_unroll_sriov: + pci_disable_sriov(pf->pdev); +err_unroll_intr: + /* rearm interrupts here */ + ice_irq_dynamic_ena(hw, NULL, NULL); + return ret; +} + +/** + * ice_pf_state_is_nominal - checks the pf for nominal state + * @pf: pointer to pf to check + * + * Check the PF's state for a collection of bits that would indicate + * the PF is in a state that would inhibit normal operation for + * driver functionality. + * + * Returns true if PF is in a nominal state. + * Returns false otherwise + */ +static bool ice_pf_state_is_nominal(struct ice_pf *pf) +{ + DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; + + if (!pf) + return false; + + bitmap_set(check_bits, 0, __ICE_STATE_NOMINAL_CHECK_BITS); + if (bitmap_intersects(pf->state, check_bits, __ICE_STATE_NBITS)) + return false; + + return true; +} + +/** + * ice_pci_sriov_ena - Enable or change number of VFs + * @pf: pointer to the PF structure + * @num_vfs: number of VFs to allocate + */ +static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs) +{ + int pre_existing_vfs = pci_num_vf(pf->pdev); + struct device *dev = &pf->pdev->dev; + int err; + + if (!ice_pf_state_is_nominal(pf)) { + dev_err(dev, "Cannot enable SR-IOV, device not ready\n"); + return -EBUSY; + } + + if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) { + dev_err(dev, "This device is not capable of SR-IOV\n"); + return -ENODEV; + } + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + ice_free_vfs(pf); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + return num_vfs; + + if (num_vfs > pf->num_vfs_supported) { + dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n", + num_vfs, pf->num_vfs_supported); + return -ENOTSUPP; + } + + dev_info(dev, "Allocating %d VFs\n", num_vfs); + err = ice_alloc_vfs(pf, num_vfs); + if (err) { + dev_err(dev, "Failed to enable SR-IOV: %d\n", err); + return err; + } + + set_bit(ICE_FLAG_SRIOV_ENA, pf->flags); + return num_vfs; +} + +/** + * ice_sriov_configure - Enable or change number of VFs via sysfs + * @pdev: pointer to a pci_dev structure + * @num_vfs: number of VFs to allocate + * + * This function is called when the user updates the number of VFs in sysfs. + */ +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + if (num_vfs) + return ice_pci_sriov_ena(pf, num_vfs); + + if (!pci_vfs_assigned(pdev)) { + ice_free_vfs(pf); + } else { + dev_err(&pf->pdev->dev, + "can't free VFs because some are assigned to VMs.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * ice_process_vflr_event - Free VF resources via IRQ calls + * @pf: pointer to the PF structure + * + * called from the VLFR IRQ handler to + * free up VF resources and state variables + */ +void ice_process_vflr_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int vf_id; + u32 reg; + + if (!test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + !pf->num_alloc_vfs) + return; + + /* Re-enable the VFLR interrupt cause here, before looking for which + * VF got reset. Otherwise, if another VF gets a reset while the + * first one is being processed, that interrupt will be lost, and + * that VF will be stuck in reset forever. + */ + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_VFLR_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); + + clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) { + struct ice_vf *vf = &pf->vf[vf_id]; + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + /* read GLGEN_VFLRSTAT register to find out the flr VFs */ + reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); + if (reg & BIT(bit_idx)) + /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + ice_reset_vf(vf, true); + } +} + +/** + * ice_vc_dis_vf - Disable a given VF via SW reset + * @vf: pointer to the VF info + * + * Disable the VF through a SW reset + */ +static void ice_vc_dis_vf(struct ice_vf *vf) +{ + ice_vc_notify_vf_reset(vf); + ice_reset_vf(vf, false); +} + +/** + * ice_vc_send_msg_to_vf - Send message to VF + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + */ +static int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + enum ice_status aq_ret; + struct ice_pf *pf; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return -EINVAL; + + pf = vf->pf; + + /* single place to detect unsuccessful return values */ + if (v_retval) { + vf->num_inval_msgs++; + dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", + vf->vf_id, v_opcode, v_retval); + if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { + dev_err(&pf->pdev->dev, + "Number of invalid messages exceeded for VF %d\n", + vf->vf_id); + dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + return -EIO; + } + } else { + vf->num_valid_msgs++; + /* reset the invalid counter, if a valid message is received. */ + vf->num_inval_msgs = 0; + } + + aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, + msg, msglen, NULL); + if (aq_ret) { + dev_info(&pf->pdev->dev, + "Unable to send the message to VF %d aq_err %d\n", + vf->vf_id, pf->hw.mailboxq.sq_last_status); + return -EIO; + } + + return 0; +} + +/** + * ice_vc_get_ver_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request the API version used by the PF + */ +static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_version_info info = { + VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR + }; + + vf->vf_ver = *(struct virtchnl_version_info *)msg; + /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */ + if (VF_IS_V10(&vf->vf_ver)) + info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, ICE_SUCCESS, + (u8 *)&info, + sizeof(struct virtchnl_version_info)); +} + +/** + * ice_vc_get_vf_res_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request its resources + */ +static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_resource *vfres = NULL; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_vf_resource); + + vfres = devm_kzalloc(&pf->pdev->dev, len, GFP_KERNEL); + if (!vfres) { + aq_ret = ICE_ERR_NO_MEMORY; + len = 0; + goto err; + } + if (VF_IS_V11(&vf->vf_ver)) + vf->driver_caps = *(u32 *)msg; + else + vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | + VIRTCHNL_VF_OFFLOAD_RSS_REG | + VIRTCHNL_VF_OFFLOAD_VLAN; + + vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi->info.pvid) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; + } else { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; + else + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; + } + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + + vfres->num_vsis = 1; + /* Tx and Rx queue are equal for VF */ + vfres->num_queue_pairs = vsi->num_txq; + vfres->max_vectors = pf->num_vf_msix; + vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; + vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + + vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; + vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; + ether_addr_copy(vfres->vsi_res[0].default_mac_addr, + vf->dflt_lan_addr.addr); + + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, aq_ret, + (u8 *)vfres, len); + + devm_kfree(&pf->pdev->dev, vfres); + return ret; +} + +/** + * ice_vc_reset_vf_msg + * @vf: pointer to the VF info + * + * called from the VF to reset itself, + * unlike other virtchnl messages, PF driver + * doesn't send the response back to the VF + */ +static void ice_vc_reset_vf_msg(struct ice_vf *vf) +{ + if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ice_reset_vf(vf, false); +} + +/** + * ice_find_vsi_from_id + * @pf: the pf structure to search for the VSI + * @id: id of the VSI it is searching for + * + * searches for the VSI with the given id + */ +static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id) +{ + int i; + + for (i = 0; i < pf->num_alloc_vsi; i++) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == id) + return pf->vsi[i]; + + return NULL; +} + +/** + * ice_vc_isvalid_vsi_id + * @vf: pointer to the VF info + * @vsi_id: VF relative VSI id + * + * check for the valid VSI id + */ +static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_find_vsi_from_id(pf, vsi_id); + + return (vsi && (vsi->vf_id == vf->vf_id)); +} + +/** + * ice_vc_isvalid_q_id + * @vf: pointer to the VF info + * @vsi_id: VSI id + * @qid: VSI relative queue id + * + * check for the valid queue id + */ +static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +{ + struct ice_vsi *vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + /* allocated Tx and Rx queues should be always equal for VF VSI */ + return (vsi && (qid < vsi->alloc_txq)); +} + +/** + * ice_vc_config_rss_key + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS key + */ +static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrk->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, vrk->key, NULL, 0); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, aq_ret, + NULL, 0); +} + +/** + * ice_vc_config_rss_lut + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS LUT + */ +static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, aq_ret, + NULL, 0); +} + +/** + * ice_vc_get_stats_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to get VSI stats + */ +static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_eth_stats stats; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + memset(&stats, 0, sizeof(struct ice_eth_stats)); + ice_update_eth_stats(vsi); + + stats = vsi->eth_stats; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, aq_ret, + (u8 *)&stats, sizeof(stats)); +} + +/** + * ice_vc_ena_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to enable all or specific queue(s) + */ +static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* Enable only Rx rings, Tx rings were enabled by the FW when the + * Tx queue group list was configured and the context bits were + * programmed using ice_vsi_cfg_txqs + */ + if (ice_vsi_start_rx_rings(vsi)) + aq_ret = ICE_ERR_PARAM; + + /* Set flag to indicate that queues are enabled */ + if (!aq_ret) + set_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_dis_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to disable all or specific + * queue(s) + */ +static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && + !test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop tx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + if (ice_vsi_stop_rx_rings(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop rx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + /* Clear enabled queues flag */ + if (!aq_ret) + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_irq_map_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the IRQ to queue map + */ +static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_irq_map_info *irqmap_info = + (struct virtchnl_irq_map_info *)msg; + u16 vsi_id, vsi_q_id, vector_id; + struct virtchnl_vector_map *map; + struct ice_vsi *vsi = NULL; + struct ice_pf *pf = vf->pf; + enum ice_status aq_ret = 0; + unsigned long qmap; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < irqmap_info->num_vectors; i++) { + map = &irqmap_info->vecmap[i]; + + vector_id = map->vector_id; + vsi_id = map->vsi_id; + /* validate msg params */ + if (!(vector_id < pf->hw.func_caps.common_cap + .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* lookout for the invalid queue index */ + qmap = map->rxq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_rx++; + q_vector->rx.itr_idx = map->rxitr_idx; + vsi->rx_rings[vsi_q_id]->q_vector = q_vector; + } + + qmap = map->txq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_tx++; + q_vector->tx.itr_idx = map->txitr_idx; + vsi->tx_rings[vsi_q_id]->q_vector = q_vector; + } + } + + if (vsi) + ice_vsi_cfg_msix(vsi); +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the Rx/Tx queues + */ +static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vsi_queue_config_info *qci = + (struct virtchnl_vsi_queue_config_info *)msg; + struct virtchnl_queue_pair_info *qpi; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, qci->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < qci->num_queue_pairs; i++) { + qpi = &qci->qpair[i]; + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != qpi->txq.queue_id || + !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + /* copy Tx queue info from VF into VSI */ + vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[i]->count = qpi->txq.ring_len; + /* copy Rx queue info from VF into vsi */ + vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; + vsi->rx_rings[i]->count = qpi->rxq.ring_len; + if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->rx_buf_len = qpi->rxq.databuffer_size; + if (qpi->rxq.max_pkt_size >= (16 * 1024) || + qpi->rxq.max_pkt_size < 64) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->max_frame = qpi->rxq.max_pkt_size; + } + + /* VF can request to configure less than allocated queues + * or default allocated queues. So update the VSI with new number + */ + vsi->num_txq = qci->num_queue_pairs; + vsi->num_rxq = qci->num_queue_pairs; + + if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi)) + aq_ret = 0; + else + aq_ret = ICE_ERR_PARAM; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_is_vf_trusted + * @vf: pointer to the VF info + */ +static bool ice_is_vf_trusted(struct ice_vf *vf) +{ + return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); +} + +/** + * ice_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool ice_can_vf_change_mac(struct ice_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !ice_is_vf_trusted(vf)) + return false; + + return true; +} + +/** + * ice_vc_handle_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @set: true if mac filters are being set, false otherwise + * + * add guest mac address filter + */ +static int +ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) +{ + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_pf *pf = vf->pf; + enum virtchnl_ops vc_op; + enum ice_status ret; + LIST_HEAD(mac_list); + struct ice_vsi *vsi; + int mac_count = 0; + int i; + + if (set) + vc_op = VIRTCHNL_OP_ADD_ETH_ADDR; + else + vc_op = VIRTCHNL_OP_DEL_ETH_ADDR; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (set && !ice_is_vf_trusted(vf) && + (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { + dev_err(&pf->pdev->dev, + "Can't add more MAC addresses, because VF is not trusted, switch the VF to trusted mode in order to add more functionalities\n"); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + + for (i = 0; i < al->num_elements; i++) { + u8 *maddr = al->list[i].addr; + + if (ether_addr_equal(maddr, vf->dflt_lan_addr.addr) || + is_broadcast_ether_addr(maddr)) { + if (set) { + /* VF is trying to add filters that the PF + * already added. Just continue. + */ + dev_info(&pf->pdev->dev, + "mac %pM already set for VF %d\n", + maddr, vf->vf_id); + continue; + } else { + /* VF can't remove dflt_lan_addr/bcast mac */ + dev_err(&pf->pdev->dev, + "can't remove mac %pM for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + } + + /* check for the invalid cases and bail if necessary */ + if (is_zero_ether_addr(maddr)) { + dev_err(&pf->pdev->dev, + "invalid mac %pM provided for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (is_unicast_ether_addr(maddr) && + !ice_can_vf_change_mac(vf)) { + dev_err(&pf->pdev->dev, + "can't change unicast mac for untrusted VF %d\n", + vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + /* get here if maddr is multicast or if VF can change mac */ + if (ice_add_mac_to_list(vsi, &mac_list, al->list[i].addr)) { + ret = ICE_ERR_NO_MEMORY; + goto handle_mac_exit; + } + mac_count++; + } + + /* program the updated filter list */ + if (set) + ret = ice_add_mac(&pf->hw, &mac_list); + else + ret = ice_remove_mac(&pf->hw, &mac_list); + + if (ret) { + dev_err(&pf->pdev->dev, + "can't update mac filters for VF %d, error %d\n", + vf->vf_id, ret); + } else { + if (set) + vf->num_mac += mac_count; + else + vf->num_mac -= mac_count; + } + +handle_mac_exit: + ice_free_fltr_list(&pf->pdev->dev, &mac_list); + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, vc_op, ret, NULL, 0); +} + +/** + * ice_vc_add_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * add guest MAC address filter + */ +static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, true); +} + +/** + * ice_vc_del_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove guest MAC address filter + */ +static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, false); +} + +/** + * ice_vc_request_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * VFs get a default number of queues but can use this message to request a + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queue pairs via virtchnl message response to VF. + */ +static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + int req_queues = vfres->num_queue_pairs; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + int tx_rx_queue_left; + int cur_queues; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + cur_queues = pf->num_vf_qps; + tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); + if (req_queues <= 0) { + dev_err(&pf->pdev->dev, + "VF %d tried to request %d queues. Ignoring.\n", + vf->vf_id, req_queues); + } else if (req_queues > ICE_MAX_QS_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d tried to request more than %d queues.\n", + vf->vf_id, ICE_MAX_QS_PER_VF); + vfres->num_queue_pairs = ICE_MAX_QS_PER_VF; + } else if (req_queues - cur_queues > tx_rx_queue_left) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but only %d left.\n", + vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); + vfres->num_queue_pairs = tx_rx_queue_left + cur_queues; + } else { + /* request is successful, then reset VF */ + vf->num_req_qs = req_queues; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, + "VF %d granted request of %d queues.\n", + vf->vf_id, req_queues); + return 0; + } + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, + aq_ret, (u8 *)vfres, sizeof(*vfres)); +} + +/** + * ice_set_vf_port_vlan + * @netdev: network interface device structure + * @vf_id: VF identifier + * @vlan_id: VLAN id being set + * @qos: priority setting + * @vlan_proto: VLAN protocol + * + * program VF Port VLAN id and/or qos + */ +int +ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) +{ + u16 vlanprio = vlan_id | (qos << ICE_VLAN_PRIORITY_S); + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct ice_vsi *vsi; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + if (vlan_id > ICE_MAX_VLANID || qos > 7) { + dev_err(&pf->pdev->dev, "Invalid VF Parameters\n"); + return -EINVAL; + } + + if (vlan_proto != htons(ETH_P_8021Q)) { + dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n"); + return -EPROTONOSUPPORT; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (le16_to_cpu(vsi->info.pvid) == vlanprio) { + /* duplicate request, so just return success */ + dev_info(&pf->pdev->dev, + "Duplicate pvid %d request\n", vlanprio); + return ret; + } + + /* If pvid, then remove all filters on the old VLAN */ + if (vsi->info.pvid) + ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) & + VLAN_VID_MASK)); + + if (vlan_id || qos) { + ret = ice_vsi_set_pvid(vsi, vlanprio); + if (ret) + goto error_set_pvid; + } else { + ice_vsi_kill_pvid(vsi); + } + + if (vlan_id) { + dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n", + vlan_id, qos, vf_id); + + /* add new VLAN filter for each MAC */ + ret = ice_vsi_add_vlan(vsi, vlan_id); + if (ret) + goto error_set_pvid; + } + + /* The Port VLAN needs to be saved across resets the same as the + * default LAN MAC address. + */ + vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + +error_set_pvid: + return ret; +} + +/** + * ice_vc_process_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @add_v: Add VLAN if true, otherwise delete VLAN + * + * Process virtchnl op to add or remove programmed guest VLAN id + */ +static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) +{ + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v && !ice_is_vf_trusted(vf) && + vf->num_vlan >= ICE_MAX_VLAN_PER_VF) { + dev_info(&pf->pdev->dev, + "VF is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n"); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < vfl->num_elements; i++) { + if (vfl->vlan_id[i] > ICE_MAX_VLANID) { + aq_ret = ICE_ERR_PARAM; + dev_err(&pf->pdev->dev, + "invalid VF VLAN id %d\n", vfl->vlan_id[i]); + goto error_param; + } + } + + vsi = ice_find_vsi_from_id(vf->pf, vfl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vsi->info.pvid) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_manage_vlan_stripping(vsi, add_v)) { + dev_err(&pf->pdev->dev, + "%sable VLAN stripping failed for VSI %i\n", + add_v ? "en" : "dis", vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v) { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + if (!ice_vsi_add_vlan(vsi, vid)) { + vf->num_vlan++; + set_bit(vid, vsi->active_vlans); + + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) + if (ice_cfg_vlan_pruning(vsi, true)) + aq_ret = ICE_ERR_PARAM; + } else { + aq_ret = ICE_ERR_PARAM; + } + } + } else { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + /* Make sure ice_vsi_kill_vlan is successful before + * updating VLAN information + */ + if (!ice_vsi_kill_vlan(vsi, vid)) { + vf->num_vlan--; + clear_bit(vid, vsi->active_vlans); + + /* Disable VLAN pruning when removing VLAN 0 */ + if (unlikely(!vid)) + ice_cfg_vlan_pruning(vsi, false); + } + } + } + +error_param: + /* send the response to the VF */ + if (add_v) + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, aq_ret, + NULL, 0); + else + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, aq_ret, + NULL, 0); +} + +/** + * ice_vc_add_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Add and program guest VLAN id + */ +static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, true); +} + +/** + * ice_vc_remove_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove programmed guest VLAN id + */ +static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, false); +} + +/** + * ice_vc_ena_vlan_stripping + * @vf: pointer to the VF info + * + * Enable VLAN header stripping for a given VF + */ +static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, true)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping + * @vf: pointer to the VF info + * + * Disable VLAN header stripping for a given VF + */ +static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, false)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_process_vf_msg - Process request from VF + * @pf: pointer to the PF structure + * @event: pointer to the AQ event + * + * called from the common asq/arq handler to + * process request from VF + */ +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 v_opcode = le32_to_cpu(event->desc.cookie_high); + s16 vf_id = le16_to_cpu(event->desc.retval); + u16 msglen = event->msg_len; + u8 *msg = event->msg_buf; + struct ice_vf *vf = NULL; + int err = 0; + + if (vf_id >= pf->num_alloc_vfs) { + err = -EINVAL; + goto error_handler; + } + + vf = &pf->vf[vf_id]; + + /* Check if VF is disabled. */ + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { + err = -EPERM; + goto error_handler; + } + + /* Perform basic checks on the msg */ + err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); + if (err) { + if (err == VIRTCHNL_ERR_PARAM) + err = -EPERM; + else + err = -EINVAL; + goto error_handler; + } + + /* Perform additional checks specific to RSS and Virtchnl */ + if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) { + struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) + err = -EINVAL; + } else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) { + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) + err = -EINVAL; + } + +error_handler: + if (err) { + ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_PARAM, NULL, 0); + dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", + vf_id, v_opcode, msglen, err); + return; + } + + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + err = ice_vc_get_ver_msg(vf, msg); + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + err = ice_vc_get_vf_res_msg(vf, msg); + break; + case VIRTCHNL_OP_RESET_VF: + ice_vc_reset_vf_msg(vf); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + err = ice_vc_add_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_ETH_ADDR: + err = ice_vc_del_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + err = ice_vc_cfg_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + err = ice_vc_ena_qs_msg(vf, msg); + ice_vc_notify_vf_link_state(vf); + break; + case VIRTCHNL_OP_DISABLE_QUEUES: + err = ice_vc_dis_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_REQUEST_QUEUES: + err = ice_vc_request_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + err = ice_vc_cfg_irq_map_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + err = ice_vc_config_rss_key(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + err = ice_vc_config_rss_lut(vf, msg); + break; + case VIRTCHNL_OP_GET_STATS: + err = ice_vc_get_stats_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_VLAN: + err = ice_vc_add_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN: + err = ice_vc_remove_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + err = ice_vc_ena_vlan_stripping(vf); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + err = ice_vc_dis_vlan_stripping(vf); + break; + case VIRTCHNL_OP_UNKNOWN: + default: + dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", + v_opcode, vf_id); + err = ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_NOT_IMPL, + NULL, 0); + break; + } + if (err) { + /* Helper function cares less about error return values here + * as it is busy with pending work. + */ + dev_info(&pf->pdev->dev, + "PF failed to honor VF %d, opcode %d\n, error %d\n", + vf_id, v_opcode, err); + } +} + +/** + * ice_get_vf_cfg + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ivi: VF configuration structure + * + * return VF configuration + */ +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + ivi->vf = vf_id; + ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr); + + /* VF configuration for VLAN and applicable QoS */ + ivi->vlan = le16_to_cpu(vsi->info.pvid) & ICE_VLAN_M; + ivi->qos = (le16_to_cpu(vsi->info.pvid) & ICE_PRIORITY_M) >> + ICE_VLAN_PRIORITY_S; + + ivi->trusted = vf->trusted; + ivi->spoofchk = vf->spoofchk; + if (!vf->link_forced) + ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + else + ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; + ivi->max_tx_rate = vf->tx_rate; + ivi->min_tx_rate = 0; + return 0; +} + +/** + * ice_set_vf_spoofchk + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ena: flag to enable or disable feature + * + * Enable or disable VF spoof checking + */ +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_ctx ctx = { 0 }; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int status; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (ena == vf->spoofchk) { + dev_dbg(&pf->pdev->dev, "VF spoofchk already %s\n", + ena ? "ON" : "OFF"); + return 0; + } + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (ena) { + ctx.info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + ctx.info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M; + } + + status = ice_update_vsi(&pf->hw, vsi->idx, &ctx, NULL); + if (status) { + dev_dbg(&pf->pdev->dev, + "Error %d, failed to update VSI* parameters\n", status); + return -EIO; + } + + vf->spoofchk = ena; + vsi->info.sec_flags = ctx.info.sec_flags; + vsi->info.sw_flags2 = ctx.info.sw_flags2; + + return status; +} + +/** + * ice_set_vf_mac + * @netdev: network interface device structure + * @vf_id: VF identifier + * @mac: mac address + * + * program VF mac address + */ +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { + netdev_err(netdev, "%pM not a valid unicast address\n", mac); + return -EINVAL; + } + + /* copy mac into dflt_lan_addr and trigger a VF reset. The reset + * flow will use the updated dflt_lan_addr and add a MAC filter + * using ice_add_mac. Also set pf_set_mac to indicate that the PF has + * set the MAC address for this VF. + */ + ether_addr_copy(vf->dflt_lan_addr.addr, mac); + vf->pf_set_mac = true; + netdev_info(netdev, + "mac on VF %d set to %pM\n. VF driver will be reinitialized\n", + vf_id, mac); + + ice_vc_dis_vf(vf); + return ret; +} + +/** + * ice_set_vf_trust + * @netdev: network interface device structure + * @vf_id: VF identifier + * @trusted: Boolean value to enable/disable trusted VF + * + * Enable or disable a given VF as trusted + */ +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + /* Check if already trusted */ + if (trusted == vf->trusted) + return 0; + + vf->trusted = trusted; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", + vf_id, trusted ? "" : "un"); + + return 0; +} + +/** + * ice_set_vf_link_state + * @netdev: network interface device structure + * @vf_id: VF identifier + * @link_state: required link state + * + * Set VF's link state, irrespective of physical link state status + */ +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_vf *vf; + struct ice_hw *hw; + + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + hw = &pf->hw; + ls = &pf->hw.port_info->phy.link_info; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "vf %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + switch (link_state) { + case IFLA_VF_LINK_STATE_AUTO: + vf->link_forced = false; + vf->link_up = ls->link_info & ICE_AQ_LINK_UP; + break; + case IFLA_VF_LINK_STATE_ENABLE: + vf->link_forced = true; + vf->link_up = true; + break; + case IFLA_VF_LINK_STATE_DISABLE: + vf->link_forced = true; + vf->link_up = false; + break; + default: + return -EINVAL; + } + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up); + + /* Notify the VF of its new link state */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h new file mode 100644 index 000000000000..10131e0180f9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -0,0 +1,173 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_PF_H_ +#define _ICE_VIRTCHNL_PF_H_ +#include "ice.h" + +#define ICE_MAX_VLANID 4095 +#define ICE_VLAN_PRIORITY_S 12 +#define ICE_VLAN_M 0xFFF +#define ICE_PRIORITY_M 0x7000 + +/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ +#define ICE_MAX_VLAN_PER_VF 8 +#define ICE_MAX_MACADDR_PER_VF 12 + +/* Malicious Driver Detection */ +#define ICE_DFLT_NUM_MDD_EVENTS_ALLOWED 3 +#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 + +/* Static VF transaction/status register def */ +#define VF_DEVICE_STATUS 0xAA +#define VF_TRANS_PENDING_M 0x20 + +/* Specific VF states */ +enum ice_vf_states { + ICE_VF_STATE_INIT = 0, + ICE_VF_STATE_ACTIVE, + ICE_VF_STATE_ENA, + ICE_VF_STATE_DIS, + ICE_VF_STATE_MC_PROMISC, + ICE_VF_STATE_UC_PROMISC, + /* state to indicate if PF needs to do vector assignment for VF. + * This needs to be set during first time VF initialization or later + * when VF asks for more Vectors through virtchnl OP. + */ + ICE_VF_STATE_CFG_INTR, + ICE_VF_STATES_NBITS +}; + +/* VF capabilities */ +enum ice_virtchnl_cap { + ICE_VIRTCHNL_VF_CAP_L2 = 0, + ICE_VIRTCHNL_VF_CAP_PRIVILEGE, +}; + +/* VF information structure */ +struct ice_vf { + struct ice_pf *pf; + + s16 vf_id; /* VF id in the PF space */ + u32 driver_caps; /* reported by VF driver */ + int first_vector_idx; /* first vector index of this VF */ + struct ice_sw *vf_sw_id; /* switch id the VF VSIs connect to */ + struct virtchnl_version_info vf_ver; + struct virtchnl_ether_addr dflt_lan_addr; + u16 port_vlan_id; + u8 pf_set_mac; /* VF MAC address set by VMM admin */ + u8 trusted; + u16 lan_vsi_idx; /* index into PF struct */ + u16 lan_vsi_num; /* ID as used by firmware */ + u64 num_mdd_events; /* number of mdd events detected */ + u64 num_inval_msgs; /* number of continuous invalid msgs */ + u64 num_valid_msgs; /* number of valid msgs detected */ + unsigned long vf_caps; /* vf's adv. capabilities */ + DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ + unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ + u8 link_forced; + u8 link_up; /* only valid if VF link is forced */ + u8 spoofchk; + u16 num_mac; + u16 num_vlan; + u8 num_req_qs; /* num of queue pairs requested by VF */ +}; + +#ifdef CONFIG_PCI_IOV +void ice_process_vflr_event(struct ice_pf *pf); +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi); + +void ice_free_vfs(struct ice_pf *pf); +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_vc_notify_link_state(struct ice_pf *pf); +void ice_vc_notify_reset(struct ice_pf *pf); +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); + +int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto); + +int ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); + +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); + +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); + +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); +#else /* CONFIG_PCI_IOV */ +#define ice_process_vflr_event(pf) do {} while (0) +#define ice_free_vfs(pf) do {} while (0) +#define ice_vc_process_vf_msg(pf, event) do {} while (0) +#define ice_vc_notify_link_state(pf) do {} while (0) +#define ice_vc_notify_reset(pf) do {} while (0) + +static inline bool +ice_reset_all_vfs(struct ice_pf __always_unused *pf, + bool __always_unused is_vflr) +{ + return true; +} + +static inline int +ice_sriov_configure(struct pci_dev __always_unused *pdev, + int __always_unused num_vfs) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_mac(struct net_device __always_unused *netdev, + int __always_unused vf_id, u8 __always_unused *mac) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_get_vf_cfg(struct net_device __always_unused *netdev, + int __always_unused vf_id, + struct ifla_vf_info __always_unused *ivi) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_trust(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused trusted) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_port_vlan(struct net_device __always_unused *netdev, + int __always_unused vf_id, u16 __always_unused vid, + u8 __always_unused qos, __be16 __always_unused v_proto) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_spoofchk(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused ena) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_link_state(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused link_state) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_bw(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused min_tx_rate, + int __always_unused max_tx_rate) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_VIRTCHNL_PF_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 5414685189ce..ca6b0c458e4a 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -8,7 +8,8 @@ obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ - ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o + ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ + ixgbe_xsk.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 5c6fd42e90ed..7a7679e7be84 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -228,13 +228,17 @@ struct ixgbe_tx_buffer { struct ixgbe_rx_buffer { struct sk_buff *skb; dma_addr_t dma; - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; -#else - __u16 page_offset; -#endif - __u16 pagecnt_bias; + union { + struct { + struct page *page; + __u32 page_offset; + __u16 pagecnt_bias; + }; + struct { + void *addr; + u64 handle; + }; + }; }; struct ixgbe_queue_stats { @@ -271,6 +275,7 @@ enum ixgbe_ring_state_t { __IXGBE_TX_DETECT_HANG, __IXGBE_HANG_CHECK_ARMED, __IXGBE_TX_XDP_RING, + __IXGBE_TX_DISABLED, }; #define ring_uses_build_skb(ring) \ @@ -347,6 +352,10 @@ struct ixgbe_ring { struct ixgbe_rx_queue_stats rx_stats; }; struct xdp_rxq_info xdp_rxq; + struct xdp_umem *xsk_umem; + struct zero_copy_allocator zca; /* ZC allocator anchor */ + u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ + u16 rx_buf_len; } ____cacheline_internodealigned_in_smp; enum ixgbe_ring_f_enum { @@ -764,6 +773,11 @@ struct ixgbe_adapter { #ifdef CONFIG_XFRM_OFFLOAD struct ixgbe_ipsec *ipsec; #endif /* CONFIG_XFRM_OFFLOAD */ + + /* AF_XDP zero-copy */ + struct xdp_umem **xsk_umems; + u16 num_xsk_umems_used; + u16 num_xsk_umems; }; static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 970f71d5da04..0bd1294ba517 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3485,17 +3485,6 @@ void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf) } /** - * ixgbe_fw_recovery_mode - Check if in FW NVM recovery mode - * @hw: pointer to hardware structure - */ -bool ixgbe_fw_recovery_mode(struct ixgbe_hw *hw) -{ - if (hw->mac.ops.fw_recovery_mode) - return hw->mac.ops.fw_recovery_mode(hw); - return false; -} - -/** * ixgbe_get_device_caps_generic - Get additional device capabilities * @hw: pointer to hardware structure * @device_caps: the EEPROM word with the extra device capabilities diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index d361f570ca37..62e6499e4146 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1055,7 +1055,7 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) int txr_remaining = adapter->num_tx_queues; int xdp_remaining = adapter->num_xdp_queues; int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0; - int err; + int err, i; /* only one q_vector if MSI-X is disabled. */ if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) @@ -1097,6 +1097,21 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) xdp_idx += xqpv; } + for (i = 0; i < adapter->num_rx_queues; i++) { + if (adapter->rx_ring[i]) + adapter->rx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->tx_ring[i]) + adapter->tx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + if (adapter->xdp_ring[i]) + adapter->xdp_ring[i]->ring_idx = i; + } + return 0; err_out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 140e87a10ff5..51268772a999 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -34,12 +34,14 @@ #include <net/tc_act/tc_mirred.h> #include <net/vxlan.h> #include <net/mpls.h> +#include <net/xdp_sock.h> #include "ixgbe.h" #include "ixgbe_common.h" #include "ixgbe_dcb_82599.h" #include "ixgbe_sriov.h" #include "ixgbe_model.h" +#include "ixgbe_txrx_common.h" char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = @@ -893,8 +895,8 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, } } -static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, - u64 qmask) +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, + u64 qmask) { u32 mask; @@ -1673,9 +1675,9 @@ static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; u32 flags = rx_ring->q_vector->adapter->flags; @@ -1708,8 +1710,8 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, skb->protocol = eth_type_trans(skb, dev); } -static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, - struct sk_buff *skb) +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) { napi_gro_receive(&q_vector->napi, skb); } @@ -1868,9 +1870,9 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, * * Returns true if an error was encountered and skb was freed. **/ -static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *netdev = rx_ring->netdev; @@ -2186,14 +2188,6 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED BIT(0) -#define IXGBE_XDP_TX BIT(1) -#define IXGBE_XDP_REDIR BIT(2) - -static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_frame *xdpf); - static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, struct xdp_buff *xdp) @@ -3167,7 +3161,11 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) { - if (!ixgbe_clean_tx_irq(q_vector, ring, budget)) + bool wd = ring->xsk_umem ? + ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : + ixgbe_clean_tx_irq(q_vector, ring, budget); + + if (!wd) clean_complete = false; } @@ -3183,7 +3181,10 @@ int ixgbe_poll(struct napi_struct *napi, int budget) per_ring_budget = budget; ixgbe_for_each_ring(ring, q_vector->rx) { - int cleaned = ixgbe_clean_rx_irq(q_vector, ring, + int cleaned = ring->xsk_umem ? + ixgbe_clean_rx_irq_zc(q_vector, ring, + per_ring_budget) : + ixgbe_clean_rx_irq(q_vector, ring, per_ring_budget); work_done += cleaned; @@ -3196,11 +3197,13 @@ int ixgbe_poll(struct napi_struct *napi, int budget) return budget; /* all work done, exit the polling mode */ - napi_complete_done(napi, work_done); - if (adapter->rx_itr_setting & 1) - ixgbe_set_itr(q_vector); - if (!test_bit(__IXGBE_DOWN, &adapter->state)) - ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx)); + if (likely(napi_complete_done(napi, work_done))) { + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + BIT_ULL(q_vector->v_idx)); + } return min(work_done, budget - 1); } @@ -3473,6 +3476,10 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, u32 txdctl = IXGBE_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; + ring->xsk_umem = NULL; + if (ring_is_xdp(ring)) + ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + /* disable queue to avoid issues while updating state */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); IXGBE_WRITE_FLUSH(hw); @@ -3577,12 +3584,18 @@ static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) else mtqc |= IXGBE_MTQC_64VF; } else { - if (tcs > 4) + if (tcs > 4) { mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; - else if (tcs > 1) + } else if (tcs > 1) { mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; - else - mtqc = IXGBE_MTQC_64Q_1PB; + } else { + u8 max_txq = adapter->num_tx_queues + + adapter->num_xdp_queues; + if (max_txq > 63) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else + mtqc = IXGBE_MTQC_64Q_1PB; + } } IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); @@ -3705,10 +3718,27 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) + if (rx_ring->xsk_umem) { + u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + + /* If the MAC support setting RXDCTL.RLPML, the + * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and + * RXDCTL.RLPML is set to the actual UMEM buffer + * size. If not, then we are stuck with a 1k buffer + * size resolution. In this case frames larger than + * the UMEM buffer size viewed in a 1k resolution will + * be dropped. + */ + if (hw->mac.type != ixgbe_mac_82599EB) + srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) { srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; - else + } else { srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } /* configure descriptor type */ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -4031,6 +4061,19 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + if (ring->xsk_umem) { + ring->zca.free = ixgbe_zca_free; + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_ZERO_COPY, + &ring->zca)); + + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL)); + } + /* disable queue to avoid use of these values while updating state */ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); rxdctl &= ~IXGBE_RXDCTL_ENABLE; @@ -4080,6 +4123,17 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } + if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN; + + ring->rx_buf_len = xsk_buf_len; + } + /* initialize rx_buffer_info */ memset(ring->rx_buffer_info, 0, sizeof(struct ixgbe_rx_buffer) * ring->count); @@ -4093,7 +4147,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); ixgbe_rx_desc_queue_enable(adapter, ring); - ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); + if (ring->xsk_umem) + ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); + else + ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); } static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) @@ -5173,6 +5230,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct hlist_node *node2; struct ixgbe_fdir_filter *filter; + u64 action; spin_lock(&adapter->fdir_perfect_lock); @@ -5181,12 +5239,17 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { + action = filter->action; + if (action != IXGBE_FDIR_DROP_QUEUE && action != 0) + action = + (action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1; + ixgbe_fdir_write_perfect_filter_82599(hw, &filter->filter, filter->sw_idx, - (filter->action == IXGBE_FDIR_DROP_QUEUE) ? + (action == IXGBE_FDIR_DROP_QUEUE) ? IXGBE_FDIR_DROP_QUEUE : - adapter->rx_ring[filter->action]->reg_idx); + adapter->rx_ring[action]->reg_idx); } spin_unlock(&adapter->fdir_perfect_lock); @@ -5201,6 +5264,11 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) u16 i = rx_ring->next_to_clean; struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; + if (rx_ring->xsk_umem) { + ixgbe_xsk_clean_rx_ring(rx_ring); + goto skip_free; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { if (rx_buffer->skb) { @@ -5239,6 +5307,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) } } +skip_free: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -5883,6 +5952,11 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) u16 i = tx_ring->next_to_clean; struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + if (tx_ring->xsk_umem) { + ixgbe_xsk_clean_tx_ring(tx_ring); + goto out; + } + while (i != tx_ring->next_to_use) { union ixgbe_adv_tx_desc *eop_desc, *tx_desc; @@ -5934,6 +6008,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) if (!ring_is_xdp(tx_ring)) netdev_tx_reset_queue(txring_txq(tx_ring)); +out: /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -6434,7 +6509,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); int ring_node = -1; - int size, err; + int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; @@ -6471,13 +6546,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->queue_index) < 0) goto err; - err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err) { - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - goto err; - } - rx_ring->xdp_prog = adapter->xdp_prog; return 0; @@ -8102,9 +8170,6 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) return __ixgbe_maybe_stop_tx(tx_ring, size); } -#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ - IXGBE_TXD_CMD_RS) - static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, const u8 hdr_len) @@ -8457,8 +8522,8 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, } #endif -static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_frame *xdpf) +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; struct ixgbe_tx_buffer *tx_buffer; @@ -8680,6 +8745,8 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state))) + return NETDEV_TX_BUSY; return ixgbe_xmit_frame_ring(skb, adapter, tx_ring); } @@ -10191,12 +10258,19 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; + case XDP_QUERY_XSK_UMEM: + return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem, + xdp->xsk.queue_id); + case XDP_SETUP_XSK_UMEM: + return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, + xdp->xsk.queue_id); + default: return -EINVAL; } } -static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) { /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. @@ -10226,6 +10300,9 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, if (unlikely(!ring)) return -ENXIO; + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state))) + return -ENXIO; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -10287,8 +10364,162 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, + .ndo_xsk_async_xmit = ixgbe_xsk_async_xmit, }; +static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = tx_ring->reg_idx; + int wait_loop; + u32 txdctl; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + + /* delay mechanism from ixgbe_disable_tx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + + if (!(txdctl & IXGBE_TXDCTL_ENABLE)) + return; + } + + e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_disable_txr(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + set_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + ixgbe_disable_txr_hw(adapter, tx_ring); +} + +static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = rx_ring->reg_idx; + int wait_loop; + u32 rxdctl; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + rxdctl |= IXGBE_RXDCTL_SWFLSH; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + + /* RXDCTL.EN may not change on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* delay mechanism from ixgbe_disable_rx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + + if (!(rxdctl & IXGBE_RXDCTL_ENABLE)) + return; + } + + e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring) +{ + memset(&tx_ring->stats, 0, sizeof(tx_ring->stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) +{ + memset(&rx_ring->stats, 0, sizeof(rx_ring->stats)); + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); +} + +/** + * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function disables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + ixgbe_disable_txr(adapter, tx_ring); + if (xdp_ring) + ixgbe_disable_txr(adapter, xdp_ring); + ixgbe_disable_rxr_hw(adapter, rx_ring); + + if (xdp_ring) + synchronize_sched(); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + ixgbe_clean_tx_ring(tx_ring); + if (xdp_ring) + ixgbe_clean_tx_ring(xdp_ring); + ixgbe_clean_rx_ring(rx_ring); + + ixgbe_reset_txr_stats(tx_ring); + if (xdp_ring) + ixgbe_reset_txr_stats(xdp_ring); + ixgbe_reset_rxr_stats(rx_ring); +} + +/** + * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function enables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + + ixgbe_configure_tx_ring(adapter, tx_ring); + if (xdp_ring) + ixgbe_configure_tx_ring(adapter, xdp_ring); + ixgbe_configure_rx_ring(adapter, rx_ring); + + clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); +} + /** * ixgbe_enumerate_functions - Get the number of ports this device has * @adapter: adapter structure diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h new file mode 100644 index 000000000000..53d4089f5644 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef _IXGBE_TXRX_COMMON_H_ +#define _IXGBE_TXRX_COMMON_H_ + +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) + +#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ + IXGBE_TXD_CMD_RS) + +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf); +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb); +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring); +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask); + +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring); +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); + +struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring); +int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, + u16 qid); +int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, + u16 qid); + +void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); + +void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count); +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget); +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring); +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget); +int ixgbe_xsk_async_xmit(struct net_device *dev, u32 queue_id); +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); + +#endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c new file mode 100644 index 000000000000..65c3e2c979d4 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -0,0 +1,801 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include <linux/bpf_trace.h> +#include <net/xdp_sock.h> +#include <net/xdp.h> + +#include "ixgbe.h" +#include "ixgbe_txrx_common.h" + +struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + bool xdp_on = READ_ONCE(adapter->xdp_prog); + int qid = ring->ring_idx; + + if (!adapter->xsk_umems || !adapter->xsk_umems[qid] || + qid >= adapter->num_xsk_umems || !xdp_on) + return NULL; + + return adapter->xsk_umems[qid]; +} + +static int ixgbe_alloc_xsk_umems(struct ixgbe_adapter *adapter) +{ + if (adapter->xsk_umems) + return 0; + + adapter->num_xsk_umems_used = 0; + adapter->num_xsk_umems = adapter->num_rx_queues; + adapter->xsk_umems = kcalloc(adapter->num_xsk_umems, + sizeof(*adapter->xsk_umems), + GFP_KERNEL); + if (!adapter->xsk_umems) { + adapter->num_xsk_umems = 0; + return -ENOMEM; + } + + return 0; +} + +static int ixgbe_add_xsk_umem(struct ixgbe_adapter *adapter, + struct xdp_umem *umem, + u16 qid) +{ + int err; + + err = ixgbe_alloc_xsk_umems(adapter); + if (err) + return err; + + adapter->xsk_umems[qid] = umem; + adapter->num_xsk_umems_used++; + + return 0; +} + +static void ixgbe_remove_xsk_umem(struct ixgbe_adapter *adapter, u16 qid) +{ + adapter->xsk_umems[qid] = NULL; + adapter->num_xsk_umems_used--; + + if (adapter->num_xsk_umems == 0) { + kfree(adapter->xsk_umems); + adapter->xsk_umems = NULL; + adapter->num_xsk_umems = 0; + } +} + +static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter, + struct xdp_umem *umem) +{ + struct device *dev = &adapter->pdev->dev; + unsigned int i, j; + dma_addr_t dma; + + for (i = 0; i < umem->npgs; i++) { + dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); + if (dma_mapping_error(dev, dma)) + goto out_unmap; + + umem->pages[i].dma = dma; + } + + return 0; + +out_unmap: + for (j = 0; j < i; j++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); + umem->pages[i].dma = 0; + } + + return -1; +} + +static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter, + struct xdp_umem *umem) +{ + struct device *dev = &adapter->pdev->dev; + unsigned int i; + + for (i = 0; i < umem->npgs; i++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); + + umem->pages[i].dma = 0; + } +} + +static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, + struct xdp_umem *umem, + u16 qid) +{ + struct xdp_umem_fq_reuse *reuseq; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (adapter->xsk_umems) { + if (qid >= adapter->num_xsk_umems) + return -EINVAL; + if (adapter->xsk_umems[qid]) + return -EBUSY; + } + + reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count); + if (!reuseq) + return -ENOMEM; + + xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); + + err = ixgbe_xsk_umem_dma_map(adapter, umem); + if (err) + return err; + + if_running = netif_running(adapter->netdev) && + READ_ONCE(adapter->xdp_prog); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + err = ixgbe_add_xsk_umem(adapter, umem, qid); + + if (if_running) + ixgbe_txrx_ring_enable(adapter, qid); + + return err; +} + +static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) +{ + bool if_running; + + if (!adapter->xsk_umems || qid >= adapter->num_xsk_umems || + !adapter->xsk_umems[qid]) + return -EINVAL; + + if_running = netif_running(adapter->netdev) && + READ_ONCE(adapter->xdp_prog); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + ixgbe_xsk_umem_dma_unmap(adapter, adapter->xsk_umems[qid]); + ixgbe_remove_xsk_umem(adapter, qid); + + if (if_running) + ixgbe_txrx_ring_enable(adapter, qid); + + return 0; +} + +int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, + u16 qid) +{ + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (adapter->xsk_umems) { + if (qid >= adapter->num_xsk_umems) + return -EINVAL; + *umem = adapter->xsk_umems[qid]; + return 0; + } + + *umem = NULL; + return 0; +} + +int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, + u16 qid) +{ + return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) : + ixgbe_xsk_umem_disable(adapter, qid); +} + +static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + act = bpf_prog_run_xdp(xdp_prog, xdp); + xdp->handle += xdp->data - xdp->data_hard_start; + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) { + result = IXGBE_XDP_CONSUMED; + break; + } + result = ixgbe_xmit_xdp_ring(adapter, xdpf); + break; + case XDP_REDIRECT: + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fallthrough */ + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } + rcu_read_unlock(); + return result; +} + +static struct +ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring, + unsigned int size) +{ + struct ixgbe_rx_buffer *bi; + + bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + bi->dma, 0, + size, + DMA_BIDIRECTIONAL); + + return bi; +} + +static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *obi) +{ + unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; + u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + u16 nta = rx_ring->next_to_alloc; + struct ixgbe_rx_buffer *nbi; + + nbi = &rx_ring->rx_buffer_info[rx_ring->next_to_alloc]; + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + nbi->dma = obi->dma & mask; + nbi->dma += hr; + + nbi->addr = (void *)((unsigned long)obi->addr & mask); + nbi->addr += hr; + + nbi->handle = obi->handle & mask; + nbi->handle += rx_ring->xsk_umem->headroom; + + obi->addr = NULL; + obi->skb = NULL; +} + +void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) +{ + struct ixgbe_rx_buffer *bi; + struct ixgbe_ring *rx_ring; + u64 hr, mask; + u16 nta; + + rx_ring = container_of(alloc, struct ixgbe_ring, zca); + hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + mask = rx_ring->xsk_umem->chunk_mask; + + nta = rx_ring->next_to_alloc; + bi = rx_ring->rx_buffer_info; + + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + handle &= mask; + + bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); + bi->addr += hr; + + bi->handle = (u64)handle + rx_ring->xsk_umem->headroom; +} + +static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + void *addr = bi->addr; + u64 handle, hr; + + if (addr) + return true; + + if (!xsk_umem_peek_addr(umem, &handle)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + hr = umem->headroom + XDP_PACKET_HEADROOM; + + bi->dma = xdp_umem_get_dma(umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(umem, handle); + bi->addr += hr; + + bi->handle = handle + umem->headroom; + + xsk_umem_discard_addr(umem); + return true; +} + +static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + u64 handle, hr; + + if (!xsk_umem_peek_addr_rq(umem, &handle)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + handle &= rx_ring->xsk_umem->chunk_mask; + + hr = umem->headroom + XDP_PACKET_HEADROOM; + + bi->dma = xdp_umem_get_dma(umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(umem, handle); + bi->addr += hr; + + bi->handle = handle + umem->headroom; + + xsk_umem_discard_addr_rq(umem); + return true; +} + +static __always_inline bool +__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, + bool alloc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi)) +{ + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + bool ok = true; + + /* nothing to do */ + if (!cleaned_count) + return true; + + rx_desc = IXGBE_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + if (!alloc(rx_ring, bi)) { + ok = false; + break; + } + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + rx_ring->rx_buf_len, + DMA_BIDIRECTIONAL); + + /* Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBE_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, rx_ring->tail); + } + + return ok; +} + +void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) +{ + __ixgbe_alloc_rx_buffers_zc(rx_ring, count, + ixgbe_alloc_buffer_slow_zc); +} + +static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring, + u16 count) +{ + return __ixgbe_alloc_rx_buffers_zc(rx_ring, count, + ixgbe_alloc_buffer_zc); +} + +static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi, + struct xdp_buff *xdp) +{ + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + struct sk_buff *skb; + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + xdp->data_end - xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), xdp->data, datasize); + if (metasize) + skb_metadata_set(skb, metasize); + + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + return skb; +} + +static void ixgbe_inc_ntc(struct ixgbe_ring *rx_ring) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + prefetch(IXGBE_RX_DESC(rx_ring, ntc)); +} + +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct ixgbe_adapter *adapter = q_vector->adapter; + u16 cleaned_count = ixgbe_desc_unused(rx_ring); + unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; + struct sk_buff *skb; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq; + + while (likely(total_rx_packets < budget)) { + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + unsigned int size; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { + failure = failure || + !ixgbe_alloc_rx_buffers_fast_zc(rx_ring, + cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + bi = ixgbe_get_rx_buffer_zc(rx_ring, size); + + if (unlikely(!ixgbe_test_staterr(rx_desc, + IXGBE_RXD_STAT_EOP))) { + struct ixgbe_rx_buffer *next_bi; + + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + ixgbe_inc_ntc(rx_ring); + next_bi = + &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + next_bi->skb = ERR_PTR(-EINVAL); + continue; + } + + if (unlikely(bi->skb)) { + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + ixgbe_inc_ntc(rx_ring); + continue; + } + + xdp.data = bi->addr; + xdp.data_meta = xdp.data; + xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; + xdp.data_end = xdp.data + size; + xdp.handle = bi->handle; + + xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp); + + if (xdp_res) { + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; + bi->addr = NULL; + bi->skb = NULL; + } else { + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + } + total_rx_packets++; + total_rx_bytes += size; + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + continue; + } + + /* XDP_PASS path */ + skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp); + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + break; + } + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + + if (eth_skb_pad(skb)) + continue; + + total_rx_bytes += skb->len; + total_rx_packets++; + + ixgbe_process_skb_fields(rx_ring, rx_desc, skb); + ixgbe_rx_skb(q_vector, skb); + } + + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return failure ? budget : (int)total_rx_packets; +} + +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) +{ + u16 i = rx_ring->next_to_clean; + struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i]; + + while (i != rx_ring->next_to_alloc) { + xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle); + i++; + bi++; + if (i == rx_ring->count) { + i = 0; + bi = rx_ring->rx_buffer_info; + } + } +} + +static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) +{ + union ixgbe_adv_tx_desc *tx_desc = NULL; + struct ixgbe_tx_buffer *tx_bi; + bool work_done = true; + u32 len, cmd_type; + dma_addr_t dma; + + while (budget-- > 0) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + work_done = false; + break; + } + + if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len)) + break; + + dma_sync_single_for_device(xdp_ring->dev, dma, len, + DMA_BIDIRECTIONAL); + + tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; + tx_bi->bytecount = len; + tx_bi->xdpf = NULL; + + tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + xdp_ring->next_to_use++; + if (xdp_ring->next_to_use == xdp_ring->count) + xdp_ring->next_to_use = 0; + } + + if (tx_desc) { + ixgbe_xdp_ring_update_tail(xdp_ring); + xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + } + + return !!budget && work_done; +} + +static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *tx_bi) +{ + xdp_return_frame(tx_bi->xdpf); + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_bi, dma), + dma_unmap_len(tx_bi, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_bi, len, 0); +} + +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget) +{ + unsigned int total_packets = 0, total_bytes = 0; + u32 i = tx_ring->next_to_clean, xsk_frames = 0; + unsigned int budget = q_vector->tx.work_limit; + struct xdp_umem *umem = tx_ring->xsk_umem; + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_bi; + bool xmit_done; + + tx_bi = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + total_bytes += tx_bi->bytecount; + total_packets += tx_bi->gso_segs; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + total_bytes += tx_bi->bytecount; + + tx_bi++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_bi = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); + + xmit_done = ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); + return budget > 0 && xmit_done; +} + +int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!READ_ONCE(adapter->xdp_prog)) + return -ENXIO; + + if (qid >= adapter->num_xdp_queues) + return -ENXIO; + + if (!adapter->xsk_umems || !adapter->xsk_umems[qid]) + return -ENXIO; + + ring = adapter->xdp_ring[qid]; + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + u64 eics = BIT_ULL(ring->q_vector->v_idx); + + ixgbe_irq_rearm_queues(adapter, eics); + } + + return 0; +} + +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) +{ + u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; + struct xdp_umem *umem = tx_ring->xsk_umem; + struct ixgbe_tx_buffer *tx_bi; + u32 xsk_frames = 0; + + while (ntc != ntu) { + tx_bi = &tx_ring->tx_buffer_info[ntc]; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + + ntc++; + if (ntc == tx_ring->count) + ntc = 0; + } + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); +} diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index 997cea675a37..e8a3231be0bf 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -21,7 +21,6 @@ static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, u32 msgbuf[IXGBE_VFMAILBOX_SIZE] = { 0 }; struct ixgbe_hw *hw = &adapter->hw; struct sa_mbx_msg *sam; - u16 msglen; int ret; /* send the important bits to the PF */ @@ -38,16 +37,14 @@ static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, memcpy(sam->key, xs->aead->alg_key, sizeof(sam->key)); msgbuf[0] = IXGBE_VF_IPSEC_ADD; - msglen = sizeof(*sam) + sizeof(msgbuf[0]); spin_lock_bh(&adapter->mbx_lock); - ret = hw->mbx.ops.write_posted(hw, msgbuf, msglen); + ret = hw->mbx.ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE); if (ret) goto out; - msglen = sizeof(msgbuf[0]) * 2; - ret = hw->mbx.ops.read_posted(hw, msgbuf, msglen); + ret = hw->mbx.ops.read_posted(hw, msgbuf, 2); if (ret) goto out; @@ -80,11 +77,11 @@ static int ixgbevf_ipsec_del_pf_sa(struct ixgbevf_adapter *adapter, int pfsa) spin_lock_bh(&adapter->mbx_lock); - err = hw->mbx.ops.write_posted(hw, msgbuf, sizeof(msgbuf)); + err = hw->mbx.ops.write_posted(hw, msgbuf, 2); if (err) goto out; - err = hw->mbx.ops.read_posted(hw, msgbuf, sizeof(msgbuf)); + err = hw->mbx.ops.read_posted(hw, msgbuf, 2); if (err) goto out; @@ -470,7 +467,7 @@ int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, } sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; - if (unlikely(sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + if (unlikely(sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) { netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", __func__, sa_idx, xs->xso.offload_handle); return 0; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2373cd41a625..14f9679c957c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1755,7 +1755,7 @@ static void mvpp2_txq_desc_put(struct mvpp2_tx_queue *txq) } /* Set Tx descriptors fields relevant for CSUM calculation */ -static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto, +static u32 mvpp2_txq_desc_csum(int l3_offs, __be16 l3_proto, int ip_hdr_len, int l4_proto) { u32 command; @@ -2645,14 +2645,15 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; u8 l4_proto; + __be16 l3_proto = vlan_get_protocol(skb); - if (skb->protocol == htons(ETH_P_IP)) { + if (l3_proto == htons(ETH_P_IP)) { struct iphdr *ip4h = ip_hdr(skb); /* Calculate IPv4 checksum and L4 checksum */ ip_hdr_len = ip4h->ihl; l4_proto = ip4h->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (l3_proto == htons(ETH_P_IPV6)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); /* Read l4_protocol from one of IPv6 extra headers */ @@ -2664,7 +2665,7 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) } return mvpp2_txq_desc_csum(skb_network_offset(skb), - skb->protocol, ip_hdr_len, l4_proto); + l3_proto, ip_hdr_len, l4_proto); } return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index ff2fea0f8b75..0bd4351b2a49 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -988,8 +988,8 @@ static int pxa168_init_phy(struct net_device *dev) cmd.base.phy_address = pep->phy_addr; cmd.base.speed = pep->phy_speed; cmd.base.duplex = pep->phy_duplex; - ethtool_convert_legacy_u32_to_link_mode(cmd.link_modes.advertising, - PHY_BASIC_FEATURES); + bitmap_copy(cmd.link_modes.advertising, PHY_BASIC_FEATURES, + __ETHTOOL_LINK_MODE_MASK_NBITS); cmd.base.autoneg = AUTONEG_ENABLE; if (cmd.base.speed != 0) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index cc1e9a96a43b..7dbfdac4067a 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -243,11 +243,7 @@ static void mtk_phy_link_adjust(struct net_device *dev) if (dev->phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - if (dev->phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (dev->phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; - + lcl_adv = ethtool_adv_to_lcl_adv_t(dev->phydev->advertising); flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (flowctrl & FLOW_CTRL_TX) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 01a967e717e7..1d743bd5d212 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -54,6 +54,7 @@ #include "en_stats.h" #include "en/fs.h" +extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) @@ -209,6 +210,7 @@ enum mlx5e_priv_flag { MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1), MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 2), MLX5E_PFLAG_RX_STRIDING_RQ = (1 << 3), + MLX5E_PFLAG_RX_NO_CSUM_COMPLETE = (1 << 4), }; #define MLX5E_SET_PFLAG(params, pflag, enable) \ @@ -290,6 +292,7 @@ struct mlx5e_dcbx_dp { enum { MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_AM, + MLX5E_RQ_STATE_NO_CSUM_COMPLETE, }; struct mlx5e_cq { @@ -906,8 +909,8 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq); int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); -int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv); -void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv); +int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); +void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); int mlx5e_create_direct_rqts(struct mlx5e_priv *priv); void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv); @@ -951,6 +954,8 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal); int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal); +u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv); +u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv); int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, struct ethtool_ts_info *info); int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv, @@ -966,6 +971,9 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 max_channels, u16 mtu); +void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params); +void mlx5e_build_rss_params(struct mlx5e_params *params); u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index bbf69e859b78..1431232c9a09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -16,6 +16,8 @@ struct mlx5e_tc_table { DECLARE_HASHTABLE(mod_hdr_tbl, 8); DECLARE_HASHTABLE(hairpin_tbl, 8); + + struct notifier_block netdevice_nb; }; struct mlx5e_flow_table { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 45cdde694d20..8657e0f26995 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -543,8 +543,11 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv, rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); - netdev_err(priv->netdev, "%s: add rule(filter id=%d, rq idx=%d) failed, err=%d\n", - __func__, arfs_rule->filter_id, arfs_rule->rxq, err); + priv->channel_stats[arfs_rule->rxq].rq.arfs_err++; + mlx5e_dbg(HW, priv, + "%s: add rule(filter id=%d, rq idx=%d, ip proto=0x%x) failed,err=%d\n", + __func__, arfs_rule->filter_id, arfs_rule->rxq, + tuple->ip_proto, err); } out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8cd338ceb237..c86fd770c463 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -140,6 +140,7 @@ static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { "tx_cqe_moder", "rx_cqe_compress", "rx_striding_rq", + "rx_no_csum_complete", }; int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset) @@ -859,18 +860,30 @@ out: return err; } +u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv) +{ + return sizeof(priv->channels.params.toeplitz_hash_key); +} + static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - return sizeof(priv->channels.params.toeplitz_hash_key); + return mlx5e_ethtool_get_rxfh_key_size(priv); } -static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev) +u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv) { return MLX5E_INDIR_RQT_SIZE; } +static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + return mlx5e_ethtool_get_rxfh_indir_size(priv); +} + static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { @@ -1519,6 +1532,27 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return 0; } +static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_channels *channels = &priv->channels; + struct mlx5e_channel *c; + int i; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + for (i = 0; i < channels->num; i++) { + c = channels->c[i]; + if (enable) + __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); + else + __clear_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); + } + + return 0; +} + static int mlx5e_handle_pflag(struct net_device *netdev, u32 wanted_flags, enum mlx5e_priv_flag flag, @@ -1570,6 +1604,12 @@ static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags) err = mlx5e_handle_pflag(netdev, pflags, MLX5E_PFLAG_RX_STRIDING_RQ, set_pflag_rx_striding_rq); + if (err) + goto out; + + err = mlx5e_handle_pflag(netdev, pflags, + MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, + set_pflag_rx_no_csum_complete); out: mutex_unlock(&priv->state_lock); 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 41cde926cdab..c18dcebe1462 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -131,14 +131,14 @@ set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m, if (ip4src_m) { memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4), &ip4src_v, sizeof(ip4src_v)); - memset(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4), - 0xff, sizeof(ip4src_m)); + memcpy(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4), + &ip4src_m, sizeof(ip4src_m)); } if (ip4dst_m) { memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), &ip4dst_v, sizeof(ip4dst_v)); - memset(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - 0xff, sizeof(ip4dst_m)); + memcpy(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &ip4dst_m, sizeof(ip4dst_m)); } MLX5E_FTE_SET(headers_c, ethertype, 0xffff); @@ -173,11 +173,11 @@ set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v, __be16 pdst_m, __be16 pdst_v) { if (psrc_m) { - MLX5E_FTE_SET(headers_c, tcp_sport, 0xffff); + MLX5E_FTE_SET(headers_c, tcp_sport, ntohs(psrc_m)); MLX5E_FTE_SET(headers_v, tcp_sport, ntohs(psrc_v)); } if (pdst_m) { - MLX5E_FTE_SET(headers_c, tcp_dport, 0xffff); + MLX5E_FTE_SET(headers_c, tcp_dport, ntohs(pdst_m)); MLX5E_FTE_SET(headers_v, tcp_dport, ntohs(pdst_v)); } @@ -190,12 +190,12 @@ set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v, __be16 pdst_m, __be16 pdst_v) { if (psrc_m) { - MLX5E_FTE_SET(headers_c, udp_sport, 0xffff); + MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_m)); MLX5E_FTE_SET(headers_v, udp_sport, ntohs(psrc_v)); } if (pdst_m) { - MLX5E_FTE_SET(headers_c, udp_dport, 0xffff); + MLX5E_FTE_SET(headers_c, udp_dport, ntohs(pdst_m)); MLX5E_FTE_SET(headers_v, udp_dport, ntohs(pdst_v)); } @@ -508,26 +508,14 @@ static int validate_tcpudp4(struct ethtool_rx_flow_spec *fs) if (l4_mask->tos) return -EINVAL; - if (l4_mask->ip4src) { - if (!all_ones(l4_mask->ip4src)) - return -EINVAL; + if (l4_mask->ip4src) ntuples++; - } - if (l4_mask->ip4dst) { - if (!all_ones(l4_mask->ip4dst)) - return -EINVAL; + if (l4_mask->ip4dst) ntuples++; - } - if (l4_mask->psrc) { - if (!all_ones(l4_mask->psrc)) - return -EINVAL; + if (l4_mask->psrc) ntuples++; - } - if (l4_mask->pdst) { - if (!all_ones(l4_mask->pdst)) - return -EINVAL; + if (l4_mask->pdst) ntuples++; - } /* Flow is TCP/UDP */ return ++ntuples; } @@ -540,16 +528,10 @@ static int validate_ip4(struct ethtool_rx_flow_spec *fs) if (l3_mask->l4_4_bytes || l3_mask->tos || fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4) return -EINVAL; - if (l3_mask->ip4src) { - if (!all_ones(l3_mask->ip4src)) - return -EINVAL; + if (l3_mask->ip4src) ntuples++; - } - if (l3_mask->ip4dst) { - if (!all_ones(l3_mask->ip4dst)) - return -EINVAL; + if (l3_mask->ip4dst) ntuples++; - } if (l3_mask->proto) ntuples++; /* Flow is IPv4 */ @@ -588,16 +570,10 @@ static int validate_tcpudp6(struct ethtool_rx_flow_spec *fs) if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6dst)) ntuples++; - if (l4_mask->psrc) { - if (!all_ones(l4_mask->psrc)) - return -EINVAL; + if (l4_mask->psrc) ntuples++; - } - if (l4_mask->pdst) { - if (!all_ones(l4_mask->pdst)) - return -EINVAL; + if (l4_mask->pdst) ntuples++; - } /* Flow is TCP/UDP */ return ++ntuples; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5955b4d844cc..bc034958c846 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -929,6 +929,9 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (params->rx_dim_enabled) __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); + if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) + __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); + return 0; err_destroy_rq: @@ -3175,7 +3178,7 @@ static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *t MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); } -int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) +int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) { struct mlx5e_tir *tir; void *tirc; @@ -3202,7 +3205,7 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) } } - if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev)) goto out; for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) { @@ -3273,14 +3276,14 @@ err_destroy_ch_tirs: return err; } -void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv) +void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) { int i; for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]); - if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev)) return; for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) @@ -4315,7 +4318,7 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static const struct net_device_ops mlx5e_netdev_ops = { +const struct net_device_ops mlx5e_netdev_ops = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, @@ -4480,6 +4483,31 @@ static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeo return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); } +void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + /* Prefer Striding RQ, unless any of the following holds: + * - Striding RQ configuration is not possible/supported. + * - Slow PCI heuristic. + * - Legacy RQ would use linear SKB while Striding RQ would use non-linear. + */ + if (!slow_pci_heuristic(mdev) && + mlx5e_striding_rq_possible(mdev, params) && + (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) || + !mlx5e_rx_is_linear_skb(mdev, params))) + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true); + mlx5e_set_rq_type(mdev, params); + mlx5e_init_rq_type_params(mdev, params); +} + +void mlx5e_build_rss_params(struct mlx5e_params *params) +{ + params->rss_hfunc = ETH_RSS_HASH_XOR; + netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key)); + mlx5e_build_default_indir_rqt(params->indirection_rqt, + MLX5E_INDIR_RQT_SIZE, params->num_channels); +} + void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 max_channels, u16 mtu) @@ -4503,20 +4531,10 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, params->rx_cqe_compress_def = slow_pci_heuristic(mdev); MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false); /* RQ */ - /* Prefer Striding RQ, unless any of the following holds: - * - Striding RQ configuration is not possible/supported. - * - Slow PCI heuristic. - * - Legacy RQ would use linear SKB while Striding RQ would use non-linear. - */ - if (!slow_pci_heuristic(mdev) && - mlx5e_striding_rq_possible(mdev, params) && - (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) || - !mlx5e_rx_is_linear_skb(mdev, params))) - MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true); - mlx5e_set_rq_type(mdev, params); - mlx5e_init_rq_type_params(mdev, params); + mlx5e_build_rq_params(mdev, params); /* HW LRO */ @@ -4539,10 +4557,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev); /* RSS */ - params->rss_hfunc = ETH_RSS_HASH_XOR; - netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key)); - mlx5e_build_default_indir_rqt(params->indirection_rqt, - MLX5E_INDIR_RQT_SIZE, max_channels); + mlx5e_build_rss_params(params); } static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, @@ -4780,7 +4795,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_rqts; - err = mlx5e_create_indirect_tirs(priv); + err = mlx5e_create_indirect_tirs(priv, true); if (err) goto err_destroy_direct_rqts; @@ -4805,7 +4820,7 @@ err_destroy_flow_steering: err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_indirect_tirs: - mlx5e_destroy_indirect_tirs(priv); + mlx5e_destroy_indirect_tirs(priv, true); err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: @@ -4822,7 +4837,7 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) mlx5e_tc_nic_cleanup(priv); mlx5e_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); - mlx5e_destroy_indirect_tirs(priv); + mlx5e_destroy_indirect_tirs(priv, true); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index f6eead24931f..9264c3332aa6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -46,8 +46,6 @@ #define MLX5E_REP_PARAMS_LOG_SQ_SIZE \ max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) -#define MLX5E_REP_PARAMS_LOG_RQ_SIZE \ - max(0x6, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE) static const char mlx5e_rep_driver_name[] = "mlx5e_rep"; @@ -182,12 +180,108 @@ static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset) } } +static void mlx5e_rep_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *param) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + mlx5e_ethtool_get_ringparam(priv, param); +} + +static int mlx5e_rep_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *param) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + return mlx5e_ethtool_set_ringparam(priv, param); +} + +static int mlx5e_replace_rep_vport_rx_rule(struct mlx5e_priv *priv, + struct mlx5_flow_destination *dest) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_flow_handle *flow_rule; + + flow_rule = mlx5_eswitch_create_vport_rx_rule(esw, + rep->vport, + dest); + if (IS_ERR(flow_rule)) + return PTR_ERR(flow_rule); + + mlx5_del_flow_rules(rpriv->vport_rx_rule); + rpriv->vport_rx_rule = flow_rule; + return 0; +} + +static void mlx5e_rep_get_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + mlx5e_ethtool_get_channels(priv, ch); +} + +static int mlx5e_rep_set_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + u16 curr_channels_amount = priv->channels.params.num_channels; + u32 new_channels_amount = ch->combined_count; + struct mlx5_flow_destination new_dest; + int err = 0; + + err = mlx5e_ethtool_set_channels(priv, ch); + if (err) + return err; + + if (curr_channels_amount == 1 && new_channels_amount > 1) { + new_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + new_dest.ft = priv->fs.ttc.ft.t; + } else if (new_channels_amount == 1 && curr_channels_amount > 1) { + new_dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; + new_dest.tir_num = priv->direct_tir[0].tirn; + } else { + return 0; + } + + err = mlx5e_replace_rep_vport_rx_rule(priv, &new_dest); + if (err) { + netdev_warn(priv->netdev, "Failed to update vport rx rule, when going from (%d) channels to (%d) channels\n", + curr_channels_amount, new_channels_amount); + return err; + } + + return 0; +} + +static u32 mlx5e_rep_get_rxfh_key_size(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + return mlx5e_ethtool_get_rxfh_key_size(priv); +} + +static u32 mlx5e_rep_get_rxfh_indir_size(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + return mlx5e_ethtool_get_rxfh_indir_size(priv); +} + static const struct ethtool_ops mlx5e_rep_ethtool_ops = { .get_drvinfo = mlx5e_rep_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = mlx5e_rep_get_strings, .get_sset_count = mlx5e_rep_get_sset_count, .get_ethtool_stats = mlx5e_rep_get_ethtool_stats, + .get_ringparam = mlx5e_rep_get_ringparam, + .set_ringparam = mlx5e_rep_set_ringparam, + .get_channels = mlx5e_rep_get_channels, + .set_channels = mlx5e_rep_set_channels, + .get_rxfh_key_size = mlx5e_rep_get_rxfh_key_size, + .get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size, }; int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) @@ -934,16 +1028,20 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev, params->hard_mtu = MLX5E_ETH_HARD_MTU; params->sw_mtu = mtu; params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE; - params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; - params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE; + /* RQ */ + mlx5e_build_rq_params(mdev, params); + + /* CQ moderation params */ params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); mlx5e_set_rx_cq_mode_params(params, cq_period_mode); params->num_tc = 1; - params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); + + /* RSS */ + mlx5e_build_rss_params(params); } static void mlx5e_build_rep_netdev(struct net_device *netdev) @@ -963,6 +1061,16 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL; netdev->hw_features |= NETIF_F_HW_TC; + netdev->hw_features |= NETIF_F_SG; + netdev->hw_features |= NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + netdev->hw_features |= NETIF_F_GRO; + netdev->hw_features |= NETIF_F_TSO; + netdev->hw_features |= NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_RXCSUM; + + netdev->features |= netdev->hw_features; + eth_hw_addr_random(netdev); netdev->min_mtu = ETH_MIN_MTU; @@ -986,7 +1094,7 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev, INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work); - priv->channels.params.num_channels = profile->max_nch(mdev); + priv->channels.params.num_channels = 1; mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu); mlx5e_build_rep_netdev(netdev); @@ -994,13 +1102,50 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); } -static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) +static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv) +{ + struct ttc_params ttc_params = {}; + int tt, err; + + priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, + MLX5_FLOW_NAMESPACE_KERNEL); + + /* The inner_ttc in the ttc params is intentionally not set */ + ttc_params.any_tt_tirn = priv->direct_tir[0].tirn; + mlx5e_set_ttc_ft_params(&ttc_params); + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) + ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn; + + err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc); + if (err) { + netdev_err(priv->netdev, "Failed to create rep ttc table, err=%d\n", err); + return err; + } + return 0; +} + +static int mlx5e_create_rep_vport_rx_rule(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_destination dest; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; + dest.tir_num = priv->direct_tir[0].tirn; + flow_rule = mlx5_eswitch_create_vport_rx_rule(esw, + rep->vport, + &dest); + if (IS_ERR(flow_rule)) + return PTR_ERR(flow_rule); + rpriv->vport_rx_rule = flow_rule; + return 0; +} + +static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; int err; mlx5e_init_l2_addr(priv); @@ -1011,29 +1156,42 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return err; } - err = mlx5e_create_direct_rqts(priv); + err = mlx5e_create_indirect_rqt(priv); if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_tirs(priv); + err = mlx5e_create_direct_rqts(priv); + if (err) + goto err_destroy_indirect_rqts; + + err = mlx5e_create_indirect_tirs(priv, false); if (err) goto err_destroy_direct_rqts; - flow_rule = mlx5_eswitch_create_vport_rx_rule(esw, - rep->vport, - priv->direct_tir[0].tirn); - if (IS_ERR(flow_rule)) { - err = PTR_ERR(flow_rule); + err = mlx5e_create_direct_tirs(priv); + if (err) + goto err_destroy_indirect_tirs; + + err = mlx5e_create_rep_ttc_table(priv); + if (err) goto err_destroy_direct_tirs; - } - rpriv->vport_rx_rule = flow_rule; + + err = mlx5e_create_rep_vport_rx_rule(priv); + if (err) + goto err_destroy_ttc_table; return 0; +err_destroy_ttc_table: + mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); +err_destroy_indirect_tirs: + mlx5e_destroy_indirect_tirs(priv, false); err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); +err_destroy_indirect_rqts: + mlx5e_destroy_rqt(priv, &priv->indir_rqt); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); return err; @@ -1044,8 +1202,11 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; mlx5_del_flow_rules(rpriv->vport_rx_rule); + mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_indirect_tirs(priv, false); mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); } @@ -1061,12 +1222,6 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return 0; } -static int mlx5e_get_rep_max_num_channels(struct mlx5_core_dev *mdev) -{ -#define MLX5E_PORT_REPRESENTOR_NCH 1 - return MLX5E_PORT_REPRESENTOR_NCH; -} - static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .init_rx = mlx5e_init_rep_rx, @@ -1074,10 +1229,10 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .init_tx = mlx5e_init_rep_tx, .cleanup_tx = mlx5e_cleanup_nic_tx, .update_stats = mlx5e_rep_update_hw_counters, - .max_nch = mlx5e_get_rep_max_num_channels, + .max_nch = mlx5e_get_max_num_channels, .update_carrier = NULL, .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, - .rx_handlers.handle_rx_cqe_mpwqe = NULL /* Not supported */, + .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = 1, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 424bc89184c6..f19067c94272 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -782,6 +782,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } + if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))) + goto csum_unnecessary; + if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) { if (unlikely(get_ip_proto(skb, proto) == IPPROTO_SCTP)) goto csum_unnecessary; @@ -805,7 +808,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, csum_unnecessary: if (likely((cqe->hds_ip_ext & CQE_L3_OK) && - (cqe->hds_ip_ext & CQE_L4_OK))) { + ((cqe->hds_ip_ext & CQE_L4_OK) || + (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) { skb->ip_summed = CHECKSUM_UNNECESSARY; if (cqe_is_tunneled(cqe)) { skb->csum_level = 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 90c7607b1f44..b7d4896c7c7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -93,6 +93,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) }, @@ -170,6 +171,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_cache_busy += rq_stats->cache_busy; s->rx_cache_waive += rq_stats->cache_waive; s->rx_congst_umr += rq_stats->congst_umr; + s->rx_arfs_err += rq_stats->arfs_err; s->ch_events += ch_stats->events; s->ch_poll += ch_stats->poll; s->ch_arm += ch_stats->arm; @@ -1161,6 +1163,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) }, }; static const struct counter_desc sq_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index a5fb3dc27f50..77f74ce11280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -106,6 +106,7 @@ struct mlx5e_sw_stats { u64 rx_cache_busy; u64 rx_cache_waive; u64 rx_congst_umr; + u64 rx_arfs_err; u64 ch_events; u64 ch_poll; u64 ch_arm; @@ -202,6 +203,7 @@ struct mlx5e_rq_stats { u64 cache_busy; u64 cache_waive; u64 congst_umr; + u64 arfs_err; }; struct mlx5e_sq_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9fed54017659..6de21d9f4fad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -532,7 +532,8 @@ static struct mlx5e_hairpin_entry *mlx5e_hairpin_get(struct mlx5e_priv *priv, #define UNKNOWN_MATCH_PRIO 8 static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, u8 *match_prio) + struct mlx5_flow_spec *spec, u8 *match_prio, + struct netlink_ext_ack *extack) { void *headers_c, *headers_v; u8 prio_val, prio_mask = 0; @@ -540,8 +541,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, #ifdef CONFIG_MLX5_CORE_EN_DCB if (priv->dcbx_dp.trust_state != MLX5_QPTS_TRUST_PCP) { - netdev_warn(priv->netdev, - "only PCP trust state supported for hairpin\n"); + NL_SET_ERR_MSG_MOD(extack, + "only PCP trust state supported for hairpin"); return -EOPNOTSUPP; } #endif @@ -557,8 +558,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, if (!vlan_present || !prio_mask) { prio_val = UNKNOWN_MATCH_PRIO; } else if (prio_mask != 0x7) { - netdev_warn(priv->netdev, - "masked priority match not supported for hairpin\n"); + NL_SET_ERR_MSG_MOD(extack, + "masked priority match not supported for hairpin"); return -EOPNOTSUPP; } @@ -568,7 +569,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { int peer_ifindex = parse_attr->mirred_ifindex; struct mlx5_hairpin_params params; @@ -583,12 +585,13 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { - netdev_warn(priv->netdev, "hairpin is not supported\n"); + NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; } peer_id = MLX5_CAP_GEN(peer_mdev, vhca_id); - err = mlx5e_hairpin_get_prio(priv, &parse_attr->spec, &match_prio); + err = mlx5e_hairpin_get_prio(priv, &parse_attr->spec, &match_prio, + extack); if (err) return err; hpe = mlx5e_hairpin_get(priv, peer_id, match_prio); @@ -677,7 +680,8 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, static struct mlx5_flow_handle * mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_nic_flow_attr *attr = flow->nic_attr; struct mlx5_core_dev *dev = priv->mdev; @@ -694,7 +698,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, int err, dest_ix = 0; if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) { - err = mlx5e_hairpin_flow_add(priv, flow, parse_attr); + err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); if (err) { rule = ERR_PTR(err); goto err_add_hairpin_flow; @@ -753,6 +757,8 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, MLX5E_TC_TABLE_NUM_GROUPS, MLX5E_TC_FT_LEVEL, 0); if (IS_ERR(priv->fs.tc.t)) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to create tc offload table\n"); netdev_err(priv->netdev, "Failed to create tc offload table\n"); rule = ERR_CAST(priv->fs.tc.t); @@ -819,12 +825,14 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct ip_tunnel_info *tun_info, struct net_device *mirred_dev, struct net_device **encap_dev, - struct mlx5e_tc_flow *flow); + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack); static struct mlx5_flow_handle * mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->esw_attr; @@ -838,7 +846,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, out_dev = __dev_get_by_index(dev_net(priv->netdev), attr->parse_attr->mirred_ifindex); err = mlx5e_attach_encap(priv, &parse_attr->tun_info, - out_dev, &encap_dev, flow); + out_dev, &encap_dev, flow, extack); if (err) { rule = ERR_PTR(err); if (err != -EAGAIN) @@ -1105,6 +1113,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f) { + struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, @@ -1133,6 +1142,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); else { + NL_SET_ERR_MSG_MOD(extack, + "port isn't an offloaded vxlan udp dport"); netdev_warn(priv->netdev, "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst)); return -EOPNOTSUPP; @@ -1149,6 +1160,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, udp_sport, ntohs(key->src)); } else { /* udp dst port must be given */ vxlan_match_offload_err: + NL_SET_ERR_MSG_MOD(extack, + "IP tunnel decap offload supported only for vxlan, must set UDP dport"); netdev_warn(priv->netdev, "IP tunnel decap offload supported only for vxlan, must set UDP dport\n"); return -EOPNOTSUPP; @@ -1225,6 +1238,16 @@ vxlan_match_offload_err: MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + + if (mask->ttl && + !MLX5_CAP_ESW_FLOWTABLE_FDB + (priv->mdev, + ft_field_support.outer_ipv4_ttl)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on TTL is not supported"); + return -EOPNOTSUPP; + } + } /* Enforce DMAC when offloading incoming tunneled flows. @@ -1247,6 +1270,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f, u8 *match_level) { + struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, @@ -1277,6 +1301,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_TCP) | BIT(FLOW_DISSECTOR_KEY_IP) | BIT(FLOW_DISSECTOR_KEY_ENC_IP))) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", f->dissector->used_keys); return -EOPNOTSUPP; @@ -1368,6 +1393,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } + } else { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) { @@ -1550,8 +1578,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, - ft_field_support.outer_ipv4_ttl)) + ft_field_support.outer_ipv4_ttl)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on TTL is not supported"); return -EOPNOTSUPP; + } if (mask->tos || mask->ttl) *match_level = MLX5_MATCH_L3; @@ -1593,6 +1624,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, udp_dport, ntohs(key->dst)); break; default: + NL_SET_ERR_MSG_MOD(extack, + "Only UDP and TCP transports are supported for L4 matching"); netdev_err(priv->netdev, "Only UDP and TCP transport are supported\n"); return -EINVAL; @@ -1629,6 +1662,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f) { + struct netlink_ext_ack *extack = f->common.extack; struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1643,6 +1677,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, if (rep->vport != FDB_UPLINK_VPORT && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && esw->offloads.inline_mode < match_level)) { + NL_SET_ERR_MSG_MOD(extack, + "Flow is not offloaded due to min inline setting"); netdev_warn(priv->netdev, "Flow is not offloaded due to min inline setting, required %d actual %d\n", match_level, esw->offloads.inline_mode); @@ -1744,7 +1780,8 @@ static struct mlx5_fields fields[] = { */ static int offload_pedit_fields(struct pedit_headers *masks, struct pedit_headers *vals, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; int i, action_size, nactions, max_actions, first, last, next_z; @@ -1783,11 +1820,15 @@ static int offload_pedit_fields(struct pedit_headers *masks, continue; if (s_mask && a_mask) { + NL_SET_ERR_MSG_MOD(extack, + "can't set and add to the same HW field"); printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field); return -EOPNOTSUPP; } if (nactions == max_actions) { + NL_SET_ERR_MSG_MOD(extack, + "too many pedit actions, can't offload"); printk(KERN_WARNING "mlx5: parsed %d pedit actions, can't do more\n", nactions); return -EOPNOTSUPP; } @@ -1820,6 +1861,8 @@ static int offload_pedit_fields(struct pedit_headers *masks, next_z = find_next_zero_bit(&mask, field_bsize, first); last = find_last_bit(&mask, field_bsize); if (first < next_z && next_z < last) { + NL_SET_ERR_MSG_MOD(extack, + "rewrite of few sub-fields isn't supported"); printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", mask); return -EOPNOTSUPP; @@ -1878,7 +1921,8 @@ static const struct pedit_headers zero_masks = {}; static int parse_tc_pedit_action(struct mlx5e_priv *priv, const struct tc_action *a, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks; int nkeys, i, err = -EOPNOTSUPP; @@ -1896,12 +1940,13 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, err = -EOPNOTSUPP; /* can't be all optimistic */ if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) { - netdev_warn(priv->netdev, "legacy pedit isn't offloaded\n"); + NL_SET_ERR_MSG_MOD(extack, + "legacy pedit isn't offloaded"); goto out_err; } if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) { - netdev_warn(priv->netdev, "pedit cmd %d isn't offloaded\n", cmd); + NL_SET_ERR_MSG_MOD(extack, "pedit cmd isn't offloaded"); goto out_err; } @@ -1918,13 +1963,15 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, if (err) goto out_err; - err = offload_pedit_fields(masks, vals, parse_attr); + err = offload_pedit_fields(masks, vals, parse_attr, extack); if (err < 0) goto out_dealloc_parsed_actions; for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { cmd_masks = &masks[cmd]; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { + NL_SET_ERR_MSG_MOD(extack, + "attempt to offload an unsupported field"); netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd); print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS, 16, 1, cmd_masks, sizeof(zero_masks), true); @@ -1941,19 +1988,26 @@ out_err: return err; } -static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 update_flags) +static bool csum_offload_supported(struct mlx5e_priv *priv, + u32 action, + u32 update_flags, + struct netlink_ext_ack *extack) { u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP; /* The HW recalcs checksums only if re-writing headers */ if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) { + NL_SET_ERR_MSG_MOD(extack, + "TC csum action is only offloaded with pedit"); netdev_warn(priv->netdev, "TC csum action is only offloaded with pedit\n"); return false; } if (update_flags & ~prot_flags) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload TC csum action for some header/s"); netdev_warn(priv->netdev, "can't offload TC csum action for some header/s - flags %#x\n", update_flags); @@ -1964,7 +2018,8 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 upda } static bool modify_header_match_supported(struct mlx5_flow_spec *spec, - struct tcf_exts *exts) + struct tcf_exts *exts, + struct netlink_ext_ack *extack) { const struct tc_action *a; bool modify_ip_header; @@ -2002,6 +2057,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload re-write of non TCP/UDP"); pr_info("can't offload re-write of ip proto %d\n", ip_proto); return false; } @@ -2013,7 +2070,8 @@ out_ok: static bool actions_match_supported(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { u32 actions; @@ -2027,7 +2085,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv, return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - return modify_header_match_supported(&parse_attr->spec, exts); + return modify_header_match_supported(&parse_attr->spec, exts, + extack); return true; } @@ -2040,15 +2099,16 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) fmdev = priv->mdev; pmdev = peer_priv->mdev; - mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid); - mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid); + fsystem_guid = mlx5_query_nic_system_image_guid(fmdev); + psystem_guid = mlx5_query_nic_system_image_guid(pmdev); return (fsystem_guid == psystem_guid); } static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_nic_flow_attr *attr = flow->nic_attr; const struct tc_action *a; @@ -2072,7 +2132,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_pedit(a)) { err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr); + parse_attr, extack); if (err) return err; @@ -2083,7 +2143,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_csum(a)) { if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a))) + tcf_csum_update_flags(a), + extack)) continue; return -EOPNOTSUPP; @@ -2099,6 +2160,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; } else { + NL_SET_ERR_MSG_MOD(extack, + "device is not on same HW, can't offload"); netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", peer_dev->name); return -EINVAL; @@ -2110,8 +2173,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 mark = tcf_skbedit_mark(a); if (mark & ~MLX5E_TC_FLOW_ID_MASK) { - netdev_warn(priv->netdev, "Bad flow mark - only 16 bit is supported: 0x%x\n", - mark); + NL_SET_ERR_MSG_MOD(extack, + "Bad flow mark - only 16 bit is supported"); return -EINVAL; } @@ -2124,7 +2187,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow)) + if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) return -EOPNOTSUPP; return 0; @@ -2526,7 +2589,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct ip_tunnel_info *tun_info, struct net_device *mirred_dev, struct net_device **encap_dev, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; unsigned short family = ip_tunnel_info_af(tun_info); @@ -2544,6 +2608,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, /* setting udp src port isn't supported */ if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) { vxlan_encap_offload_err: + NL_SET_ERR_MSG_MOD(extack, + "must set udp dst port and not set udp src port"); netdev_warn(priv->netdev, "must set udp dst port and not set udp src port\n"); return -EOPNOTSUPP; @@ -2553,6 +2619,8 @@ vxlan_encap_offload_err: MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { + NL_SET_ERR_MSG_MOD(extack, + "port isn't an offloaded vxlan udp dport"); netdev_warn(priv->netdev, "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst)); return -EOPNOTSUPP; @@ -2657,7 +2725,8 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -2683,7 +2752,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_pedit(a)) { err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB, - parse_attr); + parse_attr, extack); if (err) return err; @@ -2694,7 +2763,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_csum(a)) { if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a))) + tcf_csum_update_flags(a), + extack)) continue; return -EOPNOTSUPP; @@ -2707,6 +2777,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, out_dev = tcf_mirred_dev(a); if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { + NL_SET_ERR_MSG_MOD(extack, + "can't support more output ports, can't offload forwarding"); pr_err("can't support more than %d output ports, can't offload forwarding\n", attr->out_count); return -EOPNOTSUPP; @@ -2730,6 +2802,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, MLX5_FLOW_CONTEXT_ACTION_COUNT; /* attr->out_rep is resolved when we handle encap */ } else { + NL_SET_ERR_MSG_MOD(extack, + "devices are not on same switch HW, can't offload forwarding"); pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); return -EINVAL; @@ -2766,10 +2840,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow)) + if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) return -EOPNOTSUPP; if (attr->out_count > 1 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { + NL_SET_ERR_MSG_MOD(extack, + "current firmware doesn't support split rule for port mirroring"); netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n"); return -EOPNOTSUPP; } @@ -2811,6 +2887,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv) int mlx5e_configure_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f, int flags) { + struct netlink_ext_ack *extack = f->common.extack; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct rhashtable *tc_ht = get_tc_ht(priv); @@ -2822,6 +2899,8 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); if (flow) { + NL_SET_ERR_MSG_MOD(extack, + "flow cookie already exists, ignoring"); netdev_warn_once(priv->netdev, "flow cookie %lx already exists, ignoring\n", f->cookie); return 0; } @@ -2850,15 +2929,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, goto err_free; if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { - err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow); + err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow, + extack); if (err < 0) goto err_free; - flow->rule[0] = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, + extack); } else { - err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow); + err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, + extack); if (err < 0) goto err_free; - flow->rule[0] = mlx5e_tc_add_nic_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_nic_flow(priv, parse_attr, flow, + extack); } if (IS_ERR(flow->rule[0])) { @@ -2946,14 +3029,71 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, return 0; } +static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, + struct mlx5e_priv *peer_priv) +{ + struct mlx5_core_dev *peer_mdev = peer_priv->mdev; + struct mlx5e_hairpin_entry *hpe; + u16 peer_vhca_id; + int bkt; + + if (!same_hw_devs(priv, peer_priv)) + return; + + peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); + + hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) { + if (hpe->peer_vhca_id == peer_vhca_id) + hpe->hp->pair->peer_gone = true; + } +} + +static int mlx5e_tc_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct mlx5e_flow_steering *fs; + struct mlx5e_priv *peer_priv; + struct mlx5e_tc_table *tc; + struct mlx5e_priv *priv; + + if (ndev->netdev_ops != &mlx5e_netdev_ops || + event != NETDEV_UNREGISTER || + ndev->reg_state == NETREG_REGISTERED) + return NOTIFY_DONE; + + tc = container_of(this, struct mlx5e_tc_table, netdevice_nb); + fs = container_of(tc, struct mlx5e_flow_steering, tc); + priv = container_of(fs, struct mlx5e_priv, fs); + peer_priv = netdev_priv(ndev); + if (priv == peer_priv || + !