X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fixgbe%2Fixgbe_ethdev.c;h=8bcd0d8489ca8d8e996d409e42d82e0e26926862;hb=09419f235e099ecb265a590778fe64a685a2a241;hp=8d681252621325aa183d22fb9ca5c30ca261843d;hpb=49508ecd257df28a4adb093479ea08c6d6216eb5;p=dpdk.git diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c index 8d68125262..8bcd0d8489 100644 --- a/drivers/net/ixgbe/ixgbe_ethdev.c +++ b/drivers/net/ixgbe/ixgbe_ethdev.c @@ -1,7 +1,7 @@ /*- * BSD LICENSE * - * Copyright(c) 2010-2015 Intel Corporation. All rights reserved. + * Copyright(c) 2010-2016 Intel Corporation. All rights reserved. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -68,6 +68,9 @@ #include "ixgbe_ethdev.h" #include "ixgbe_bypass.h" #include "ixgbe_rxtx.h" +#include "base/ixgbe_type.h" +#include "base/ixgbe_phy.h" +#include "ixgbe_regs.h" /* * High threshold controlling when to start sending XOFF frames. Must be at @@ -82,6 +85,9 @@ */ #define IXGBE_FC_LO 0x40 +/* Default minimum inter-interrupt interval for EITR configuration */ +#define IXGBE_MIN_INTER_INTERRUPT_INTERVAL_DEFAULT 0x79E + /* Timer value included in XOFF frames. */ #define IXGBE_FC_PAUSE 0x680 @@ -91,6 +97,7 @@ #define IXGBE_MMW_SIZE_DEFAULT 0x4 #define IXGBE_MMW_SIZE_JUMBO_FRAME 0x14 +#define IXGBE_MAX_RING_DESC 4096 /* replicate define from rxtx */ /* * Default values for RX/TX configuration @@ -119,12 +126,39 @@ #define IXGBE_HKEY_MAX_INDEX 10 /* Additional timesync values. */ -#define IXGBE_TIMINCA_16NS_SHIFT 24 -#define IXGBE_TIMINCA_INCVALUE 16000000 -#define IXGBE_TIMINCA_INIT ((0x02 << IXGBE_TIMINCA_16NS_SHIFT) \ - | IXGBE_TIMINCA_INCVALUE) +#define NSEC_PER_SEC 1000000000L +#define IXGBE_INCVAL_10GB 0x66666666 +#define IXGBE_INCVAL_1GB 0x40000000 +#define IXGBE_INCVAL_100 0x50000000 +#define IXGBE_INCVAL_SHIFT_10GB 28 +#define IXGBE_INCVAL_SHIFT_1GB 24 +#define IXGBE_INCVAL_SHIFT_100 21 +#define IXGBE_INCVAL_SHIFT_82599 7 +#define IXGBE_INCPER_SHIFT_82599 24 + +#define IXGBE_CYCLECOUNTER_MASK 0xffffffffffffffffULL + +#define IXGBE_VT_CTL_POOLING_MODE_MASK 0x00030000 +#define IXGBE_VT_CTL_POOLING_MODE_ETAG 0x00010000 +#define DEFAULT_ETAG_ETYPE 0x893f +#define IXGBE_ETAG_ETYPE 0x00005084 +#define IXGBE_ETAG_ETYPE_MASK 0x0000ffff +#define IXGBE_ETAG_ETYPE_VALID 0x80000000 +#define IXGBE_RAH_ADTYPE 0x40000000 +#define IXGBE_RAL_ETAG_FILTER_MASK 0x00003fff +#define IXGBE_VMVIR_TAGA_MASK 0x18000000 +#define IXGBE_VMVIR_TAGA_ETAG_INSERT 0x08000000 +#define IXGBE_VMTIR(_i) (0x00017000 + ((_i) * 4)) /* 64 of these (0-63) */ +#define IXGBE_QDE_STRIP_TAG 0x00000004 + +enum ixgbevf_xcast_modes { + IXGBEVF_XCAST_MODE_NONE = 0, + IXGBEVF_XCAST_MODE_MULTI, + IXGBEVF_XCAST_MODE_ALLMULTI, +}; static int eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev); +static int eth_ixgbe_dev_uninit(struct rte_eth_dev *eth_dev); static int ixgbe_dev_configure(struct rte_eth_dev *dev); static int ixgbe_dev_start(struct rte_eth_dev *dev); static void ixgbe_dev_stop(struct rte_eth_dev *dev); @@ -139,20 +173,28 @@ static int ixgbe_dev_link_update(struct rte_eth_dev *dev, int wait_to_complete); static void ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats); +static int ixgbe_dev_xstats_get(struct rte_eth_dev *dev, + struct rte_eth_xstats *xstats, unsigned n); +static int ixgbevf_dev_xstats_get(struct rte_eth_dev *dev, + struct rte_eth_xstats *xstats, unsigned n); static void ixgbe_dev_stats_reset(struct rte_eth_dev *dev); +static void ixgbe_dev_xstats_reset(struct rte_eth_dev *dev); static int ixgbe_dev_queue_stats_mapping_set(struct rte_eth_dev *eth_dev, uint16_t queue_id, uint8_t stat_idx, uint8_t is_rx); static void ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info); +static const uint32_t *ixgbe_dev_supported_ptypes_get(struct rte_eth_dev *dev); static void ixgbevf_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info); static int ixgbe_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu); static int ixgbe_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on); -static void ixgbe_vlan_tpid_set(struct rte_eth_dev *dev, uint16_t tpid_id); +static int ixgbe_vlan_tpid_set(struct rte_eth_dev *dev, + enum rte_vlan_type vlan_type, + uint16_t tpid_id); static void ixgbe_vlan_hw_strip_bitmap_set(struct rte_eth_dev *dev, uint16_t queue, bool on); static void ixgbe_vlan_strip_queue_set(struct rte_eth_dev *dev, uint16_t queue, @@ -179,6 +221,7 @@ static int ixgbe_dev_rss_reta_query(struct rte_eth_dev *dev, uint16_t reta_size); static void ixgbe_dev_link_status_print(struct rte_eth_dev *dev); static int ixgbe_dev_lsc_interrupt_setup(struct rte_eth_dev *dev); +static int ixgbe_dev_rxq_interrupt_setup(struct rte_eth_dev *dev); static int ixgbe_dev_interrupt_get_status(struct rte_eth_dev *dev); static int ixgbe_dev_interrupt_action(struct rte_eth_dev *dev); static void ixgbe_dev_interrupt_handler(struct rte_intr_handle *handle, @@ -187,15 +230,19 @@ static void ixgbe_dev_interrupt_delayed_handler(void *param); static void ixgbe_add_rar(struct rte_eth_dev *dev, struct ether_addr *mac_addr, uint32_t index, uint32_t pool); static void ixgbe_remove_rar(struct rte_eth_dev *dev, uint32_t index); +static void ixgbe_set_default_mac_addr(struct rte_eth_dev *dev, + struct ether_addr *mac_addr); static void ixgbe_dcb_init(struct ixgbe_hw *hw,struct ixgbe_dcb_config *dcb_config); /* For Virtual Function support */ static int eth_ixgbevf_dev_init(struct rte_eth_dev *eth_dev); +static int eth_ixgbevf_dev_uninit(struct rte_eth_dev *eth_dev); static int ixgbevf_dev_configure(struct rte_eth_dev *dev); static int ixgbevf_dev_start(struct rte_eth_dev *dev); static void ixgbevf_dev_stop(struct rte_eth_dev *dev); static void ixgbevf_dev_close(struct rte_eth_dev *dev); static void ixgbevf_intr_disable(struct ixgbe_hw *hw); +static void ixgbevf_intr_enable(struct ixgbe_hw *hw); static void ixgbevf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats); static void ixgbevf_dev_stats_reset(struct rte_eth_dev *dev); @@ -205,6 +252,15 @@ static void ixgbevf_vlan_strip_queue_set(struct rte_eth_dev *dev, uint16_t queue, int on); static void ixgbevf_vlan_offload_set(struct rte_eth_dev *dev, int mask); static void ixgbevf_set_vfta_all(struct rte_eth_dev *dev, bool on); +static int ixgbevf_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, + uint16_t queue_id); +static int ixgbevf_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, + uint16_t queue_id); +static void ixgbevf_set_ivar_map(struct ixgbe_hw *hw, int8_t direction, + uint8_t queue, uint8_t msix_vector); +static void ixgbevf_configure_msix(struct rte_eth_dev *dev); +static void ixgbevf_dev_allmulticast_enable(struct rte_eth_dev *dev); +static void ixgbevf_dev_allmulticast_disable(struct rte_eth_dev *dev); /* For Eth VMDQ APIs support */ static int ixgbe_uc_hash_table_set(struct rte_eth_dev *dev, struct @@ -221,6 +277,13 @@ static int ixgbe_mirror_rule_set(struct rte_eth_dev *dev, uint8_t rule_id, uint8_t on); static int ixgbe_mirror_rule_reset(struct rte_eth_dev *dev, uint8_t rule_id); +static int ixgbe_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, + uint16_t queue_id); +static int ixgbe_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, + uint16_t queue_id); +static void ixgbe_set_ivar_map(struct ixgbe_hw *hw, int8_t direction, + uint8_t queue, uint8_t msix_vector); +static void ixgbe_configure_msix(struct rte_eth_dev *dev); static int ixgbe_set_queue_rate_limit(struct rte_eth_dev *dev, uint16_t queue_idx, uint16_t tx_rate); @@ -231,6 +294,8 @@ static void ixgbevf_add_mac_addr(struct rte_eth_dev *dev, struct ether_addr *mac_addr, uint32_t index, uint32_t pool); static void ixgbevf_remove_mac_addr(struct rte_eth_dev *dev, uint32_t index); +static void ixgbevf_set_default_mac_addr(struct rte_eth_dev *dev, + struct ether_addr *mac_addr); static int ixgbe_syn_filter_set(struct rte_eth_dev *dev, struct rte_eth_syn_filter *filter, bool add); @@ -268,6 +333,21 @@ static int ixgbevf_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu); static int ixgbe_dev_set_mc_addr_list(struct rte_eth_dev *dev, struct ether_addr *mc_addr_set, uint32_t nb_mc_addr); +static int ixgbe_dev_get_dcb_info(struct rte_eth_dev *dev, + struct rte_eth_dcb_info *dcb_info); + +static int ixgbe_get_reg_length(struct rte_eth_dev *dev); +static int ixgbe_get_regs(struct rte_eth_dev *dev, + struct rte_dev_reg_info *regs); +static int ixgbe_get_eeprom_length(struct rte_eth_dev *dev); +static int ixgbe_get_eeprom(struct rte_eth_dev *dev, + struct rte_dev_eeprom_info *eeprom); +static int ixgbe_set_eeprom(struct rte_eth_dev *dev, + struct rte_dev_eeprom_info *eeprom); + +static int ixgbevf_get_reg_length(struct rte_eth_dev *dev); +static int ixgbevf_get_regs(struct rte_eth_dev *dev, + struct rte_dev_reg_info *regs); static int ixgbe_timesync_enable(struct rte_eth_dev *dev); static int ixgbe_timesync_disable(struct rte_eth_dev *dev); @@ -276,14 +356,35 @@ static int ixgbe_timesync_read_rx_timestamp(struct rte_eth_dev *dev, uint32_t flags); static int ixgbe_timesync_read_tx_timestamp(struct rte_eth_dev *dev, struct timespec *timestamp); +static int ixgbe_timesync_adjust_time(struct rte_eth_dev *dev, int64_t delta); +static int ixgbe_timesync_read_time(struct rte_eth_dev *dev, + struct timespec *timestamp); +static int ixgbe_timesync_write_time(struct rte_eth_dev *dev, + const struct timespec *timestamp); + +static int ixgbe_dev_l2_tunnel_eth_type_conf + (struct rte_eth_dev *dev, struct rte_eth_l2_tunnel_conf *l2_tunnel); +static int ixgbe_dev_l2_tunnel_offload_set + (struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel, + uint32_t mask, + uint8_t en); +static int ixgbe_dev_l2_tunnel_filter_handle(struct rte_eth_dev *dev, + enum rte_filter_op filter_op, + void *arg); + +static int ixgbe_dev_udp_tunnel_port_add(struct rte_eth_dev *dev, + struct rte_eth_udp_tunnel *udp_tunnel); +static int ixgbe_dev_udp_tunnel_port_del(struct rte_eth_dev *dev, + struct rte_eth_udp_tunnel *udp_tunnel); /* * Define VF Stats MACRO for Non "cleared on read" register */ -#define UPDATE_VF_STAT(reg, last, cur) \ +#define UPDATE_VF_STAT(reg, last, cur) \ { \ - u32 latest = IXGBE_READ_REG(hw, reg); \ - cur += latest - last; \ + uint32_t latest = IXGBE_READ_REG(hw, reg); \ + cur += (latest - last) & UINT_MAX; \ last = latest; \ } @@ -300,19 +401,19 @@ static int ixgbe_timesync_read_tx_timestamp(struct rte_eth_dev *dev, uint32_t idx = (q) / (sizeof ((h)->bitmap[0]) * NBBY); \ uint32_t bit = (q) % (sizeof ((h)->bitmap[0]) * NBBY); \ (h)->bitmap[idx] |= 1 << bit;\ - }while(0) + } while (0) #define IXGBE_CLEAR_HWSTRIP(h, q) do{\ uint32_t idx = (q) / (sizeof ((h)->bitmap[0]) * NBBY); \ uint32_t bit = (q) % (sizeof ((h)->bitmap[0]) * NBBY); \ (h)->bitmap[idx] &= ~(1 << bit);\ - }while(0) + } while (0) #define IXGBE_GET_HWSTRIP(h, q, r) do{\ uint32_t idx = (q) / (sizeof ((h)->bitmap[0]) * NBBY); \ uint32_t bit = (q) % (sizeof ((h)->bitmap[0]) * NBBY); \ (r) = (h)->bitmap[idx] >> bit & 1;\ - }while(0) + } while (0) /* * The set of PCI devices this driver supports @@ -337,6 +438,18 @@ static const struct rte_pci_id pci_id_ixgbevf_map[] = { }; +static const struct rte_eth_desc_lim rx_desc_lim = { + .nb_max = IXGBE_MAX_RING_DESC, + .nb_min = IXGBE_MIN_RING_DESC, + .nb_align = IXGBE_RXD_ALIGN, +}; + +static const struct rte_eth_desc_lim tx_desc_lim = { + .nb_max = IXGBE_MAX_RING_DESC, + .nb_min = IXGBE_MIN_RING_DESC, + .nb_align = IXGBE_TXD_ALIGN, +}; + static const struct eth_dev_ops ixgbe_eth_dev_ops = { .dev_configure = ixgbe_dev_configure, .dev_start = ixgbe_dev_start, @@ -350,9 +463,12 @@ static const struct eth_dev_ops ixgbe_eth_dev_ops = { .allmulticast_disable = ixgbe_dev_allmulticast_disable, .link_update = ixgbe_dev_link_update, .stats_get = ixgbe_dev_stats_get, + .xstats_get = ixgbe_dev_xstats_get, .stats_reset = ixgbe_dev_stats_reset, + .xstats_reset = ixgbe_dev_xstats_reset, .queue_stats_mapping_set = ixgbe_dev_queue_stats_mapping_set, .dev_infos_get = ixgbe_dev_info_get, + .dev_supported_ptypes_get = ixgbe_dev_supported_ptypes_get, .mtu_set = ixgbe_dev_mtu_set, .vlan_filter_set = ixgbe_vlan_filter_set, .vlan_tpid_set = ixgbe_vlan_tpid_set, @@ -363,6 +479,8 @@ static const struct eth_dev_ops ixgbe_eth_dev_ops = { .tx_queue_start = ixgbe_dev_tx_queue_start, .tx_queue_stop = ixgbe_dev_tx_queue_stop, .rx_queue_setup = ixgbe_dev_rx_queue_setup, + .rx_queue_intr_enable = ixgbe_dev_rx_queue_intr_enable, + .rx_queue_intr_disable = ixgbe_dev_rx_queue_intr_disable, .rx_queue_release = ixgbe_dev_rx_queue_release, .rx_queue_count = ixgbe_dev_rx_queue_count, .rx_descriptor_done = ixgbe_dev_rx_descriptor_done, @@ -375,6 +493,7 @@ static const struct eth_dev_ops ixgbe_eth_dev_ops = { .priority_flow_ctrl_set = ixgbe_priority_flow_ctrl_set, .mac_addr_add = ixgbe_add_rar, .mac_addr_remove = ixgbe_remove_rar, + .mac_addr_set = ixgbe_set_default_mac_addr, .uc_hash_table_set = ixgbe_uc_hash_table_set, .uc_all_hash_table_set = ixgbe_uc_all_hash_table_set, .mirror_rule_set = ixgbe_mirror_rule_set, @@ -402,10 +521,25 @@ static const struct eth_dev_ops ixgbe_eth_dev_ops = { .rss_hash_conf_get = ixgbe_dev_rss_hash_conf_get, .filter_ctrl = ixgbe_dev_filter_ctrl, .set_mc_addr_list = ixgbe_dev_set_mc_addr_list, + .rxq_info_get = ixgbe_rxq_info_get, + .txq_info_get = ixgbe_txq_info_get, .timesync_enable = ixgbe_timesync_enable, .timesync_disable = ixgbe_timesync_disable, .timesync_read_rx_timestamp = ixgbe_timesync_read_rx_timestamp, .timesync_read_tx_timestamp = ixgbe_timesync_read_tx_timestamp, + .get_reg_length = ixgbe_get_reg_length, + .get_reg = ixgbe_get_regs, + .get_eeprom_length = ixgbe_get_eeprom_length, + .get_eeprom = ixgbe_get_eeprom, + .set_eeprom = ixgbe_set_eeprom, + .get_dcb_info = ixgbe_dev_get_dcb_info, + .timesync_adjust_time = ixgbe_timesync_adjust_time, + .timesync_read_time = ixgbe_timesync_read_time, + .timesync_write_time = ixgbe_timesync_write_time, + .l2_tunnel_eth_type_conf = ixgbe_dev_l2_tunnel_eth_type_conf, + .l2_tunnel_offload_set = ixgbe_dev_l2_tunnel_offload_set, + .udp_tunnel_port_add = ixgbe_dev_udp_tunnel_port_add, + .udp_tunnel_port_del = ixgbe_dev_udp_tunnel_port_del, }; /* @@ -418,22 +552,157 @@ static const struct eth_dev_ops ixgbevf_eth_dev_ops = { .dev_stop = ixgbevf_dev_stop, .link_update = ixgbe_dev_link_update, .stats_get = ixgbevf_dev_stats_get, + .xstats_get = ixgbevf_dev_xstats_get, .stats_reset = ixgbevf_dev_stats_reset, + .xstats_reset = ixgbevf_dev_stats_reset, .dev_close = ixgbevf_dev_close, + .allmulticast_enable = ixgbevf_dev_allmulticast_enable, + .allmulticast_disable = ixgbevf_dev_allmulticast_disable, .dev_infos_get = ixgbevf_dev_info_get, + .dev_supported_ptypes_get = ixgbe_dev_supported_ptypes_get, .mtu_set = ixgbevf_dev_set_mtu, .vlan_filter_set = ixgbevf_vlan_filter_set, .vlan_strip_queue_set = ixgbevf_vlan_strip_queue_set, .vlan_offload_set = ixgbevf_vlan_offload_set, .rx_queue_setup = ixgbe_dev_rx_queue_setup, .rx_queue_release = ixgbe_dev_rx_queue_release, + .rx_descriptor_done = ixgbe_dev_rx_descriptor_done, .tx_queue_setup = ixgbe_dev_tx_queue_setup, .tx_queue_release = ixgbe_dev_tx_queue_release, + .rx_queue_intr_enable = ixgbevf_dev_rx_queue_intr_enable, + .rx_queue_intr_disable = ixgbevf_dev_rx_queue_intr_disable, .mac_addr_add = ixgbevf_add_mac_addr, .mac_addr_remove = ixgbevf_remove_mac_addr, .set_mc_addr_list = ixgbe_dev_set_mc_addr_list, + .rxq_info_get = ixgbe_rxq_info_get, + .txq_info_get = ixgbe_txq_info_get, + .mac_addr_set = ixgbevf_set_default_mac_addr, + .get_reg_length = ixgbevf_get_reg_length, + .get_reg = ixgbevf_get_regs, + .reta_update = ixgbe_dev_rss_reta_update, + .reta_query = ixgbe_dev_rss_reta_query, + .rss_hash_update = ixgbe_dev_rss_hash_update, + .rss_hash_conf_get = ixgbe_dev_rss_hash_conf_get, +}; + +/* store statistics names and its offset in stats structure */ +struct rte_ixgbe_xstats_name_off { + char name[RTE_ETH_XSTATS_NAME_SIZE]; + unsigned offset; +}; + +static const struct rte_ixgbe_xstats_name_off rte_ixgbe_stats_strings[] = { + {"rx_crc_errors", offsetof(struct ixgbe_hw_stats, crcerrs)}, + {"rx_illegal_byte_errors", offsetof(struct ixgbe_hw_stats, illerrc)}, + {"rx_error_bytes", offsetof(struct ixgbe_hw_stats, errbc)}, + {"mac_local_errors", offsetof(struct ixgbe_hw_stats, mlfc)}, + {"mac_remote_errors", offsetof(struct ixgbe_hw_stats, mrfc)}, + {"rx_length_errors", offsetof(struct ixgbe_hw_stats, rlec)}, + {"tx_xon_packets", offsetof(struct ixgbe_hw_stats, lxontxc)}, + {"rx_xon_packets", offsetof(struct ixgbe_hw_stats, lxonrxc)}, + {"tx_xoff_packets", offsetof(struct ixgbe_hw_stats, lxofftxc)}, + {"rx_xoff_packets", offsetof(struct ixgbe_hw_stats, lxoffrxc)}, + {"rx_size_64_packets", offsetof(struct ixgbe_hw_stats, prc64)}, + {"rx_size_65_to_127_packets", offsetof(struct ixgbe_hw_stats, prc127)}, + {"rx_size_128_to_255_packets", offsetof(struct ixgbe_hw_stats, prc255)}, + {"rx_size_256_to_511_packets", offsetof(struct ixgbe_hw_stats, prc511)}, + {"rx_size_512_to_1023_packets", offsetof(struct ixgbe_hw_stats, + prc1023)}, + {"rx_size_1024_to_max_packets", offsetof(struct ixgbe_hw_stats, + prc1522)}, + {"rx_broadcast_packets", offsetof(struct ixgbe_hw_stats, bprc)}, + {"rx_multicast_packets", offsetof(struct ixgbe_hw_stats, mprc)}, + {"rx_fragment_errors", offsetof(struct ixgbe_hw_stats, rfc)}, + {"rx_undersize_errors", offsetof(struct ixgbe_hw_stats, ruc)}, + {"rx_oversize_errors", offsetof(struct ixgbe_hw_stats, roc)}, + {"rx_jabber_errors", offsetof(struct ixgbe_hw_stats, rjc)}, + {"rx_management_packets", offsetof(struct ixgbe_hw_stats, mngprc)}, + {"rx_management_dropped", offsetof(struct ixgbe_hw_stats, mngpdc)}, + {"tx_management_packets", offsetof(struct ixgbe_hw_stats, mngptc)}, + {"rx_total_packets", offsetof(struct ixgbe_hw_stats, tpr)}, + {"rx_total_bytes", offsetof(struct ixgbe_hw_stats, tor)}, + {"tx_total_packets", offsetof(struct ixgbe_hw_stats, tpt)}, + {"tx_size_64_packets", offsetof(struct ixgbe_hw_stats, ptc64)}, + {"tx_size_65_to_127_packets", offsetof(struct ixgbe_hw_stats, ptc127)}, + {"tx_size_128_to_255_packets", offsetof(struct ixgbe_hw_stats, ptc255)}, + {"tx_size_256_to_511_packets", offsetof(struct ixgbe_hw_stats, ptc511)}, + {"tx_size_512_to_1023_packets", offsetof(struct ixgbe_hw_stats, + ptc1023)}, + {"tx_size_1024_to_max_packets", offsetof(struct ixgbe_hw_stats, + ptc1522)}, + {"tx_multicast_packets", offsetof(struct ixgbe_hw_stats, mptc)}, + {"tx_broadcast_packets", offsetof(struct ixgbe_hw_stats, bptc)}, + {"rx_mac_short_packet_dropped", offsetof(struct ixgbe_hw_stats, mspdc)}, + {"rx_l3_l4_xsum_error", offsetof(struct ixgbe_hw_stats, xec)}, + + {"flow_director_added_filters", offsetof(struct ixgbe_hw_stats, + fdirustat_add)}, + {"flow_director_removed_filters", offsetof(struct ixgbe_hw_stats, + fdirustat_remove)}, + {"flow_director_filter_add_errors", offsetof(struct ixgbe_hw_stats, + fdirfstat_fadd)}, + {"flow_director_filter_remove_errors", offsetof(struct ixgbe_hw_stats, + fdirfstat_fremove)}, + {"flow_director_matched_filters", offsetof(struct ixgbe_hw_stats, + fdirmatch)}, + {"flow_director_missed_filters", offsetof(struct ixgbe_hw_stats, + fdirmiss)}, + + {"rx_fcoe_crc_errors", offsetof(struct ixgbe_hw_stats, fccrc)}, + {"rx_fcoe_dropped", offsetof(struct ixgbe_hw_stats, fcoerpdc)}, + {"rx_fcoe_mbuf_allocation_errors", offsetof(struct ixgbe_hw_stats, + fclast)}, + {"rx_fcoe_packets", offsetof(struct ixgbe_hw_stats, fcoeprc)}, + {"tx_fcoe_packets", offsetof(struct ixgbe_hw_stats, fcoeptc)}, + {"rx_fcoe_bytes", offsetof(struct ixgbe_hw_stats, fcoedwrc)}, + {"tx_fcoe_bytes", offsetof(struct ixgbe_hw_stats, fcoedwtc)}, + {"rx_fcoe_no_direct_data_placement", offsetof(struct ixgbe_hw_stats, + fcoe_noddp)}, + {"rx_fcoe_no_direct_data_placement_ext_buff", + offsetof(struct ixgbe_hw_stats, fcoe_noddp_ext_buff)}, + + {"tx_flow_control_xon_packets", offsetof(struct ixgbe_hw_stats, + lxontxc)}, + {"rx_flow_control_xon_packets", offsetof(struct ixgbe_hw_stats, + lxonrxc)}, + {"tx_flow_control_xoff_packets", offsetof(struct ixgbe_hw_stats, + lxofftxc)}, + {"rx_flow_control_xoff_packets", offsetof(struct ixgbe_hw_stats, + lxoffrxc)}, + {"rx_total_missed_packets", offsetof(struct ixgbe_hw_stats, mpctotal)}, +}; + +#define IXGBE_NB_HW_STATS (sizeof(rte_ixgbe_stats_strings) / \ + sizeof(rte_ixgbe_stats_strings[0])) + +/* Per-queue statistics */ +static const struct rte_ixgbe_xstats_name_off rte_ixgbe_rxq_strings[] = { + {"mbuf_allocation_errors", offsetof(struct ixgbe_hw_stats, rnbc)}, + {"dropped", offsetof(struct ixgbe_hw_stats, mpc)}, + {"xon_packets", offsetof(struct ixgbe_hw_stats, pxonrxc)}, + {"xoff_packets", offsetof(struct ixgbe_hw_stats, pxoffrxc)}, +}; + +#define IXGBE_NB_RXQ_PRIO_STATS (sizeof(rte_ixgbe_rxq_strings) / \ + sizeof(rte_ixgbe_rxq_strings[0])) + +static const struct rte_ixgbe_xstats_name_off rte_ixgbe_txq_strings[] = { + {"xon_packets", offsetof(struct ixgbe_hw_stats, pxontxc)}, + {"xoff_packets", offsetof(struct ixgbe_hw_stats, pxofftxc)}, + {"xon_to_xoff_packets", offsetof(struct ixgbe_hw_stats, + pxon2offc)}, +}; + +#define IXGBE_NB_TXQ_PRIO_STATS (sizeof(rte_ixgbe_txq_strings) / \ + sizeof(rte_ixgbe_txq_strings[0])) + +static const struct rte_ixgbe_xstats_name_off rte_ixgbevf_stats_strings[] = { + {"rx_multicast_packets", offsetof(struct ixgbevf_hw_stats, vfmprc)}, }; +#define IXGBEVF_NB_XSTATS (sizeof(rte_ixgbevf_stats_strings) / \ + sizeof(rte_ixgbevf_stats_strings[0])) + /** * Atomically reads the link status information from global * structure rte_eth_dev. @@ -563,7 +832,7 @@ ixgbe_reset_qstat_mappings(struct ixgbe_hw *hw) { uint32_t i; - for(i = 0; i != IXGBE_NB_STAT_MAPPING_REGS; i++) { + for (i = 0; i != IXGBE_NB_STAT_MAPPING_REGS; i++) { IXGBE_WRITE_REG(hw, IXGBE_RQSMR(i), 0); IXGBE_WRITE_REG(hw, IXGBE_TQSM(i), 0); } @@ -591,10 +860,11 @@ ixgbe_dev_queue_stats_mapping_set(struct rte_eth_dev *eth_dev, if ((hw->mac.type != ixgbe_mac_82599EB) && (hw->mac.type != ixgbe_mac_X540) && (hw->mac.type != ixgbe_mac_X550) && - (hw->mac.type != ixgbe_mac_X550EM_x)) + (hw->mac.type != ixgbe_mac_X550EM_x) && + (hw->mac.type != ixgbe_mac_X550EM_a)) return -ENOSYS; - PMD_INIT_LOG(INFO, "Setting port %d, %s queue_id %d to stat index %d", + PMD_INIT_LOG(DEBUG, "Setting port %d, %s queue_id %d to stat index %d", (int)(eth_dev->data->port_id), is_rx ? "RX" : "TX", queue_id, stat_idx); @@ -620,20 +890,20 @@ ixgbe_dev_queue_stats_mapping_set(struct rte_eth_dev *eth_dev, else