diff options
Diffstat (limited to 'drivers/net/ethernet/cavium/thunder')
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nic.h | 83 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nic_main.c | 74 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nic_reg.h | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c | 222 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nicvf_main.c | 221 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 151 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nicvf_queues.h | 51 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/q_struct.h | 8 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 78 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/thunder_bgx.h | 14 |
10 files changed, 607 insertions, 296 deletions
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 30426109711c..e739c7153562 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -47,7 +47,7 @@ /* Min/Max packet size */ #define NIC_HW_MIN_FRS 64 -#define NIC_HW_MAX_FRS 9200 /* 9216 max packet including FCS */ +#define NIC_HW_MAX_FRS 9190 /* Excluding L2 header and FCS */ /* Max pkinds */ #define NIC_MAX_PKIND 16 @@ -149,6 +149,12 @@ struct nicvf_rss_info { u64 key[RSS_HASH_KEY_SIZE]; } ____cacheline_aligned_in_smp; +struct nicvf_pfc { + u8 autoneg; + u8 fc_rx; + u8 fc_tx; +}; + enum rx_stats_reg_offset { RX_OCTS = 0x0, RX_UCAST = 0x1, @@ -178,11 +184,11 @@ enum tx_stats_reg_offset { struct nicvf_hw_stats { u64 rx_bytes; + u64 rx_frames; u64 rx_ucast_frames; u64 rx_bcast_frames; u64 rx_mcast_frames; - u64 rx_fcs_errors; - u64 rx_l2_errors; + u64 rx_drops; u64 rx_drop_red; u64 rx_drop_red_bytes; u64 rx_drop_overrun; @@ -191,6 +197,19 @@ struct nicvf_hw_stats { u64 rx_drop_mcast; u64 rx_drop_l3_bcast; u64 rx_drop_l3_mcast; + u64 rx_fcs_errors; + u64 rx_l2_errors; + + u64 tx_bytes; + u64 tx_frames; + u64 tx_ucast_frames; + u64 tx_bcast_frames; + u64 tx_mcast_frames; + u64 tx_drops; +}; + +struct nicvf_drv_stats { + /* CQE Rx errs */ u64 rx_bgx_truncated_pkts; u64 rx_jabber_errs; u64 rx_fcs_errs; @@ -216,34 +235,30 @@ struct nicvf_hw_stats { u64 rx_l4_pclp; u64 rx_truncated_pkts; - u64 tx_bytes_ok; - u64 tx_ucast_frames_ok; - u64 tx_bcast_frames_ok; - u64 tx_mcast_frames_ok; - u64 tx_drops; -}; - -struct nicvf_drv_stats { - /* Rx */ - u64 rx_frames_ok; - u64 rx_frames_64; - u64 rx_frames_127; - u64 rx_frames_255; - u64 rx_frames_511; - u64 rx_frames_1023; - u64 rx_frames_1518; - u64 rx_frames_jumbo; - u64 rx_drops; - + /* CQE Tx errs */ + u64 tx_desc_fault; + u64 tx_hdr_cons_err; + u64 tx_subdesc_err; + u64 tx_max_size_exceeded; + u64 tx_imm_size_oflow; + u64 tx_data_seq_err; + u64 tx_mem_seq_err; + u64 tx_lock_viol; + u64 tx_data_fault; + u64 tx_tstmp_conflict; + u64 tx_tstmp_timeout; + u64 tx_mem_fault; + u64 tx_csum_overlap; + u64 tx_csum_overflow; + + /* driver debug stats */ u64 rcv_buffer_alloc_failures; - - /* Tx */ - u64 tx_frames_ok; - u64 tx_drops; u64 tx_tso; u64 tx_timeout; u64 txq_stop; u64 txq_wake; + + struct u64_stats_sync syncp; }; struct nicvf { @@ -282,13 +297,14 @@ struct nicvf { u8 node; u8 cpi_alg; - u16 mtu; bool link_up; + u8 mac_type; u8 duplex; u32 speed; bool tns_mode; bool loopback_supported; struct nicvf_rss_info rss_info; + struct nicvf_pfc pfc; struct tasklet_struct qs_err_task; struct work_struct reset_task; @@ -298,7 +314,7 @@ struct nicvf { /* Stats */ struct nicvf_hw_stats hw_stats; - struct nicvf_drv_stats drv_stats; + struct nicvf_drv_stats __percpu *drv_stats; struct bgx_stats bgx_stats; /* MSI-X */ @@ -349,6 +365,7 @@ struct nicvf { #define NIC_MBOX_MSG_SNICVF_PTR 0x15 /* Send sqet nicvf ptr to PVF */ #define NIC_MBOX_MSG_LOOPBACK 0x16 /* Set interface in loopback */ #define NIC_MBOX_MSG_RESET_STAT_COUNTER 0x17 /* Reset statistics counters */ +#define NIC_MBOX_MSG_PFC 0x18 /* Pause frame control */ #define NIC_MBOX_MSG_CFG_DONE 0xF0 /* VF configuration done */ #define NIC_MBOX_MSG_SHUTDOWN 0xF1 /* VF is being shutdown */ @@ -438,6 +455,7 @@ struct bgx_stats_msg { /* Physical interface link status */ struct bgx_link_status { u8 msg; + u8 mac_type; u8 link_up; u8 duplex; u32 speed; @@ -490,6 +508,14 @@ struct reset_stat_cfg { u16 sq_stat_mask; }; +struct pfc { + u8 msg; + u8 get; /* Get or set PFC settings */ + u8 autoneg; + u8 fc_rx; + u8 fc_tx; +}; + /* 128 bit shared memory between PF and each VF */ union nic_mbx { struct { u8 msg; } msg; @@ -508,6 +534,7 @@ union nic_mbx { struct nicvf_ptr nicvf; struct set_loopback lbk; struct reset_stat_cfg reset_stat; + struct pfc pfc; }; #define NIC_NODE_ID_MASK 0x03 diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 2bbf4cbf08b2..767234e2e8f9 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/etherdevice.h> #include <linux/of.h> +#include <linux/if_vlan.h> #include "nic_reg.h" #include "nic.h" @@ -260,18 +261,31 @@ static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx) /* Update hardware min/max frame size */ static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf) { - if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) { - dev_err(&nic->pdev->dev, - "Invalid MTU setting from VF%d rejected, should be between %d and %d\n", - vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS); + int bgx, lmac, lmac_cnt; + u64 lmac_credits; + + if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) return 1; - } - new_frs += ETH_HLEN; - if (new_frs <= nic->pkind.maxlen) - return 0; - nic->pkind.maxlen = new_frs; - nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind); + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac += bgx * MAX_LMAC_PER_BGX; + + new_frs += VLAN_ETH_HLEN + ETH_FCS_LEN + 4; + + /* Update corresponding LMAC credits */ + lmac_cnt = bgx_get_lmac_count(nic->node, bgx); + lmac_credits = nic_reg_read(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8)); + lmac_credits &= ~(0xFFFFFULL << 12); + lmac_credits |= (((((48 * 1024) / lmac_cnt) - new_frs) / 16) << 12); + nic_reg_write(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), lmac_credits); + + /* Enforce MTU in HW + * This config is supported only from 88xx pass 2.0 onwards. + */ + if (!pass1_silicon(nic->pdev)) + nic_reg_write(nic, + NIC_PF_LMAC_0_7_CFG2 + (lmac * 8), new_frs); return 0; } @@ -464,7 +478,7 @@ static int nic_init_hw(struct nicpf *nic) /* PKIND configuration */ nic->pkind.minlen = 0; - nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN; + nic->pkind.maxlen = NIC_HW_MAX_FRS + VLAN_ETH_HLEN + ETH_FCS_LEN + 4; nic->pkind.lenerr_en = 1; nic->pkind.rx_hdr = 0; nic->pkind.hdr_sl = 0; @@ -795,6 +809,15 @@ static int nic_config_loopback(struct nicpf *nic, struct set_loopback *lbk) bgx_lmac_internal_loopback(nic->node, bgx_idx, lmac_idx, lbk->enable); + /* Enable moving average calculation. + * Keep the LVL/AVG delay to HW enforced minimum so that, not too many + * packets sneek in between average calculations. + */ + nic_reg_write(nic, NIC_PF_CQ_AVG_CFG, + (BIT_ULL(20) | 0x2ull << 14 | 0x1)); + nic_reg_write(nic, NIC_PF_RRM_AVG_CFG, + (BIT_ULL(20) | 0x3ull << 14 | 0x1)); + return 0; } @@ -837,6 +860,7 @@ static int nic_reset_stat_counters(struct nicpf *nic, nic_reg_write(nic, reg_addr, 0); } } + return 0; } @@ -874,6 +898,30 @@ static void nic_enable_vf(struct nicpf *nic, int vf, bool enable) bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, enable); } +static void nic_pause_frame(struct nicpf *nic, int vf, struct pfc *cfg) +{ + int bgx, lmac; + struct pfc pfc; + union nic_mbx mbx = {}; + + if (vf >= nic->num_vf_en) + return; + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + if (cfg->get) { + bgx_lmac_get_pfc(nic->node, bgx, lmac, &pfc); + mbx.pfc.msg = NIC_MBOX_MSG_PFC; + mbx.pfc.autoneg = pfc.autoneg; + mbx.pfc.fc_rx = pfc.fc_rx; + mbx.pfc.fc_tx = pfc.fc_tx; + nic_send_msg_to_vf(nic, vf, &mbx); + } else { + bgx_lmac_set_pfc(nic->node, bgx, lmac, cfg); + nic_mbx_send_ack(nic, vf); + } +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -1013,6 +1061,9 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) case NIC_MBOX_MSG_RESET_STAT_COUNTER: ret = nic_reset_stat_counters(nic, vf, &mbx.reset_stat); break; + case NIC_MBOX_MSG_PFC: + nic_pause_frame(nic, vf, &mbx.pfc); + goto unlock; default: dev_err(&nic->pdev->dev, "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); @@ -1243,6 +1294,7 @@ static void nic_poll_for_link(struct work_struct *work) mbx.link_status.link_up = link.link_up; mbx.link_status.duplex = link.duplex; mbx.link_status.speed = link.speed; + mbx.link_status.mac_type = link.mac_type; nic_send_msg_to_vf(nic, vf, &mbx); } } diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index edf779f5a227..80d46337cf29 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -106,6 +106,7 @@ #define NIC_PF_MPI_0_2047_CFG (0x210000) #define NIC_PF_RSSI_0_4097_RQ (0x220000) #define NIC_PF_LMAC_0_7_CFG (0x240000) +#define NIC_PF_LMAC_0_7_CFG2 (0x240100) #define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) #define NIC_PF_LMAC_0_7_CREDIT (0x244000) #define NIC_PF_CHAN_0_255_TX_CFG (0x400000) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index ad4fddb55421..2e74bbaa38e1 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -36,11 +36,11 @@ struct nicvf_stat { static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_bytes), + NICVF_HW_STAT(rx_frames), NICVF_HW_STAT(rx_ucast_frames), NICVF_HW_STAT(rx_bcast_frames), NICVF_HW_STAT(rx_mcast_frames), - NICVF_HW_STAT(rx_fcs_errors), - NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(rx_drops), NICVF_HW_STAT(rx_drop_red), NICVF_HW_STAT(rx_drop_red_bytes), NICVF_HW_STAT(rx_drop_overrun), @@ -49,50 +49,59 @@ static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_drop_mcast), NICVF_HW_STAT(rx_drop_l3_bcast), NICVF_HW_STAT(rx_drop_l3_mcast), - NICVF_HW_STAT(rx_bgx_truncated_pkts), - NICVF_HW_STAT(rx_jabber_errs), - NICVF_HW_STAT(rx_fcs_errs), - NICVF_HW_STAT(rx_bgx_errs), - NICVF_HW_STAT(rx_prel2_errs), - NICVF_HW_STAT(rx_l2_hdr_malformed), - NICVF_HW_STAT(rx_oversize), - NICVF_HW_STAT(rx_undersize), - NICVF_HW_STAT(rx_l2_len_mismatch), - NICVF_HW_STAT(rx_l2_pclp), - NICVF_HW_STAT(rx_ip_ver_errs), - NICVF_HW_STAT(rx_ip_csum_errs), - NICVF_HW_STAT(rx_ip_hdr_malformed), - NICVF_HW_STAT(rx_ip_payload_malformed), - NICVF_HW_STAT(rx_ip_ttl_errs), - NICVF_HW_STAT(rx_l3_pclp), - NICVF_HW_STAT(rx_l4_malformed), - NICVF_HW_STAT(rx_l4_csum_errs), - NICVF_HW_STAT(rx_udp_len_errs), - NICVF_HW_STAT(rx_l4_port_errs), - NICVF_HW_STAT(rx_tcp_flag_errs), - NICVF_HW_STAT(rx_tcp_offset_errs), - NICVF_HW_STAT(rx_l4_pclp), - NICVF_HW_STAT(rx_truncated_pkts), - NICVF_HW_STAT(tx_bytes_ok), - NICVF_HW_STAT(tx_ucast_frames_ok), - NICVF_HW_STAT(tx_bcast_frames_ok), - NICVF_HW_STAT(tx_mcast_frames_ok), + NICVF_HW_STAT(rx_fcs_errors), + NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(tx_bytes), + NICVF_HW_STAT(tx_frames), + NICVF_HW_STAT(tx_ucast_frames), + NICVF_HW_STAT(tx_bcast_frames), + NICVF_HW_STAT(tx_mcast_frames), + NICVF_HW_STAT(tx_drops), }; static const struct nicvf_stat nicvf_drv_stats[] = { - NICVF_DRV_STAT(rx_frames_ok), - NICVF_DRV_STAT(rx_frames_64), - NICVF_DRV_STAT(rx_frames_127), - NICVF_DRV_STAT(rx_frames_255), - NICVF_DRV_STAT(rx_frames_511), - NICVF_DRV_STAT(rx_frames_1023), - NICVF_DRV_STAT(rx_frames_1518), - NICVF_DRV_STAT(rx_frames_jumbo), - NICVF_DRV_STAT(rx_drops), + NICVF_DRV_STAT(rx_bgx_truncated_pkts), + NICVF_DRV_STAT(rx_jabber_errs), + NICVF_DRV_STAT(rx_fcs_errs), + NICVF_DRV_STAT(rx_bgx_errs), + NICVF_DRV_STAT(rx_prel2_errs), + NICVF_DRV_STAT(rx_l2_hdr_malformed), + NICVF_DRV_STAT(rx_oversize), + NICVF_DRV_STAT(rx_undersize), + NICVF_DRV_STAT(rx_l2_len_mismatch), + NICVF_DRV_STAT(rx_l2_pclp), + NICVF_DRV_STAT(rx_ip_ver_errs), + NICVF_DRV_STAT(rx_ip_csum_errs), + NICVF_DRV_STAT(rx_ip_hdr_malformed), + NICVF_DRV_STAT(rx_ip_payload_malformed), + NICVF_DRV_STAT(rx_ip_ttl_errs), + NICVF_DRV_STAT(rx_l3_pclp), + NICVF_DRV_STAT(rx_l4_malformed), + NICVF_DRV_STAT(rx_l4_csum_errs), + NICVF_DRV_STAT(rx_udp_len_errs), + NICVF_DRV_STAT(rx_l4_port_errs), + NICVF_DRV_STAT(rx_tcp_flag_errs), + NICVF_DRV_STAT(rx_tcp_offset_errs), + NICVF_DRV_STAT(rx_l4_pclp), + NICVF_DRV_STAT(rx_truncated_pkts), + + NICVF_DRV_STAT(tx_desc_fault), + NICVF_DRV_STAT(tx_hdr_cons_err), + NICVF_DRV_STAT(tx_subdesc_err), + NICVF_DRV_STAT(tx_max_size_exceeded), + NICVF_DRV_STAT(tx_imm_size_oflow), + NICVF_DRV_STAT(tx_data_seq_err), + NICVF_DRV_STAT(tx_mem_seq_err), + NICVF_DRV_STAT(tx_lock_viol), + NICVF_DRV_STAT(tx_data_fault), + NICVF_DRV_STAT(tx_tstmp_conflict), + NICVF_DRV_STAT(tx_tstmp_timeout), + NICVF_DRV_STAT(tx_mem_fault), + NICVF_DRV_STAT(tx_csum_overlap), + NICVF_DRV_STAT(tx_csum_overflow), + NICVF_DRV_STAT(rcv_buffer_alloc_failures), - NICVF_DRV_STAT(tx_frames_ok), NICVF_DRV_STAT(tx_tso), - NICVF_DRV_STAT(tx_drops), NICVF_DRV_STAT(tx_timeout), NICVF_DRV_STAT(txq_stop), NICVF_DRV_STAT(txq_wake), @@ -107,29 +116,65 @@ static const unsigned int nicvf_n_hw_stats = ARRAY_SIZE(nicvf_hw_stats); static const unsigned int nicvf_n_drv_stats = ARRAY_SIZE(nicvf_drv_stats); static const unsigned int nicvf_n_queue_stats = ARRAY_SIZE(nicvf_queue_stats); -static int nicvf_get_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +static int nicvf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct nicvf *nic = netdev_priv(netdev); + u32 supported, advertising; - cmd->supported = 0; - cmd->transceiver = XCVR_EXTERNAL; + supported = 0; + advertising = 0; if (!nic->link_up) { - cmd->duplex = DUPLEX_UNKNOWN; - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; return 0; } - if (nic->speed <= 1000) { - cmd->port = PORT_MII; - cmd->autoneg = AUTONEG_ENABLE; - } else { - cmd->port = PORT_FIBRE; - cmd->autoneg = AUTONEG_DISABLE; + switch (nic->speed) { + case SPEED_1000: + cmd->base.port = PORT_MII | PORT_TP; + cmd->base.autoneg = AUTONEG_ENABLE; + supported |= SUPPORTED_MII | SUPPORTED_TP; + supported |= SUPPORTED_1000baseT_Full | + SUPPORTED_1000baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_10baseT_Half; + supported |= SUPPORTED_Autoneg; + advertising |= ADVERTISED_1000baseT_Full | + ADVERTISED_1000baseT_Half | + ADVERTISED_100baseT_Full | + ADVERTISED_100baseT_Half | + ADVERTISED_10baseT_Full | + ADVERTISED_10baseT_Half; + break; + case SPEED_10000: + if (nic->mac_type == BGX_MODE_RXAUI) { + cmd->base.port = PORT_TP; + supported |= SUPPORTED_TP; + } else { + cmd->base.port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + } + cmd->base.autoneg = AUTONEG_DISABLE; + supported |= SUPPORTED_10000baseT_Full; + break; + case SPEED_40000: + cmd->base.port = PORT_FIBRE; + cmd->base.autoneg = AUTONEG_DISABLE; + supported |= SUPPORTED_FIBRE; + supported |= SUPPORTED_40000baseCR4_Full; + break; } - cmd->duplex = nic->duplex; - ethtool_cmd_speed_set(cmd, nic->speed); + cmd->base.duplex = nic->duplex; + cmd->base.speed = nic->speed; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } @@ -278,8 +323,8 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct nicvf *nic = netdev_priv(netdev); - int stat; - int sqs; + int stat, tmp_stats; + int sqs, cpu; nicvf_update_stats(nic); @@ -289,9 +334,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, for (stat = 0; stat < nicvf_n_hw_stats; stat++) *(data++) = ((u64 *)&nic->hw_stats) [nicvf_hw_stats[stat].index]; - for (stat = 0; stat < nicvf_n_drv_stats; stat++) - *(data++) = ((u64 *)&nic->drv_stats) - [nicvf_drv_stats[stat].index]; + for (stat = 0; stat < nicvf_n_drv_stats; stat++) { + tmp_stats = 0; + for_each_possible_cpu(cpu) + tmp_stats += ((u64 *)per_cpu_ptr(nic->drv_stats, cpu)) + [nicvf_drv_stats[stat].index]; + *(data++) = tmp_stats; + } nicvf_get_qset_stats(nic, stats, &data); @@ -677,8 +726,56 @@ static int nicvf_set_channels(struct net_device *dev, return err; } +static void nicvf_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct nicvf *nic = netdev_priv(dev); + union nic_mbx mbx = {}; + + /* Supported only for 10G/40G interfaces */ + if ((nic->mac_type == BGX_MODE_SGMII) || + (nic->mac_type == BGX_MODE_QSGMII) || + (nic->mac_type == BGX_MODE_RGMII)) + return; + + mbx.pfc.msg = NIC_MBOX_MSG_PFC; + mbx.pfc.get = 1; + if (!nicvf_send_msg_to_pf(nic, &mbx)) { + pause->autoneg = nic->pfc.autoneg; + pause->rx_pause = nic->pfc.fc_rx; + pause->tx_pause = nic->pfc.fc_tx; + } +} + +static int nicvf_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct nicvf *nic = netdev_priv(dev); + union nic_mbx mbx = {}; + + /* Supported only for 10G/40G interfaces */ + if ((nic->mac_type == BGX_MODE_SGMII) || + (nic->mac_type == BGX_MODE_QSGMII) || + (nic->mac_type == BGX_MODE_RGMII)) + return -EOPNOTSUPP; + + if (pause->autoneg) + return -EOPNOTSUPP; + + mbx.pfc.msg = NIC_MBOX_MSG_PFC; + mbx.pfc.get = 0; + mbx.pfc.fc_rx = pause->rx_pause; + mbx.pfc.fc_tx = pause->tx_pause; + if (nicvf_send_msg_to_pf(nic, &mbx)) + return -EAGAIN; + + nic->pfc.fc_rx = pause->rx_pause; + nic->pfc.fc_tx = pause->tx_pause; + + return 0; +} + static const struct ethtool_ops nicvf_ethtool_ops = { - .get_settings = nicvf_get_settings, .get_link = nicvf_get_link, .get_drvinfo = nicvf_get_drvinfo, .get_msglevel = nicvf_get_msglevel, @@ -698,7 +795,10 @@ static const struct ethtool_ops nicvf_ethtool_ops = { .set_rxfh = nicvf_set_rxfh, .get_channels = nicvf_get_channels, .set_channels = nicvf_set_channels, + .get_pauseparam = nicvf_get_pauseparam, + .set_pauseparam = nicvf_set_pauseparam, .get_ts_info = ethtool_op_get_ts_info, + .get_link_ksettings = nicvf_get_link_ksettings, }; void nicvf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 45a13f718863..2006f58b14b1 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -69,25 +69,6 @@ static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) return qidx; } -static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic, - struct sk_buff *skb) -{ - if (skb->len <= 64) - nic->drv_stats.rx_frames_64++; - else if (skb->len <= 127) - nic->drv_stats.rx_frames_127++; - else if (skb->len <= 255) - nic->drv_stats.rx_frames_255++; - else if (skb->len <= 511) - nic->drv_stats.rx_frames_511++; - else if (skb->len <= 1023) - nic->drv_stats.rx_frames_1023++; - else if (skb->len <= 1518) - nic->drv_stats.rx_frames_1518++; - else - nic->drv_stats.rx_frames_jumbo++; -} - /* The Cavium ThunderX network controller can *only* be found in SoCs * containing the ThunderX ARM64 CPU implementation. All accesses to the device * registers on this platform are implicitly strongly ordered with respect @@ -240,6 +221,7 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) nic->link_up = mbx.link_status.link_up; nic->duplex = mbx.link_status.duplex; nic->speed = mbx.link_status.speed; + nic->mac_type = mbx.link_status.mac_type; if (nic->link_up) { netdev_info(nic->netdev, "%s: Link is Up %d Mbps %s\n", nic->netdev->name, nic->speed, @@ -274,6 +256,12 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) nic->pnicvf = (struct nicvf *)mbx.nicvf.nicvf; nic->pf_acked = true; break; + case NIC_MBOX_MSG_PFC: + nic->pfc.autoneg = mbx.pfc.autoneg; + nic->pfc.fc_rx = mbx.pfc.fc_rx; + nic->pfc.fc_tx = mbx.pfc.fc_tx; + nic->pf_acked = true; + break; default: netdev_err(nic->netdev, "Invalid message from PF, msg 0x%x\n", mbx.msg.msg); @@ -492,9 +480,6 @@ int nicvf_set_real_num_queues(struct net_device *netdev, static int nicvf_init_resources(struct nicvf *nic) { int err; - union nic_mbx mbx = {}; - - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; /* Enable Qset */ nicvf_qset_config(nic, true); @@ -507,14 +492,10 @@ static int nicvf_init_resources(struct nicvf *nic) return err; } - /* Send VF config done msg to PF */ - nicvf_write_to_mbx(nic, &mbx); - return 0; } static void nicvf_snd_pkt_handler(struct net_device *netdev, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx, int cqe_type, int budget, unsigned int *tx_pkts, unsigned int *tx_bytes) @@ -536,7 +517,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, __func__, cqe_tx->sq_qs, cqe_tx->sq_idx, cqe_tx->sqe_ptr, hdr->subdesc_cnt); - nicvf_check_cqe_tx_errs(nic, cq, cqe_tx); + nicvf_check_cqe_tx_errs(nic, cqe_tx); skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr]; if (skb) { /* Check for dummy descriptor used for HW TSO offload on 88xx */ @@ -630,8 +611,6 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, return; } - nicvf_set_rx_frame_cnt(nic, skb); - nicvf_set_rxhash(netdev, cqe_rx, skb); skb_record_rx_queue(skb, rq_idx); @@ -665,6 +644,7 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx, struct cmp_queue *cq = &qs->cq[cq_idx]; struct cqe_rx_t *cq_desc; struct netdev_queue *txq; + struct snd_queue *sq; unsigned int tx_pkts = 0, tx_bytes = 0; spin_lock_bh(&cq->lock); @@ -703,7 +683,7 @@ loop: work_done++; break; case CQE_TYPE_SEND: - nicvf_snd_pkt_handler(netdev, cq, + nicvf_snd_pkt_handler(netdev, (void *)cq_desc, CQE_TYPE_SEND, budget, &tx_pkts, &tx_bytes); tx_done++; @@ -730,17 +710,21 @@ loop: done: /* Wakeup TXQ if its stopped earlier due to SQ full */ - if (tx_done) { + sq = &nic->qs->sq[cq_idx]; + if (tx_done || + (atomic_read(&sq->free_cnt) >= MIN_SQ_DESC_PER_PKT_XMIT)) { netdev = nic->pnicvf->netdev; txq = netdev_get_tx_queue(netdev, nicvf_netdev_qidx(nic, cq_idx)); if (tx_pkts) netdev_tx_completed_queue(txq, tx_pkts, tx_bytes); - nic = nic->pnicvf; + /* To read updated queue and carrier status */ + smp_mb(); if (netif_tx_queue_stopped(txq) && netif_carrier_ok(netdev)) { - netif_tx_start_queue(txq); - nic->drv_stats.txq_wake++; + netif_tx_wake_queue(txq); + nic = nic->pnicvf; + this_cpu_inc(nic->drv_stats->txq_wake); if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit queue wakeup SQ%d\n", @@ -1075,6 +1059,9 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) struct nicvf *nic = netdev_priv(netdev); int qid = skb_get_queue_mapping(skb); struct netdev_queue *txq = netdev_get_tx_queue(netdev, qid); + struct nicvf *snic; + struct snd_queue *sq; + int tmp; /* Check for minimum packet length */ if (skb->len <= ETH_HLEN) { @@ -1082,13 +1069,39 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) { + snic = nic; + /* Get secondary Qset's SQ structure */ + if (qid >= MAX_SND_QUEUES_PER_QS) { + tmp = qid / MAX_SND_QUEUES_PER_QS; + snic = (struct nicvf *)nic->snicvf[tmp - 1]; + if (!snic) { + netdev_warn(nic->netdev, + "Secondary Qset#%d's ptr not initialized\n", + tmp - 1); + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + qid = qid % MAX_SND_QUEUES_PER_QS; + } + + sq = &snic->qs->sq[qid]; + if (!netif_tx_queue_stopped(txq) && + !nicvf_sq_append_skb(snic, sq, skb, qid)) { netif_tx_stop_queue(txq); - nic->drv_stats.txq_stop++; - if (netif_msg_tx_err(nic)) - netdev_warn(netdev, - "%s: Transmit ring full, stopping SQ%d\n", - netdev->name, qid); + + /* Barrier, so that stop_queue visible to other cpus */ + smp_mb(); + + /* Check again, incase another cpu freed descriptors */ + if (atomic_read(&sq->free_cnt) > MIN_SQ_DESC_PER_PKT_XMIT) { + netif_tx_wake_queue(txq); + } else { + this_cpu_inc(nic->drv_stats->txq_stop); + if (netif_msg_tx_err(nic)) + netdev_warn(netdev, + "%s: Transmit ring full, stopping SQ%d\n", + netdev->name, qid); + } return NETDEV_TX_BUSY; } @@ -1189,14 +1202,24 @@ int nicvf_stop(struct net_device *netdev) return 0; } +static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) +{ + union nic_mbx mbx = {}; + + mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; + mbx.frs.max_frs = mtu; + mbx.frs.vf_id = nic->vf_id; + + return nicvf_send_msg_to_pf(nic, &mbx); +} + int nicvf_open(struct net_device *netdev) { - int err, qidx; + int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - - nic->mtu = netdev->mtu; + union nic_mbx mbx = {}; netif_carrier_off(netdev); @@ -1248,9 +1271,17 @@ int nicvf_open(struct net_device *netdev) if (nic->sqs_mode) nicvf_get_primary_vf_struct(nic); - /* Configure receive side scaling */ - if (!nic->sqs_mode) + /* Configure receive side scaling and MTU */ + if (!nic->sqs_mode) { nicvf_rss_init(nic); + if (nicvf_update_hw_max_frs(nic, netdev->mtu)) + goto cleanup; + + /* Clear percpu stats */ + for_each_possible_cpu(cpu) + memset(per_cpu_ptr(nic->drv_stats, cpu), 0, + sizeof(struct nicvf_drv_stats)); + } err = nicvf_register_interrupts(nic); if (err) @@ -1276,8 +1307,9 @@ int nicvf_open(struct