(priv->netdev->features & NETIF_F_HW_TC)) + return NOTIFY_DONE; + + mlx5e_tc_hairpin_update_dead_peer(priv, peer_priv); + + return NOTIFY_DONE; +} + int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; + int err; hash_init(tc->mod_hdr_tbl); hash_init(tc->hairpin_tbl); - return rhashtable_init(&tc->ht, &tc_ht_params); + err = rhashtable_init(&tc->ht, &tc_ht_params); + if (err) + return err; + + tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; + if (register_netdevice_notifier(&tc->netdevice_nb)) { + tc->netdevice_nb.notifier_call = NULL; + mlx5_core_warn(priv->mdev, "Failed to register netdev notifier\n"); + } + + return err; } static void _mlx5e_tc_del_flow(void *ptr, void *arg) @@ -2969,6 +3109,9 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; + if (tc->netdevice_nb.notifier_call) + unregister_netdevice_notifier(&tc->netdevice_nb); + rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL); if (!IS_ERR_OR_NULL(tc->t)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2b252cde5cc2..ea7dedc2d5ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2000,7 +2000,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i; - for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; @@ -2020,7 +2020,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i; - for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c17bfcab517c..dfc642de4e6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -230,7 +230,8 @@ mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr); struct mlx5_flow_handle * -mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn); +mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, + struct mlx5_flow_destination *dest); enum { SET_VLAN_STRIP = BIT(0), @@ -268,12 +269,15 @@ struct mlx5_esw_flow_attr { struct mlx5e_tc_flow_parse_attr *parse_attr; }; -int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode); +int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode); -int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode); +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode); int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode); -int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap); +int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3028e8d90920..a35a2310f871 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -775,10 +775,10 @@ static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw) } struct mlx5_flow_handle * -mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn) +mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, + struct mlx5_flow_destination *dest) { struct mlx5_flow_act flow_act = {0}; - struct mlx5_flow_destination dest = {}; struct mlx5_flow_handle *flow_rule; struct mlx5_flow_spec *spec; void *misc; @@ -796,12 +796,10 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn) MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; - dest.tir_num = tirn; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec, - &flow_act, &dest, 1); + &flow_act, dest, 1); if (IS_ERR(flow_rule)) { esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule)); goto out; @@ -812,29 +810,35 @@ out: return flow_rule; } -static int esw_offloads_start(struct mlx5_eswitch *esw) +static int esw_offloads_start(struct mlx5_eswitch *esw, + struct netlink_ext_ack *extack) { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; if (esw->mode != SRIOV_LEGACY) { - esw_warn(esw->dev, "Can't set offloads mode, SRIOV legacy not enabled\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set offloads mode, SRIOV legacy not enabled"); return -EINVAL; } mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); if (err) { - esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch to offloads"); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); - if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1); + if (err1) { + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch back to legacy"); + } } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { if (mlx5_eswitch_inline_mode_get(esw, num_vfs, &esw->offloads.inline_mode)) { esw->offloads.inline_mode = MLX5_INLINE_MODE_L2; - esw_warn(esw->dev, "Inline mode is different between vports\n"); + NL_SET_ERR_MSG_MOD(extack, + "Inline mode is different between vports"); } } return err; @@ -975,17 +979,20 @@ create_ft_err: return err; } -static int esw_offloads_stop(struct mlx5_eswitch *esw) +static int esw_offloads_stop(struct mlx5_eswitch *esw, + struct netlink_ext_ack *extack) { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); if (err) { - esw_warn(esw->dev, "Failed setting eswitch to legacy, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); - if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err); + if (err1) { + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch back to offloads"); + } } /* enable back PF RoCE */ @@ -1094,7 +1101,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) return 0; } -int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); u16 cur_mlx5_mode, mlx5_mode = 0; @@ -1113,9 +1121,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) return 0; if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) - return esw_offloads_start(dev->priv.eswitch); + return esw_offloads_start(dev->priv.eswitch, extack); else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) - return esw_offloads_stop(dev->priv.eswitch); + return esw_offloads_stop(dev->priv.eswitch, extack); else return -EINVAL; } @@ -1132,7 +1140,8 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } -int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1149,14 +1158,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) return 0; /* fall through */ case MLX5_CAP_INLINE_MODE_L2: - esw_warn(dev, "Inline mode can't be set\n"); + NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set"); return -EOPNOTSUPP; case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: break; } if (esw->offloads.num_flows > 0) { - esw_warn(dev, "Can't set inline mode when flows are configured\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set inline mode when flows are configured"); return -EOPNOTSUPP; } @@ -1167,8 +1177,8 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) for (vport = 1; vport < esw->enabled_vports; vport++) { err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode); if (err) { - esw_warn(dev, "Failed to set min inline on vport %d\n", - vport); + NL_SET_ERR_MSG_MOD(extack, + "Failed to set min inline on vport"); goto revert_inline_mode; } } @@ -1234,7 +1244,8 @@ out: return 0; } -int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) +int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1261,7 +1272,8 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) return 0; if (esw->offloads.num_flows > 0) { - esw_warn(dev, "Can't set encapsulation when flows are configured\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set encapsulation when flows are configured"); return -EOPNOTSUPP; } @@ -1270,7 +1282,8 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) esw->offloads.encap = encap; err = esw_create_offloads_fast_fdb_table(esw); if (err) { - esw_warn(esw->dev, "Failed re-creating fast FDB table, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "Failed re-creating fast FDB table"); esw->offloads.encap = !encap; (void)esw_create_offloads_fast_fdb_table(esw); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 41ad24f0de2c..1ab6f7e3bec6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -250,7 +250,7 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) if (ret) return ret; - force_state = MLX5_GET(teardown_hca_out, out, force_state); + force_state = MLX5_GET(teardown_hca_out, out, state); if (force_state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { mlx5_core_warn(dev, "teardown with force mode failed, doing normal teardown\n"); return -EIO; @@ -259,6 +259,54 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } +#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) +{ + unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {0}; + int state; + int ret; + + if (!MLX5_CAP_GEN(dev, fast_teardown)) { + mlx5_core_dbg(dev, "fast teardown is not supported in the firmware\n"); + return -EOPNOTSUPP; + } + + MLX5_SET(teardown_hca_in, in, opcode, MLX5_CMD_OP_TEARDOWN_HCA); + MLX5_SET(teardown_hca_in, in, profile, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) + return ret; + + state = MLX5_GET(teardown_hca_out, out, state); + if (state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { + mlx5_core_warn(dev, "teardown with fast mode failed\n"); + return -EIO; + } + + mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED); + + /* Loop until device state turns to disable */ + end = jiffies + msecs_to_jiffies(delay_ms); + do { + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + break; + + cond_resched(); + } while (!time_after(jiffies, end)); + + if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", + mlx5_get_nic_state(dev), delay_ms); + return -EIO; + } + + return 0; +} + enum mlxsw_reg_mcc_instruction { MLX5_REG_MCC_INSTRUCTION_LOCK_UPDATE_HANDLE = 0x01, MLX5_REG_MCC_INSTRUCTION_RELEASE_UPDATE_HANDLE = 0x02, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9f39aeca863f..43118de8ee99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -59,22 +59,25 @@ enum { }; enum { - MLX5_NIC_IFC_FULL = 0, - MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2, - MLX5_NIC_IFC_INVALID = 3 -}; - -enum { MLX5_DROP_NEW_HEALTH_WORK, MLX5_DROP_NEW_RECOVERY_WORK, }; -static u8 get_nic_state(struct mlx5_core_dev *dev) +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3; } +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state) +{ + u32 cur_cmdq_addr_l_sz; + + cur_cmdq_addr_l_sz = ioread32be(&dev->iseg->cmdq_addr_l_sz); + iowrite32be((cur_cmdq_addr_l_sz & 0xFFFFF000) | + state << MLX5_NIC_IFC_OFFSET, + &dev->iseg->cmdq_addr_l_sz); +} + static void trigger_cmd_completions(struct mlx5_core_dev *dev) { unsigned long flags; @@ -103,7 +106,7 @@ static int in_fatal(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) return 1; if (ioread32be(&h->fw_ver) == 0xffffffff) @@ -133,7 +136,7 @@ unlock: static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) { - u8 nic_interface = get_nic_state(dev); + u8 nic_interface = mlx5_get_nic_state(dev); switch (nic_interface) { case MLX5_NIC_IFC_FULL: @@ -168,7 +171,7 @@ static void health_recover(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); - nic_state = get_nic_state(dev); + nic_state = mlx5_get_nic_state(dev); if (nic_state == MLX5_NIC_IFC_INVALID) { dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n"); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index a825ed093efd..299e2a897f7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -368,7 +368,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_rqts; - err = mlx5e_create_indirect_tirs(priv); + err = mlx5e_create_indirect_tirs(priv, true); if (err) goto err_destroy_direct_rqts; @@ -385,7 +385,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_indirect_tirs: - mlx5e_destroy_indirect_tirs(priv); + mlx5e_destroy_indirect_tirs(priv, true); err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: @@ -401,7 +401,7 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { mlx5i_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); - mlx5e_destroy_indirect_tirs(priv); + mlx5e_destroy_indirect_tirs(priv, true); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b5e9f664fc66..28132c7dc05f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1594,12 +1594,17 @@ static const struct pci_error_handlers mlx5_err_handler = { static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) { - int ret; + bool fast_teardown = false, force_teardown = false; + int ret = 1; + + fast_teardown = MLX5_CAP_GEN(dev, fast_teardown); + force_teardown = MLX5_CAP_GEN(dev, force_teardown); + + mlx5_core_dbg(dev, "force teardown firmware support=%d\n", force_teardown); + mlx5_core_dbg(dev, "fast teardown firmware support=%d\n", fast_teardown); - if (!MLX5_CAP_GEN(dev, force_teardown)) { - mlx5_core_dbg(dev, "force teardown is not supported in the firmware\n"); + if (!fast_teardown && !force_teardown) return -EOPNOTSUPP; - } if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5_core_dbg(dev, "Device in internal error state, giving up\n"); @@ -1612,13 +1617,19 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); + ret = mlx5_cmd_fast_teardown_hca(dev); + if (!ret) + goto succeed; + ret = mlx5_cmd_force_teardown_hca(dev); - if (ret) { - mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); - mlx5_start_health_poll(dev); - return ret; - } + if (!ret) + goto succeed; + + mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); + mlx5_start_health_poll(dev); + return ret; +succeed: mlx5_enter_error_state(dev, true); /* Some platforms requiring freeing the IRQ's in the shutdown diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b4134fa0bba3..cc298527baf1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -95,6 +95,8 @@ int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev); +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev); + void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, @@ -214,4 +216,14 @@ int mlx5_lag_allow(struct mlx5_core_dev *dev); int mlx5_lag_forbid(struct mlx5_core_dev *dev); void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); + +enum { + MLX5_NIC_IFC_FULL = 0, + MLX5_NIC_IFC_DISABLED = 1, + MLX5_NIC_IFC_NO_DRAM_NIC = 2, + MLX5_NIC_IFC_INVALID = 3 +}; + +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index d2f76070ea7c..a1ee9a8a769e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -475,7 +475,8 @@ static void mlx5_hairpin_destroy_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) { mlx5_core_destroy_rq(hp->func_mdev, hp->rqn[i]); - mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + if (!hp->peer_gone) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); } } @@ -567,6 +568,8 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) MLX5_RQC_STATE_RST, 0, 0); /* unset peer SQs */ + if (hp->peer_gone) + return; for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_RST, 0, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index b02af317c125..cfbea66b4879 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -1201,3 +1201,12 @@ int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev) return err; } EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport); + +u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) +{ + if (!mdev->sys_image_guid) + mlx5_query_nic_vport_system_image_guid(mdev, &mdev->sys_image_guid); + + return mdev->sys_image_guid; +} +EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 4d271fb3de3d..5890fdfd62c3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -718,14 +718,17 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) memset(&active_cqns, 0, sizeof(active_cqns)); while ((eqe = mlxsw_pci_eq_sw_eqe_get(q))) { - u8 event_type = mlxsw_pci_eqe_event_type_get(eqe); - switch (event_type) { - case MLXSW_PCI_EQE_EVENT_TYPE_CMD: + /* Command interface completion events are always received on + * queue MLXSW_PCI_EQ_ASYNC_NUM (EQ0) and completion events + * are mapped to queue MLXSW_PCI_EQ_COMP_NUM (EQ1). + */ + switch (q->num) { + case MLXSW_PCI_EQ_ASYNC_NUM: mlxsw_pci_eq_cmd_event(mlxsw_pci, eqe); q->u.eq.ev_cmd_count++; break; - case MLXSW_PCI_EQE_EVENT_TYPE_COMP: + case MLXSW_PCI_EQ_COMP_NUM: cqn = mlxsw_pci_eqe_cqn_get(eqe); set_bit(cqn, active_cqns); cq_handle = true; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 88c33a8474eb..2b14fd0dcc42 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4855,6 +4855,8 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, upper_dev = info->upper_dev; if (info->linking) break; + if (is_vlan_dev(upper_dev)) + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, upper_dev); if (netif_is_macvlan(upper_dev)) mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev); break; diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig index 36c84625d54e..bcec0587cf61 100644 --- a/drivers/net/ethernet/mscc/Kconfig +++ b/drivers/net/ethernet/mscc/Kconfig @@ -23,6 +23,8 @@ config MSCC_OCELOT_SWITCH config MSCC_OCELOT_SWITCH_OCELOT tristate "Ocelot switch driver on Ocelot" depends on MSCC_OCELOT_SWITCH + depends on GENERIC_PHY + depends on OF_NET help This driver supports the Ocelot network switch device as present on the Ocelot SoCs. diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 1a4f2bb48ead..8f11fdba8d0e 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -472,6 +472,7 @@ static int ocelot_port_open(struct net_device *dev) { struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; + enum phy_mode phy_mode; int err; /* Enable receiving frames on the port, and activate auto-learning of @@ -482,8 +483,21 @@ static int ocelot_port_open(struct net_device *dev) ANA_PORT_PORT_CFG_PORTID_VAL(port->chip_port), ANA_PORT_PORT_CFG, port->chip_port); + if (port->serdes) { + if (port->phy_mode == PHY_INTERFACE_MODE_SGMII) + phy_mode = PHY_MODE_SGMII; + else + phy_mode = PHY_MODE_QSGMII; + + err = phy_set_mode(port->serdes, phy_mode); + if (err) { + netdev_err(dev, "Could not set mode of SerDes\n"); + return err; + } + } + err = phy_connect_direct(dev, port->phy, &ocelot_port_adjust_link, - PHY_INTERFACE_MODE_NA); + port->phy_mode); if (err) { netdev_err(dev, "Could not attach to PHY\n"); return err; diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 616bec30dfa3..62c7c8eb00d9 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -11,12 +11,13 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include <linux/phy.h> +#include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/regmap.h> #include "ocelot_ana.h" #include "ocelot_dev.h" -#include "ocelot_hsio.h" #include "ocelot_qsys.h" #include "ocelot_rew.h" #include "ocelot_sys.h" @@ -333,79 +334,6 @@ enum ocelot_reg { SYS_CM_DATA_RD, SYS_CM_OP, SYS_CM_DATA, - HSIO_PLL5G_CFG0 = HSIO << TARGET_OFFSET, - HSIO_PLL5G_CFG1, - HSIO_PLL5G_CFG2, - HSIO_PLL5G_CFG3, - HSIO_PLL5G_CFG4, - HSIO_PLL5G_CFG5, - HSIO_PLL5G_CFG6, - HSIO_PLL5G_STATUS0, - HSIO_PLL5G_STATUS1, - HSIO_PLL5G_BIST_CFG0, - HSIO_PLL5G_BIST_CFG1, - HSIO_PLL5G_BIST_CFG2, - HSIO_PLL5G_BIST_STAT0, - HSIO_PLL5G_BIST_STAT1, - HSIO_RCOMP_CFG0, - HSIO_RCOMP_STATUS, - HSIO_SYNC_ETH_CFG, - HSIO_SYNC_ETH_PLL_CFG, - HSIO_S1G_DES_CFG, - HSIO_S1G_IB_CFG, - HSIO_S1G_OB_CFG, - HSIO_S1G_SER_CFG, - HSIO_S1G_COMMON_CFG, - HSIO_S1G_PLL_CFG, - HSIO_S1G_PLL_STATUS, - HSIO_S1G_DFT_CFG0, - HSIO_S1G_DFT_CFG1, - HSIO_S1G_DFT_CFG2, - HSIO_S1G_TP_CFG, - HSIO_S1G_RC_PLL_BIST_CFG, - HSIO_S1G_MISC_CFG, - HSIO_S1G_DFT_STATUS, - HSIO_S1G_MISC_STATUS, - HSIO_MCB_S1G_ADDR_CFG, - HSIO_S6G_DIG_CFG, - HSIO_S6G_DFT_CFG0, - HSIO_S6G_DFT_CFG1, - HSIO_S6G_DFT_CFG2, - HSIO_S6G_TP_CFG0, - HSIO_S6G_TP_CFG1, - HSIO_S6G_RC_PLL_BIST_CFG, - HSIO_S6G_MISC_CFG, - HSIO_S6G_OB_ANEG_CFG, - HSIO_S6G_DFT_STATUS, - HSIO_S6G_ERR_CNT, - HSIO_S6G_MISC_STATUS, - HSIO_S6G_DES_CFG, - HSIO_S6G_IB_CFG, - HSIO_S6G_IB_CFG1, - HSIO_S6G_IB_CFG2, - HSIO_S6G_IB_CFG3, - HSIO_S6G_IB_CFG4, - HSIO_S6G_IB_CFG5, - HSIO_S6G_OB_CFG, - HSIO_S6G_OB_CFG1, - HSIO_S6G_SER_CFG, - HSIO_S6G_COMMON_CFG, - HSIO_S6G_PLL_CFG, - HSIO_S6G_ACJTAG_CFG, - HSIO_S6G_GP_CFG, - HSIO_S6G_IB_STATUS0, - HSIO_S6G_IB_STATUS1, - HSIO_S6G_ACJTAG_STATUS, - HSIO_S6G_PLL_STATUS, - HSIO_S6G_REVID, - HSIO_MCB_S6G_ADDR_CFG, - HSIO_HW_CFG, - HSIO_HW_QSGMII_CFG, - HSIO_HW_QSGMII_STAT, - HSIO_CLK_CFG, - HSIO_TEMP_SENSOR_CTRL, - HSIO_TEMP_SENSOR_CFG, - HSIO_TEMP_SENSOR_STAT, }; enum ocelot_regfield { @@ -527,6 +455,9 @@ struct ocelot_port { u8 vlan_aware; u64 *stats; + + phy_interface_t phy_mode; + struct phy *serdes; }; u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 3cdf63e35b53..0cf0b0935b3b 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -6,9 +6,11 @@ */ #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/of_net.h> #include <linux/netdevice.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> +#include <linux/mfd/syscon.h> #include <linux/skbuff.h> #include "ocelot.h" @@ -168,6 +170,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct device_node *ports, *portnp; struct ocelot *ocelot; + struct regmap *hsio; u32 val; struct { @@ -179,7 +182,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) { QSYS, "qsys" }, { ANA, "ana" }, { QS, "qs" }, - { HSIO, "hsio" }, }; if (!np && !pdev->dev.platform_data) @@ -202,6 +204,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ocelot->targets[res[i].id] = target; } + hsio = syscon_regmap_lookup_by_compatible("mscc,ocelot-hsio"); + if (IS_ERR(hsio)) { + dev_err(&pdev->dev, "missing hsio syscon\n"); + return PTR_ERR(hsio); + } + + ocelot->targets[HSIO] = hsio; + err = ocelot_chip_init(ocelot); if (err) return err; @@ -244,18 +254,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev) INIT_LIST_HEAD(&ocelot->multicast); ocelot_init(ocelot); - ocelot_rmw(ocelot, HSIO_HW_CFG_DEV1G_4_MODE | - HSIO_HW_CFG_DEV1G_6_MODE | - HSIO_HW_CFG_DEV1G_9_MODE, - HSIO_HW_CFG_DEV1G_4_MODE | - HSIO_HW_CFG_DEV1G_6_MODE | - HSIO_HW_CFG_DEV1G_9_MODE, - HSIO_HW_CFG); - for_each_available_child_of_node(ports, portnp) { struct device_node *phy_node; struct phy_device *phy; struct resource *res; + struct phy *serdes; void __iomem *regs; char res_name[8]; u32 port; @@ -280,10 +283,43 @@ static int mscc_ocelot_probe(struct platform_device *pdev) continue; err = ocelot_probe_port(ocelot, port, regs, phy); - if (err) { - dev_err(&pdev->dev, "failed to probe ports\n"); + if (err) + return err; + + err = of_get_phy_mode(portnp); + if (err < 0) + ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA; + else + ocelot->ports[port]->phy_mode = err; + + switch (ocelot->ports[port]->phy_mode) { + case PHY_INTERFACE_MODE_NA: + continue; + case PHY_INTERFACE_MODE_SGMII: + break; + case PHY_INTERFACE_MODE_QSGMII: + break; + default: + dev_err(ocelot->dev, + "invalid phy mode for port%d, (Q)SGMII only\n", + port); + return -EINVAL; + } + + serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = PTR_ERR(serdes); + if (err == -EPROBE_DEFER) + dev_dbg(ocelot->dev, "deferring probe\n"); + else + dev_err(ocelot->dev, + "missing SerDes phys for port%d\n", + port); + goto err_probe_ports; } + + ocelot->ports[port]->serdes = serdes; } register_netdevice_notifier(&ocelot_netdevice_nb); diff --git a/drivers/net/ethernet/mscc/ocelot_hsio.h b/drivers/net/ethernet/mscc/ocelot_hsio.h deleted file mode 100644 index d93ddec3931b..000000000000 --- a/drivers/net/ethernet/mscc/ocelot_hsio.h +++ /dev/null @@ -1,785 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ -/* - * Microsemi Ocelot Switch driver - * - * Copyright (c) 2017 Microsemi Corporation - */ - -#ifndef _MSCC_OCELOT_HSIO_H_ -#define _MSCC_OCELOT_HSIO_H_ - -#define HSIO_PLL5G_CFG0_ENA_ROT BIT(31) -#define HSIO_PLL5G_CFG0_ENA_LANE BIT(30) -#define HSIO_PLL5G_CFG0_ENA_CLKTREE BIT(29) -#define HSIO_PLL5G_CFG0_DIV4 BIT(28) -#define HSIO_PLL5G_CFG0_ENA_LOCK_FINE BIT(27) -#define HSIO_PLL5G_CFG0_SELBGV820(x) (((x) << 23) & GENMASK(26, 23)) -#define HSIO_PLL5G_CFG0_SELBGV820_M GENMASK(26, 23) -#define HSIO_PLL5G_CFG0_SELBGV820_X(x) (((x) & GENMASK(26, 23)) >> 23) -#define HSIO_PLL5G_CFG0_LOOP_BW_RES(x) (((x) << 18) & GENMASK(22, 18)) -#define HSIO_PLL5G_CFG0_LOOP_BW_RES_M GENMASK(22, 18) -#define HSIO_PLL5G_CFG0_LOOP_BW_RES_X(x) (((x) & GENMASK(22, 18)) >> 18) -#define HSIO_PLL5G_CFG0_SELCPI(x) (((x) << 16) & GENMASK(17, 16)) -#define HSIO_PLL5G_CFG0_SELCPI_M GENMASK(17, 16) -#define HSIO_PLL5G_CFG0_SELCPI_X(x) (((x) & GENMASK(17, 16)) >> 16) -#define HSIO_PLL5G_CFG0_ENA_VCO_CONTRH BIT(15) -#define HSIO_PLL5G_CFG0_ENA_CP1 BIT(14) -#define HSIO_PLL5G_CFG0_ENA_VCO_BUF BIT(13) -#define HSIO_PLL5G_CFG0_ENA_BIAS BIT(12) -#define HSIO_PLL5G_CFG0_CPU_CLK_DIV(x) (((x) << 6) & GENMASK(11, 6)) -#define HSIO_PLL5G_CFG0_CPU_CLK_DIV_M GENMASK(11, 6) -#define HSIO_PLL5G_CFG0_CPU_CLK_DIV_X(x) (((x) & GENMASK(11, 6)) >> 6) -#define HSIO_PLL5G_CFG0_CORE_CLK_DIV(x) ((x) & GENMASK(5, 0)) -#define HSIO_PLL5G_CFG0_CORE_CLK_DIV_M GENMASK(5, 0) - -#define HSIO_PLL5G_CFG1_ENA_DIRECT BIT(18) -#define HSIO_PLL5G_CFG1_ROT_SPEED BIT(17) -#define HSIO_PLL5G_CFG1_ROT_DIR BIT(16) -#define HSIO_PLL5G_CFG1_READBACK_DATA_SEL BIT(15) -#define HSIO_PLL5G_CFG1_RC_ENABLE BIT(14) -#define HSIO_PLL5G_CFG1_RC_CTRL_DATA(x) (((x) << 6) & GENMASK(13, 6)) -#define HSIO_PLL5G_CFG1_RC_CTRL_DATA_M GENMASK(13, 6) -#define HSIO_PLL5G_CFG1_RC_CTRL_DATA_X(x) (((x) & GENMASK(13, 6)) >> 6) -#define HSIO_PLL5G_CFG1_QUARTER_RATE BIT(5) -#define HSIO_PLL5G_CFG1_PWD_TX BIT(4) -#define HSIO_PLL5G_CFG1_PWD_RX BIT(3) -#define HSIO_PLL5G_CFG1_OUT_OF_RANGE_RECAL_ENA BIT(2) -#define HSIO_PLL5G_CFG1_HALF_RATE BIT(1) -#define HSIO_PLL5G_CFG1_FORCE_SET_ENA BIT(0) - -#define HSIO_PLL5G_CFG2_ENA_TEST_MODE BIT(30) -#define HSIO_PLL5G_CFG2_ENA_PFD_IN_FLIP BIT(29) -#define HSIO_PLL5G_CFG2_ENA_VCO_NREF_TESTOUT BIT(28) -#define HSIO_PLL5G_CFG2_ENA_FBTESTOUT BIT(27) -#define HSIO_PLL5G_CFG2_ENA_RCPLL BIT(26) -#define HSIO_PLL5G_CFG2_ENA_CP2 BIT(25) -#define HSIO_PLL5G_CFG2_ENA_CLK_BYPASS1 BIT(24) -#define HSIO_PLL5G_CFG2_AMPC_SEL(x) (((x) << 16) & GENMASK(23, 16)) -#define HSIO_PLL5G_CFG2_AMPC_SEL_M GENMASK(23, 16) -#define HSIO_PLL5G_CFG2_AMPC_SEL_X(x) (((x) & GENMASK(23, 16)) >> 16) -#define HSIO_PLL5G_CFG2_ENA_CLK_BYPASS BIT(15) -#define HSIO_PLL5G_CFG2_PWD_AMPCTRL_N BIT(14) -#define HSIO_PLL5G_CFG2_ENA_AMPCTRL BIT(13) -#define HSIO_PLL5G_CFG2_ENA_AMP_CTRL_FORCE BIT(12) -#define HSIO_PLL5G_CFG2_FRC_FSM_POR BIT(11) -#define HSIO_PLL5G_CFG2_DISABLE_FSM_POR BIT(10) -#define HSIO_PLL5G_CFG2_GAIN_TEST(x) (((x) << 5) & GENMASK(9, 5)) -#define HSIO_PLL5G_CFG2_GAIN_TEST_M GENMASK(9, 5) -#define HSIO_PLL5G_CFG2_GAIN_TEST_X(x) (((x) & GENMASK(9, 5)) >> 5) -#define HSIO_PLL5G_CFG2_EN_RESET_OVERRUN BIT(4) -#define HSIO_PLL5G_CFG2_EN_RESET_LIM_DET BIT(3) -#define HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET BIT(2) -#define HSIO_PLL5G_CFG2_DISABLE_FSM BIT(1) -#define HSIO_PLL5G_CFG2_ENA_GAIN_TEST BIT(0) - -#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL(x) (((x) << 22) & GENMASK(23, 22)) -#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL_M GENMASK(23, 22) -#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL_X(x) (((x) & GENMASK(23, 22)) >> 22) -#define HSIO_PLL5G_CFG3_TESTOUT_SEL(x) (((x) << 19) & GENMASK(21, 19)) -#define HSIO_PLL5G_CFG3_TESTOUT_SEL_M GENMASK(21, 19) -#define HSIO_PLL5G_CFG3_TESTOUT_SEL_X(x) (((x) & GENMASK(21, 19)) >> 19) -#define HSIO_PLL5G_CFG3_ENA_ANA_TEST_OUT BIT(18) -#define HSIO_PLL5G_CFG3_ENA_TEST_OUT BIT(17) -#define HSIO_PLL5G_CFG3_SEL_FBDCLK BIT(16) -#define HSIO_PLL5G_CFG3_SEL_CML_CMOS_PFD BIT(15) -#define HSIO_PLL5G_CFG3_RST_FB_N BIT(14) -#define HSIO_PLL5G_CFG3_FORCE_VCO_CONTRH BIT(13) -#define HSIO_PLL5G_CFG3_FORCE_LO BIT(12) -#define HSIO_PLL5G_CFG3_FORCE_HI BIT(11) -#define HSIO_PLL5G_CFG3_FORCE_ENA BIT(10) -#define HSIO_PLL5G_CFG3_FORCE_CP BIT(9) -#define HSIO_PLL5G_CFG3_FBDIVSEL_TST_ENA BIT(8) -#define HSIO_PLL5G_CFG3_FBDIVSEL(x) ((x) & GENMASK(7, 0)) -#define HSIO_PLL5G_CFG3_FBDIVSEL_M GENMASK(7, 0) - -#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL(x) (((x) << 16) & GENMASK(23, 16)) -#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL_M GENMASK(23, 16) -#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL_X(x) (((x) & GENMASK(23, 16)) >> 16) -#define HSIO_PLL5G_CFG4_IB_CTRL(x) ((x) & GENMASK(15, 0)) -#define HSIO_PLL5G_CFG4_IB_CTRL_M GENMASK(15, 0) - -#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL(x) (((x) << 16) & GENMASK(23, 16)) -#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL_M GENMASK(23, 16) -#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL_X(x) (((x) & GENMASK(23, 16)) >> 16) -#define HSIO_PLL5G_CFG5_OB_CTRL(x) ((x) & GENMASK(15, 0)) -#define HSIO_PLL5G_CFG5_OB_CTRL_M GENMASK(15, 0) - -#define HSIO_PLL5G_CFG6_REFCLK_SEL_SRC BIT(23) -#define HSIO_PLL5G_CFG6_REFCLK_SEL(x) (((x) << 20) & GENMASK(22, 20)) -#define HSIO_PLL5G_CFG6_REFCLK_SEL_M GENMASK(22, 20) -#define HSIO_PLL5G_CFG6_REFCLK_SEL_X(x) (((x) & GENMASK(22, 20)) >> 20) -#define HSIO_PLL5G_CFG6_REFCLK_SRC BIT(19) -#define HSIO_PLL5G_CFG6_POR_DEL_SEL(x) (((x) << 16) & GENMASK(17, 16)) -#define HSIO_PLL5G_CFG6_POR_DEL_SEL_M GENMASK(17, 16) -#define HSIO_PLL5G_CFG6_POR_DEL_SEL_X(x) (((x) & GENMASK(17, 16)) >> 16) -#define HSIO_PLL5G_CFG6_DIV125REF_SEL(x) (((x) << 8) & GENMASK(15, 8)) -#define HSIO_PLL5G_CFG6_DIV125REF_SEL_M GENMASK(15, 8) -#define HSIO_PLL5G_CFG6_DIV125REF_SEL_X(x) (((x) & GENMASK(15, 8)) >> 8) -#define HSIO_PLL5G_CFG6_ENA_REFCLKC2 BIT(7) -#define HSIO_PLL5G_CFG6_ENA_FBCLKC2 BIT(6) -#define HSIO_PLL5G_CFG6_DDR_CLK_DIV(x) ((x) & GENMASK(5, 0)) -#define HSIO_PLL5G_CFG6_DDR_CLK_DIV_M GENMASK(5, 0) - -#define HSIO_PLL5G_STATUS0_RANGE_LIM BIT(12) -#define HSIO_PLL5G_STATUS0_OUT_OF_RANGE_ERR BIT(11) -#define HSIO_PLL5G_STATUS0_CALIBRATION_ERR BIT(10) -#define HSIO_PLL5G_STATUS0_CALIBRATION_DONE BIT(9) -#define HSIO_PLL5G_STATUS0_READBACK_DATA(x) (((x) << 1) & GENMASK(8, 1)) -#define HSIO_PLL5G_STATUS0_READBACK_DATA_M GENMASK(8, 1) -#define HSIO_PLL5G_STATUS0_READBACK_DATA_X(x) (((x) & GENMASK(8, 1)) >> 1) -#define HSIO_PLL5G_STATUS0_LOCK_STATUS BIT(0) - -#define HSIO_PLL5G_STATUS1_SIG_DEL(x) (((x) << 21) & GENMASK(28, 21)) -#define HSIO_PLL5G_STATUS1_SIG_DEL_M GENMASK(28, 21) -#define HSIO_PLL5G_STATUS1_SIG_DEL_X(x) (((x) & GENMASK(28, 21)) >> 21) -#define HSIO_PLL5G_STATUS1_GAIN_STAT(x) (((x) << 16) & GENMASK(20, 16)) -#define HSIO_PLL5G_STATUS1_GAIN_STAT_M GENMASK(20, 16) -#define HSIO_PLL5G_STATUS1_GAIN_STAT_X(x) (((x) & GENMASK(20, 16)) >> 16) -#define HSIO_PLL5G_STATUS1_FBCNT_DIF(x) (((x) << 4) & GENMASK(13, 4)) -#define HSIO_PLL5G_STATUS1_FBCNT_DIF_M GENMASK(13, 4) -#define HSIO_PLL5G_STATUS1_FBCNT_DIF_X(x) (((x) & GENMASK(13, 4)) >> 4) -#define HSIO_PLL5G_STATUS1_FSM_STAT(x) (((x) << 1) & GENMASK(3, 1)) -#define HSIO_PLL5G_STATUS1_FSM_STAT_M GENMASK(3, 1) -#define HSIO_PLL5G_STATUS1_FSM_STAT_X(x) (((x) & GENMASK(3, 1)) >> 1) -#define HSIO_PLL5G_STATUS1_FSM_LOCK BIT(0) - -#define HSIO_PLL5G_BIST_CFG0_PLLB_START_BIST BIT(31) -#define HSIO_PLL5G_BIST_CFG0_PLLB_MEAS_MODE BIT(30) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT(x) (((x) << 20) & GENMASK(23, 20)) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT_M GENMASK(23, 20) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT_X(x) (((x) & GENMASK(23, 20)) >> 20) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT(x) (((x) << 16) & GENMASK(19, 16)) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT_M GENMASK(19, 16) -#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT_X(x) (((x) & GENMASK(19, 16)) >> 16) -#define HSIO_PLL5G_BIST_CFG0_PLLB_DIV_FACTOR_PRE(x) ((x) & GENMASK(15, 0)) -#define HSIO_PLL5G_BIST_CFG0_PLLB_DIV_FACTOR_PRE_M GENMASK(15, 0) - -#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT_M GENMASK(7, 4) -#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_PLL5G_BIST_STAT0_PLLB_BUSY BIT(2) -#define HSIO_PLL5G_BIST_STAT0_PLLB_DONE_N BIT(1) -#define HSIO_PLL5G_BIST_STAT0_PLLB_FAIL BIT(0) - -#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT(x) (((x) << 16) & GENMASK(31, 16)) -#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT_M GENMASK(31, 16) -#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT_X(x) (((x) & GENMASK(31, 16)) >> 16) -#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_REF_DIFF(x) ((x) & GENMASK(15, 0)) -#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_REF_DIFF_M GENMASK(15, 0) - -#define HSIO_RCOMP_CFG0_PWD_ENA BIT(13) -#define HSIO_RCOMP_CFG0_RUN_CAL BIT(12) -#define HSIO_RCOMP_CFG0_SPEED_SEL(x) (((x) << 10) & GENMASK(11, 10)) -#define HSIO_RCOMP_CFG0_SPEED_SEL_M GENMASK(11, 10) -#define HSIO_RCOMP_CFG0_SPEED_SEL_X(x) (((x) & GENMASK(11, 10)) >> 10) -#define HSIO_RCOMP_CFG0_MODE_SEL(x) (((x) << 8) & GENMASK(9, 8)) -#define HSIO_RCOMP_CFG0_MODE_SEL_M GENMASK(9, 8) -#define HSIO_RCOMP_CFG0_MODE_SEL_X(x) (((x) & GENMASK(9, 8)) >> 8) -#define HSIO_RCOMP_CFG0_FORCE_ENA BIT(4) -#define HSIO_RCOMP_CFG0_RCOMP_VAL(x) ((x) & GENMASK(3, 0)) -#define HSIO_RCOMP_CFG0_RCOMP_VAL_M GENMASK(3, 0) - -#define HSIO_RCOMP_STATUS_BUSY BIT(12) -#define HSIO_RCOMP_STATUS_DELTA_ALERT BIT(7) -#define HSIO_RCOMP_STATUS_RCOMP(x) ((x) & GENMASK(3, 0)) -#define HSIO_RCOMP_STATUS_RCOMP_M GENMASK(3, 0) - -#define HSIO_SYNC_ETH_CFG_RSZ 0x4 - -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC_M GENMASK(7, 4) -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV(x) (((x) << 1) & GENMASK(3, 1)) -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV_M GENMASK(3, 1) -#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV_X(x) (((x) & GENMASK(3, 1)) >> 1) -#define HSIO_SYNC_ETH_CFG_RECO_CLK_ENA BIT(0) - -#define HSIO_SYNC_ETH_PLL_CFG_PLL_AUTO_SQUELCH_ENA BIT(0) - -#define HSIO_S1G_DES_CFG_DES_PHS_CTRL(x) (((x) << 13) & GENMASK(16, 13)) -#define HSIO_S1G_DES_CFG_DES_PHS_CTRL_M GENMASK(16, 13) -#define HSIO_S1G_DES_CFG_DES_PHS_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13) -#define HSIO_S1G_DES_CFG_DES_CPMD_SEL(x) (((x) << 11) & GENMASK(12, 11)) -#define HSIO_S1G_DES_CFG_DES_CPMD_SEL_M GENMASK(12, 11) -#define HSIO_S1G_DES_CFG_DES_CPMD_SEL_X(x) (((x) & GENMASK(12, 11)) >> 11) -#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL(x) (((x) << 8) & GENMASK(10, 8)) -#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL_M GENMASK(10, 8) -#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL_X(x) (((x) & GENMASK(10, 8)) >> 8) -#define HSIO_S1G_DES_CFG_DES_BW_ANA(x) (((x) << 5) & GENMASK(7, 5)) -#define HSIO_S1G_DES_CFG_DES_BW_ANA_M GENMASK(7, 5) -#define HSIO_S1G_DES_CFG_DES_BW_ANA_X(x) (((x) & GENMASK(7, 5)) >> 5) -#define HSIO_S1G_DES_CFG_DES_SWAP_ANA BIT(4) -#define HSIO_S1G_DES_CFG_DES_BW_HYST(x) (((x) << 1) & GENMASK(3, 1)) -#define HSIO_S1G_DES_CFG_DES_BW_HYST_M GENMASK(3, 1) -#define HSIO_S1G_DES_CFG_DES_BW_HYST_X(x) (((x) & GENMASK(3, 1)) >> 1) -#define HSIO_S1G_DES_CFG_DES_SWAP_HYST BIT(0) - -#define HSIO_S1G_IB_CFG_IB_FX100_ENA BIT(27) -#define HSIO_S1G_IB_CFG_ACJTAG_HYST(x) (((x) << 24) & GENMASK(26, 24)) -#define HSIO_S1G_IB_CFG_ACJTAG_HYST_M GENMASK(26, 24) -#define HSIO_S1G_IB_CFG_ACJTAG_HYST_X(x) (((x) & GENMASK(26, 24)) >> 24) -#define HSIO_S1G_IB_CFG_IB_DET_LEV(x) (((x) << 19) & GENMASK(21, 19)) -#define HSIO_S1G_IB_CFG_IB_DET_LEV_M GENMASK(21, 19) -#define HSIO_S1G_IB_CFG_IB_DET_LEV_X(x) (((x) & GENMASK(21, 19)) >> 19) -#define HSIO_S1G_IB_CFG_IB_HYST_LEV BIT(14) -#define HSIO_S1G_IB_CFG_IB_ENA_CMV_TERM BIT(13) -#define HSIO_S1G_IB_CFG_IB_ENA_DC_COUPLING BIT(12) -#define HSIO_S1G_IB_CFG_IB_ENA_DETLEV BIT(11) -#define HSIO_S1G_IB_CFG_IB_ENA_HYST BIT(10) -#define HSIO_S1G_IB_CFG_IB_ENA_OFFSET_COMP BIT(9) -#define HSIO_S1G_IB_CFG_IB_EQ_GAIN(x) (((x) << 6) & GENMASK(8, 6)) -#define HSIO_S1G_IB_CFG_IB_EQ_GAIN_M GENMASK(8, 6) -#define HSIO_S1G_IB_CFG_IB_EQ_GAIN_X(x) (((x) & GENMASK(8, 6)) >> 6) -#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ(x) (((x) << 4) & GENMASK(5, 4)) -#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ_M GENMASK(5, 4) -#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ_X(x) (((x) & GENMASK(5, 4)) >> 4) -#define HSIO_S1G_IB_CFG_IB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0)) -#define HSIO_S1G_IB_CFG_IB_RESISTOR_CTRL_M GENMASK(3, 0) - -#define HSIO_S1G_OB_CFG_OB_SLP(x) (((x) << 17) & GENMASK(18, 17)) -#define HSIO_S1G_OB_CFG_OB_SLP_M GENMASK(18, 17) -#define HSIO_S1G_OB_CFG_OB_SLP_X(x) (((x) & GENMASK(18, 17)) >> 17) -#define HSIO_S1G_OB_CFG_OB_AMP_CTRL(x) (((x) << 13) & GENMASK(16, 13)) -#define HSIO_S1G_OB_CFG_OB_AMP_CTRL_M GENMASK(16, 13) -#define HSIO_S1G_OB_CFG_OB_AMP_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13) -#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL(x) (((x) << 10) & GENMASK(12, 10)) -#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL_M GENMASK(12, 10) -#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL_X(x) (((x) & GENMASK(12, 10)) >> 10) -#define HSIO_S1G_OB_CFG_OB_DIS_VCM_CTRL BIT(9) -#define HSIO_S1G_OB_CFG_OB_EN_MEAS_VREG BIT(8) -#define HSIO_S1G_OB_CFG_OB_VCM_CTRL(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S1G_OB_CFG_OB_VCM_CTRL_M GENMASK(7, 4) -#define HSIO_S1G_OB_CFG_OB_VCM_CTRL_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S1G_OB_CFG_OB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0)) -#define HSIO_S1G_OB_CFG_OB_RESISTOR_CTRL_M GENMASK(3, 0) - -#define HSIO_S1G_SER_CFG_SER_IDLE BIT(9) -#define HSIO_S1G_SER_CFG_SER_DEEMPH BIT(8) -#define HSIO_S1G_SER_CFG_SER_CPMD_SEL BIT(7) -#define HSIO_S1G_SER_CFG_SER_SWAP_CPMD BIT(6) -#define HSIO_S1G_SER_CFG_SER_ALISEL(x) (((x) << 4) & GENMASK(5, 4)) -#define HSIO_S1G_SER_CFG_SER_ALISEL_M GENMASK(5, 4) -#define HSIO_S1G_SER_CFG_SER_ALISEL_X(x) (((x) & GENMASK(5, 4)) >> 4) -#define HSIO_S1G_SER_CFG_SER_ENHYS BIT(3) -#define HSIO_S1G_SER_CFG_SER_BIG_WIN BIT(2) -#define HSIO_S1G_SER_CFG_SER_EN_WIN BIT(1) -#define HSIO_S1G_SER_CFG_SER_ENALI BIT(0) - -#define HSIO_S1G_COMMON_CFG_SYS_RST BIT(31) -#define HSIO_S1G_COMMON_CFG_SE_AUTO_SQUELCH_ENA BIT(21) -#define HSIO_S1G_COMMON_CFG_ENA_LANE BIT(18) -#define HSIO_S1G_COMMON_CFG_PWD_RX BIT(17) -#define HSIO_S1G_COMMON_CFG_PWD_TX BIT(16) -#define HSIO_S1G_COMMON_CFG_LANE_CTRL(x) (((x) << 13) & GENMASK(15, 13)) -#define HSIO_S1G_COMMON_CFG_LANE_CTRL_M GENMASK(15, 13) -#define HSIO_S1G_COMMON_CFG_LANE_CTRL_X(x) (((x) & GENMASK(15, 13)) >> 13) -#define HSIO_S1G_COMMON_CFG_ENA_DIRECT BIT(12) -#define HSIO_S1G_COMMON_CFG_ENA_ELOOP BIT(11) -#define HSIO_S1G_COMMON_CFG_ENA_FLOOP BIT(10) -#define HSIO_S1G_COMMON_CFG_ENA_ILOOP BIT(9) -#define HSIO_S1G_COMMON_CFG_ENA_PLOOP BIT(8) -#define HSIO_S1G_COMMON_CFG_HRATE BIT(7) -#define HSIO_S1G_COMMON_CFG_IF_MODE BIT(0) - -#define HSIO_S1G_PLL_CFG_PLL_ENA_FB_DIV2 BIT(22) -#define HSIO_S1G_PLL_CFG_PLL_ENA_RC_DIV2 BIT(21) -#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA(x) (((x) << 8) & GENMASK(15, 8)) -#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA_M GENMASK(15, 8) -#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA_X(x) (((x) & GENMASK(15, 8)) >> 8) -#define HSIO_S1G_PLL_CFG_PLL_FSM_ENA BIT(7) -#define HSIO_S1G_PLL_CFG_PLL_FSM_FORCE_SET_ENA BIT(6) -#define HSIO_S1G_PLL_CFG_PLL_FSM_OOR_RECAL_ENA BIT(5) -#define HSIO_S1G_PLL_CFG_PLL_RB_DATA_SEL BIT(3) - -#define HSIO_S1G_PLL_STATUS_PLL_CAL_NOT_DONE BIT(12) -#define HSIO_S1G_PLL_STATUS_PLL_CAL_ERR BIT(11) -#define HSIO_S1G_PLL_STATUS_PLL_OUT_OF_RANGE_ERR BIT(10) -#define HSIO_S1G_PLL_STATUS_PLL_RB_DATA(x) ((x) & GENMASK(7, 0)) -#define HSIO_S1G_PLL_STATUS_PLL_RB_DATA_M GENMASK(7, 0) - -#define HSIO_S1G_DFT_CFG0_LAZYBIT BIT(31) -#define HSIO_S1G_DFT_CFG0_INV_DIS BIT(23) -#define HSIO_S1G_DFT_CFG0_PRBS_SEL(x) (((x) << 20) & GENMASK(21, 20)) -#define HSIO_S1G_DFT_CFG0_PRBS_SEL_M GENMASK(21, 20) -#define HSIO_S1G_DFT_CFG0_PRBS_SEL_X(x) (((x) & GENMASK(21, 20)) >> 20) -#define HSIO_S1G_DFT_CFG0_TEST_MODE(x) (((x) << 16) & GENMASK(18, 16)) -#define HSIO_S1G_DFT_CFG0_TEST_MODE_M GENMASK(18, 16) -#define HSIO_S1G_DFT_CFG0_TEST_MODE_X(x) (((x) & GENMASK(18, 16)) >> 16) -#define HSIO_S1G_DFT_CFG0_RX_PHS_CORR_DIS BIT(4) -#define HSIO_S1G_DFT_CFG0_RX_PDSENS_ENA BIT(3) -#define HSIO_S1G_DFT_CFG0_RX_DFT_ENA BIT(2) -#define HSIO_S1G_DFT_CFG0_TX_DFT_ENA BIT(0) - -#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8)) -#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL_M GENMASK(17, 8) -#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8) -#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ_M GENMASK(7, 4) -#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S1G_DFT_CFG1_TX_JI_ENA BIT(3) -#define HSIO_S1G_DFT_CFG1_TX_WAVEFORM_SEL BIT(2) -#define HSIO_S1G_DFT_CFG1_TX_FREQOFF_DIR BIT(1) -#define HSIO_S1G_DFT_CFG1_TX_FREQOFF_ENA BIT(0) - -#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8)) -#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL_M GENMASK(17, 8) -#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8) -#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ_M GENMASK(7, 4) -#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S1G_DFT_CFG2_RX_JI_ENA BIT(3) -#define HSIO_S1G_DFT_CFG2_RX_WAVEFORM_SEL BIT(2) -#define HSIO_S1G_DFT_CFG2_RX_FREQOFF_DIR BIT(1) -#define HSIO_S1G_DFT_CFG2_RX_FREQOFF_ENA BIT(0) - -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_ENA BIT(20) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH(x) (((x) << 16) & GENMASK(17, 16)) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_M GENMASK(17, 16) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_X(x) (((x) & GENMASK(17, 16)) >> 16) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH(x) (((x) << 8) & GENMASK(15, 8)) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_M GENMASK(15, 8) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_X(x) (((x) & GENMASK(15, 8)) >> 8) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_LOW(x) ((x) & GENMASK(7, 0)) -#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_LOW_M GENMASK(7, 0) - -#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE(x) (((x) << 11) & GENMASK(12, 11)) -#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE_M GENMASK(12, 11) -#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE_X(x) (((x) & GENMASK(12, 11)) >> 11) -#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_SWAP BIT(10) -#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_MODE BIT(9) -#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_ENA BIT(8) -#define HSIO_S1G_MISC_CFG_RX_LPI_MODE_ENA BIT(5) -#define HSIO_S1G_MISC_CFG_TX_LPI_MODE_ENA BIT(4) -#define HSIO_S1G_MISC_CFG_RX_DATA_INV_ENA BIT(3) -#define HSIO_S1G_MISC_CFG_TX_DATA_INV_ENA BIT(2) -#define HSIO_S1G_MISC_CFG_LANE_RST BIT(0) - -#define HSIO_S1G_DFT_STATUS_PLL_BIST_NOT_DONE BIT(7) -#define HSIO_S1G_DFT_STATUS_PLL_BIST_FAILED BIT(6) -#define HSIO_S1G_DFT_STATUS_PLL_BIST_TIMEOUT_ERR BIT(5) -#define HSIO_S1G_DFT_STATUS_BIST_ACTIVE BIT(3) -#define HSIO_S1G_DFT_STATUS_BIST_NOSYNC BIT(2) -#define HSIO_S1G_DFT_STATUS_BIST_COMPLETE_N BIT(1) -#define HSIO_S1G_DFT_STATUS_BIST_ERROR BIT(0) - -#define HSIO_S1G_MISC_STATUS_DES_100FX_PHASE_SEL BIT(0) - -#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_WR_ONE_SHOT BIT(31) -#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_RD_ONE_SHOT BIT(30) -#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_ADDR(x) ((x) & GENMASK(8, 0)) -#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_ADDR_M GENMASK(8, 0) - -#define HSIO_S6G_DIG_CFG_GP(x) (((x) << 16) & GENMASK(18, 16)) -#define HSIO_S6G_DIG_CFG_GP_M GENMASK(18, 16) -#define HSIO_S6G_DIG_CFG_GP_X(x) (((x) & GENMASK(18, 16)) >> 16) -#define HSIO_S6G_DIG_CFG_TX_BIT_DOUBLING_MODE_ENA BIT(7) -#define HSIO_S6G_DIG_CFG_SIGDET_TESTMODE BIT(6) -#define HSIO_S6G_DIG_CFG_SIGDET_AST(x) (((x) << 3) & GENMASK(5, 3)) -#define HSIO_S6G_DIG_CFG_SIGDET_AST_M GENMASK(5, 3) -#define HSIO_S6G_DIG_CFG_SIGDET_AST_X(x) (((x) & GENMASK(5, 3)) >> 3) -#define HSIO_S6G_DIG_CFG_SIGDET_DST(x) ((x) & GENMASK(2, 0)) -#define HSIO_S6G_DIG_CFG_SIGDET_DST_M GENMASK(2, 0) - -#define HSIO_S6G_DFT_CFG0_LAZYBIT BIT(31) -#define HSIO_S6G_DFT_CFG0_INV_DIS BIT(23) -#define HSIO_S6G_DFT_CFG0_PRBS_SEL(x) (((x) << 20) & GENMASK(21, 20)) -#define HSIO_S6G_DFT_CFG0_PRBS_SEL_M GENMASK(21, 20) -#define HSIO_S6G_DFT_CFG0_PRBS_SEL_X(x) (((x) & GENMASK(21, 20)) >> 20) -#define HSIO_S6G_DFT_CFG0_TEST_MODE(x) (((x) << 16) & GENMASK(18, 16)) -#define HSIO_S6G_DFT_CFG0_TEST_MODE_M GENMASK(18, 16) -#define HSIO_S6G_DFT_CFG0_TEST_MODE_X(x) (((x) & GENMASK(18, 16)) >> 16) -#define HSIO_S6G_DFT_CFG0_RX_PHS_CORR_DIS BIT(4) -#define HSIO_S6G_DFT_CFG0_RX_PDSENS_ENA BIT(3) -#define HSIO_S6G_DFT_CFG0_RX_DFT_ENA BIT(2) -#define HSIO_S6G_DFT_CFG0_TX_DFT_ENA BIT(0) - -#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8)) -#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL_M GENMASK(17, 8) -#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8) -#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ_M GENMASK(7, 4) -#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S6G_DFT_CFG1_TX_JI_ENA BIT(3) -#define HSIO_S6G_DFT_CFG1_TX_WAVEFORM_SEL BIT(2) -#define HSIO_S6G_DFT_CFG1_TX_FREQOFF_DIR BIT(1) -#define HSIO_S6G_DFT_CFG1_TX_FREQOFF_ENA BIT(0) - -#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8)) -#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL_M GENMASK(17, 8) -#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8) -#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ_M GENMASK(7, 4) -#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S6G_DFT_CFG2_RX_JI_ENA BIT(3) -#define HSIO_S6G_DFT_CFG2_RX_WAVEFORM_SEL BIT(2) -#define HSIO_S6G_DFT_CFG2_RX_FREQOFF_DIR BIT(1) -#define HSIO_S6G_DFT_CFG2_RX_FREQOFF_ENA BIT(0) - -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_ENA BIT(20) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH(x) (((x) << 16) & GENMASK(19, 16)) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_M GENMASK(19, 16) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_X(x) (((x) & GENMASK(19, 16)) >> 16) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH(x) (((x) << 8) & GENMASK(15, 8)) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_M GENMASK(15, 8) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_X(x) (((x) & GENMASK(15, 8)) >> 8) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_LOW(x) ((x) & GENMASK(7, 0)) -#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_LOW_M GENMASK(7, 0) - -#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK(x) (((x) << 13) & GENMASK(14, 13)) -#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK_M GENMASK(14, 13) -#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK_X(x) (((x) & GENMASK(14, 13)) >> 13) -#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE(x) (((x) << 11) & GENMASK(12, 11)) -#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE_M GENMASK(12, 11) -#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE_X(x) (((x) & GENMASK(12, 11)) >> 11) -#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_SWAP BIT(10) -#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_MODE BIT(9) -#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_ENA BIT(8) -#define HSIO_S6G_MISC_CFG_RX_BUS_FLIP_ENA BIT(7) -#define HSIO_S6G_MISC_CFG_TX_BUS_FLIP_ENA BIT(6) -#define HSIO_S6G_MISC_CFG_RX_LPI_MODE_ENA BIT(5) -#define HSIO_S6G_MISC_CFG_TX_LPI_MODE_ENA BIT(4) -#define HSIO_S6G_MISC_CFG_RX_DATA_INV_ENA BIT(3) -#define HSIO_S6G_MISC_CFG_TX_DATA_INV_ENA BIT(2) -#define HSIO_S6G_MISC_CFG_LANE_RST BIT(0) - -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0(x) (((x) << 23) & GENMASK(28, 23)) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0_M GENMASK(28, 23) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0_X(x) (((x) & GENMASK(28, 23)) >> 23) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1(x) (((x) << 18) & GENMASK(22, 18)) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1_M GENMASK(22, 18) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1_X(x) (((x) & GENMASK(22, 18)) >> 18) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC(x) (((x) << 13) & GENMASK(17, 13)) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC_M GENMASK(17, 13) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC_X(x) (((x) & GENMASK(17, 13)) >> 13) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS(x) (((x) << 6) & GENMASK(8, 6)) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS_M GENMASK(8, 6) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS_X(x) (((x) & GENMASK(8, 6)) >> 6) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_LEV(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_OB_ANEG_CFG_AN_OB_LEV_M GENMASK(5, 0) - -#define HSIO_S6G_DFT_STATUS_PRBS_SYNC_STAT BIT(8) -#define HSIO_S6G_DFT_STATUS_PLL_BIST_NOT_DONE BIT(7) -#define HSIO_S6G_DFT_STATUS_PLL_BIST_FAILED BIT(6) -#define HSIO_S6G_DFT_STATUS_PLL_BIST_TIMEOUT_ERR BIT(5) -#define HSIO_S6G_DFT_STATUS_BIST_ACTIVE BIT(3) -#define HSIO_S6G_DFT_STATUS_BIST_NOSYNC BIT(2) -#define HSIO_S6G_DFT_STATUS_BIST_COMPLETE_N BIT(1) -#define HSIO_S6G_DFT_STATUS_BIST_ERROR BIT(0) - -#define HSIO_S6G_MISC_STATUS_DES_100FX_PHASE_SEL BIT(0) - -#define HSIO_S6G_DES_CFG_DES_PHS_CTRL(x) (((x) << 13) & GENMASK(16, 13)) -#define HSIO_S6G_DES_CFG_DES_PHS_CTRL_M GENMASK(16, 13) -#define HSIO_S6G_DES_CFG_DES_PHS_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13) -#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL(x) (((x) << 10) & GENMASK(12, 10)) -#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL_M GENMASK(12, 10) -#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL_X(x) (((x) & GENMASK(12, 10)) >> 10) -#define HSIO_S6G_DES_CFG_DES_CPMD_SEL(x) (((x) << 8) & GENMASK(9, 8)) -#define HSIO_S6G_DES_CFG_DES_CPMD_SEL_M GENMASK(9, 8) -#define HSIO_S6G_DES_CFG_DES_CPMD_SEL_X(x) (((x) & GENMASK(9, 8)) >> 8) -#define HSIO_S6G_DES_CFG_DES_BW_HYST(x) (((x) << 5) & GENMASK(7, 5)) -#define HSIO_S6G_DES_CFG_DES_BW_HYST_M GENMASK(7, 5) -#define HSIO_S6G_DES_CFG_DES_BW_HYST_X(x) (((x) & GENMASK(7, 5)) >> 5) -#define HSIO_S6G_DES_CFG_DES_SWAP_HYST BIT(4) -#define HSIO_S6G_DES_CFG_DES_BW_ANA(x) (((x) << 1) & GENMASK(3, 1)) -#define HSIO_S6G_DES_CFG_DES_BW_ANA_M GENMASK(3, 1) -#define HSIO_S6G_DES_CFG_DES_BW_ANA_X(x) (((x) & GENMASK(3, 1)) >> 1) -#define HSIO_S6G_DES_CFG_DES_SWAP_ANA BIT(0) - -#define HSIO_S6G_IB_CFG_IB_SOFSI(x) (((x) << 29) & GENMASK(30, 29)) -#define HSIO_S6G_IB_CFG_IB_SOFSI_M GENMASK(30, 29) -#define HSIO_S6G_IB_CFG_IB_SOFSI_X(x) (((x) & GENMASK(30, 29)) >> 29) -#define HSIO_S6G_IB_CFG_IB_VBULK_SEL BIT(28) -#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ(x) (((x) << 24) & GENMASK(27, 24)) -#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ_M GENMASK(27, 24) -#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ_X(x) (((x) & GENMASK(27, 24)) >> 24) -#define HSIO_S6G_IB_CFG_IB_ICML_ADJ(x) (((x) << 20) & GENMASK(23, 20)) -#define HSIO_S6G_IB_CFG_IB_ICML_ADJ_M GENMASK(23, 20) -#define HSIO_S6G_IB_CFG_IB_ICML_ADJ_X(x) (((x) & GENMASK(23, 20)) >> 20) -#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL(x) (((x) << 18) & GENMASK(19, 18)) -#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL_M GENMASK(19, 18) -#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL_X(x) (((x) & GENMASK(19, 18)) >> 18) -#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL(x) (((x) << 15) & GENMASK(17, 15)) -#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL_M