net_device *netdev) for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); - nic->drv_stats.txq_stop = 0; - nic->drv_stats.txq_wake = 0; + /* Send VF config done msg to PF */ + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + nicvf_write_to_mbx(nic, &mbx); return 0; cleanup: @@ -1297,31 +1329,20 @@ napi_del: return err; } -static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) -{ - union nic_mbx mbx = {}; - - mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; - mbx.frs.max_frs = mtu; - mbx.frs.vf_id = nic->vf_id; - - return nicvf_send_msg_to_pf(nic, &mbx); -} - static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) { struct nicvf *nic = netdev_priv(netdev); + int orig_mtu = netdev->mtu; - if (new_mtu > NIC_HW_MAX_FRS) - return -EINVAL; + netdev->mtu = new_mtu; - if (new_mtu < NIC_HW_MIN_FRS) - return -EINVAL; + if (!netif_running(netdev)) + return 0; - if (nicvf_update_hw_max_frs(nic, new_mtu)) + if (nicvf_update_hw_max_frs(nic, new_mtu)) { + netdev->mtu = orig_mtu; return -EINVAL; - netdev->mtu = new_mtu; - nic->mtu = new_mtu; + } return 0; } @@ -1379,9 +1400,10 @@ void nicvf_update_lmac_stats(struct nicvf *nic) void nicvf_update_stats(struct nicvf *nic) { - int qidx; + int qidx, cpu; + u64 tmp_stats = 0; struct nicvf_hw_stats *stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; + struct nicvf_drv_stats *drv_stats; struct queue_set *qs = nic->qs; #define GET_RX_STATS(reg) \ @@ -1404,21 +1426,33 @@ void nicvf_update_stats(struct nicvf *nic) stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST); stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST); - stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS); - stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST); - stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST); - stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST); + stats->tx_bytes = GET_TX_STATS(TX_OCTS); + stats->tx_ucast_frames = GET_TX_STATS(TX_UCAST); + stats->tx_bcast_frames = GET_TX_STATS(TX_BCAST); + stats->tx_mcast_frames = GET_TX_STATS(TX_MCAST); stats->tx_drops = GET_TX_STATS(TX_DROP); - drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok + - stats->tx_bcast_frames_ok + - stats->tx_mcast_frames_ok; - drv_stats->rx_frames_ok = stats->rx_ucast_frames + - stats->rx_bcast_frames + - stats->rx_mcast_frames; - drv_stats->rx_drops = stats->rx_drop_red + - stats->rx_drop_overrun; - drv_stats->tx_drops = stats->tx_drops; + /* On T88 pass 2.0, the dummy SQE added for TSO notification + * via CQE has 'dont_send' set. Hence HW drops the pkt pointed + * pointed by dummy SQE and results in tx_drops counter being + * incremented. Subtracting it from tx_tso counter will give + * exact tx_drops counter. + */ + if (nic->t88 && nic->hw_tso) { + for_each_possible_cpu(cpu) { + drv_stats = per_cpu_ptr(nic->drv_stats, cpu); + tmp_stats += drv_stats->tx_tso; + } + stats->tx_drops = tmp_stats - stats->tx_drops; + } + stats->tx_frames = stats->tx_ucast_frames + + stats->tx_bcast_frames + + stats->tx_mcast_frames; + stats->rx_frames = stats->rx_ucast_frames + + stats->rx_bcast_frames + + stats->rx_mcast_frames; + stats->rx_drops = stats->rx_drop_red + + stats->rx_drop_overrun; /* Update RQ and SQ stats */ for (qidx = 0; qidx < qs->rq_cnt; qidx++) @@ -1432,18 +1466,17 @@ static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev, { struct nicvf *nic = netdev_priv(netdev); struct nicvf_hw_stats *hw_stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; nicvf_update_stats(nic); stats->rx_bytes = hw_stats->rx_bytes; - stats->rx_packets = drv_stats->rx_frames_ok; - stats->rx_dropped = drv_stats->rx_drops; + stats->rx_packets = hw_stats->rx_frames; + stats->rx_dropped = hw_stats->rx_drops; stats->multicast = hw_stats->rx_mcast_frames; - stats->tx_bytes = hw_stats->tx_bytes_ok; - stats->tx_packets = drv_stats->tx_frames_ok; - stats->tx_dropped = drv_stats->tx_drops; + stats->tx_bytes = hw_stats->tx_bytes; + stats->tx_packets = hw_stats->tx_frames; + stats->tx_dropped = hw_stats->tx_drops; return stats; } @@ -1456,7 +1489,7 @@ static void nicvf_tx_timeout(struct net_device *dev) netdev_warn(dev, "%s: Transmit timed out, resetting\n", dev->name); - nic->drv_stats.tx_timeout++; + this_cpu_inc(nic->drv_stats->tx_timeout); schedule_work(&nic->reset_task); } @@ -1590,6 +1623,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free_netdev; } + nic->drv_stats = netdev_alloc_pcpu_stats(struct nicvf_drv_stats); + if (!nic->drv_stats) { + err = -ENOMEM; + goto err_free_netdev; + } + err = nicvf_set_qset_resources(nic); if (err) goto err_free_netdev; @@ -1630,6 +1669,10 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &nicvf_netdev_ops; netdev->watchdog_timeo = NICVF_TX_TIMEOUT; + /* MTU range: 64 - 9200 */ + netdev->min_mtu = NIC_HW_MIN_FRS; + netdev->max_mtu = NIC_HW_MAX_FRS; + INIT_WORK(&nic->reset_task, nicvf_reset_task); err = register_netdev(netdev); @@ -1648,6 +1691,8 @@ err_unregister_interrupts: nicvf_unregister_interrupts(nic); err_free_netdev: pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); err_release_regions: pci_release_regions(pdev); @@ -1675,6 +1720,8 @@ static void nicvf_remove(struct pci_dev *pdev) unregister_netdev(pnetdev); nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index a4fc50155881..d2ac133e36f1 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -104,7 +104,8 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, order); if (!nic->rb_page) { - nic->drv_stats.rcv_buffer_alloc_failures++; + this_cpu_inc(nic->pnicvf->drv_stats-> + rcv_buffer_alloc_failures); return -ENOMEM; } nic->rb_page_offset = 0; @@ -270,7 +271,8 @@ refill: rbdr_idx, new_rb); next_rbdr: /* Re-enable RBDR interrupts only if buffer allocation is success */ - if (!nic->rb_alloc_fail && rbdr->enable) + if (!nic->rb_alloc_fail && rbdr->enable && + netif_running(nic->pnicvf->netdev)) nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx); if (rbdr_idx) @@ -361,6 +363,8 @@ static int nicvf_init_snd_queue(struct nicvf *nic, static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) { + struct sk_buff *skb; + if (!sq) return; if (!sq->dmem.base) @@ -371,6 +375,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) sq->dmem.q_len * TSO_HEADER_SIZE, sq->tso_hdrs, sq->tso_hdrs_phys); + /* Free pending skbs in the queue */ + smp_rmb(); + while (sq->head != sq->tail) { + skb = (struct sk_buff *)sq->skbuff[sq->head]; + if (skb) + dev_kfree_skb_any(skb); + sq->head++; + sq->head &= (sq->dmem.q_len - 1); + } kfree(sq->skbuff); nicvf_free_q_desc_mem(nic, &sq->dmem); } @@ -483,9 +496,12 @@ static void nicvf_reset_rcv_queue_stats(struct nicvf *nic) { union nic_mbx mbx = {}; - /* Reset all RXQ's stats */ + /* Reset all RQ/SQ and VF stats */ mbx.reset_stat.msg = NIC_MBOX_MSG_RESET_STAT_COUNTER; + mbx.reset_stat.rx_stat_mask = 0x3FFF; + mbx.reset_stat.tx_stat_mask = 0x1F; mbx.reset_stat.rq_stat_mask = 0xFFFF; + mbx.reset_stat.sq_stat_mask = 0xFFFF; nicvf_send_msg_to_pf(nic, &mbx); } @@ -528,19 +544,26 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, nicvf_send_msg_to_pf(nic, &mbx); mbx.rq.msg = NIC_MBOX_MSG_RQ_BP_CFG; - mbx.rq.cfg = (1ULL << 63) | (1ULL << 62) | (qs->vnic_id << 0); + mbx.rq.cfg = BIT_ULL(63) | BIT_ULL(62) | + (RQ_PASS_RBDR_LVL << 16) | (RQ_PASS_CQ_LVL << 8) | + (qs->vnic_id << 0); nicvf_send_msg_to_pf(nic, &mbx); /* RQ drop config * Enable CQ drop to reserve sufficient CQEs for all tx packets */ mbx.rq.msg = NIC_MBOX_MSG_RQ_DROP_CFG; - mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8); + mbx.rq.cfg = BIT_ULL(63) | BIT_ULL(62) | + (RQ_PASS_RBDR_LVL << 40) | (RQ_DROP_RBDR_LVL << 32) | + (RQ_PASS_CQ_LVL << 16) | (RQ_DROP_CQ_LVL << 8); nicvf_send_msg_to_pf(nic, &mbx); - nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, 0x00); - if (!nic->sqs_mode) + if (!nic->sqs_mode && (qidx == 0)) { + /* Enable checking L3/L4 length and TCP/UDP checksums */ + nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, + (BIT(24) | BIT(23) | BIT(21))); nicvf_config_vlan_stripping(nic, nic->netdev->features); + } /* Enable Receive queue */ memset(&rq_cfg, 0, sizeof(struct rq_cfg)); @@ -631,6 +654,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs, sq_cfg.ldwb = 0; sq_cfg.qsize = SND_QSIZE; sq_cfg.tstmp_bgx_intf = 0; + sq_cfg.cq_limit = 0; nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, *(u64 *)&sq_cfg); /* Set threshold value for interrupt generation */ @@ -1029,7 +1053,7 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, hdr->tso_max_paysize = skb_shinfo(skb)->gso_size; /* For non-tunneled pkts, point this to L2 ethertype */ hdr->inner_l3_offset = skb_network_offset(skb) - 2; - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); } } @@ -1161,35 +1185,17 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, nicvf_sq_doorbell(nic, skb, sq_num, desc_cnt); - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); return 1; } /* Append an skb to a SQ for packet transfer. */ -int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb) +int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, + struct sk_buff *skb, u8 sq_num) { int i, size; int subdesc_cnt, tso_sqe = 0; - int sq_num, qentry; - struct queue_set *qs; - struct snd_queue *sq; - - sq_num = skb_get_queue_mapping(skb); - if (sq_num >= MAX_SND_QUEUES_PER_QS) { - /* Get secondary Qset's SQ structure */ - i = sq_num / MAX_SND_QUEUES_PER_QS; - if (!nic->snicvf[i - 1]) { - netdev_warn(nic->netdev, - "Secondary Qset#%d's ptr not initialized\n", - i - 1); - return 1; - } - nic = (struct nicvf *)nic->snicvf[i - 1]; - sq_num = sq_num % MAX_SND_QUEUES_PER_QS; - } - - qs = nic->qs; - sq = &qs->sq[sq_num]; + int qentry; subdesc_cnt = nicvf_sq_subdesc_required(nic, skb); if (subdesc_cnt > atomic_read(&sq->free_cnt)) @@ -1422,8 +1428,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx) /* Check for errors in the receive cmp.queue entry */ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) { - struct nicvf_hw_stats *stats = &nic->hw_stats; - if (!cqe_rx->err_level && !cqe_rx->err_opcode) return 0; @@ -1435,76 +1439,76 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) switch (cqe_rx->err_opcode) { case CQ_RX_ERROP_RE_PARTIAL: - stats->rx_bgx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_bgx_truncated_pkts); break; case CQ_RX_ERROP_RE_JABBER: - stats->rx_jabber_errs++; + this_cpu_inc(nic->drv_stats->rx_jabber_errs); break; case CQ_RX_ERROP_RE_FCS: - stats->rx_fcs_errs++; + this_cpu_inc(nic->drv_stats->rx_fcs_errs); break; case CQ_RX_ERROP_RE_RX_CTL: - stats->rx_bgx_errs++; + this_cpu_inc(nic->drv_stats->rx_bgx_errs); break; case CQ_RX_ERROP_PREL2_ERR: - stats->rx_prel2_errs++; + this_cpu_inc(nic->drv_stats->rx_prel2_errs); break; case CQ_RX_ERROP_L2_MAL: - stats->rx_l2_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_l2_hdr_malformed); break; case CQ_RX_ERROP_L2_OVERSIZE: - stats->rx_oversize++; + this_cpu_inc(nic->drv_stats->rx_oversize); break; case CQ_RX_ERROP_L2_UNDERSIZE: - stats->rx_undersize++; + this_cpu_inc(nic->drv_stats->rx_undersize); break; case CQ_RX_ERROP_L2_LENMISM: - stats->rx_l2_len_mismatch++; + this_cpu_inc(nic->drv_stats->rx_l2_len_mismatch); break; case CQ_RX_ERROP_L2_PCLP: - stats->rx_l2_pclp++; + this_cpu_inc(nic->drv_stats->rx_l2_pclp); break; case CQ_RX_ERROP_IP_NOT: - stats->rx_ip_ver_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ver_errs); break; case CQ_RX_ERROP_IP_CSUM_ERR: - stats->rx_ip_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_csum_errs); break; case CQ_RX_ERROP_IP_MAL: - stats->rx_ip_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_hdr_malformed); break; case CQ_RX_ERROP_IP_MALD: - stats->rx_ip_payload_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_payload_malformed); break; case CQ_RX_ERROP_IP_HOP: - stats->rx_ip_ttl_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ttl_errs); break; case CQ_RX_ERROP_L3_PCLP: - stats->rx_l3_pclp++; + this_cpu_inc(nic->drv_stats->rx_l3_pclp); break; case CQ_RX_ERROP_L4_MAL: - stats->rx_l4_malformed++; + this_cpu_inc(nic->drv_stats->rx_l4_malformed); break; case CQ_RX_ERROP_L4_CHK: - stats->rx_l4_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_csum_errs); break; case CQ_RX_ERROP_UDP_LEN: - stats->rx_udp_len_errs++; + this_cpu_inc(nic->drv_stats->rx_udp_len_errs); break; case CQ_RX_ERROP_L4_PORT: - stats->rx_l4_port_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_port_errs); break; case CQ_RX_ERROP_TCP_FLAG: - stats->rx_tcp_flag_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_flag_errs); break; case CQ_RX_ERROP_TCP_OFFSET: - stats->rx_tcp_offset_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_offset_errs); break; case CQ_RX_ERROP_L4_PCLP: - stats->rx_l4_pclp++; + this_cpu_inc(nic->drv_stats->rx_l4_pclp); break; case CQ_RX_ERROP_RBDR_TRUNC: - stats->rx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_truncated_pkts); break; } @@ -1512,53 +1516,52 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) } /* Check for errors in the send cmp.queue entry */ -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx) +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx) { - struct cmp_queue_stats *stats = &cq->stats; - switch (cqe_tx->send_status) { case CQ_TX_ERROP_GOOD: - stats->tx.good++; return 0; case CQ_TX_ERROP_DESC_FAULT: - stats->tx.desc_fault++; + this_cpu_inc(nic->drv_stats->tx_desc_fault); break; case CQ_TX_ERROP_HDR_CONS_ERR: - stats->tx.hdr_cons_err++; + this_cpu_inc(nic->drv_stats->tx_hdr_cons_err); break; case CQ_TX_ERROP_SUBDC_ERR: - stats->tx.subdesc_err++; + this_cpu_inc(nic->drv_stats->tx_subdesc_err); + break; + case CQ_TX_ERROP_MAX_SIZE_VIOL: + this_cpu_inc(nic->drv_stats->tx_max_size_exceeded); break; case CQ_TX_ERROP_IMM_SIZE_OFLOW: - stats->tx.imm_size_oflow++; + this_cpu_inc(nic->drv_stats->tx_imm_size_oflow); break; case CQ_TX_ERROP_DATA_SEQUENCE_ERR: - stats->tx.data_seq_err++; + this_cpu_inc(nic->drv_stats->tx_data_seq_err); break; case CQ_TX_ERROP_MEM_SEQUENCE_ERR: - stats->tx.mem_seq_err++; + this_cpu_inc(nic->drv_stats->tx_mem_seq_err); break; case CQ_TX_ERROP_LOCK_VIOL: - stats->tx.lock_viol++; + this_cpu_inc(nic->drv_stats->tx_lock_viol); break; case CQ_TX_ERROP_DATA_FAULT: - stats->tx.data_fault++; + this_cpu_inc(nic->drv_stats->tx_data_fault); break; case CQ_TX_ERROP_TSTMP_CONFLICT: - stats->tx.tstmp_conflict++; + this_cpu_inc(nic->drv_stats->tx_tstmp_conflict); break; case CQ_TX_ERROP_TSTMP_TIMEOUT: - stats->tx.tstmp_timeout++; + this_cpu_inc(nic->drv_stats->tx_tstmp_timeout); break; case CQ_TX_ERROP_MEM_FAULT: - stats->tx.mem_fault++; + this_cpu_inc(nic->drv_stats->tx_mem_fault); break; case CQ_TX_ERROP_CK_OVERLAP: - stats->tx.csum_overlap++; + this_cpu_inc(nic->drv_stats->tx_csum_overlap); break; case CQ_TX_ERROP_CK_OFLOW: - stats->tx.csum_overflow++; + this_cpu_inc(nic->drv_stats->tx_csum_overflow); break; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 869f3386028b..9e2104675bc9 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -85,12 +85,26 @@ #define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \ MAX_CQE_PER_PKT_XMIT) -/* Calculate number of CQEs to reserve for all SQEs. - * Its 1/256th level of CQ size. - * '+ 1' to account for pipelining + +/* RED and Backpressure levels of CQ for pkt reception + * For CQ, level is a measure of emptiness i.e 0x0 means full + * eg: For CQ of size 4K, and for pass/drop levels of 160/144 + * HW accepts pkt if unused CQE >= 2560 + * RED accepts pkt if unused CQE < 2304 & >= 2560 + * DROPs pkts if unused CQE < 2304 + */ +#define RQ_PASS_CQ_LVL 160ULL +#define RQ_DROP_CQ_LVL 144ULL + +/* RED and Backpressure levels of RBDR for pkt reception + * For RBDR, level is a measure of fullness i.e 0x0 means empty + * eg: For RBDR of size 8K, and for pass/drop levels of 4/0 + * HW accepts pkt if unused RBs >= 256 + * RED accepts pkt if unused RBs < 256 & >= 0 + * DROPs pkts if unused RBs < 0 */ -#define RQ_CQ_DROP ((256 / (CMP_QUEUE_LEN / \ - (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1) +#define RQ_PASS_RBDR_LVL 8ULL +#define RQ_DROP_RBDR_LVL 0ULL /* Descriptor size in bytes */ #define SND_QUEUE_DESC_SIZE 16 @@ -158,6 +172,7 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_DESC_FAULT = 0x10, CQ_TX_ERROP_HDR_CONS_ERR = 0x11, CQ_TX_ERROP_SUBDC_ERR = 0x12, + CQ_TX_ERROP_MAX_SIZE_VIOL = 0x13, CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80, CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81, CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82, @@ -171,25 +186,6 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_ENUM_LAST = 0x8a, }; -struct cmp_queue_stats { - struct tx_stats { - u64 good; - u64 desc_fault; - u64 hdr_cons_err; - u64 subdesc_err; - u64 imm_size_oflow; - u64 data_seq_err; - u64 mem_seq_err; - u64 lock_viol; - u64 data_fault; - u64 tstmp_conflict; - u64 tstmp_timeout; - u64 mem_fault; - u64 csum_overlap; - u64 csum_overflow; - } tx; -} ____cacheline_aligned_in_smp; - enum RQ_SQ_STATS { RQ_SQ_STATS_OCTS, RQ_SQ_STATS_PKTS, @@ -241,7 +237,6 @@ struct cmp_queue { spinlock_t lock; /* lock to serialize processing CQEs */ void *desc; struct q_desc_mem dmem; - struct cmp_queue_stats stats; int irq; } ____cacheline_aligned_in_smp; @@ -311,7 +306,8 @@ void nicvf_sq_disable(struct nicvf *nic, int qidx); void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt); void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq, int qidx); -int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb); +int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, + struct sk_buff *skb, u8 sq_num); struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx); void nicvf_rbdr_task(unsigned long data); @@ -336,6 +332,5 @@ u64 nicvf_queue_reg_read(struct nicvf *nic, void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx); void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx); int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx); -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx); +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx); #endif /* NICVF_QUEUES_H */ diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h index 9e6d9876bfd0..f36347237a54 