GENMASK(17, 15) -#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL_X(x) (((x) & GENMASK(17, 15)) >> 15) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP(x) (((x) << 13) & GENMASK(14, 13)) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP_M GENMASK(14, 13) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP_X(x) (((x) & GENMASK(14, 13)) >> 13) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID(x) (((x) << 11) & GENMASK(12, 11)) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID_M GENMASK(12, 11) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID_X(x) (((x) & GENMASK(12, 11)) >> 11) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP(x) (((x) << 9) & GENMASK(10, 9)) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP_M GENMASK(10, 9) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP_X(x) (((x) & GENMASK(10, 9)) >> 9) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET(x) (((x) << 7) & GENMASK(8, 7)) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET_M GENMASK(8, 7) -#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET_X(x) (((x) & GENMASK(8, 7)) >> 7) -#define HSIO_S6G_IB_CFG_IB_ANA_TEST_ENA BIT(6) -#define HSIO_S6G_IB_CFG_IB_SIG_DET_ENA BIT(5) -#define HSIO_S6G_IB_CFG_IB_CONCUR BIT(4) -#define HSIO_S6G_IB_CFG_IB_CAL_ENA BIT(3) -#define HSIO_S6G_IB_CFG_IB_SAM_ENA BIT(2) -#define HSIO_S6G_IB_CFG_IB_EQZ_ENA BIT(1) -#define HSIO_S6G_IB_CFG_IB_REG_ENA BIT(0) - -#define HSIO_S6G_IB_CFG1_IB_TJTAG(x) (((x) << 17) & GENMASK(21, 17)) -#define HSIO_S6G_IB_CFG1_IB_TJTAG_M GENMASK(21, 17) -#define HSIO_S6G_IB_CFG1_IB_TJTAG_X(x) (((x) & GENMASK(21, 17)) >> 17) -#define HSIO_S6G_IB_CFG1_IB_TSDET(x) (((x) << 12) & GENMASK(16, 12)) -#define HSIO_S6G_IB_CFG1_IB_TSDET_M GENMASK(16, 12) -#define HSIO_S6G_IB_CFG1_IB_TSDET_X(x) (((x) & GENMASK(16, 12)) >> 12) -#define HSIO_S6G_IB_CFG1_IB_SCALY(x) (((x) << 8) & GENMASK(11, 8)) -#define HSIO_S6G_IB_CFG1_IB_SCALY_M GENMASK(11, 8) -#define HSIO_S6G_IB_CFG1_IB_SCALY_X(x) (((x) & GENMASK(11, 8)) >> 8) -#define HSIO_S6G_IB_CFG1_IB_FILT_HP BIT(7) -#define HSIO_S6G_IB_CFG1_IB_FILT_MID BIT(6) -#define HSIO_S6G_IB_CFG1_IB_FILT_LP BIT(5) -#define HSIO_S6G_IB_CFG1_IB_FILT_OFFSET BIT(4) -#define HSIO_S6G_IB_CFG1_IB_FRC_HP BIT(3) -#define HSIO_S6G_IB_CFG1_IB_FRC_MID BIT(2) -#define HSIO_S6G_IB_CFG1_IB_FRC_LP BIT(1) -#define HSIO_S6G_IB_CFG1_IB_FRC_OFFSET BIT(0) - -#define HSIO_S6G_IB_CFG2_IB_TINFV(x) (((x) << 27) & GENMASK(29, 27)) -#define HSIO_S6G_IB_CFG2_IB_TINFV_M GENMASK(29, 27) -#define HSIO_S6G_IB_CFG2_IB_TINFV_X(x) (((x) & GENMASK(29, 27)) >> 27) -#define HSIO_S6G_IB_CFG2_IB_OINFI(x) (((x) << 22) & GENMASK(26, 22)) -#define HSIO_S6G_IB_CFG2_IB_OINFI_M GENMASK(26, 22) -#define HSIO_S6G_IB_CFG2_IB_OINFI_X(x) (((x) & GENMASK(26, 22)) >> 22) -#define HSIO_S6G_IB_CFG2_IB_TAUX(x) (((x) << 19) & GENMASK(21, 19)) -#define HSIO_S6G_IB_CFG2_IB_TAUX_M GENMASK(21, 19) -#define HSIO_S6G_IB_CFG2_IB_TAUX_X(x) (((x) & GENMASK(21, 19)) >> 19) -#define HSIO_S6G_IB_CFG2_IB_OINFS(x) (((x) << 16) & GENMASK(18, 16)) -#define HSIO_S6G_IB_CFG2_IB_OINFS_M GENMASK(18, 16) -#define HSIO_S6G_IB_CFG2_IB_OINFS_X(x) (((x) & GENMASK(18, 16)) >> 16) -#define HSIO_S6G_IB_CFG2_IB_OCALS(x) (((x) << 10) & GENMASK(15, 10)) -#define HSIO_S6G_IB_CFG2_IB_OCALS_M GENMASK(15, 10) -#define HSIO_S6G_IB_CFG2_IB_OCALS_X(x) (((x) & GENMASK(15, 10)) >> 10) -#define HSIO_S6G_IB_CFG2_IB_TCALV(x) (((x) << 5) & GENMASK(9, 5)) -#define HSIO_S6G_IB_CFG2_IB_TCALV_M GENMASK(9, 5) -#define HSIO_S6G_IB_CFG2_IB_TCALV_X(x) (((x) & GENMASK(9, 5)) >> 5) -#define HSIO_S6G_IB_CFG2_IB_UMAX(x) (((x) << 3) & GENMASK(4, 3)) -#define HSIO_S6G_IB_CFG2_IB_UMAX_M GENMASK(4, 3) -#define HSIO_S6G_IB_CFG2_IB_UMAX_X(x) (((x) & GENMASK(4, 3)) >> 3) -#define HSIO_S6G_IB_CFG2_IB_UREG(x) ((x) & GENMASK(2, 0)) -#define HSIO_S6G_IB_CFG2_IB_UREG_M GENMASK(2, 0) - -#define HSIO_S6G_IB_CFG3_IB_INI_HP(x) (((x) << 18) & GENMASK(23, 18)) -#define HSIO_S6G_IB_CFG3_IB_INI_HP_M GENMASK(23, 18) -#define HSIO_S6G_IB_CFG3_IB_INI_HP_X(x) (((x) & GENMASK(23, 18)) >> 18) -#define HSIO_S6G_IB_CFG3_IB_INI_MID(x) (((x) << 12) & GENMASK(17, 12)) -#define HSIO_S6G_IB_CFG3_IB_INI_MID_M GENMASK(17, 12) -#define HSIO_S6G_IB_CFG3_IB_INI_MID_X(x) (((x) & GENMASK(17, 12)) >> 12) -#define HSIO_S6G_IB_CFG3_IB_INI_LP(x) (((x) << 6) & GENMASK(11, 6)) -#define HSIO_S6G_IB_CFG3_IB_INI_LP_M GENMASK(11, 6) -#define HSIO_S6G_IB_CFG3_IB_INI_LP_X(x) (((x) & GENMASK(11, 6)) >> 6) -#define HSIO_S6G_IB_CFG3_IB_INI_OFFSET(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_IB_CFG3_IB_INI_OFFSET_M GENMASK(5, 0) - -#define HSIO_S6G_IB_CFG4_IB_MAX_HP(x) (((x) << 18) & GENMASK(23, 18)) -#define HSIO_S6G_IB_CFG4_IB_MAX_HP_M GENMASK(23, 18) -#define HSIO_S6G_IB_CFG4_IB_MAX_HP_X(x) (((x) & GENMASK(23, 18)) >> 18) -#define HSIO_S6G_IB_CFG4_IB_MAX_MID(x) (((x) << 12) & GENMASK(17, 12)) -#define HSIO_S6G_IB_CFG4_IB_MAX_MID_M GENMASK(17, 12) -#define HSIO_S6G_IB_CFG4_IB_MAX_MID_X(x) (((x) & GENMASK(17, 12)) >> 12) -#define HSIO_S6G_IB_CFG4_IB_MAX_LP(x) (((x) << 6) & GENMASK(11, 6)) -#define HSIO_S6G_IB_CFG4_IB_MAX_LP_M GENMASK(11, 6) -#define HSIO_S6G_IB_CFG4_IB_MAX_LP_X(x) (((x) & GENMASK(11, 6)) >> 6) -#define HSIO_S6G_IB_CFG4_IB_MAX_OFFSET(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_IB_CFG4_IB_MAX_OFFSET_M GENMASK(5, 0) - -#define HSIO_S6G_IB_CFG5_IB_MIN_HP(x) (((x) << 18) & GENMASK(23, 18)) -#define HSIO_S6G_IB_CFG5_IB_MIN_HP_M GENMASK(23, 18) -#define HSIO_S6G_IB_CFG5_IB_MIN_HP_X(x) (((x) & GENMASK(23, 18)) >> 18) -#define HSIO_S6G_IB_CFG5_IB_MIN_MID(x) (((x) << 12) & GENMASK(17, 12)) -#define HSIO_S6G_IB_CFG5_IB_MIN_MID_M GENMASK(17, 12) -#define HSIO_S6G_IB_CFG5_IB_MIN_MID_X(x) (((x) & GENMASK(17, 12)) >> 12) -#define HSIO_S6G_IB_CFG5_IB_MIN_LP(x) (((x) << 6) & GENMASK(11, 6)) -#define HSIO_S6G_IB_CFG5_IB_MIN_LP_M GENMASK(11, 6) -#define HSIO_S6G_IB_CFG5_IB_MIN_LP_X(x) (((x) & GENMASK(11, 6)) >> 6) -#define HSIO_S6G_IB_CFG5_IB_MIN_OFFSET(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_IB_CFG5_IB_MIN_OFFSET_M GENMASK(5, 0) - -#define HSIO_S6G_OB_CFG_OB_IDLE BIT(31) -#define HSIO_S6G_OB_CFG_OB_ENA1V_MODE BIT(30) -#define HSIO_S6G_OB_CFG_OB_POL BIT(29) -#define HSIO_S6G_OB_CFG_OB_POST0(x) (((x) << 23) & GENMASK(28, 23)) -#define HSIO_S6G_OB_CFG_OB_POST0_M GENMASK(28, 23) -#define HSIO_S6G_OB_CFG_OB_POST0_X(x) (((x) & GENMASK(28, 23)) >> 23) -#define HSIO_S6G_OB_CFG_OB_PREC(x) (((x) << 18) & GENMASK(22, 18)) -#define HSIO_S6G_OB_CFG_OB_PREC_M GENMASK(22, 18) -#define HSIO_S6G_OB_CFG_OB_PREC_X(x) (((x) & GENMASK(22, 18)) >> 18) -#define HSIO_S6G_OB_CFG_OB_R_ADJ_MUX BIT(17) -#define HSIO_S6G_OB_CFG_OB_R_ADJ_PDR BIT(16) -#define HSIO_S6G_OB_CFG_OB_POST1(x) (((x) << 11) & GENMASK(15, 11)) -#define HSIO_S6G_OB_CFG_OB_POST1_M GENMASK(15, 11) -#define HSIO_S6G_OB_CFG_OB_POST1_X(x) (((x) & GENMASK(15, 11)) >> 11) -#define HSIO_S6G_OB_CFG_OB_R_COR BIT(10) -#define HSIO_S6G_OB_CFG_OB_SEL_RCTRL BIT(9) -#define HSIO_S6G_OB_CFG_OB_SR_H BIT(8) -#define HSIO_S6G_OB_CFG_OB_SR(x) (((x) << 4) & GENMASK(7, 4)) -#define HSIO_S6G_OB_CFG_OB_SR_M GENMASK(7, 4) -#define HSIO_S6G_OB_CFG_OB_SR_X(x) (((x) & GENMASK(7, 4)) >> 4) -#define HSIO_S6G_OB_CFG_OB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0)) -#define HSIO_S6G_OB_CFG_OB_RESISTOR_CTRL_M GENMASK(3, 0) - -#define HSIO_S6G_OB_CFG1_OB_ENA_CAS(x) (((x) << 6) & GENMASK(8, 6)) -#define HSIO_S6G_OB_CFG1_OB_ENA_CAS_M GENMASK(8, 6) -#define HSIO_S6G_OB_CFG1_OB_ENA_CAS_X(x) (((x) & GENMASK(8, 6)) >> 6) -#define HSIO_S6G_OB_CFG1_OB_LEV(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_OB_CFG1_OB_LEV_M GENMASK(5, 0) - -#define HSIO_S6G_SER_CFG_SER_4TAP_ENA BIT(8) -#define HSIO_S6G_SER_CFG_SER_CPMD_SEL BIT(7) -#define HSIO_S6G_SER_CFG_SER_SWAP_CPMD BIT(6) -#define HSIO_S6G_SER_CFG_SER_ALISEL(x) (((x) << 4) & GENMASK(5, 4)) -#define HSIO_S6G_SER_CFG_SER_ALISEL_M GENMASK(5, 4) -#define HSIO_S6G_SER_CFG_SER_ALISEL_X(x) (((x) & GENMASK(5, 4)) >> 4) -#define HSIO_S6G_SER_CFG_SER_ENHYS BIT(3) -#define HSIO_S6G_SER_CFG_SER_BIG_WIN BIT(2) -#define HSIO_S6G_SER_CFG_SER_EN_WIN BIT(1) -#define HSIO_S6G_SER_CFG_SER_ENALI BIT(0) - -#define HSIO_S6G_COMMON_CFG_SYS_RST BIT(17) -#define HSIO_S6G_COMMON_CFG_SE_DIV2_ENA BIT(16) -#define HSIO_S6G_COMMON_CFG_SE_AUTO_SQUELCH_ENA BIT(15) -#define HSIO_S6G_COMMON_CFG_ENA_LANE BIT(14) -#define HSIO_S6G_COMMON_CFG_PWD_RX BIT(13) -#define HSIO_S6G_COMMON_CFG_PWD_TX BIT(12) -#define HSIO_S6G_COMMON_CFG_LANE_CTRL(x) (((x) << 9) & GENMASK(11, 9)) -#define HSIO_S6G_COMMON_CFG_LANE_CTRL_M GENMASK(11, 9) -#define HSIO_S6G_COMMON_CFG_LANE_CTRL_X(x) (((x) & GENMASK(11, 9)) >> 9) -#define HSIO_S6G_COMMON_CFG_ENA_DIRECT BIT(8) -#define HSIO_S6G_COMMON_CFG_ENA_ELOOP BIT(7) -#define HSIO_S6G_COMMON_CFG_ENA_FLOOP BIT(6) -#define HSIO_S6G_COMMON_CFG_ENA_ILOOP BIT(5) -#define HSIO_S6G_COMMON_CFG_ENA_PLOOP BIT(4) -#define HSIO_S6G_COMMON_CFG_HRATE BIT(3) -#define HSIO_S6G_COMMON_CFG_QRATE BIT(2) -#define HSIO_S6G_COMMON_CFG_IF_MODE(x) ((x) & GENMASK(1, 0)) -#define HSIO_S6G_COMMON_CFG_IF_MODE_M GENMASK(1, 0) - -#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS(x) (((x) << 16) & GENMASK(17, 16)) -#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS_M GENMASK(17, 16) -#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS_X(x) (((x) & GENMASK(17, 16)) >> 16) -#define HSIO_S6G_PLL_CFG_PLL_DIV4 BIT(15) -#define HSIO_S6G_PLL_CFG_PLL_ENA_ROT BIT(14) -#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA(x) (((x) << 6) & GENMASK(13, 6)) -#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA_M GENMASK(13, 6) -#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA_X(x) (((x) & GENMASK(13, 6)) >> 6) -#define HSIO_S6G_PLL_CFG_PLL_FSM_ENA BIT(5) -#define HSIO_S6G_PLL_CFG_PLL_FSM_FORCE_SET_ENA BIT(4) -#define HSIO_S6G_PLL_CFG_PLL_FSM_OOR_RECAL_ENA BIT(3) -#define HSIO_S6G_PLL_CFG_PLL_RB_DATA_SEL BIT(2) -#define HSIO_S6G_PLL_CFG_PLL_ROT_DIR BIT(1) -#define HSIO_S6G_PLL_CFG_PLL_ROT_FRQ BIT(0) - -#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_DATA_N BIT(5) -#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_DATA_P BIT(4) -#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_CLK BIT(3) -#define HSIO_S6G_ACJTAG_CFG_OB_DIRECT BIT(2) -#define HSIO_S6G_ACJTAG_CFG_ACJTAG_ENA BIT(1) -#define HSIO_S6G_ACJTAG_CFG_JTAG_CTRL_ENA BIT(0) - -#define HSIO_S6G_GP_CFG_GP_MSB(x) (((x) << 16) & GENMASK(31, 16)) -#define HSIO_S6G_GP_CFG_GP_MSB_M GENMASK(31, 16) -#define HSIO_S6G_GP_CFG_GP_MSB_X(x) (((x) & GENMASK(31, 16)) >> 16) -#define HSIO_S6G_GP_CFG_GP_LSB(x) ((x) & GENMASK(15, 0)) -#define HSIO_S6G_GP_CFG_GP_LSB_M GENMASK(15, 0) - -#define HSIO_S6G_IB_STATUS0_IB_CAL_DONE BIT(8) -#define HSIO_S6G_IB_STATUS0_IB_HP_GAIN_ACT BIT(7) -#define HSIO_S6G_IB_STATUS0_IB_MID_GAIN_ACT BIT(6) -#define HSIO_S6G_IB_STATUS0_IB_LP_GAIN_ACT BIT(5) -#define HSIO_S6G_IB_STATUS0_IB_OFFSET_ACT BIT(4) -#define HSIO_S6G_IB_STATUS0_IB_OFFSET_VLD BIT(3) -#define HSIO_S6G_IB_STATUS0_IB_OFFSET_ERR BIT(2) -#define HSIO_S6G_IB_STATUS0_IB_OFFSDIR BIT(1) -#define HSIO_S6G_IB_STATUS0_IB_SIG_DET BIT(0) - -#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT(x) (((x) << 18) & GENMASK(23, 18)) -#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT_M GENMASK(23, 18) -#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT_X(x) (((x) & GENMASK(23, 18)) >> 18) -#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT(x) (((x) << 12) & GENMASK(17, 12)) -#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT_M GENMASK(17, 12) -#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT_X(x) (((x) & GENMASK(17, 12)) >> 12) -#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT(x) (((x) << 6) & GENMASK(11, 6)) -#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT_M GENMASK(11, 6) -#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT_X(x) (((x) & GENMASK(11, 6)) >> 6) -#define HSIO_S6G_IB_STATUS1_IB_OFFSET_STAT(x) ((x) & GENMASK(5, 0)) -#define HSIO_S6G_IB_STATUS1_IB_OFFSET_STAT_M GENMASK(5, 0) - -#define HSIO_S6G_ACJTAG_STATUS_ACJTAG_CAPT_DATA_N BIT(2) -#define HSIO_S6G_ACJTAG_STATUS_ACJTAG_CAPT_DATA_P BIT(1) -#define HSIO_S6G_ACJTAG_STATUS_IB_DIRECT BIT(0) - -#define HSIO_S6G_PLL_STATUS_PLL_CAL_NOT_DONE BIT(10) -#define HSIO_S6G_PLL_STATUS_PLL_CAL_ERR BIT(9) -#define HSIO_S6G_PLL_STATUS_PLL_OUT_OF_RANGE_ERR BIT(8) -#define HSIO_S6G_PLL_STATUS_PLL_RB_DATA(x) ((x) & GENMASK(7, 0)) -#define HSIO_S6G_PLL_STATUS_PLL_RB_DATA_M GENMASK(7, 0) - -#define HSIO_S6G_REVID_SERDES_REV(x) (((x) << 26) & GENMASK(31, 26)) -#define HSIO_S6G_REVID_SERDES_REV_M GENMASK(31, 26) -#define HSIO_S6G_REVID_SERDES_REV_X(x) (((x) & GENMASK(31, 26)) >> 26) -#define HSIO_S6G_REVID_RCPLL_REV(x) (((x) << 21) & GENMASK(25, 21)) -#define HSIO_S6G_REVID_RCPLL_REV_M GENMASK(25, 21) -#define HSIO_S6G_REVID_RCPLL_REV_X(x) (((x) & GENMASK(25, 21)) >> 21) -#define HSIO_S6G_REVID_SER_REV(x) (((x) << 16) & GENMASK(20, 16)) -#define HSIO_S6G_REVID_SER_REV_M GENMASK(20, 16) -#define HSIO_S6G_REVID_SER_REV_X(x) (((x) & GENMASK(20, 16)) >> 16) -#define HSIO_S6G_REVID_DES_REV(x) (((x) << 10) & GENMASK(15, 10)) -#define HSIO_S6G_REVID_DES_REV_M GENMASK(15, 10) -#define HSIO_S6G_REVID_DES_REV_X(x) (((x) & GENMASK(15, 10)) >> 10) -#define HSIO_S6G_REVID_OB_REV(x) (((x) << 5) & GENMASK(9, 5)) -#define HSIO_S6G_REVID_OB_REV_M GENMASK(9, 5) -#define HSIO_S6G_REVID_OB_REV_X(x) (((x) & GENMASK(9, 5)) >> 5) -#define HSIO_S6G_REVID_IB_REV(x) ((x) & GENMASK(4, 0)) -#define HSIO_S6G_REVID_IB_REV_M GENMASK(4, 0) - -#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_WR_ONE_SHOT BIT(31) -#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_RD_ONE_SHOT BIT(30) -#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_ADDR(x) ((x) & GENMASK(24, 0)) -#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_ADDR_M GENMASK(24, 0) - -#define HSIO_HW_CFG_DEV2G5_10_MODE BIT(6) -#define HSIO_HW_CFG_DEV1G_9_MODE BIT(5) -#define HSIO_HW_CFG_DEV1G_6_MODE BIT(4) -#define HSIO_HW_CFG_DEV1G_5_MODE BIT(3) -#define HSIO_HW_CFG_DEV1G_4_MODE BIT(2) -#define HSIO_HW_CFG_PCIE_ENA BIT(1) -#define HSIO_HW_CFG_QSGMII_ENA BIT(0) - -#define HSIO_HW_QSGMII_CFG_SHYST_DIS BIT(3) -#define HSIO_HW_QSGMII_CFG_E_DET_ENA BIT(2) -#define HSIO_HW_QSGMII_CFG_USE_I1_ENA BIT(1) -#define HSIO_HW_QSGMII_CFG_FLIP_LANES BIT(0) - -#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS(x) (((x) << 1) & GENMASK(6, 1)) -#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS_M GENMASK(6, 1) -#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS_X(x) (((x) & GENMASK(6, 1)) >> 1) -#define HSIO_HW_QSGMII_STAT_SYNC BIT(0) - -#define HSIO_CLK_CFG_CLKDIV_PHY(x) (((x) << 1) & GENMASK(8, 1)) -#define HSIO_CLK_CFG_CLKDIV_PHY_M GENMASK(8, 1) -#define HSIO_CLK_CFG_CLKDIV_PHY_X(x) (((x) & GENMASK(8, 1)) >> 1) -#define HSIO_CLK_CFG_CLKDIV_PHY_DIS BIT(0) - -#define HSIO_TEMP_SENSOR_CTRL_FORCE_TEMP_RD BIT(5) -#define HSIO_TEMP_SENSOR_CTRL_FORCE_RUN BIT(4) -#define HSIO_TEMP_SENSOR_CTRL_FORCE_NO_RST BIT(3) -#define HSIO_TEMP_SENSOR_CTRL_FORCE_POWER_UP BIT(2) -#define HSIO_TEMP_SENSOR_CTRL_FORCE_CLK BIT(1) -#define HSIO_TEMP_SENSOR_CTRL_SAMPLE_ENA BIT(0) - -#define HSIO_TEMP_SENSOR_CFG_RUN_WID(x) (((x) << 8) & GENMASK(15, 8)) -#define HSIO_TEMP_SENSOR_CFG_RUN_WID_M GENMASK(15, 8) -#define HSIO_TEMP_SENSOR_CFG_RUN_WID_X(x) (((x) & GENMASK(15, 8)) >> 8) -#define HSIO_TEMP_SENSOR_CFG_SAMPLE_PER(x) ((x) & GENMASK(7, 0)) -#define HSIO_TEMP_SENSOR_CFG_SAMPLE_PER_M GENMASK(7, 0) - -#define HSIO_TEMP_SENSOR_STAT_TEMP_VALID BIT(8) -#define HSIO_TEMP_SENSOR_STAT_TEMP(x) ((x) & GENMASK(7, 0)) -#define HSIO_TEMP_SENSOR_STAT_TEMP_M GENMASK(7, 0) - -#endif diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index e334b406c40c..9271af18b93b 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -5,6 +5,7 @@ * Copyright (c) 2017 Microsemi Corporation */ #include "ocelot.h" +#include <soc/mscc/ocelot_hsio.h> static const u32 ocelot_ana_regmap[] = { REG(ANA_ADVLEARN, 0x009000), @@ -102,82 +103,6 @@ static const u32 ocelot_qs_regmap[] = { REG(QS_INH_DBG, 0x000048), }; -static const u32 ocelot_hsio_regmap[] = { - REG(HSIO_PLL5G_CFG0, 0x000000), - REG(HSIO_PLL5G_CFG1, 0x000004), - REG(HSIO_PLL5G_CFG2, 0x000008), - REG(HSIO_PLL5G_CFG3, 0x00000c), - REG(HSIO_PLL5G_CFG4, 0x000010), - REG(HSIO_PLL5G_CFG5, 0x000014), - REG(HSIO_PLL5G_CFG6, 0x000018), - REG(HSIO_PLL5G_STATUS0, 0x00001c), - REG(HSIO_PLL5G_STATUS1, 0x000020), - REG(HSIO_PLL5G_BIST_CFG0, 0x000024), - REG(HSIO_PLL5G_BIST_CFG1, 0x000028), - REG(HSIO_PLL5G_BIST_CFG2, 0x00002c), - REG(HSIO_PLL5G_BIST_STAT0, 0x000030), - REG(HSIO_PLL5G_BIST_STAT1, 0x000034), - REG(HSIO_RCOMP_CFG0, 0x000038), - REG(HSIO_RCOMP_STATUS, 0x00003c), - REG(HSIO_SYNC_ETH_CFG, 0x000040), - REG(HSIO_SYNC_ETH_PLL_CFG, 0x000048), - REG(HSIO_S1G_DES_CFG, 0x00004c), - REG(HSIO_S1G_IB_CFG, 0x000050), - REG(HSIO_S1G_OB_CFG, 0x000054), - REG(HSIO_S1G_SER_CFG, 0x000058), - REG(HSIO_S1G_COMMON_CFG, 0x00005c), - REG(HSIO_S1G_PLL_CFG, 0x000060), - REG(HSIO_S1G_PLL_STATUS, 0x000064), - REG(HSIO_S1G_DFT_CFG0, 0x000068), - REG(HSIO_S1G_DFT_CFG1, 0x00006c), - REG(HSIO_S1G_DFT_CFG2, 0x000070), - REG(HSIO_S1G_TP_CFG, 0x000074), - REG(HSIO_S1G_RC_PLL_BIST_CFG, 0x000078), - REG(HSIO_S1G_MISC_CFG, 0x00007c), - REG(HSIO_S1G_DFT_STATUS, 0x000080), - REG(HSIO_S1G_MISC_STATUS, 0x000084), - REG(HSIO_MCB_S1G_ADDR_CFG, 0x000088), - REG(HSIO_S6G_DIG_CFG, 0x00008c), - REG(HSIO_S6G_DFT_CFG0, 0x000090), - REG(HSIO_S6G_DFT_CFG1, 0x000094), - REG(HSIO_S6G_DFT_CFG2, 0x000098), - REG(HSIO_S6G_TP_CFG0, 0x00009c), - REG(HSIO_S6G_TP_CFG1, 0x0000a0), - REG(HSIO_S6G_RC_PLL_BIST_CFG, 0x0000a4), - REG(HSIO_S6G_MISC_CFG, 0x0000a8), - REG(HSIO_S6G_OB_ANEG_CFG, 0x0000ac), - REG(HSIO_S6G_DFT_STATUS, 0x0000b0), - REG(HSIO_S6G_ERR_CNT, 0x0000b4), - REG(HSIO_S6G_MISC_STATUS, 0x0000b8), - REG(HSIO_S6G_DES_CFG, 0x0000bc), - REG(HSIO_S6G_IB_CFG, 0x0000c0), - REG(HSIO_S6G_IB_CFG1, 0x0000c4), - REG(HSIO_S6G_IB_CFG2, 0x0000c8), - REG(HSIO_S6G_IB_CFG3, 0x0000cc), - REG(HSIO_S6G_IB_CFG4, 0x0000d0), - REG(HSIO_S6G_IB_CFG5, 0x0000d4), - REG(HSIO_S6G_OB_CFG, 0x0000d8), - REG(HSIO_S6G_OB_CFG1, 0x0000dc), - REG(HSIO_S6G_SER_CFG, 0x0000e0), - REG(HSIO_S6G_COMMON_CFG, 0x0000e4), - REG(HSIO_S6G_PLL_CFG, 0x0000e8), - REG(HSIO_S6G_ACJTAG_CFG, 0x0000ec), - REG(HSIO_S6G_GP_CFG, 0x0000f0), - REG(HSIO_S6G_IB_STATUS0, 0x0000f4), - REG(HSIO_S6G_IB_STATUS1, 0x0000f8), - REG(HSIO_S6G_ACJTAG_STATUS, 0x0000fc), - REG(HSIO_S6G_PLL_STATUS, 0x000100), - REG(HSIO_S6G_REVID, 0x000104), - REG(HSIO_MCB_S6G_ADDR_CFG, 0x000108), - REG(HSIO_HW_CFG, 0x00010c), - REG(HSIO_HW_QSGMII_CFG, 0x000110), - REG(HSIO_HW_QSGMII_STAT, 0x000114), - REG(HSIO_CLK_CFG, 0x000118), - REG(HSIO_TEMP_SENSOR_CTRL, 0x00011c), - REG(HSIO_TEMP_SENSOR_CFG, 0x000120), - REG(HSIO_TEMP_SENSOR_STAT, 0x000124), -}; - static const u32 ocelot_qsys_regmap[] = { REG(QSYS_PORT_MODE, 0x011200), REG(QSYS_SWITCH_PORT_MODE, 0x011234), @@ -302,7 +227,6 @@ static const u32 ocelot_sys_regmap[] = { static const u32 *ocelot_regmap[] = { [ANA] = ocelot_ana_regmap, [QS] = ocelot_qs_regmap, - [HSIO] = ocelot_hsio_regmap, [QSYS] = ocelot_qsys_regmap, [REW] = ocelot_rew_regmap, [SYS] = ocelot_sys_regmap, @@ -453,9 +377,11 @@ static void ocelot_pll5_init(struct ocelot *ocelot) /* Configure PLL5. This will need a proper CCF driver * The values are coming from the VTSS API for Ocelot */ - ocelot_write(ocelot, HSIO_PLL5G_CFG4_IB_CTRL(0x7600) | - HSIO_PLL5G_CFG4_IB_BIAS_CTRL(0x8), HSIO_PLL5G_CFG4); - ocelot_write(ocelot, HSIO_PLL5G_CFG0_CORE_CLK_DIV(0x11) | + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG4, + HSIO_PLL5G_CFG4_IB_CTRL(0x7600) | + HSIO_PLL5G_CFG4_IB_BIAS_CTRL(0x8)); + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG0, + HSIO_PLL5G_CFG0_CORE_CLK_DIV(0x11) | HSIO_PLL5G_CFG0_CPU_CLK_DIV(2) | HSIO_PLL5G_CFG0_ENA_BIAS | HSIO_PLL5G_CFG0_ENA_VCO_BUF | @@ -465,13 +391,14 @@ static void ocelot_pll5_init(struct ocelot *ocelot) HSIO_PLL5G_CFG0_SELBGV820(4) | HSIO_PLL5G_CFG0_DIV4 | HSIO_PLL5G_CFG0_ENA_CLKTREE | - HSIO_PLL5G_CFG0_ENA_LANE, HSIO_PLL5G_CFG0); - ocelot_write(ocelot, HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET | + HSIO_PLL5G_CFG0_ENA_LANE); + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG2, + HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET | HSIO_PLL5G_CFG2_EN_RESET_OVERRUN | HSIO_PLL5G_CFG2_GAIN_TEST(0x8) | HSIO_PLL5G_CFG2_ENA_AMPCTRL | HSIO_PLL5G_CFG2_PWD_AMPCTRL_N | - HSIO_PLL5G_CFG2_AMPC_SEL(0x10), HSIO_PLL5G_CFG2); + HSIO_PLL5G_CFG2_AMPC_SEL(0x10)); } int ocelot_chip_init(struct ocelot *ocelot) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index db463e20a876..4213fe42ac4d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -177,7 +177,8 @@ static int nfp_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) return nfp_app_eswitch_mode_get(pf->app, mode); } -static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct nfp_pf *pf = devlink_priv(devlink); int ret; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 8e8dc0db2493..7b91e77b2016 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2077,14 +2077,17 @@ nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp, return true; } -static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) +static bool nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) { struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring; struct nfp_net *nn = r_vec->nfp_net; struct nfp_net_dp *dp = &nn->dp; + unsigned int budget = 512; - while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring)) + while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring) && budget--) continue; + + return budget; } static void nfp_ctrl_poll(unsigned long arg) @@ -2096,9 +2099,13 @@ static void nfp_ctrl_poll(unsigned long arg) __nfp_ctrl_tx_queued(r_vec); spin_unlock(&r_vec->lock); - nfp_ctrl_rx(r_vec); - - nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + if (nfp_ctrl_rx(r_vec)) { + nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + } else { + tasklet_schedule(&r_vec->tasklet); + nn_dp_warn(&r_vec->nfp_net->dp, + "control message budget exceeded!\n"); + } } /* Setup and Configuration diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c index 1f9149bb2ae6..2190836eaa1d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c @@ -113,6 +113,13 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem, caps->mbox_len = length; } break; + case NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0: + case NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1: + dev_warn(dev, + "experimental TLV type:%u offset:%u len:%u\n", + FIELD_GET(NFP_NET_CFG_TLV_HEADER_TYPE, hdr), + offset, length); + break; default: if (!FIELD_GET(NFP_NET_CFG_TLV_HEADER_REQUIRED, hdr)) break; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 4c6fb9ecb72c..863ca04fffbf 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -488,12 +488,20 @@ * %NFP_NET_CFG_TLV_TYPE_MBOX: * Variable, mailbox area. Overwrites the default location which is * %NFP_NET_CFG_MBOX_BASE and length %NFP_NET_CFG_MBOX_VAL_MAX_SZ. + * + * %NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0: + * %NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1: + * Variable, experimental IDs. IDs designated for internal development and + * experiments before a stable TLV ID has been allocated to a feature. Should + * never be present in production firmware. */ #define NFP_NET_CFG_TLV_TYPE_UNKNOWN 0 #define NFP_NET_CFG_TLV_TYPE_RESERVED 1 #define NFP_NET_CFG_TLV_TYPE_END 2 #define NFP_NET_CFG_TLV_TYPE_ME_FREQ 3 #define NFP_NET_CFG_TLV_TYPE_MBOX 4 +#define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0 5 +#define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1 6 struct device; diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 74cf52e3fb09..0611f2335b4a 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -127,8 +127,8 @@ struct nixge_hw_dma_bd { #ifdef CONFIG_PHYS_ADDR_T_64BIT #define nixge_hw_dma_bd_set_addr(bd, field, addr) \ do { \ - (bd)->field##_lo = lower_32_bits(((u64)addr)); \ - (bd)->field##_hi = upper_32_bits(((u64)addr)); \ + (bd)->field##_lo = lower_32_bits((addr)); \ + (bd)->field##_hi = upper_32_bits((addr)); \ } while (0) #else #define nixge_hw_dma_bd_set_addr(bd, field, addr) \ @@ -251,7 +251,7 @@ static void nixge_hw_dma_bd_release(struct net_device *ndev) NIXGE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); - skb = (struct sk_buff *) + skb = (struct sk_buff *)(uintptr_t) nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], sw_id_offset); dev_kfree_skb(skb); @@ -323,7 +323,7 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev) if (!skb) goto out; - nixge_hw_dma_bd_set_offset(&priv->rx_bd_v[i], skb); + nixge_hw_dma_bd_set_offset(&priv->rx_bd_v[i], (uintptr_t)skb); phys = dma_map_single(ndev->dev.parent, skb->data, NIXGE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); @@ -601,8 +601,8 @@ static int nixge_recv(struct net_device *ndev, int budget) tail_p = priv->rx_bd_p + sizeof(*priv->rx_bd_v) * priv->rx_bd_ci; - skb = (struct sk_buff *)nixge_hw_dma_bd_get_addr(cur_p, - sw_id_offset); + skb = (struct sk_buff *)(uintptr_t) + nixge_hw_dma_bd_get_addr(cur_p, sw_id_offset); length = cur_p->status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK; if (length > NIXGE_MAX_JUMBO_FRAME_SIZE) @@ -643,7 +643,7 @@ static int nixge_recv(struct net_device *ndev, int budget) nixge_hw_dma_bd_set_phys(cur_p, cur_phys); cur_p->cntrl = NIXGE_MAX_JUMBO_FRAME_SIZE; cur_p->status = 0; - nixge_hw_dma_bd_set_offset(cur_p, new_skb); + nixge_hw_dma_bd_set_offset(cur_p, (uintptr_t)new_skb); ++priv->rx_bd_ci; priv->rx_bd_ci %= RX_BD_NUM; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 69aa7fc392c5..59c70be22a84 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -72,9 +72,6 @@ static void netxen_schedule_work(struct netxen_adapter *adapter, work_func_t func, int delay); static void netxen_cancel_fw_work(struct netxen_adapter *adapter); static int netxen_nic_poll(struct napi_struct *napi, int budget); -#ifdef CONFIG_NET_POLL_CONTROLLER -static void netxen_nic_poll_controller(struct net_device *netdev); -#endif static void netxen_create_sysfs_entries(struct netxen_adapter *adapter); static void netxen_remove_sysfs_entries(struct netxen_adapter *adapter); @@ -581,9 +578,6 @@ static const struct net_device_ops netxen_netdev_ops = { .ndo_tx_timeout = netxen_tx_timeout, .ndo_fix_features = netxen_fix_features, .ndo_set_features = netxen_set_features, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = netxen_nic_poll_controller, -#endif }; static inline bool netxen_function_zero(struct pci_dev *pdev) @@ -2402,23 +2396,6 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget) return work_done; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void netxen_nic_poll_controller(struct net_device *netdev) -{ - int ring; - struct nx_host_sds_ring *sds_ring; - struct netxen_adapter *adapter = netdev_priv(netdev); - struct netxen_recv_context *recv_ctx = &adapter->recv_ctx; - - disable_irq(adapter->irq); - for (ring = 0; ring < adapter->max_sds_rings; ring++) { - sds_ring = &recv_ctx->sds_rings[ring]; - netxen_intr(adapter->irq, sds_ring); - } - enable_irq(adapter->irq); -} -#endif - static int nx_incr_dev_ref_cnt(struct netxen_adapter *adapter) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 0fbeafeef7a0..7ceb2b97538d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -2679,6 +2679,9 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) case NVM_CFG1_PORT_DRV_LINK_SPEED_10G: link->speed.forced_speed = 10000; break; + case NVM_CFG1_PORT_DRV_LINK_SPEED_20G: + link->speed.forced_speed = 20000; + break; case NVM_CFG1_PORT_DRV_LINK_SPEED_25G: link->speed.forced_speed = 25000; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index d4d08383c753..bf431ab86864 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12102,6 +12102,7 @@ struct public_global { u32 running_bundle_id; s32 external_temperature; u32 mdump_reason; + u64 reserved; u32 data_ptr; u32 data_size; }; @@ -13154,6 +13155,7 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_OFFSET 0 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G 0x1 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G 0x2 +#define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G 0x4 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G 0x8 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G 0x10 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G 0x20 @@ -13164,6 +13166,7 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DRV_LINK_SPEED_AUTONEG 0x0 #define NVM_CFG1_PORT_DRV_LINK_SPEED_1G 0x1 #define NVM_CFG1_PORT_DRV_LINK_SPEED_10G 0x2 +#define NVM_CFG1_PORT_DRV_LINK_SPEED_20G 0x3 #define NVM_CFG1_PORT_DRV_LINK_SPEED_25G 0x4 #define NVM_CFG1_PORT_DRV_LINK_SPEED_40G 0x5 #define NVM_CFG1_PORT_DRV_LINK_SPEED_50G 0x6 diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index f99797a149a4..beb8e5d6401a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1709,7 +1709,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, cm_info->local_ip[0] = ntohl(iph->daddr); cm_info->remote_ip[0] = ntohl(iph->saddr); - cm_info->ip_version = TCP_IPV4; + cm_info->ip_version = QED_TCP_IPV4; ip_hlen = (iph->ihl) * sizeof(u32); *payload_len = ntohs(iph->tot_len) - ip_hlen; @@ -1729,7 +1729,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, cm_info->remote_ip[i] = ntohl(ip6h->saddr.in6_u.u6_addr32[i]); } - cm_info->ip_version = TCP_IPV6; + cm_info->ip_version = QED_TCP_IPV6; ip_hlen = sizeof(*ip6h); *payload_len = ntohs(ip6h->payload_len); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 14ac9cab2653..aa633381aa47 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -63,8 +63,8 @@ #include "qed_sp.h" #include "qed_rdma.h" -#define QED_LL2_RX_REGISTERED(ll2) ((ll2)->rx_queue.b_cb_registred) -#define QED_LL2_TX_REGISTERED(ll2) ((ll2)->tx_queue.b_cb_registred) +#define QED_LL2_RX_REGISTERED(ll2) ((ll2)->rx_queue.b_cb_registered) +#define QED_LL2_TX_REGISTERED(ll2) ((ll2)->tx_queue.b_cb_registered) #define QED_LL2_TX_SIZE (256) #define QED_LL2_RX_SIZE (4096) @@ -796,7 +796,18 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn, tx_pkt.vlan = p_buffer->vlan; tx_pkt.bd_flags = bd_flags; tx_pkt.l4_hdr_offset_w = l4_hdr_offset_w; - tx_pkt.tx_dest = p_ll2_conn->tx_dest; + switch (p_ll2_conn->tx_dest) { + case CORE_TX_DEST_NW: + tx_pkt.tx_dest = QED_LL2_TX_DEST_NW; + break; + case CORE_TX_DEST_LB: + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + break; + case CORE_TX_DEST_DROP: + default: + tx_pkt.tx_dest = QED_LL2_TX_DEST_DROP; + break; + } tx_pkt.first_frag = first_frag; tx_pkt.first_frag_len = p_buffer->packet_length; tx_pkt.cookie = p_buffer; @@ -1404,7 +1415,7 @@ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data) &p_hwfn->p_ll2_info[i], &p_ll2_info->rx_queue.rx_sb_index, &p_ll2_info->rx_queue.p_fw_cons); - p_ll2_info->rx_queue.b_cb_registred = true; + p_ll2_info->rx_queue.b_cb_registered = true; } if (data->input.tx_num_desc) { @@ -1413,7 +1424,7 @@ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data) &p_hwfn->p_ll2_info[i], &p_ll2_info->tx_queue.tx_sb_index, &p_ll2_info->tx_queue.p_fw_cons); - p_ll2_info->tx_queue.b_cb_registred = true; + p_ll2_info->tx_queue.b_cb_registered = true; } *data->p_connection_handle = i; @@ -1929,7 +1940,7 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle) /* Stop Tx & Rx of connection, if needed */ if (QED_LL2_TX_REGISTERED(p_ll2_conn)) { - p_ll2_conn->tx_queue.b_cb_registred = false; + p_ll2_conn->tx_queue.b_cb_registered = false; smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */ rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn); if (rc) @@ -1940,7 +1951,7 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle) } if (QED_LL2_RX_REGISTERED(p_ll2_conn)) { - p_ll2_conn->rx_queue.b_cb_registred = false; + p_ll2_conn->rx_queue.b_cb_registered = false; smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */ rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn); if (rc) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index f65817012e97..1a5c1ae01474 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -79,7 +79,7 @@ struct qed_ll2_rx_queue { struct qed_chain rxq_chain; struct qed_chain rcq_chain; u8 rx_sb_index; - bool b_cb_registred; + bool b_cb_registered; __le16 *p_fw_cons; struct list_head active_descq; struct list_head free_descq; @@ -93,7 +93,7 @@ struct qed_ll2_tx_queue { spinlock_t lock; struct qed_chain txq_chain; u8 tx_sb_index; - bool b_cb_registred; + bool b_cb_registered; __le16 *p_fw_cons; struct list_head active_descq; struct list_head free_descq; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 2094d86a7a08..75d217aaf8ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1337,6 +1337,9 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params) if (params->adv_speeds & QED_LM_10000baseKR_Full_BIT) link_params->speed.advertised_speeds |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G; + if (params->adv_speeds & QED_LM_20000baseKR2_Full_BIT) + link_params->speed.advertised_speeds |= + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G; if (params->adv_speeds & QED_LM_25000baseKR_Full_BIT) link_params->speed.advertised_speeds |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G; @@ -1503,6 +1506,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn, NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) if_link->advertised_caps |= QED_LM_10000baseKR_Full_BIT; if (params.speed.advertised_speeds & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + if_link->advertised_caps |= QED_LM_20000baseKR2_Full_BIT; + if (params.speed.advertised_speeds & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) if_link->advertised_caps |= QED_LM_25000baseKR_Full_BIT; if (params.speed.advertised_speeds & @@ -1523,6 +1529,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn, NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) if_link->supported_caps |= QED_LM_10000baseKR_Full_BIT; if (link_caps.speed_capabilities & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + if_link->supported_caps |= QED_LM_20000baseKR2_Full_BIT; + if (link_caps.speed_capabilities & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) if_link->supported_caps |= QED_LM_25000baseKR_Full_BIT; if (link_caps.speed_capabilities & @@ -1559,6 +1568,8 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->lp_caps |= QED_LM_1000baseT_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_10G) if_link->lp_caps |= QED_LM_10000baseKR_Full_BIT; + if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_20G) + if_link->lp_caps |= QED_LM_20000baseKR2_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_25G) if_link->lp_caps |= QED_LM_25000baseKR_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_40G) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 63931dfc77cf..ffac4ac87394 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -351,11 +351,9 @@ void qed_ooo_delete_isles(struct qed_hwfn *p_hwfn, struct qed_ooo_info *p_ooo_info, u32 cid, u8 drop_isle, u8 drop_size) { - struct qed_ooo_archipelago *p_archipelago = NULL; struct qed_ooo_isle *p_isle = NULL; u8 isle_idx; - p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid); for (isle_idx = 0; isle_idx < drop_size; isle_idx++) { p_isle = qed_ooo_seek_isle(p_hwfn, p_ooo_info, cid, drop_isle); if (!p_isle) { @@ -460,7 +458,6 @@ void qed_ooo_add_new_buffer(struct qed_hwfn *p_hwfn, void qed_ooo_join_isles(struct qed_hwfn *p_hwfn, struct qed_ooo_info *p_ooo_info, u32 cid, u8 left_isle) { - struct qed_ooo_archipelago *p_archipelago = NULL; struct qed_ooo_isle *p_right_isle = NULL; struct qed_ooo_isle *p_left_isle = NULL; @@ -473,7 +470,6 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn, return; } - p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid); list_del(&p_right_isle->list_entry); p_ooo_info->cur_isles_number--; if (left_isle) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index be941cfaa2d4..c71391b9c757 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -228,7 +228,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, num_cons, "Toggle"); if (rc) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, - "Failed to allocate toogle bits, rc = %d\n", rc); + "Failed to allocate toggle bits, rc = %d\n", rc); goto free_cq_map; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 7d7a64c55ff1..f9167d1354bb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -140,23 +140,16 @@ static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid, static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) { - enum roce_flavor flavor; - switch (roce_mode) { case ROCE_V1: - flavor = PLAIN_ROCE; - break; + return PLAIN_ROCE; case ROCE_V2_IPV4: - flavor = RROCE_IPV4; - break; + return RROCE_IPV4; case ROCE_V2_IPV6: - flavor = ROCE_V2_IPV6; - break; + return RROCE_IPV6; default: - flavor = MAX_ROCE_MODE; - break; + return MAX_ROCE_FLAVOR; } - return flavor; } static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 8de644b4721e..77b6248ad3b9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -154,7 +154,7 @@ qed_set_pf_update_tunn_mode(struct qed_tunnel_info *p_tun, static void qed_set_tunn_cls_info(struct qed_tunnel_info *p_tun, struct qed_tunnel_info *p_src) { - enum tunnel_clss type; + int type; p_tun->b_update_rx_cls = p_src->b_update_rx_cls; p_tun->b_update_tx_cls = p_src->b_update_tx_cls; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 3d4269659820..be118d057b92 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -413,7 +413,6 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) } if (!p_iov->b_pre_fp_hsi && - ETH_HSI_VER_MINOR && (resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) { DP_INFO(p_hwfn, "PF is using older fastpath HSI; %02x.%02x is configured\n", @@ -572,7 +571,7 @@ free_p_iov: static void __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, u8 *p_cls) + enum qed_tunn_mode mask, u8 *p_cls) { if (p_src->b_update_mode) { p_req->tun_mode_update_mask |= BIT(mask); @@ -587,7 +586,7 @@ __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, static void qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, + enum qed_tunn_mode mask, u8 *p_cls, struct qed_tunn_update_udp_port *p_port, u8 *p_update_port, u16 *p_udp_port) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 19652cd27ca7..7ff50b4488f6 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -420,6 +420,7 @@ static const struct qede_link_mode_mapping qed_lm_map[] = { {QED_LM_1000baseT_Half_BIT, ETHTOOL_LINK_MODE_1000baseT_Half_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, {QED_LM_10000baseKR_Full_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT}, + {QED_LM_20000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT}, {QED_LM_25000baseKR_Full_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT}, {QED_LM_40000baseLR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT}, {QED_LM_50000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT}, @@ -535,6 +536,14 @@ static int qede_set_link_ksettings(struct net_device *dev, } params.adv_speeds = QED_LM_10000baseKR_Full_BIT; break; + case SPEED_20000: + if (!(current_link.supported_caps & + QED_LM_20000baseKR2_Full_BIT)) { + DP_INFO(edev, "20G speed not supported\n"); + return -EINVAL; + } + params.adv_speeds = QED_LM_20000baseKR2_Full_BIT; + break; case SPEED_25000: if (!(current_link.supported_caps & QED_LM_25000baseKR_Full_BIT)) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 81312924df14..0c443ea98479 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1800,7 +1800,8 @@ struct qlcnic_hardware_ops { int (*config_loopback) (struct qlcnic_adapter *, u8); int (*clear_loopback) (struct qlcnic_adapter *, u8); int (*config_promisc_mode) (struct qlcnic_adapter *, u32); - void (*change_l2_filter) (struct qlcnic_adapter *, u64 *, u16); + void (*change_l2_filter)(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *tx_ring); int (*get_board_info) (struct qlcnic_adapter *); void (*set_mac_filter_count) (struct qlcnic_adapter *); void (*free_mac_list) (struct qlcnic_adapter *); @@ -2064,9 +2065,10 @@ static inline int qlcnic_nic_set_promisc(struct qlcnic_adapter *adapter, } static inline void qlcnic_change_filter(struct qlcnic_adapter *adapter, - u64 *addr, u16 id) + u64 *addr, u16 vlan, + struct qlcnic_host_tx_ring *tx_ring) { - adapter->ahw->hw_ops->change_l2_filter(adapter, addr, id); + adapter->ahw->hw_ops->change_l2_filter(adapter, addr, vlan, tx_ring); } static inline int qlcnic_get_board_info(struct qlcnic_adapter *adapter) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 569d54ededec..a79d84f99102 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -2135,7 +2135,8 @@ out: } void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, - u16 vlan_id) + u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring) { u8 mac[ETH_ALEN]; memcpy(&mac, addr, ETH_ALEN); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index b75a81246856..73fe2f64491d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -550,7 +550,8 @@ int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *, ulong, u32); int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *, u32); int qlcnic_83xx_config_hw_lro(struct qlcnic_adapter *, int); int qlcnic_83xx_config_rss(struct qlcnic_adapter *, int); -void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *, u64 *, u16); +void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *ring); int qlcnic_83xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info *); int qlcnic_83xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *); void qlcnic_83xx_initialize_nic(struct qlcnic_adapter *, int); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 4bb33af8e2b3..56a3bd9e37dc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -173,7 +173,8 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, struct net_device *netdev); void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *); void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, - u64 *uaddr, u16 vlan_id); + u64 *uaddr, u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring); int qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *, struct ethtool_coalesce *); int qlcnic_82xx_set_rx_coalesce(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 84dd83031a1b..9647578cbe6a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -268,13 +268,12 @@ static void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, } void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, - u16 vlan_id) + u16 vlan_id, struct qlcnic_host_tx_ring *tx_ring) { struct cmd_desc_type0 *hwdesc; struct qlcnic_nic_req *req; struct qlcnic_mac_req *mac_req; struct qlcnic_vlan_req *vlan_req; - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; u32 producer; u64 word; @@ -301,7 +300,8 @@ void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, static void qlcnic_send_filter(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, - struct sk_buff *skb) + struct sk_buff *skb, + struct qlcnic_host_tx_ring *tx_ring) { struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data); struct ethhdr *phdr = (struct ethhdr *)(skb->data); @@ -335,7 +335,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, tmp_fil->vlan_id == vlan_id) { if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime)) qlcnic_change_filter(adapter, &src_addr, - vlan_id); + vlan_id, tx_ring); tmp_fil->ftime = jiffies; return; } @@ -350,7 +350,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, if (!fil) return; - qlcnic_change_filter(adapter, &src_addr, vlan_id); + qlcnic_change_filter(adapter, &src_addr, vlan_id, tx_ring); fil->ftime = jiffies; fil->vlan_id = vlan_id; memcpy(fil->faddr, &src_addr, ETH_ALEN); @@ -766,7 +766,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) } if (adapter->drv_mac_learn) - qlcnic_send_filter(adapter, first_desc, skb); + qlcnic_send_filter(adapter, first_desc, skb, tx_ring); tx_ring->tx_stats.tx_bytes += skb->len; tx_ring->tx_stats.xmit_called++; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 2d38d1ac2aae..dbd48012224f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -59,9 +59,6 @@ static int qlcnic_close(struct net_device *netdev); static void qlcnic_tx_timeout(struct net_device *netdev); static void qlcnic_attach_work(struct work_struct *work); static void qlcnic_fwinit_work(struct work_struct *work); -#ifdef CONFIG_NET_POLL_CONTROLLER -static void qlcnic_poll_controller(struct net_device *netdev); -#endif static void qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding); static int qlcnic_can_start_firmware(struct qlcnic_adapter *adapter); @@ -545,9 +542,6 @@ static const struct net_device_ops qlcnic_netdev_ops = { .ndo_udp_tunnel_add = qlcnic_add_vxlan_port, .ndo_udp_tunnel_del = qlcnic_del_vxlan_port, .ndo_features_check = qlcnic_features_check, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = qlcnic_poll_controller, -#endif #ifdef CONFIG_QLCNIC_SRIOV .ndo_set_vf_mac = qlcnic_sriov_set_vf_mac, .ndo_set_vf_rate = qlcnic_sriov_set_vf_tx_rate, @@ -3200,45 +3194,6 @@ static irqreturn_t qlcnic_msix_tx_intr(int irq, void *data) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void qlcnic_poll_controller(struct net_device *netdev) -{ - struct qlcnic_adapter *adapter = netdev_priv(netdev); - struct qlcnic_host_sds_ring *sds_ring; - struct qlcnic_recv_context *recv_ctx; - struct qlcnic_host_tx_ring *tx_ring; - int ring; - - if (!test_bit(__QLCNIC_DEV_UP, &adapter->state)) - return; - - recv_ctx = adapter->recv_ctx; - - for (ring = 0; ring < adapter->drv_sds_rings; ring++) { - sds_ring = &recv_ctx->sds_rings[ring]; - qlcnic_disable_sds_intr(adapter, sds_ring); - napi_schedule(&sds_ring->napi); - } - - if (adapter->flags & QLCNIC_MSIX_ENABLED) { - /* Only Multi-Tx queue capable devices need to - * schedule NAPI for TX rings - */ - if ((qlcnic_83xx_check(adapter) && - (adapter->flags & QLCNIC_TX_INTR_SHARED)) || - (qlcnic_82xx_check(adapter) && - !qlcnic_check_multi_tx(adapter))) - return; - - for (ring = 0; ring < adapter->drv_tx_rings; ring++) { - tx_ring = &adapter->tx_ring[ring]; - qlcnic_disable_tx_intr(adapter, tx_ring); - napi_schedule(&tx_ring->napi); - } - } -} -#endif - static void qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding) { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 7fd86d40a337..11167abe5934 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -113,7 +113,7 @@ rmnet_map_ingress_handler(struct sk_buff *skb, struct sk_buff *skbn; if (skb->dev->type == ARPHRD_ETHER) { - if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_KERNEL)) { + if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_ATOMIC)) { kfree_skb(skb); return; } @@ -147,7 +147,7 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, } if (skb_headroom(skb) < required_headroom) { - if (pskb_expand_head(skb, required_headroom, 0, GFP_KERNEL)) + if (pskb_expand_head(skb, required_headroom, 0, GFP_ATOMIC)) return -ENOMEM; } @@ -189,6 +189,9 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) if (!skb) goto done; + if (skb->pkt_type == PACKET_LOOPBACK) + return RX_HANDLER_PASS; + dev = skb->dev; port = rmnet_get_port(dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index ed8ffd498c88..7d3f671e1bb3 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4059,13 +4059,12 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) genphy_soft_reset(dev->phydev); - /* It was reported that chip version 33 ends up with 10MBit/Half on a + /* It was reported that several chips end up with 10MBit/Half on a * 1GBit link after resuming from S3. For whatever reason the PHY on - * this chip doesn't properly start a renegotiation when soft-reset. + * these chips doesn't properly start a renegotiation when soft-reset. * Explicitly requesting a renegotiation fixes this. */ - if (tp->mac_version == RTL_GIGA_MAC_VER_33 && - dev->phydev->autoneg == AUTONEG_ENABLE) + if (dev->phydev->autoneg == AUTONEG_ENABLE) phy_restart_aneg(dev->phydev); } @@ -4523,9 +4522,14 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) static void rtl_set_tx_config_registers(struct rtl8169_private *tp) { - /* Set DMA burst size and Interframe Gap Time */ - RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) | - (InterFrameGap << TxInterFrameGapShift)); + u32 val = TX_DMA_BURST << TxDMAShift | + InterFrameGap << TxInterFrameGapShift; + + if (tp->mac_version >= RTL_GIGA_MAC_VER_34 && + tp->mac_version != RTL_GIGA_MAC_VER_39) + val |= TXCFG_AUTO_FIFO; + + RTL_W32(tp, TxConfig, val); } static void rtl_set_rx_max_size(struct rtl8169_private *tp) @@ -5020,7 +5024,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_disable_clock_request(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); /* Adjust EEE LED frequency */ @@ -5054,7 +5057,6 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) rtl_disable_clock_request(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); @@ -5099,8 +5101,6 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static void rtl_hw_start_8168g(struct rtl8169_private *tp) { - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); @@ -5198,8 +5198,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1)); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); @@ -5282,8 +5280,6 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) { rtl8168ep_stop_cmac(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x2f, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC); @@ -5605,7 +5601,6 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402)); @@ -6856,8 +6851,10 @@ static int rtl8169_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct net_device *dev = pci_get_drvdata(pdev); + struct rtl8169_private *tp = netdev_priv(dev); rtl8169_net_suspend(dev); + clk_disable_unprepare(tp->clk); return 0; } @@ -6885,6 +6882,9 @@ static int rtl8169_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct net_device *dev = pci_get_drvdata(pdev); + struct rtl8169_private *tp = netdev_priv(dev); + + clk_prepare_enable(tp->clk); if (netif_running(dev)) __rtl8169_resume(dev); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 330233286e78..3d0dd39c289e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2208,29 +2208,6 @@ static void efx_fini_napi(struct efx_nic *efx) /************************************************************************** * - * Kernel netpoll interface - * - *************************************************************************/ - -#ifdef CONFIG_NET_POLL_CONTROLLER - -/* Although in the common case interrupts will be disabled, this is not - * guaranteed. However, all our work happens inside the NAPI callback, - * so no locking is required. - */ -static void efx_netpoll(struct net_device *net_dev) -{ - struct efx_nic *efx = netdev_priv(net_dev); - struct efx_channel *channel; - - efx_for_each_channel(channel, efx) - efx_schedule_channel(channel); -} - -#endif - -/************************************************************************** - * * Kernel net device interface * *************************************************************************/ @@ -2509,9 +2486,6 @@ static const struct net_device_ops efx_netdev_ops = { #endif .ndo_get_phys_port_id = efx_get_phys_port_id, .ndo_get_phys_port_name = efx_get_phys_port_name, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = efx_netpoll, -#endif .ndo_setup_tc = efx_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = efx_filter_rfs, diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index dd5530a4f8c8..03e2455c502e 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2054,29 +2054,6 @@ static void ef4_fini_napi(struct ef4_nic *efx) /************************************************************************** * - * Kernel netpoll interface - * - *************************************************************************/ - -#ifdef CONFIG_NET_POLL_CONTROLLER - -/* Although in the common case interrupts will be disabled, this is not - * guaranteed. However, all our work happens inside the NAPI callback, - * so no locking is required. - */ -static void ef4_netpoll(struct net_device *net_dev) -{ - struct ef4_nic *efx = netdev_priv(net_dev); - struct ef4_channel *channel; - - ef4_for_each_channel(channel, efx) - ef4_schedule_channel(channel); -} - -#endif - -/************************************************************************** - * * Kernel net device interface * *************************************************************************/ @@ -2250,9 +2227,6 @@ static const struct net_device_ops ef4_netdev_ops = { .ndo_set_mac_address = ef4_set_mac_address, .ndo_set_rx_mode = ef4_set_rx_mode, .ndo_set_features = ef4_set_features, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ef4_netpoll, -#endif .ndo_setup_tc = ef4_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = ef4_filter_rfs, diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 2a156dcd4534..6732f5cbde08 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1116,11 +1116,8 @@ static void ave_phy_adjust_link(struct net_device *ndev) rmt_adv |= LPA_PAUSE_CAP; if (phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - if (phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising); cap = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (cap & FLOW_CTRL_TX) txcr |= AVE_TXCR_FLOCTR; |