100644 --- a/drivers/net/ethernet/cavium/thunder/q_struct.h +++ b/drivers/net/ethernet/cavium/thunder/q_struct.h @@ -624,7 +624,9 @@ struct cq_cfg { struct sq_cfg { #if defined(__BIG_ENDIAN_BITFIELD) - u64 reserved_20_63:44; + u64 reserved_32_63:32; + u64 cq_limit:8; + u64 reserved_20_23:4; u64 ena:1; u64 reserved_18_18:1; u64 reset:1; @@ -642,7 +644,9 @@ struct sq_cfg { u64 reset:1; u64 reserved_18_18:1; u64 ena:1; - u64 reserved_20_63:44; + u64 reserved_20_23:4; + u64 cq_limit:8; + u64 reserved_32_63:32; #endif }; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 8bbaedbb7b94..9211c750e064 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -161,6 +161,7 @@ void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status) return; lmac = &bgx->lmac[lmacid]; + link->mac_type = lmac->lmac_type; link->link_up = lmac->link_up; link->duplex = lmac->last_duplex; link->speed = lmac->last_speed; @@ -211,6 +212,47 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) } EXPORT_SYMBOL(bgx_lmac_rx_tx_enable); +void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause) +{ + struct pfc *pfc = (struct pfc *)pause; + struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + struct lmac *lmac; + u64 cfg; + + if (!bgx) + return; + lmac = &bgx->lmac[lmacid]; + if (lmac->is_sgmii) + return; + + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_CBFC_CTL); + pfc->fc_rx = cfg & RX_EN; + pfc->fc_tx = cfg & TX_EN; + pfc->autoneg = 0; +} +EXPORT_SYMBOL(bgx_lmac_get_pfc); + +void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause) +{ + struct pfc *pfc = (struct pfc *)pause; + struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx]; + struct lmac *lmac; + u64 cfg; + + if (!bgx) + return; + lmac = &bgx->lmac[lmacid]; + if (lmac->is_sgmii) + return; + + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_CBFC_CTL); + cfg &= ~(RX_EN | TX_EN); + cfg |= (pfc->fc_rx ? RX_EN : 0x00); + cfg |= (pfc->fc_tx ? TX_EN : 0x00); + bgx_reg_write(bgx, lmacid, BGX_SMUX_CBFC_CTL, cfg); +} +EXPORT_SYMBOL(bgx_lmac_set_pfc); + static void bgx_sgmii_change_link_state(struct lmac *lmac) { struct bgx *bgx = lmac->bgx; @@ -524,6 +566,18 @@ static int bgx_lmac_xaui_init(struct bgx *bgx, struct lmac *lmac) cfg |= SMU_TX_CTL_DIC_EN; bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_CTL, cfg); + /* Enable receive and transmission of pause frames */ + bgx_reg_write(bgx, lmacid, BGX_SMUX_CBFC_CTL, ((0xffffULL << 32) | + BCK_EN | DRP_EN | TX_EN | RX_EN)); + /* Configure pause time and interval */ + bgx_reg_write(bgx, lmacid, + BGX_SMUX_TX_PAUSE_PKT_TIME, DEFAULT_PAUSE_TIME); + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_PAUSE_PKT_INTERVAL); + cfg &= ~0xFFFFull; + bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_PAUSE_PKT_INTERVAL, + cfg | (DEFAULT_PAUSE_TIME - 0x1000)); + bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_PAUSE_ZERO, 0x01); + /* take lmac_count into account */ bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_THRESH, (0x100 - 1)); /* max packet size */ @@ -970,11 +1024,25 @@ static void bgx_set_lmac_config(struct bgx *bgx, u8 idx) lmac_set_training(bgx, lmac, lmac->lmacid); lmac_set_lane2sds(bgx, lmac); - /* Set LMAC type of other lmac on same DLM i.e LMAC 1/3 */ olmac = &bgx->lmac[idx + 1]; - olmac->lmac_type = lmac->lmac_type; + /* Check if other LMAC on the same DLM is already configured by + * firmware, if so use the same config or else set as same, as + * that of LMAC 0/2. + * This check is needed as on 80xx only one lane of each of the + * DLM of BGX0 is used, so have to rely on firmware for + * distingushing 80xx from 81xx. + */ + cmr_cfg = bgx_reg_read(bgx, idx + 1, BGX_CMRX_CFG); + lmac_type = (u8)((cmr_cfg >> 8) & 0x07); + lane_to_sds = (u8)(cmr_cfg & 0xFF); + if ((lmac_type == 0) && (lane_to_sds == 0xE4)) { + olmac->lmac_type = lmac->lmac_type; + lmac_set_lane2sds(bgx, olmac); + } else { + olmac->lmac_type = lmac_type; + olmac->lane_to_sds = lane_to_sds; + } lmac_set_training(bgx, olmac, olmac->lmacid); - lmac_set_lane2sds(bgx, olmac); } } @@ -1242,8 +1310,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid); if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) { - bgx->bgx_id = - (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1; + bgx->bgx_id = (pci_resource_start(pdev, + PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK; bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE; bgx->max_lmac = MAX_LMAC_PER_BGX; bgx_vnic[bgx->bgx_id] = bgx; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index d59c71e4a000..c18ebfeb2039 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -27,6 +27,9 @@ #define MAX_BGX_CHANS_PER_LMAC 16 #define MAX_DMAC_PER_LMAC 8 #define MAX_FRAME_SIZE 9216 +#define DEFAULT_PAUSE_TIME 0xFFFF + +#define BGX_ID_MASK 0x3 #define MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE 2 @@ -124,7 +127,10 @@ #define SMU_RX_CTL_STATUS (3ull << 0) #define BGX_SMUX_TX_APPEND 0x20100 #define SMU_TX_APPEND_FCS_D BIT_ULL(2) +#define BGX_SMUX_TX_PAUSE_PKT_TIME 0x20110 #define BGX_SMUX_TX_MIN_PKT 0x20118 +#define BGX_SMUX_TX_PAUSE_PKT_INTERVAL 0x20120 +#define BGX_SMUX_TX_PAUSE_ZERO 0x20138 #define BGX_SMUX_TX_INT 0x20140 #define BGX_SMUX_TX_CTL 0x20178 #define SMU_TX_CTL_DIC_EN BIT_ULL(0) @@ -134,6 +140,11 @@ #define BGX_SMUX_CTL 0x20200 #define SMU_CTL_RX_IDLE BIT_ULL(0) #define SMU_CTL_TX_IDLE BIT_ULL(1) +#define BGX_SMUX_CBFC_CTL 0x20218 +#define RX_EN BIT_ULL(0) +#define TX_EN BIT_ULL(1) +#define BCK_EN BIT_ULL(2) +#define DRP_EN BIT_ULL(3) #define BGX_GMP_PCS_MRX_CTL 0x30000 #define PCS_MRX_CTL_RST_AN BIT_ULL(9) @@ -205,6 +216,9 @@ void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac); void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status); void bgx_lmac_internal_loopback(int node, int bgx_idx, int lmac_idx, bool enable); +void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause); +void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause); + void xcv_init_hw(void); void xcv_setup_link(bool link_up, int link_speed); |