stat_mappings->rqsmr[n] |= qsmr_mask; - PMD_INIT_LOG(INFO, "Set port %d, %s queue_id %d to stat index %d", + PMD_INIT_LOG(DEBUG, "Set port %d, %s queue_id %d to stat index %d", (int)(eth_dev->data->port_id), is_rx ? "RX" : "TX", queue_id, stat_idx); - PMD_INIT_LOG(INFO, "%s[%d] = 0x%08x", is_rx ? "RQSMR" : "TQSM", n, + PMD_INIT_LOG(DEBUG, "%s[%d] = 0x%08x", is_rx ? "RQSMR" : "TQSM", n, is_rx ? stat_mappings->rqsmr[n] : stat_mappings->tqsm[n]); /* Now write the mapping in the appropriate register */ if (is_rx) { - PMD_INIT_LOG(INFO, "Write 0x%x to RX IXGBE stat mapping reg:%d", + PMD_INIT_LOG(DEBUG, "Write 0x%x to RX IXGBE stat mapping reg:%d", stat_mappings->rqsmr[n], n); IXGBE_WRITE_REG(hw, IXGBE_RQSMR(n), stat_mappings->rqsmr[n]); } else { - PMD_INIT_LOG(INFO, "Write 0x%x to TX IXGBE stat mapping reg:%d", + PMD_INIT_LOG(DEBUG, "Write 0x%x to TX IXGBE stat mapping reg:%d", stat_mappings->tqsm[n], n); IXGBE_WRITE_REG(hw, IXGBE_TQSM(n), stat_mappings->tqsm[n]); } @@ -696,7 +966,8 @@ ixgbe_dcb_init(struct ixgbe_hw *hw,struct ixgbe_dcb_config *dcb_config) /*we only support 4 Tcs for X540, X550 */ if (hw->mac.type == ixgbe_mac_X540 || hw->mac.type == ixgbe_mac_X550 || - hw->mac.type == ixgbe_mac_X550EM_x) { + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_X550EM_a) { dcb_config->num_tcs.pg_tcs = 4; dcb_config->num_tcs.pfc_tcs = 4; } @@ -777,8 +1048,8 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev) ixgbe_set_tx_function(eth_dev, txq); } else { /* Use default TX function if we get here */ - PMD_INIT_LOG(INFO, "No TX queues configured yet. " - "Using default TX function."); + PMD_INIT_LOG(NOTICE, "No TX queues configured yet. " + "Using default TX function."); } ixgbe_set_rx_function(eth_dev); @@ -787,6 +1058,8 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev) } pci_dev = eth_dev->pci_dev; + rte_eth_copy_pci_info(eth_dev, pci_dev); + /* Vendor and Device ID need to be set before init of shared code */ hw->device_id = pci_dev->id.device_id; hw->vendor_id = pci_dev->id.vendor_id; @@ -928,11 +1201,12 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev) eth_dev->data->port_id, pci_dev->id.vendor_id, pci_dev->id.device_id); - rte_intr_callback_register(&(pci_dev->intr_handle), - ixgbe_dev_interrupt_handler, (void *)eth_dev); + rte_intr_callback_register(&pci_dev->intr_handle, + ixgbe_dev_interrupt_handler, + (void *)eth_dev); - /* enable uio intr after callback register */ - rte_intr_enable(&(pci_dev->intr_handle)); + /* enable uio/vfio intr/eventfd mapping */ + rte_intr_enable(&pci_dev->intr_handle); /* enable support intr */ ixgbe_enable_intr(eth_dev); @@ -945,6 +1219,46 @@ eth_ixgbe_dev_init(struct rte_eth_dev *eth_dev) return 0; } +static int +eth_ixgbe_dev_uninit(struct rte_eth_dev *eth_dev) +{ + struct rte_pci_device *pci_dev; + struct ixgbe_hw *hw; + + PMD_INIT_FUNC_TRACE(); + + if (rte_eal_process_type() != RTE_PROC_PRIMARY) + return -EPERM; + + hw = IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private); + pci_dev = eth_dev->pci_dev; + + if (hw->adapter_stopped == 0) + ixgbe_dev_close(eth_dev); + + eth_dev->dev_ops = NULL; + eth_dev->rx_pkt_burst = NULL; + eth_dev->tx_pkt_burst = NULL; + + /* Unlock any pending hardware semaphore */ + ixgbe_swfw_lock_reset(hw); + + /* disable uio intr before callback unregister */ + rte_intr_disable(&(pci_dev->intr_handle)); + rte_intr_callback_unregister(&(pci_dev->intr_handle), + ixgbe_dev_interrupt_handler, (void *)eth_dev); + + /* uninitialize PF if max_vfs not zero */ + ixgbe_pf_host_uninit(eth_dev); + + rte_free(eth_dev->data->mac_addrs); + eth_dev->data->mac_addrs = NULL; + + rte_free(eth_dev->data->hash_mac_addrs); + eth_dev->data->hash_mac_addrs = NULL; + + return 0; +} /* * Negotiate mailbox API version with the PF. @@ -960,6 +1274,7 @@ ixgbevf_negotiate_api(struct ixgbe_hw *hw) /* start with highest supported, proceed down */ static const enum ixgbe_pfvf_api_rev sup_ver[] = { + ixgbe_mbox_api_12, ixgbe_mbox_api_11, ixgbe_mbox_api_10, }; @@ -1014,13 +1329,28 @@ eth_ixgbevf_dev_init(struct rte_eth_dev *eth_dev) * has already done this work. Only check we don't need a different * RX function */ if (rte_eal_process_type() != RTE_PROC_PRIMARY){ - if (eth_dev->data->scattered_rx) - eth_dev->rx_pkt_burst = ixgbe_recv_pkts_lro_single_alloc; + struct ixgbe_tx_queue *txq; + /* TX queue function in primary, set by last queue initialized + * Tx queue may not initialized by primary process + */ + if (eth_dev->data->tx_queues) { + txq = eth_dev->data->tx_queues[eth_dev->data->nb_tx_queues - 1]; + ixgbe_set_tx_function(eth_dev, txq); + } else { + /* Use default TX function if we get here */ + PMD_INIT_LOG(NOTICE, + "No TX queues configured yet. Using default TX function."); + } + + ixgbe_set_rx_function(eth_dev); + return 0; } pci_dev = eth_dev->pci_dev; + rte_eth_copy_pci_info(eth_dev, pci_dev); + hw->device_id = pci_dev->id.device_id; hw->vendor_id = pci_dev->id.vendor_id; hw->hw_addr = (void *)pci_dev->mem_resource[0].addr; @@ -1057,7 +1387,7 @@ eth_ixgbevf_dev_init(struct rte_eth_dev *eth_dev) */ if ((diag != IXGBE_SUCCESS) && (diag != IXGBE_ERR_INVALID_MAC_ADDR)) { PMD_INIT_LOG(ERR, "VF Initialization Failure: %d", diag); - return (diag); + return diag; } /* negotiate mailbox API version to use with the PF. */ @@ -1108,7 +1438,7 @@ eth_ixgbevf_dev_init(struct rte_eth_dev *eth_dev) default: PMD_INIT_LOG(ERR, "VF Initialization Failure: %d", diag); - return (-EIO); + return -EIO; } PMD_INIT_LOG(DEBUG, "port %d vendorID=0x%x deviceID=0x%x mac.type=%s", @@ -1118,13 +1448,45 @@ eth_ixgbevf_dev_init(struct rte_eth_dev *eth_dev) return 0; } +/* Virtual Function device uninit */ + +static int +eth_ixgbevf_dev_uninit(struct rte_eth_dev *eth_dev) +{ + struct ixgbe_hw *hw; + + PMD_INIT_FUNC_TRACE(); + + if (rte_eal_process_type() != RTE_PROC_PRIMARY) + return -EPERM; + + hw = IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private); + + if (hw->adapter_stopped == 0) + ixgbevf_dev_close(eth_dev); + + eth_dev->dev_ops = NULL; + eth_dev->rx_pkt_burst = NULL; + eth_dev->tx_pkt_burst = NULL; + + /* Disable the interrupts for VF */ + ixgbevf_intr_disable(hw); + + rte_free(eth_dev->data->mac_addrs); + eth_dev->data->mac_addrs = NULL; + + return 0; +} + static struct eth_driver rte_ixgbe_pmd = { .pci_drv = { .name = "rte_ixgbe_pmd", .id_table = pci_id_ixgbe_map, - .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC, + .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC | + RTE_PCI_DRV_DETACHABLE, }, .eth_dev_init = eth_ixgbe_dev_init, + .eth_dev_uninit = eth_ixgbe_dev_uninit, .dev_private_size = sizeof(struct ixgbe_adapter), }; @@ -1135,9 +1497,10 @@ static struct eth_driver rte_ixgbevf_pmd = { .pci_drv = { .name = "rte_ixgbevf_pmd", .id_table = pci_id_ixgbevf_map, - .drv_flags = RTE_PCI_DRV_NEED_MAPPING, + .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_DETACHABLE, }, .eth_dev_init = eth_ixgbevf_dev_init, + .eth_dev_uninit = eth_ixgbevf_dev_uninit, .dev_private_size = sizeof(struct ixgbe_adapter), }; @@ -1166,7 +1529,7 @@ rte_ixgbevf_pmd_init(const char *name __rte_unused, const char *param __rte_unus PMD_INIT_FUNC_TRACE(); rte_eth_driver_register(&rte_ixgbevf_pmd); - return (0); + return 0; } static int @@ -1204,14 +1567,27 @@ ixgbe_vlan_strip_queue_set(struct rte_eth_dev *dev, uint16_t queue, int on) ixgbe_vlan_hw_strip_disable(dev, queue); } -static void -ixgbe_vlan_tpid_set(struct rte_eth_dev *dev, uint16_t tpid) +static int +ixgbe_vlan_tpid_set(struct rte_eth_dev *dev, + enum rte_vlan_type vlan_type, + uint16_t tpid) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + int ret = 0; + + switch (vlan_type) { + case ETH_VLAN_TYPE_INNER: + /* Only the high 16-bits is valid */ + IXGBE_WRITE_REG(hw, IXGBE_EXVET, tpid << 16); + break; + default: + ret = -EINVAL; + PMD_DRV_LOG(ERR, "Unsupported vlan type %d\n", vlan_type); + break; + } - /* Only the high 16-bits is valid */ - IXGBE_WRITE_REG(hw, IXGBE_EXVET, tpid << 16); + return ret; } void @@ -1260,7 +1636,7 @@ ixgbe_vlan_hw_strip_bitmap_set(struct rte_eth_dev *dev, uint16_t queue, bool on) struct ixgbe_hwstrip *hwstrip = IXGBE_DEV_PRIVATE_TO_HWSTRIP_BITMAP(dev->data->dev_private); - if(queue >= IXGBE_MAX_RX_QUEUE_NUM) + if (queue >= IXGBE_MAX_RX_QUEUE_NUM) return; if (on) @@ -1280,7 +1656,7 @@ ixgbe_vlan_hw_strip_disable(struct rte_eth_dev *dev, uint16_t queue) if (hw->mac.type == ixgbe_mac_82598EB) { /* No queue level support */ - PMD_INIT_LOG(INFO, "82598EB not support queue level hw strip"); + PMD_INIT_LOG(NOTICE, "82598EB not support queue level hw strip"); return; } else { @@ -1304,7 +1680,7 @@ ixgbe_vlan_hw_strip_enable(struct rte_eth_dev *dev, uint16_t queue) if (hw->mac.type == ixgbe_mac_82598EB) { /* No queue level supported */ - PMD_INIT_LOG(INFO, "82598EB not support queue level hw strip"); + PMD_INIT_LOG(NOTICE, "82598EB not support queue level hw strip"); return; } else { @@ -1413,6 +1789,15 @@ ixgbe_vlan_hw_extend_enable(struct rte_eth_dev *dev) ctrl |= IXGBE_EXTENDED_VLAN; IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl); + /* Clear pooling mode of PFVTCTL. It's required by X550. */ + if (hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_X550EM_a) { + ctrl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + ctrl &= ~IXGBE_VT_CTL_POOLING_MODE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, ctrl); + } + /* * VET EXT field in the EXVET register = 0x8100 by default * So no need to change. Same to VT field of DMATXCTL register @@ -1422,21 +1807,21 @@ ixgbe_vlan_hw_extend_enable(struct rte_eth_dev *dev) static void ixgbe_vlan_offload_set(struct rte_eth_dev *dev, int mask) { - if(mask & ETH_VLAN_STRIP_MASK){ + if (mask & ETH_VLAN_STRIP_MASK) { if (dev->data->dev_conf.rxmode.hw_vlan_strip) ixgbe_vlan_hw_strip_enable_all(dev); else ixgbe_vlan_hw_strip_disable_all(dev); } - if(mask & ETH_VLAN_FILTER_MASK){ + if (mask & ETH_VLAN_FILTER_MASK) { if (dev->data->dev_conf.rxmode.hw_vlan_filter) ixgbe_vlan_hw_filter_enable(dev); else ixgbe_vlan_hw_filter_disable(dev); } - if(mask & ETH_VLAN_EXTEND_MASK){ + if (mask & ETH_VLAN_EXTEND_MASK) { if (dev->data->dev_conf.rxmode.hw_vlan_extend) ixgbe_vlan_hw_extend_enable(dev); else @@ -1451,10 +1836,196 @@ ixgbe_vmdq_vlan_hw_filter_enable(struct rte_eth_dev *dev) IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); /* VLNCTRL: enable vlan filtering and allow all vlan tags through */ uint32_t vlanctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlanctrl |= IXGBE_VLNCTRL_VFE ; /* enable vlan filters */ + vlanctrl |= IXGBE_VLNCTRL_VFE; /* enable vlan filters */ IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlanctrl); } +static int +ixgbe_check_vf_rss_rxq_num(struct rte_eth_dev *dev, uint16_t nb_rx_q) +{ + switch (nb_rx_q) { + case 1: + case 2: + RTE_ETH_DEV_SRIOV(dev).active = ETH_64_POOLS; + break; + case 4: + RTE_ETH_DEV_SRIOV(dev).active = ETH_32_POOLS; + break; + default: + return -EINVAL; + } + + RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool = nb_rx_q; + RTE_ETH_DEV_SRIOV(dev).def_pool_q_idx = dev->pci_dev->max_vfs * nb_rx_q; + + return 0; +} + +static int +ixgbe_check_mq_mode(struct rte_eth_dev *dev) +{ + struct rte_eth_conf *dev_conf = &dev->data->dev_conf; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint16_t nb_rx_q = dev->data->nb_rx_queues; + uint16_t nb_tx_q = dev->data->nb_tx_queues; + + if (RTE_ETH_DEV_SRIOV(dev).active != 0) { + /* check multi-queue mode */ + switch (dev_conf->rxmode.mq_mode) { + case ETH_MQ_RX_VMDQ_DCB: + case ETH_MQ_RX_VMDQ_DCB_RSS: + /* DCB/RSS VMDQ in SRIOV mode, not implement yet */ + PMD_INIT_LOG(ERR, "SRIOV active," + " unsupported mq_mode rx %d.", + dev_conf->rxmode.mq_mode); + return -EINVAL; + case ETH_MQ_RX_RSS: + case ETH_MQ_RX_VMDQ_RSS: + dev->data->dev_conf.rxmode.mq_mode = ETH_MQ_RX_VMDQ_RSS; + if (nb_rx_q <= RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool) + if (ixgbe_check_vf_rss_rxq_num(dev, nb_rx_q)) { + PMD_INIT_LOG(ERR, "SRIOV is active," + " invalid queue number" + " for VMDQ RSS, allowed" + " value are 1, 2 or 4."); + return -EINVAL; + } + break; + case ETH_MQ_RX_VMDQ_ONLY: + case ETH_MQ_RX_NONE: + /* if nothing mq mode configure, use default scheme */ + dev->data->dev_conf.rxmode.mq_mode = ETH_MQ_RX_VMDQ_ONLY; + if (RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool > 1) + RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool = 1; + break; + default: /* ETH_MQ_RX_DCB, ETH_MQ_RX_DCB_RSS or ETH_MQ_TX_DCB*/ + /* SRIOV only works in VMDq enable mode */ + PMD_INIT_LOG(ERR, "SRIOV is active," + " wrong mq_mode rx %d.", + dev_conf->rxmode.mq_mode); + return -EINVAL; + } + + switch (dev_conf->txmode.mq_mode) { + case ETH_MQ_TX_VMDQ_DCB: + /* DCB VMDQ in SRIOV mode, not implement yet */ + PMD_INIT_LOG(ERR, "SRIOV is active," + " unsupported VMDQ mq_mode tx %d.", + dev_conf->txmode.mq_mode); + return -EINVAL; + default: /* ETH_MQ_TX_VMDQ_ONLY or ETH_MQ_TX_NONE */ + dev->data->dev_conf.txmode.mq_mode = ETH_MQ_TX_VMDQ_ONLY; + break; + } + + /* check valid queue number */ + if ((nb_rx_q > RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool) || + (nb_tx_q > RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool)) { + PMD_INIT_LOG(ERR, "SRIOV is active," + " nb_rx_q=%d nb_tx_q=%d queue number" + " must be less than or equal to %d.", + nb_rx_q, nb_tx_q, + RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool); + return -EINVAL; + } + } else { + if (dev_conf->rxmode.mq_mode == ETH_MQ_RX_VMDQ_DCB_RSS) { + PMD_INIT_LOG(ERR, "VMDQ+DCB+RSS mq_mode is" + " not supported."); + return -EINVAL; + } + /* check configuration for vmdb+dcb mode */ + if (dev_conf->rxmode.mq_mode == ETH_MQ_RX_VMDQ_DCB) { + const struct rte_eth_vmdq_dcb_conf *conf; + + if (nb_rx_q != IXGBE_VMDQ_DCB_NB_QUEUES) { + PMD_INIT_LOG(ERR, "VMDQ+DCB, nb_rx_q != %d.", + IXGBE_VMDQ_DCB_NB_QUEUES); + return -EINVAL; + } + conf = &dev_conf->rx_adv_conf.vmdq_dcb_conf; + if (!(conf->nb_queue_pools == ETH_16_POOLS || + conf->nb_queue_pools == ETH_32_POOLS)) { + PMD_INIT_LOG(ERR, "VMDQ+DCB selected," + " nb_queue_pools must be %d or %d.", + ETH_16_POOLS, ETH_32_POOLS); + return -EINVAL; + } + } + if (dev_conf->txmode.mq_mode == ETH_MQ_TX_VMDQ_DCB) { + const struct rte_eth_vmdq_dcb_tx_conf *conf; + + if (nb_tx_q != IXGBE_VMDQ_DCB_NB_QUEUES) { + PMD_INIT_LOG(ERR, "VMDQ+DCB, nb_tx_q != %d", + IXGBE_VMDQ_DCB_NB_QUEUES); + return -EINVAL; + } + conf = &dev_conf->tx_adv_conf.vmdq_dcb_tx_conf; + if (!(conf->nb_queue_pools == ETH_16_POOLS || + conf->nb_queue_pools == ETH_32_POOLS)) { + PMD_INIT_LOG(ERR, "VMDQ+DCB selected," + " nb_queue_pools != %d and" + " nb_queue_pools != %d.", + ETH_16_POOLS, ETH_32_POOLS); + return -EINVAL; + } + } + + /* For DCB mode check our configuration before we go further */ + if (dev_conf->rxmode.mq_mode == ETH_MQ_RX_DCB) { + const struct rte_eth_dcb_rx_conf *conf; + + if (nb_rx_q != IXGBE_DCB_NB_QUEUES) { + PMD_INIT_LOG(ERR, "DCB selected, nb_rx_q != %d.", + IXGBE_DCB_NB_QUEUES); + return -EINVAL; + } + conf = &dev_conf->rx_adv_conf.dcb_rx_conf; + if (!(conf->nb_tcs == ETH_4_TCS || + conf->nb_tcs == ETH_8_TCS)) { + PMD_INIT_LOG(ERR, "DCB selected, nb_tcs != %d" + " and nb_tcs != %d.", + ETH_4_TCS, ETH_8_TCS); + return -EINVAL; + } + } + + if (dev_conf->txmode.mq_mode == ETH_MQ_TX_DCB) { + const struct rte_eth_dcb_tx_conf *conf; + + if (nb_tx_q != IXGBE_DCB_NB_QUEUES) { + PMD_INIT_LOG(ERR, "DCB, nb_tx_q != %d.", + IXGBE_DCB_NB_QUEUES); + return -EINVAL; + } + conf = &dev_conf->tx_adv_conf.dcb_tx_conf; + if (!(conf->nb_tcs == ETH_4_TCS || + conf->nb_tcs == ETH_8_TCS)) { + PMD_INIT_LOG(ERR, "DCB selected, nb_tcs != %d" + " and nb_tcs != %d.", + ETH_4_TCS, ETH_8_TCS); + return -EINVAL; + } + } + + /* + * When DCB/VT is off, maximum number of queues changes, + * except for 82598EB, which remains constant. + */ + if (dev_conf->txmode.mq_mode == ETH_MQ_TX_NONE && + hw->mac.type != ixgbe_mac_82598EB) { + if (nb_tx_q > IXGBE_NONE_MODE_TX_NB_QUEUES) { + PMD_INIT_LOG(ERR, + "Neither VT nor DCB are enabled, " + "nb_tx_q > %d.", + IXGBE_NONE_MODE_TX_NB_QUEUES); + return -EINVAL; + } + } + } + return 0; +} + static int ixgbe_dev_configure(struct rte_eth_dev *dev) { @@ -1462,8 +2033,16 @@ ixgbe_dev_configure(struct rte_eth_dev *dev) IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private); struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)dev->data->dev_private; + int ret; PMD_INIT_FUNC_TRACE(); + /* multipe queue mode checking */ + ret = ixgbe_check_mq_mode(dev); + if (ret != 0) { + PMD_DRV_LOG(ERR, "ixgbe_check_mq_mode fails with %d.", + ret); + return ret; + } /* set flag to update link status after init */ intr->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; @@ -1478,6 +2057,25 @@ ixgbe_dev_configure(struct rte_eth_dev *dev) return 0; } +static void +ixgbe_dev_phy_intr_setup(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_interrupt *intr = + IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private); + uint32_t gpie; + + /* only set up it on X550EM_X */ + if (hw->mac.type == ixgbe_mac_X550EM_x) { + gpie = IXGBE_READ_REG(hw, IXGBE_GPIE); + gpie |= IXGBE_SDP0_GPIEN_X550EM_x; + IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); + if (hw->phy.type == ixgbe_phy_x550em_ext_t) + intr->mask |= IXGBE_EICR_GPI_SDP0_X550EM_x; + } +} + /* * Configure device link speed and setup link. * It returns 0 on success. @@ -1489,6 +2087,8 @@ ixgbe_dev_start(struct rte_eth_dev *dev) IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); struct ixgbe_vf_info *vfinfo = *IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private); + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; + uint32_t intr_vector = 0; int err, link_up = 0, negotiate = 0; uint32_t speed = 0; int mask = 0; @@ -1506,8 +2106,11 @@ ixgbe_dev_start(struct rte_eth_dev *dev) return -EINVAL; } + /* disable uio/vfio intr/eventfd mapping */ + rte_intr_disable(intr_handle); + /* stop adapter */ - hw->adapter_stopped = FALSE; + hw->adapter_stopped = 0; ixgbe_stop_adapter(hw); /* reinitialize adapter @@ -1521,6 +2124,36 @@ ixgbe_dev_start(struct rte_eth_dev *dev) /* configure PF module if SRIOV enabled */ ixgbe_pf_host_configure(dev); + ixgbe_dev_phy_intr_setup(dev); + + /* check and configure queue intr-vector mapping */ + if ((rte_intr_cap_multiple(intr_handle) || + !RTE_ETH_DEV_SRIOV(dev).active) && + dev->data->dev_conf.intr_conf.rxq != 0) { + intr_vector = dev->data->nb_rx_queues; + if (intr_vector > IXGBE_MAX_INTR_QUEUE_NUM) { + PMD_INIT_LOG(ERR, "At most %d intr queues supported", + IXGBE_MAX_INTR_QUEUE_NUM); + return -ENOTSUP; + } + if (rte_intr_efd_enable(intr_handle, intr_vector)) + return -1; + } + + if (rte_intr_dp_is_en(intr_handle) && !intr_handle->intr_vec) { + intr_handle->intr_vec = + rte_zmalloc("intr_vec", + dev->data->nb_rx_queues * sizeof(int), 0); + if (intr_handle->intr_vec == NULL) { + PMD_INIT_LOG(ERR, "Failed to allocate %d rx_queues" + " intr_vec\n", dev->data->nb_rx_queues); + return -ENOMEM; + } + } + + /* confiugre msix for sleep until rx interrupt */ + ixgbe_configure_msix(dev); + /* initialize transmission unit */ ixgbe_dev_tx_init(dev); @@ -1597,9 +2230,26 @@ ixgbe_dev_start(struct rte_eth_dev *dev) skip_link_setup: - /* check if lsc interrupt is enabled */ - if (dev->data->dev_conf.intr_conf.lsc != 0) - ixgbe_dev_lsc_interrupt_setup(dev); + if (rte_intr_allow_others(intr_handle)) { + /* check if lsc interrupt is enabled */ + if (dev->data->dev_conf.intr_conf.lsc != 0) + ixgbe_dev_lsc_interrupt_setup(dev); + } else { + rte_intr_callback_unregister(intr_handle, + ixgbe_dev_interrupt_handler, + (void *)dev); + if (dev->data->dev_conf.intr_conf.lsc != 0) + PMD_INIT_LOG(INFO, "lsc won't enable because of" + " no intr multiplex\n"); + } + + /* check if rxq interrupt is enabled */ + if (dev->data->dev_conf.intr_conf.rxq != 0 && + rte_intr_dp_is_en(intr_handle)) + ixgbe_dev_rxq_interrupt_setup(dev); + + /* enable uio/vfio intr/eventfd mapping */ + rte_intr_enable(intr_handle); /* resume enabled intr since hw reset */ ixgbe_enable_intr(dev); @@ -1634,7 +2284,7 @@ skip_link_setup: ixgbe_restore_statistics_mapping(dev); - return (0); + return 0; error: PMD_INIT_LOG(ERR, "failure in ixgbe_dev_start(): %d", err); @@ -1656,6 +2306,7 @@ ixgbe_dev_stop(struct rte_eth_dev *dev) struct ixgbe_filter_info *filter_info = IXGBE_DEV_PRIVATE_TO_FILTER_INFO(dev->data->dev_private); struct ixgbe_5tuple_filter *p_5tuple, *p_5tuple_next; + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; int vf; PMD_INIT_FUNC_TRACE(); @@ -1665,7 +2316,7 @@ ixgbe_dev_stop(struct rte_eth_dev *dev) /* reset the NIC */ ixgbe_pf_reset_hw(hw); - hw->adapter_stopped = FALSE; + hw->adapter_stopped = 0; /* stop adapter */ ixgbe_stop_adapter(hw); @@ -1703,6 +2354,18 @@ ixgbe_dev_stop(struct rte_eth_dev *dev) memset(filter_info->fivetuple_mask, 0, sizeof(uint32_t) * IXGBE_5TUPLE_ARRAY_SIZE); + if (!rte_intr_allow_others(intr_handle)) + /* resume to the default handler */ + rte_intr_callback_register(intr_handle, + ixgbe_dev_interrupt_handler, + (void *)dev); + + /* Clean datapath event and queue/vec mapping */ + rte_intr_efd_disable(intr_handle); + if (intr_handle->intr_vec != NULL) { + rte_free(intr_handle->intr_vec); + intr_handle->intr_vec = NULL; + } } /* @@ -1781,29 +2444,29 @@ ixgbe_dev_close(struct rte_eth_dev *dev) ixgbe_dev_stop(dev); hw->adapter_stopped = 1; + ixgbe_dev_free_queues(dev); + ixgbe_disable_pcie_master(hw); /* reprogram the RAR[0] in case user changed it. */ ixgbe_set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV); } -/* - * This function is based on ixgbe_update_stats_counters() in base/ixgbe.c - */ static void -ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) +ixgbe_read_stats_registers(struct ixgbe_hw *hw, + struct ixgbe_hw_stats *hw_stats, + uint64_t *total_missed_rx, uint64_t *total_qbrc, + uint64_t *total_qprc, uint64_t *total_qprdc) { - struct ixgbe_hw *hw = - IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - struct ixgbe_hw_stats *hw_stats = - IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); uint32_t bprc, lxon, lxoff, total; - uint64_t total_missed_rx, total_qbrc, total_qprc; + uint32_t delta_gprc = 0; unsigned i; - - total_missed_rx = 0; - total_qbrc = 0; - total_qprc = 0; + /* Workaround for RX byte count not including CRC bytes when CRC ++ * strip is enabled. CRC bytes are removed from counters when crc_strip + * is disabled. ++ */ + int crc_strip = (IXGBE_READ_REG(hw, IXGBE_HLREG0) & + IXGBE_HLREG0_RXCRCSTRP); hw_stats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS); hw_stats->illerrc += IXGBE_READ_REG(hw, IXGBE_ILLERRC); @@ -1816,41 +2479,62 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) /* global total per queue */ hw_stats->mpc[i] += mp; /* Running comprehensive total for stats display */ - total_missed_rx += hw_stats->mpc[i]; - if (hw->mac.type == ixgbe_mac_82598EB) + *total_missed_rx += hw_stats->mpc[i]; + if (hw->mac.type == ixgbe_mac_82598EB) { hw_stats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i)); + hw_stats->pxonrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXONRXC(i)); + hw_stats->pxoffrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); + } else { + hw_stats->pxonrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); + hw_stats->pxoffrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); + hw_stats->pxon2offc[i] += + IXGBE_READ_REG(hw, IXGBE_PXON2OFFCNT(i)); + } hw_stats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i)); - hw_stats->pxonrxc[i] += - IXGBE_READ_REG(hw, IXGBE_PXONRXC(i)); hw_stats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i)); - hw_stats->pxoffrxc[i] += - IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); - hw_stats->pxon2offc[i] += - IXGBE_READ_REG(hw, IXGBE_PXON2OFFCNT(i)); } for (i = 0; i < IXGBE_QUEUE_STAT_COUNTERS; i++) { - hw_stats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i)); - hw_stats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i)); + uint32_t delta_qprc = IXGBE_READ_REG(hw, IXGBE_QPRC(i)); + uint32_t delta_qptc = IXGBE_READ_REG(hw, IXGBE_QPTC(i)); + uint32_t delta_qprdc = IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); + + delta_gprc += delta_qprc; + + hw_stats->qprc[i] += delta_qprc; + hw_stats->qptc[i] += delta_qptc; + hw_stats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); hw_stats->qbrc[i] += ((uint64_t)IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)) << 32); + if (crc_strip == 0) + hw_stats->qbrc[i] -= delta_qprc * ETHER_CRC_LEN; + hw_stats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); hw_stats->qbtc[i] += ((uint64_t)IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)) << 32); - hw_stats->qprdc[i] += IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); - total_qprc += hw_stats->qprc[i]; - total_qbrc += hw_stats->qbrc[i]; + hw_stats->qprdc[i] += delta_qprdc; + *total_qprdc += hw_stats->qprdc[i]; + + *total_qprc += hw_stats->qprc[i]; + *total_qbrc += hw_stats->qbrc[i]; } hw_stats->mlfc += IXGBE_READ_REG(hw, IXGBE_MLFC); hw_stats->mrfc += IXGBE_READ_REG(hw, IXGBE_MRFC); hw_stats->rlec += IXGBE_READ_REG(hw, IXGBE_RLEC); - /* Note that gprc counts missed packets */ - hw_stats->gprc += IXGBE_READ_REG(hw, IXGBE_GPRC); + /* + * An errata states that gprc actually counts good + missed packets: + * Workaround to set gprc to summated queue packet receives + */ + hw_stats->gprc = *total_qprc; if (hw->mac.type != ixgbe_mac_82598EB) { hw_stats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL); @@ -1869,6 +2553,18 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) hw_stats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH); hw_stats->tor += IXGBE_READ_REG(hw, IXGBE_TORH); } + uint64_t old_tpr = hw_stats->tpr; + + hw_stats->tpr += IXGBE_READ_REG(hw, IXGBE_TPR); + hw_stats->tpt += IXGBE_READ_REG(hw, IXGBE_TPT); + + if (crc_strip == 0) + hw_stats->gorc -= delta_gprc * ETHER_CRC_LEN; + + uint64_t delta_gptc = IXGBE_READ_REG(hw, IXGBE_GPTC); + hw_stats->gptc += delta_gptc; + hw_stats->gotc -= delta_gptc * ETHER_CRC_LEN; + hw_stats->tor -= (hw_stats->tpr - old_tpr) * ETHER_CRC_LEN; /* * Workaround: mprc hardware is incorrectly counting @@ -1893,7 +2589,6 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) hw_stats->lxofftxc += lxoff; total = lxon + lxoff; - hw_stats->gptc += IXGBE_READ_REG(hw, IXGBE_GPTC); hw_stats->mptc += IXGBE_READ_REG(hw, IXGBE_MPTC); hw_stats->ptc64 += IXGBE_READ_REG(hw, IXGBE_PTC64); hw_stats->gptc -= total; @@ -1908,8 +2603,6 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) hw_stats->mngprc += IXGBE_READ_REG(hw, IXGBE_MNGPRC); hw_stats->mngpdc += IXGBE_READ_REG(hw, IXGBE_MNGPDC); hw_stats->mngptc += IXGBE_READ_REG(hw, IXGBE_MNGPTC); - hw_stats->tpr += IXGBE_READ_REG(hw, IXGBE_TPR); - hw_stats->tpt += IXGBE_READ_REG(hw, IXGBE_TPT); hw_stats->ptc127 += IXGBE_READ_REG(hw, IXGBE_PTC127); hw_stats->ptc255 += IXGBE_READ_REG(hw, IXGBE_PTC255); hw_stats->ptc511 += IXGBE_READ_REG(hw, IXGBE_PTC511); @@ -1928,6 +2621,32 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) hw_stats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC); } + /* Flow Director Stats registers */ + hw_stats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH); + hw_stats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS); +} + +/* + * This function is based on ixgbe_update_stats_counters() in ixgbe/ixgbe.c + */ +static void +ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) +{ + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_hw_stats *hw_stats = + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + uint64_t total_missed_rx, total_qbrc, total_qprc, total_qprdc; + unsigned i; + + total_missed_rx = 0; + total_qbrc = 0; + total_qprc = 0; + total_qprdc = 0; + + ixgbe_read_stats_registers(hw, hw_stats, &total_missed_rx, &total_qbrc, + &total_qprc, &total_qprdc); + if (stats == NULL) return; @@ -1936,7 +2655,6 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) stats->ibytes = total_qbrc; stats->opackets = hw_stats->gptc; stats->obytes = hw_stats->gotc; - stats->imcasts = hw_stats->mprc; for (i = 0; i < IXGBE_QUEUE_STAT_COUNTERS; i++) { stats->q_ipackets[i] = hw_stats->qprc[i]; @@ -1947,28 +2665,20 @@ ixgbe_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) } /* Rx Errors */ - stats->ibadcrc = hw_stats->crcerrs; - stats->ibadlen = hw_stats->rlec + hw_stats->ruc + hw_stats->roc; stats->imissed = total_missed_rx; - stats->ierrors = stats->ibadcrc + - stats->ibadlen + - stats->imissed + - hw_stats->illerrc + hw_stats->errbc; + stats->ierrors = hw_stats->crcerrs + + hw_stats->mspdc + + hw_stats->rlec + + hw_stats->ruc + + hw_stats->roc + + hw_stats->illerrc + + hw_stats->errbc + + hw_stats->rfc + + hw_stats->fccrc + + hw_stats->fclast; /* Tx Errors */ stats->oerrors = 0; - - /* XON/XOFF pause frames */ - stats->tx_pause_xon = hw_stats->lxontxc; - stats->rx_pause_xon = hw_stats->lxonrxc; - stats->tx_pause_xoff = hw_stats->lxofftxc; - stats->rx_pause_xoff = hw_stats->lxoffrxc; - - /* Flow Director Stats registers */ - hw_stats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH); - hw_stats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS); - stats->fdirmatch = hw_stats->fdirmatch; - stats->fdirmiss = hw_stats->fdirmiss; } static void @@ -1984,24 +2694,115 @@ ixgbe_dev_stats_reset(struct rte_eth_dev *dev) memset(stats, 0, sizeof(*stats)); } -static void -ixgbevf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) +/* This function calculates the number of xstats based on the current config */ +static unsigned +ixgbe_xstats_calc_num(void) { + return IXGBE_NB_HW_STATS + (IXGBE_NB_RXQ_PRIO_STATS * 8) + + (IXGBE_NB_TXQ_PRIO_STATS * 8); +} + +static int +ixgbe_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstats *xstats, + unsigned n) { - struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - struct ixgbevf_hw_stats *hw_stats = (struct ixgbevf_hw_stats*) - IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_hw_stats *hw_stats = + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + uint64_t total_missed_rx, total_qbrc, total_qprc, total_qprdc; + unsigned i, stat, count = 0; - /* Good Rx packet, include VF loopback */ - UPDATE_VF_STAT(IXGBE_VFGPRC, - hw_stats->last_vfgprc, hw_stats->vfgprc); + count = ixgbe_xstats_calc_num(); - /* Good Rx octets, include VF loopback */ - UPDATE_VF_STAT_36BIT(IXGBE_VFGORC_LSB, IXGBE_VFGORC_MSB, - hw_stats->last_vfgorc, hw_stats->vfgorc); + if (n < count) + return count; - /* Good Tx packet, include VF loopback */ - UPDATE_VF_STAT(IXGBE_VFGPTC, - hw_stats->last_vfgptc, hw_stats->vfgptc); + total_missed_rx = 0; + total_qbrc = 0; + total_qprc = 0; + total_qprdc = 0; + + ixgbe_read_stats_registers(hw, hw_stats, &total_missed_rx, &total_qbrc, + &total_qprc, &total_qprdc); + + /* If this is a reset xstats is NULL, and we have cleared the + * registers by reading them. + */ + if (!xstats) + return 0; + + /* Extended stats from ixgbe_hw_stats */ + count = 0; + for (i = 0; i < IXGBE_NB_HW_STATS; i++) { + snprintf(xstats[count].name, sizeof(xstats[count].name), "%s", + rte_ixgbe_stats_strings[i].name); + xstats[count].value = *(uint64_t *)(((char *)hw_stats) + + rte_ixgbe_stats_strings[i].offset); + count++; + } + + /* RX Priority Stats */ + for (stat = 0; stat < IXGBE_NB_RXQ_PRIO_STATS; stat++) { + for (i = 0; i < 8; i++) { + snprintf(xstats[count].name, sizeof(xstats[count].name), + "rx_priority%u_%s", i, + rte_ixgbe_rxq_strings[stat].name); + xstats[count].value = *(uint64_t *)(((char *)hw_stats) + + rte_ixgbe_rxq_strings[stat].offset + + (sizeof(uint64_t) * i)); + count++; + } + } + + /* TX Priority Stats */ + for (stat = 0; stat < IXGBE_NB_TXQ_PRIO_STATS; stat++) { + for (i = 0; i < 8; i++) { + snprintf(xstats[count].name, sizeof(xstats[count].name), + "tx_priority%u_%s", i, + rte_ixgbe_txq_strings[stat].name); + xstats[count].value = *(uint64_t *)(((char *)hw_stats) + + rte_ixgbe_txq_strings[stat].offset + + (sizeof(uint64_t) * i)); + count++; + } + } + + return count; +} + +static void +ixgbe_dev_xstats_reset(struct rte_eth_dev *dev) +{ + struct ixgbe_hw_stats *stats = + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + + unsigned count = ixgbe_xstats_calc_num(); + + /* HW registers are cleared on read */ + ixgbe_dev_xstats_get(dev, NULL, count); + + /* Reset software totals */ + memset(stats, 0, sizeof(*stats)); +} + +static void +ixgbevf_update_stats(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbevf_hw_stats *hw_stats = (struct ixgbevf_hw_stats*) + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + + /* Good Rx packet, include VF loopback */ + UPDATE_VF_STAT(IXGBE_VFGPRC, + hw_stats->last_vfgprc, hw_stats->vfgprc); + + /* Good Rx octets, include VF loopback */ + UPDATE_VF_STAT_36BIT(IXGBE_VFGORC_LSB, IXGBE_VFGORC_MSB, + hw_stats->last_vfgorc, hw_stats->vfgorc); + + /* Good Tx packet, include VF loopback */ + UPDATE_VF_STAT(IXGBE_VFGPTC, + hw_stats->last_vfgptc, hw_stats->vfgptc); /* Good Tx octets, include VF loopback */ UPDATE_VF_STAT_36BIT(IXGBE_VFGOTC_LSB, IXGBE_VFGOTC_MSB, @@ -2010,6 +2811,42 @@ ixgbevf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) /* Rx Multicst Packet */ UPDATE_VF_STAT(IXGBE_VFMPRC, hw_stats->last_vfmprc, hw_stats->vfmprc); +} + +static int +ixgbevf_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstats *xstats, + unsigned n) +{ + struct ixgbevf_hw_stats *hw_stats = (struct ixgbevf_hw_stats *) + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + unsigned i; + + if (n < IXGBEVF_NB_XSTATS) + return IXGBEVF_NB_XSTATS; + + ixgbevf_update_stats(dev); + + if (!xstats) + return 0; + + /* Extended stats */ + for (i = 0; i < IXGBEVF_NB_XSTATS; i++) { + snprintf(xstats[i].name, sizeof(xstats[i].name), + "%s", rte_ixgbevf_stats_strings[i].name); + xstats[i].value = *(uint64_t *)(((char *)hw_stats) + + rte_ixgbevf_stats_strings[i].offset); + } + + return IXGBEVF_NB_XSTATS; +} + +static void +ixgbevf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) +{ + struct ixgbevf_hw_stats *hw_stats = (struct ixgbevf_hw_stats *) + IXGBE_DEV_PRIVATE_TO_STATS(dev->data->dev_private); + + ixgbevf_update_stats(dev); if (stats == NULL) return; @@ -2019,6 +2856,7 @@ ixgbevf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) stats->opackets = hw_stats->vfgptc; stats->obytes = hw_stats->vfgotc; stats->imcasts = hw_stats->vfmprc; + /* stats->imcasts should be removed as imcasts is deprecated */ } static void @@ -2043,9 +2881,19 @@ static void ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct rte_eth_conf *dev_conf = &dev->data->dev_conf; dev_info->max_rx_queues = (uint16_t)hw->mac.max_rx_queues; dev_info->max_tx_queues = (uint16_t)hw->mac.max_tx_queues; + if (RTE_ETH_DEV_SRIOV(dev).active == 0) { + /* + * When DCB/VT is off, maximum number of queues changes, + * except for 82598EB, which remains constant. + */ + if (dev_conf->txmode.mq_mode == ETH_MQ_TX_NONE && + hw->mac.type != ixgbe_mac_82598EB) + dev_info->max_tx_queues = IXGBE_NONE_MODE_TX_NB_QUEUES; + } dev_info->min_rx_bufsize = 1024; /* cf BSIZEPACKET in SRRCTL register */ dev_info->max_rx_pktlen = 15872; /* includes CRC, cf MAXFRS register */ dev_info->max_mac_addrs = hw->mac.num_rar_entries; @@ -2071,6 +2919,11 @@ ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) !RTE_ETH_DEV_SRIOV(dev).active) dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO; + if (hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_X550EM_a) + dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM; + dev_info->tx_offload_capa = DEV_TX_OFFLOAD_VLAN_INSERT | DEV_TX_OFFLOAD_IPV4_CKSUM | @@ -2079,6 +2932,11 @@ ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) DEV_TX_OFFLOAD_SCTP_CKSUM | DEV_TX_OFFLOAD_TCP_TSO; + if (hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_X550EM_a) + dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM; + dev_info->default_rxconf = (struct rte_eth_rxconf) { .rx_thresh = { .pthresh = IXGBE_DEFAULT_RX_PTHRESH, @@ -2100,11 +2958,48 @@ ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) .txq_flags = ETH_TXQ_FLAGS_NOMULTSEGS | ETH_TXQ_FLAGS_NOOFFLOADS, }; + + dev_info->rx_desc_lim = rx_desc_lim; + dev_info->tx_desc_lim = tx_desc_lim; + dev_info->hash_key_size = IXGBE_HKEY_MAX_INDEX * sizeof(uint32_t); - dev_info->reta_size = ETH_RSS_RETA_SIZE_128; + dev_info->reta_size = ixgbe_reta_size_get(hw->mac.type); dev_info->flow_type_rss_offloads = IXGBE_RSS_OFFLOAD_ALL; } +static const uint32_t * +ixgbe_dev_supported_ptypes_get(struct rte_eth_dev *dev) +{ + static const uint32_t ptypes[] = { + /* For non-vec functions, + * refers to ixgbe_rxd_pkt_info_to_pkt_type(); + * for vec functions, + * refers to _recv_raw_pkts_vec(). + */ + RTE_PTYPE_L2_ETHER, + RTE_PTYPE_L3_IPV4, + RTE_PTYPE_L3_IPV4_EXT, + RTE_PTYPE_L3_IPV6, + RTE_PTYPE_L3_IPV6_EXT, + RTE_PTYPE_L4_SCTP, + RTE_PTYPE_L4_TCP, + RTE_PTYPE_L4_UDP, + RTE_PTYPE_TUNNEL_IP, + RTE_PTYPE_INNER_L3_IPV6, + RTE_PTYPE_INNER_L3_IPV6_EXT, + RTE_PTYPE_INNER_L4_TCP, + RTE_PTYPE_INNER_L4_UDP, + RTE_PTYPE_UNKNOWN + }; + + if (dev->rx_pkt_burst == ixgbe_recv_pkts || + dev->rx_pkt_burst == ixgbe_recv_pkts_lro_single_alloc || + dev->rx_pkt_burst == ixgbe_recv_pkts_lro_bulk_alloc || + dev->rx_pkt_burst == ixgbe_recv_pkts_bulk_alloc) + return ptypes; + return NULL; +} + static void ixgbevf_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) @@ -2130,7 +3025,8 @@ ixgbevf_dev_info_get(struct rte_eth_dev *dev, DEV_TX_OFFLOAD_IPV4_CKSUM | DEV_TX_OFFLOAD_UDP_CKSUM | DEV_TX_OFFLOAD_TCP_CKSUM | - DEV_TX_OFFLOAD_SCTP_CKSUM; + DEV_TX_OFFLOAD_SCTP_CKSUM | + DEV_TX_OFFLOAD_TCP_TSO; dev_info->default_rxconf = (struct rte_eth_rxconf) { .rx_thresh = { @@ -2153,6 +3049,9 @@ ixgbevf_dev_info_get(struct rte_eth_dev *dev, .txq_flags = ETH_TXQ_FLAGS_NOMULTSEGS | ETH_TXQ_FLAGS_NOOFFLOADS, }; + + dev_info->rx_desc_lim = rx_desc_lim; + dev_info->tx_desc_lim = tx_desc_lim; } /* return 0 means link status changed, -1 means not changed */ @@ -2165,7 +3064,7 @@ ixgbe_dev_link_update(struct rte_eth_dev *dev, int wait_to_complete) int link_up; int diag; - link.link_status = 0; + link.link_status = ETH_LINK_DOWN; link.link_speed = 0; link.link_duplex = 0; memset(&old, 0, sizeof(old)); @@ -2194,7 +3093,7 @@ ixgbe_dev_link_update(struct rte_eth_dev *dev, int wait_to_complete) return -1; return 0; } - link.link_status = 1; + link.link_status = ETH_LINK_UP; link.link_duplex = ETH_LINK_FULL_DUPLEX; switch (link_speed) { @@ -2298,6 +3197,28 @@ ixgbe_dev_lsc_interrupt_setup(struct rte_eth_dev *dev) return 0; } +/** + * It clears the interrupt causes and enables the interrupt. + * It will be called once only during nic initialized. + * + * @param dev + * Pointer to struct rte_eth_dev. + * + * @return + * - On success, zero. + * - On failure, a negative value. + */ +static int +ixgbe_dev_rxq_interrupt_setup(struct rte_eth_dev *dev) +{ + struct ixgbe_interrupt *intr = + IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private); + + intr->mask |= IXGBE_EICR_RTX_QUEUE; + + return 0; +} + /* * It reads ICR and sets flag (IXGBE_EICR_LSC) for the link_update. * @@ -2321,17 +3242,22 @@ ixgbe_dev_interrupt_get_status(struct rte_eth_dev *dev) /* read-on-clear nic registers here */ eicr = IXGBE_READ_REG(hw, IXGBE_EICR); - PMD_DRV_LOG(INFO, "eicr %x", eicr); + PMD_DRV_LOG(DEBUG, "eicr %x", eicr); intr->flags = 0; - if (eicr & IXGBE_EICR_LSC) { - /* set flag for async link update */ + + /* set flag for async link update */ + if (eicr & IXGBE_EICR_LSC) intr->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; - } if (eicr & IXGBE_EICR_MAILBOX) intr->flags |= IXGBE_FLAG_MAILBOX; + if (hw->mac.type == ixgbe_mac_X550EM_x && + hw->phy.type == ixgbe_phy_x550em_ext_t && + (eicr & IXGBE_EICR_GPI_SDP0_X550EM_x)) + intr->flags |= IXGBE_FLAG_PHY_INTERRUPT; + return 0; } @@ -2362,7 +3288,7 @@ ixgbe_dev_link_status_print(struct rte_eth_dev *dev) PMD_INIT_LOG(INFO, " Port %d: Link Down", (int)(dev->data->port_id)); } - PMD_INIT_LOG(INFO, "PCI Address: %04d:%02d:%02d:%d", + PMD_INIT_LOG(DEBUG, "PCI Address: %04d:%02d:%02d:%d", dev->pci_dev->addr.domain, dev->pci_dev->addr.bus, dev->pci_dev->addr.devid, @@ -2387,6 +3313,8 @@ ixgbe_dev_interrupt_action(struct rte_eth_dev *dev) int64_t timeout; struct rte_eth_link link; int intr_enable_delay = false; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); PMD_DRV_LOG(DEBUG, "intr action type %d", intr->flags); @@ -2395,6 +3323,11 @@ ixgbe_dev_interrupt_action(struct rte_eth_dev *dev) intr->flags &= ~IXGBE_FLAG_MAILBOX; } + if (intr->flags & IXGBE_FLAG_PHY_INTERRUPT) { + ixgbe_handle_lasi(hw); + intr->flags &= ~IXGBE_FLAG_PHY_INTERRUPT; + } + if (intr->flags & IXGBE_FLAG_NEED_LINK_UPDATE) { /* get the link status before link update, for predicting later */ memset(&link, 0, sizeof(link)); @@ -2458,6 +3391,11 @@ ixgbe_dev_interrupt_delayed_handler(void *param) if (eicr & IXGBE_EICR_MAILBOX) ixgbe_pf_mbx_process(dev); + if (intr->flags & IXGBE_FLAG_PHY_INTERRUPT) { + ixgbe_handle_lasi(hw); + intr->flags &= ~IXGBE_FLAG_PHY_INTERRUPT; + } + if (intr->flags & IXGBE_FLAG_NEED_LINK_UPDATE) { ixgbe_dev_link_update(dev, 0); intr->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; @@ -2484,9 +3422,10 @@ ixgbe_dev_interrupt_delayed_handler(void *param) */ static void ixgbe_dev_interrupt_handler(__rte_unused struct rte_intr_handle *handle, - void *param) + void *param) { struct rte_eth_dev *dev = (struct rte_eth_dev *)param; + ixgbe_dev_interrupt_get_status(dev); ixgbe_dev_interrupt_action(dev); } @@ -2497,7 +3436,7 @@ ixgbe_dev_led_on(struct rte_eth_dev *dev) struct ixgbe_hw *hw; hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - return (ixgbe_led_on(hw, 0) == IXGBE_SUCCESS ? 0 : -ENOTSUP); + return ixgbe_led_on(hw, 0) == IXGBE_SUCCESS ? 0 : -ENOTSUP; } static int @@ -2506,7 +3445,7 @@ ixgbe_dev_led_off(struct rte_eth_dev *dev) struct ixgbe_hw *hw; hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - return (ixgbe_led_off(hw, 0) == IXGBE_SUCCESS ? 0 : -ENOTSUP); + return ixgbe_led_off(hw, 0) == IXGBE_SUCCESS ? 0 : -ENOTSUP; } static int @@ -2588,7 +3527,7 @@ ixgbe_flow_ctrl_set(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf) (fc_conf->high_water < fc_conf->low_water)) { PMD_INIT_LOG(ERR, "Invalid high/low water setup value in KB"); PMD_INIT_LOG(ERR, "High_water must <= 0x%x", max_high_water); - return (-EINVAL); + return -EINVAL; } hw->fc.requested_mode = rte_fcmode_2_ixgbe_fcmode[fc_conf->mode]; @@ -2649,13 +3588,13 @@ ixgbe_dcb_pfc_enable_generic(struct ixgbe_hw *hw,uint8_t tc_num) /* Low water mark of zero causes XOFF floods */ if (hw->fc.current_mode & ixgbe_fc_tx_pause) { /* High/Low water can not be 0 */ - if( (!hw->fc.high_water[tc_num])|| (!hw->fc.low_water[tc_num])) { + if ((!hw->fc.high_water[tc_num]) || (!hw->fc.low_water[tc_num])) { PMD_INIT_LOG(ERR, "Invalid water mark configuration"); ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; goto out; } - if(hw->fc.low_water[tc_num] >= hw->fc.high_water[tc_num]) { + if (hw->fc.low_water[tc_num] >= hw->fc.high_water[tc_num]) { PMD_INIT_LOG(ERR, "Invalid water mark configuration"); ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; goto out; @@ -2769,7 +3708,7 @@ ixgbe_dcb_pfc_enable(struct rte_eth_dev *dev,uint8_t tc_num) struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); int32_t ret_val = IXGBE_NOT_IMPLEMENTED; - if(hw->mac.type != ixgbe_mac_82598EB) { + if (hw->mac.type != ixgbe_mac_82598EB) { ret_val = ixgbe_dcb_pfc_enable_generic(hw,tc_num); } return ret_val; @@ -2810,7 +3749,7 @@ ixgbe_priority_flow_ctrl_set(struct rte_eth_dev *dev, struct rte_eth_pfc_conf *p (pfc_conf->fc.high_water <= pfc_conf->fc.low_water)) { PMD_INIT_LOG(ERR, "Invalid high/low water setup value in KB"); PMD_INIT_LOG(ERR, "High_water must <= 0x%x", max_high_water); - return (-EINVAL); + return -EINVAL; } hw->fc.requested_mode = rte_fcmode_2_ixgbe_fcmode[pfc_conf->fc.mode]; @@ -2834,16 +3773,26 @@ ixgbe_dev_rss_reta_update(struct rte_eth_dev *dev, struct rte_eth_rss_reta_entry64 *reta_conf, uint16_t reta_size) { - uint8_t i, j, mask; + uint16_t i, sp_reta_size; + uint8_t j, mask; uint32_t reta, r; uint16_t idx, shift; struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t reta_reg; PMD_INIT_FUNC_TRACE(); - if (reta_size != ETH_RSS_RETA_SIZE_128) { + + if (!ixgbe_rss_update_sp(hw->mac.type)) { + PMD_DRV_LOG(ERR, "RSS reta update is not supported on this " + "NIC."); + return -ENOTSUP; + } + + sp_reta_size = ixgbe_reta_size_get(hw->mac.type); + if (reta_size != sp_reta_size) { PMD_DRV_LOG(ERR, "The size of hash lookup table configured " "(%d) doesn't match the number hardware can supported " - "(%d)\n", reta_size, ETH_RSS_RETA_SIZE_128); + "(%d)\n", reta_size, sp_reta_size); return -EINVAL; } @@ -2854,10 +3803,11 @@ ixgbe_dev_rss_reta_update(struct rte_eth_dev *dev, IXGBE_4_BIT_MASK); if (!mask) continue; + reta_reg = ixgbe_reta_reg_get(hw->mac.type, i); if (mask == IXGBE_4_BIT_MASK) r = 0; else - r = IXGBE_READ_REG(hw, IXGBE_RETA(i >> 2)); + r = IXGBE_READ_REG(hw, reta_reg); for (j = 0, reta = 0; j < IXGBE_4_BIT_WIDTH; j++) { if (mask & (0x1 << j)) reta |= reta_conf[idx].reta[shift + j] << @@ -2866,7 +3816,7 @@ ixgbe_dev_rss_reta_update(struct rte_eth_dev *dev, reta |= r & (IXGBE_8_BIT_MASK << (CHAR_BIT * j)); } - IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta); + IXGBE_WRITE_REG(hw, reta_reg, reta); } return 0; @@ -2877,20 +3827,23 @@ ixgbe_dev_rss_reta_query(struct rte_eth_dev *dev, struct rte_eth_rss_reta_entry64 *reta_conf, uint16_t reta_size) { - uint8_t i, j, mask; + uint16_t i, sp_reta_size; + uint8_t j, mask; uint32_t reta; uint16_t idx, shift; struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t reta_reg; PMD_INIT_FUNC_TRACE(); - if (reta_size != ETH_RSS_RETA_SIZE_128) { + sp_reta_size = ixgbe_reta_size_get(hw->mac.type); + if (reta_size != sp_reta_size) { PMD_DRV_LOG(ERR, "The size of hash lookup table configured " "(%d) doesn't match the number hardware can supported " - "(%d)\n", reta_size, ETH_RSS_RETA_SIZE_128); + "(%d)\n", reta_size, sp_reta_size); return -EINVAL; } - for (i = 0; i < ETH_RSS_RETA_SIZE_128; i += IXGBE_4_BIT_WIDTH) { + for (i = 0; i < reta_size; i += IXGBE_4_BIT_WIDTH) { idx = i / RTE_RETA_GROUP_SIZE; shift = i % RTE_RETA_GROUP_SIZE; mask = (uint8_t)((reta_conf[idx].mask >> shift) & @@ -2898,7 +3851,8 @@ ixgbe_dev_rss_reta_query(struct rte_eth_dev *dev, if (!mask) continue; - reta = IXGBE_READ_REG(hw, IXGBE_RETA(i >> 2)); + reta_reg = ixgbe_reta_reg_get(hw->mac.type, i); + reta = IXGBE_READ_REG(hw, reta_reg); for (j = 0; j < IXGBE_4_BIT_WIDTH; j++) { if (mask & (0x1 << j)) reta_conf[idx].reta[shift + j] = @@ -2928,6 +3882,14 @@ ixgbe_remove_rar(struct rte_eth_dev *dev, uint32_t index) ixgbe_clear_rar(hw, index); } +static void +ixgbe_set_default_mac_addr(struct rte_eth_dev *dev, struct ether_addr *addr) +{ + ixgbe_remove_rar(dev, 0); + + ixgbe_add_rar(dev, addr, 0, 0); +} + static int ixgbe_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu) { @@ -2988,6 +3950,19 @@ ixgbevf_intr_disable(struct ixgbe_hw *hw) IXGBE_WRITE_FLUSH(hw); } +static void +ixgbevf_intr_enable(struct ixgbe_hw *hw) +{ + PMD_INIT_FUNC_TRACE(); + + /* VF enable interrupt autoclean */ + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, IXGBE_VF_IRQ_ENABLE_MASK); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, IXGBE_VF_IRQ_ENABLE_MASK); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, IXGBE_VF_IRQ_ENABLE_MASK); + + IXGBE_WRITE_FLUSH(hw); +} + static int ixgbevf_dev_configure(struct rte_eth_dev *dev) { @@ -3004,12 +3979,12 @@ ixgbevf_dev_configure(struct rte_eth_dev *dev) */ #ifndef RTE_LIBRTE_IXGBE_PF_DISABLE_STRIP_CRC if (!conf->rxmode.hw_strip_crc) { - PMD_INIT_LOG(INFO, "VF can't disable HW CRC Strip"); + PMD_INIT_LOG(NOTICE, "VF can't disable HW CRC Strip"); conf->rxmode.hw_strip_crc = 1; } #else if (conf->rxmode.hw_strip_crc) { - PMD_INIT_LOG(INFO, "VF can't enable HW CRC Strip"); + PMD_INIT_LOG(NOTICE, "VF can't enable HW CRC Strip"); conf->rxmode.hw_strip_crc = 0; } #endif @@ -3029,6 +4004,9 @@ ixgbevf_dev_start(struct rte_eth_dev *dev) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t intr_vector = 0; + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; + int err, mask = 0; PMD_INIT_FUNC_TRACE(); @@ -3059,6 +4037,30 @@ ixgbevf_dev_start(struct rte_eth_dev *dev) ixgbevf_dev_rxtx_start(dev); + /* check and configure queue intr-vector mapping */ + if (dev->data->dev_conf.intr_conf.rxq != 0) { + intr_vector = dev->data->nb_rx_queues; + if (rte_intr_efd_enable(intr_handle, intr_vector)) + return -1; + } + + if (rte_intr_dp_is_en(intr_handle) && !intr_handle->intr_vec) { + intr_handle->intr_vec = + rte_zmalloc("intr_vec", + dev->data->nb_rx_queues * sizeof(int), 0); + if (intr_handle->intr_vec == NULL) { + PMD_INIT_LOG(ERR, "Failed to allocate %d rx_queues" + " intr_vec\n", dev->data->nb_rx_queues); + return -ENOMEM; + } + } + ixgbevf_configure_msix(dev); + + rte_intr_enable(intr_handle); + + /* Re-enable interrupt for VF */ + ixgbevf_intr_enable(hw); + return 0; } @@ -3066,10 +4068,11 @@ static void ixgbevf_dev_stop(struct rte_eth_dev *dev) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; PMD_INIT_FUNC_TRACE(); - hw->adapter_stopped = TRUE; + hw->adapter_stopped = 1; ixgbe_stop_adapter(hw); /* @@ -3082,6 +4085,13 @@ ixgbevf_dev_stop(struct rte_eth_dev *dev) dev->data->scattered_rx = 0; ixgbe_dev_clear_queues(dev); + + /* Clean datapath event and queue/vec mapping */ + rte_intr_efd_disable(intr_handle); + if (intr_handle->intr_vec != NULL) { + rte_free(intr_handle->intr_vec); + intr_handle->intr_vec = NULL; + } } static void @@ -3095,8 +4105,14 @@ ixgbevf_dev_close(struct rte_eth_dev *dev) ixgbevf_dev_stop(dev); - /* reprogram the RAR[0] in case user changed it. */ - ixgbe_set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV); + ixgbe_dev_free_queues(dev); + + /** + * Remove the VF MAC address ro ensure + * that the VF traffic goes to the PF + * after stop, close and detach of the VF + **/ + ixgbevf_remove_mac_addr(dev, 0); } static void ixgbevf_set_vfta_all(struct rte_eth_dev *dev, bool on) @@ -3108,10 +4124,10 @@ static void ixgbevf_set_vfta_all(struct rte_eth_dev *dev, bool on) for (i = 0; i < IXGBE_VFTA_SIZE; i++){ vfta = shadow_vfta->vfta[i]; - if(vfta){ + if (vfta) { mask = 1; for (j = 0; j < 32; j++){ - if(vfta & mask) + if (vfta & mask) ixgbe_set_vfta(hw, (i<<5)+j, 0, on); mask<<=1; } @@ -3135,7 +4151,7 @@ ixgbevf_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) /* vind is not used in VF driver, set to 0, check ixgbe_set_vfta_vf */ ret = ixgbe_set_vfta(hw, vlan_id, 0, !!on); - if(ret){ + if (ret) { PMD_INIT_LOG(ERR, "Unable to set VF vlan"); return ret; } @@ -3160,11 +4176,11 @@ ixgbevf_vlan_strip_queue_set(struct rte_eth_dev *dev, uint16_t queue, int on) PMD_INIT_FUNC_TRACE(); - if(queue >= hw->mac.max_rx_queues) + if (queue >= hw->mac.max_rx_queues) return; ctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(queue)); - if(on) + if (on) ctrl |= IXGBE_RXDCTL_VME; else ctrl &= ~IXGBE_RXDCTL_VME; @@ -3182,10 +4198,10 @@ ixgbevf_vlan_offload_set(struct rte_eth_dev *dev, int mask) int on = 0; /* VF function only support hw strip feature, others are not support */ - if(mask & ETH_VLAN_STRIP_MASK){ + if (mask & ETH_VLAN_STRIP_MASK) { on = !!(dev->data->dev_conf.rxmode.hw_vlan_strip); - for(i=0; i < hw->mac.max_rx_queues; i++) + for (i = 0; i < hw->mac.max_rx_queues; i++) ixgbevf_vlan_strip_queue_set(dev,i,on); } } @@ -3199,7 +4215,7 @@ ixgbe_vmdq_mode_check(struct ixgbe_hw *hw) reg_val = IXGBE_READ_REG(hw, IXGBE_VT_CTL); if (!(reg_val & IXGBE_VT_CTL_VT_ENABLE)) { PMD_INIT_LOG(ERR, "VMDq must be enabled for this setting"); - return (-1); + return -1; } return 0; @@ -3256,14 +4272,14 @@ ixgbe_uc_hash_table_set(struct rte_eth_dev *dev,struct ether_addr* mac_addr, /* The UTA table only exists on 82599 hardware and newer */ if (hw->mac.type < ixgbe_mac_82599EB) - return (-ENOTSUP); + return -ENOTSUP; vector = ixgbe_uta_vector(hw,mac_addr); uta_idx = (vector >> ixgbe_uta_bit_shift) & ixgbe_uta_idx_mask; uta_shift = vector & ixgbe_uta_bit_mask; rc = ((uta_info->uta_shadow[uta_idx] >> uta_shift & bit1) != 0); - if(rc == on) + if (rc == on) return 0; reg_val = IXGBE_READ_REG(hw, IXGBE_UTA(uta_idx)); @@ -3299,9 +4315,9 @@ ixgbe_uc_all_hash_table_set(struct rte_eth_dev *dev, uint8_t on) /* The UTA table only exists on 82599 hardware and newer */ if (hw->mac.type < ixgbe_mac_82599EB) - return (-ENOTSUP); + return -ENOTSUP; - if(on) { + if (on) { for (i = 0; i < ETH_VMDQ_NUM_UC_HASH_ARRAY; i++) { uta_info->uta_shadow[i] = ~0; IXGBE_WRITE_REG(hw, IXGBE_UTA(i), ~0); @@ -3348,10 +4364,10 @@ ixgbe_set_pool_rx_mode(struct rte_eth_dev *dev, uint16_t pool, if (hw->mac.type == ixgbe_mac_82598EB) { PMD_INIT_LOG(ERR, "setting VF receive mode set should be done" " on 82599 hardware and newer"); - return (-ENOTSUP); + return -ENOTSUP; } if (ixgbe_vmdq_mode_check(hw) < 0) - return (-ENOTSUP); + return -ENOTSUP; val = ixgbe_convert_vm_rx_mask_to_val(rx_mask, val); @@ -3376,7 +4392,7 @@ ixgbe_set_pool_rx(struct rte_eth_dev *dev, uint16_t pool, uint8_t on) IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); if (ixgbe_vmdq_mode_check(hw) < 0) - return (-ENOTSUP); + return -ENOTSUP; addr = IXGBE_VFRE(pool >= ETH_64_POOLS/2); reg = IXGBE_READ_REG(hw, addr); @@ -3403,7 +4419,7 @@ ixgbe_set_pool_tx(struct rte_eth_dev *dev, uint16_t pool, uint8_t on) IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); if (ixgbe_vmdq_mode_check(hw) < 0) - return (-ENOTSUP); + return -ENOTSUP; addr = IXGBE_VFTE(pool >= ETH_64_POOLS/2); reg = IXGBE_READ_REG(hw, addr); @@ -3429,12 +4445,13 @@ ixgbe_set_pool_vlan_filter(struct rte_eth_dev *dev, uint16_t vlan, IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); if (ixgbe_vmdq_mode_check(hw) < 0) - return (-ENOTSUP); + return -ENOTSUP; for (pool_idx = 0; pool_idx < ETH_64_POOLS; pool_idx++) { - if (pool_mask & ((uint64_t)(1ULL << pool_idx))) + if (pool_mask & ((uint64_t)(1ULL << pool_idx))) { ret = hw->mac.ops.set_vfta(hw,vlan,pool_idx,vlan_on); if (ret < 0) return ret; + } } return ret; @@ -3494,7 +4511,7 @@ ixgbe_mirror_rule_set(struct rte_eth_dev *dev, /* search vlan id related pool vlan filter index */ reg_index = ixgbe_find_vlvf_slot(hw, mirror_conf->vlan.vlan_id[i]); - if(reg_index < 0) + if (reg_index < 0) return -EINVAL; vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(reg_index)); if ((vlvf & IXGBE_VLVF_VIEN) && @@ -3512,8 +4529,8 @@ ixgbe_mirror_rule_set(struct rte_eth_dev *dev, mr_info->mr_conf[rule_id].vlan.vlan_mask = mirror_conf->vlan.vlan_mask; - for(i = 0 ;i < ETH_VMDQ_MAX_VLAN_FILTERS; i++) { - if(mirror_conf->vlan.vlan_mask & (1ULL << i)) + for (i = 0; i < ETH_VMDQ_MAX_VLAN_FILTERS; i++) { + if (mirror_conf->vlan.vlan_mask & (1ULL << i)) mr_info->mr_conf[rule_id].vlan.vlan_id[i] = mirror_conf->vlan.vlan_id[i]; } @@ -3521,7 +4538,7 @@ ixgbe_mirror_rule_set(struct rte_eth_dev *dev, mv_lsb = 0; mv_msb = 0; mr_info->mr_conf[rule_id].vlan.vlan_mask = 0; - for(i = 0 ;i < ETH_VMDQ_MAX_VLAN_FILTERS; i++) + for (i = 0; i < ETH_VMDQ_MAX_VLAN_FILTERS; i++) mr_info->mr_conf[rule_id].vlan.vlan_id[i] = 0; } } @@ -3595,7 +4612,7 @@ ixgbe_mirror_rule_reset(struct rte_eth_dev *dev, uint8_t rule_id) (IXGBE_DEV_PRIVATE_TO_PFDATA(dev->data->dev_private)); if (ixgbe_vmdq_mode_check(hw) < 0) - return (-ENOTSUP); + return -ENOTSUP; memset(&mr_info->mr_conf[rule_id], 0, sizeof(struct rte_eth_mirror_conf)); @@ -3614,93 +4631,352 @@ ixgbe_mirror_rule_reset(struct rte_eth_dev *dev, uint8_t rule_id) return 0; } -static int ixgbe_set_queue_rate_limit(struct rte_eth_dev *dev, - uint16_t queue_idx, uint16_t tx_rate) +static int +ixgbevf_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id) { - struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - uint32_t rf_dec, rf_int; - uint32_t bcnrc_val; - uint16_t link_speed = dev->data->dev_link.link_speed; + uint32_t mask; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - if (queue_idx >= hw->mac.max_tx_queues) - return -EINVAL; + mask = IXGBE_READ_REG(hw, IXGBE_VTEIMS); + mask |= (1 << IXGBE_MISC_VEC_ID); + RTE_SET_USED(queue_id); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); - if (tx_rate != 0) { - /* Calculate the rate factor values to set */ - rf_int = (uint32_t)link_speed / (uint32_t)tx_rate; - rf_dec = (uint32_t)link_speed % (uint32_t)tx_rate; - rf_dec = (rf_dec << IXGBE_RTTBCNRC_RF_INT_SHIFT) / tx_rate; + rte_intr_enable(&dev->pci_dev->intr_handle); - bcnrc_val = IXGBE_RTTBCNRC_RS_ENA; - bcnrc_val |= ((rf_int << IXGBE_RTTBCNRC_RF_INT_SHIFT) & - IXGBE_RTTBCNRC_RF_INT_MASK_M); - bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK); - } else { - bcnrc_val = 0; - } + return 0; +} - /* - * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM - * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported, otherwise - * set as 0x4. - */ - if ((dev->data->dev_conf.rxmode.jumbo_frame == 1) && - (dev->data->dev_conf.rxmode.max_rx_pkt_len >= - IXGBE_MAX_JUMBO_FRAME_SIZE)) - IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, - IXGBE_MMW_SIZE_JUMBO_FRAME); - else - IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, - IXGBE_MMW_SIZE_DEFAULT); +static int +ixgbevf_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id) +{ + uint32_t mask; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - /* Set RTTBCNRC of queue X */ - IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, queue_idx); - IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); - IXGBE_WRITE_FLUSH(hw); + mask = IXGBE_READ_REG(hw, IXGBE_VTEIMS); + mask &= ~(1 << IXGBE_MISC_VEC_ID); + RTE_SET_USED(queue_id); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); return 0; } -static int ixgbe_set_vf_rate_limit(struct rte_eth_dev *dev, uint16_t vf, - uint16_t tx_rate, uint64_t q_msk) +static int +ixgbe_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id) { - struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); - struct ixgbe_vf_info *vfinfo = - *(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private)); - uint8_t nb_q_per_pool = RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool; - uint32_t queue_stride = - IXGBE_MAX_RX_QUEUE_NUM / RTE_ETH_DEV_SRIOV(dev).active; - uint32_t queue_idx = vf * queue_stride, idx = 0, vf_idx; - uint32_t queue_end = queue_idx + nb_q_per_pool - 1; - uint16_t total_rate = 0; + uint32_t mask; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_interrupt *intr = + IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private); - if (queue_end >= hw->mac.max_tx_queues) - return -EINVAL; + if (queue_id < 16) { + ixgbe_disable_intr(hw); + intr->mask |= (1 << queue_id); + ixgbe_enable_intr(dev); + } else if (queue_id < 32) { + mask = IXGBE_READ_REG(hw, IXGBE_EIMS_EX(0)); + mask &= (1 << queue_id); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + } else if (queue_id < 64) { + mask = IXGBE_READ_REG(hw, IXGBE_EIMS_EX(1)); + mask &= (1 << (queue_id - 32)); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + } + rte_intr_enable(&dev->pci_dev->intr_handle); - if (vfinfo != NULL) { - for (vf_idx = 0; vf_idx < dev->pci_dev->max_vfs; vf_idx++) { - if (vf_idx == vf) - continue; - for (idx = 0; idx < RTE_DIM(vfinfo[vf_idx].tx_rate); - idx++) - total_rate += vfinfo[vf_idx].tx_rate[idx]; - } - } else - return -EINVAL; + return 0; +} - /* Store tx_rate for this vf. */ - for (idx = 0; idx < nb_q_per_pool; idx++) { - if (((uint64_t)0x1 << idx) & q_msk) { - if (vfinfo[vf].tx_rate[idx] != tx_rate) - vfinfo[vf].tx_rate[idx] = tx_rate; - total_rate += tx_rate; - } +static int +ixgbe_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id) +{ + uint32_t mask; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_interrupt *intr = + IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private); + + if (queue_id < 16) { + ixgbe_disable_intr(hw); + intr->mask &= ~(1 << queue_id); + ixgbe_enable_intr(dev); + } else if (queue_id < 32) { + mask = IXGBE_READ_REG(hw, IXGBE_EIMS_EX(0)); + mask &= ~(1 << queue_id); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + } else if (queue_id < 64) { + mask = IXGBE_READ_REG(hw, IXGBE_EIMS_EX(1)); + mask &= ~(1 << (queue_id - 32)); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); } - if (total_rate > dev->data->dev_link.link_speed) { - /* - * Reset stored TX rate of the VF if it causes exceed - * link speed. + return 0; +} + +static void +ixgbevf_set_ivar_map(struct ixgbe_hw *hw, int8_t direction, + uint8_t queue, uint8_t msix_vector) +{ + uint32_t tmp, idx; + + if (direction == -1) { + /* other causes */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + tmp = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC); + tmp &= ~0xFF; + tmp |= msix_vector; + IXGBE_WRITE_REG(hw, IXGBE_VTIVAR_MISC, tmp); + } else { + /* rx or tx cause */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + idx = ((16 * (queue & 1)) + (8 * direction)); + tmp = IXGBE_READ_REG(hw, IXGBE_VTIVAR(queue >> 1)); + tmp &= ~(0xFF << idx); + tmp |= (msix_vector << idx); + IXGBE_WRITE_REG(hw, IXGBE_VTIVAR(queue >> 1), tmp); + } +} + +/** + * set the IVAR registers, mapping interrupt causes to vectors + * @param hw + * pointer to ixgbe_hw struct + * @direction + * 0 for Rx, 1 for Tx, -1 for other causes + * @queue + * queue to map the corresponding interrupt to + * @msix_vector + * the vector to map to the corresponding queue + */ +static void +ixgbe_set_ivar_map(struct ixgbe_hw *hw, int8_t direction, + uint8_t queue, uint8_t msix_vector) +{ + uint32_t tmp, idx; + + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + if (hw->mac.type == ixgbe_mac_82598EB) { + if (direction == -1) + direction = 0; + idx = (((direction * 64) + queue) >> 2) & 0x1F; + tmp = IXGBE_READ_REG(hw, IXGBE_IVAR(idx)); + tmp &= ~(0xFF << (8 * (queue & 0x3))); + tmp |= (msix_vector << (8 * (queue & 0x3))); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(idx), tmp); + } else if ((hw->mac.type == ixgbe_mac_82599EB) || + (hw->mac.type == ixgbe_mac_X540)) { + if (direction == -1) { + /* other causes */ + idx = ((queue & 1) * 8); + tmp = IXGBE_READ_REG(hw, IXGBE_IVAR_MISC); + tmp &= ~(0xFF << idx); + tmp |= (msix_vector << idx); + IXGBE_WRITE_REG(hw, IXGBE_IVAR_MISC, tmp); + } else { + /* rx or tx causes */ + idx = ((16 * (queue & 1)) + (8 * direction)); + tmp = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1)); + tmp &= ~(0xFF << idx); + tmp |= (msix_vector << idx); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), tmp); + } + } +} + +static void +ixgbevf_configure_msix(struct rte_eth_dev *dev) +{ + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t q_idx; + uint32_t vector_idx = IXGBE_MISC_VEC_ID; + + /* won't configure msix register if no mapping is done + * between intr vector and event fd. + */ + if (!rte_intr_dp_is_en(intr_handle)) + return; + + /* Configure all RX queues of VF */ + for (q_idx = 0; q_idx < dev->data->nb_rx_queues; q_idx++) { + /* Force all queue use vector 0, + * as IXGBE_VF_MAXMSIVECOTR = 1 + */ + ixgbevf_set_ivar_map(hw, 0, q_idx, vector_idx); + intr_handle->intr_vec[q_idx] = vector_idx; + } + + /* Configure VF other cause ivar */ + ixgbevf_set_ivar_map(hw, -1, 1, vector_idx); +} + +/** + * Sets up the hardware to properly generate MSI-X interrupts + * @hw + * board private structure + */ +static void +ixgbe_configure_msix(struct rte_eth_dev *dev) +{ + struct rte_intr_handle *intr_handle = &dev->pci_dev->intr_handle; + struct ixgbe_hw *hw = + IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t queue_id, base = IXGBE_MISC_VEC_ID; + uint32_t vec = IXGBE_MISC_VEC_ID; + uint32_t mask; + uint32_t gpie; + + /* won't configure msix register if no mapping is done + * between intr vector and event fd + */ + if (!rte_intr_dp_is_en(intr_handle)) + return; + + if (rte_intr_allow_others(intr_handle)) + vec = base = IXGBE_RX_VEC_START; + + /* setup GPIE for MSI-x mode */ + gpie = IXGBE_READ_REG(hw, IXGBE_GPIE); + gpie |= IXGBE_GPIE_MSIX_MODE | IXGBE_GPIE_PBA_SUPPORT | + IXGBE_GPIE_OCD | IXGBE_GPIE_EIAME; + /* auto clearing and auto setting corresponding bits in EIMS + * when MSI-X interrupt is triggered + */ + if (hw->mac.type == ixgbe_mac_82598EB) { + IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE); + } else { + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); + } + IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); + + /* Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (queue_id = 0; queue_id < dev->data->nb_rx_queues; + queue_id++) { + /* by default, 1:1 mapping */ + ixgbe_set_ivar_map(hw, 0, queue_id, vec); + intr_handle->intr_vec[queue_id] = vec; + if (vec < base + intr_handle->nb_efd - 1) + vec++; + } + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ixgbe_set_ivar_map(hw, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX, + IXGBE_MISC_VEC_ID); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ixgbe_set_ivar_map(hw, -1, 1, IXGBE_MISC_VEC_ID); + break; + default: + break; + } + IXGBE_WRITE_REG(hw, IXGBE_EITR(IXGBE_MISC_VEC_ID), + IXGBE_MIN_INTER_INTERRUPT_INTERVAL_DEFAULT & 0xFFF); + + /* set up to autoclear timer, and the vectors */ + mask = IXGBE_EIMS_ENABLE_MASK; + mask &= ~(IXGBE_EIMS_OTHER | + IXGBE_EIMS_MAILBOX | + IXGBE_EIMS_LSC); + + IXGBE_WRITE_REG(hw, IXGBE_EIAC, mask); +} + +static int ixgbe_set_queue_rate_limit(struct rte_eth_dev *dev, + uint16_t queue_idx, uint16_t tx_rate) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t rf_dec, rf_int; + uint32_t bcnrc_val; + uint16_t link_speed = dev->data->dev_link.link_speed; + + if (queue_idx >= hw->mac.max_tx_queues) + return -EINVAL; + + if (tx_rate != 0) { + /* Calculate the rate factor values to set */ + rf_int = (uint32_t)link_speed / (uint32_t)tx_rate; + rf_dec = (uint32_t)link_speed % (uint32_t)tx_rate; + rf_dec = (rf_dec << IXGBE_RTTBCNRC_RF_INT_SHIFT) / tx_rate; + + bcnrc_val = IXGBE_RTTBCNRC_RS_ENA; + bcnrc_val |= ((rf_int << IXGBE_RTTBCNRC_RF_INT_SHIFT) & + IXGBE_RTTBCNRC_RF_INT_MASK_M); + bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK); + } else { + bcnrc_val = 0; + } + + /* + * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM + * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported, otherwise + * set as 0x4. + */ + if ((dev->data->dev_conf.rxmode.jumbo_frame == 1) && + (dev->data->dev_conf.rxmode.max_rx_pkt_len >= + IXGBE_MAX_JUMBO_FRAME_SIZE)) + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, + IXGBE_MMW_SIZE_JUMBO_FRAME); + else + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, + IXGBE_MMW_SIZE_DEFAULT); + + /* Set RTTBCNRC of queue X */ + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, queue_idx); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +static int ixgbe_set_vf_rate_limit(struct rte_eth_dev *dev, uint16_t vf, + uint16_t tx_rate, uint64_t q_msk) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_vf_info *vfinfo = + *(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private)); + uint8_t nb_q_per_pool = RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool; + uint32_t queue_stride = + IXGBE_MAX_RX_QUEUE_NUM / RTE_ETH_DEV_SRIOV(dev).active; + uint32_t queue_idx = vf * queue_stride, idx = 0, vf_idx; + uint32_t queue_end = queue_idx + nb_q_per_pool - 1; + uint16_t total_rate = 0; + + if (queue_end >= hw->mac.max_tx_queues) + return -EINVAL; + + if (vfinfo != NULL) { + for (vf_idx = 0; vf_idx < dev->pci_dev->max_vfs; vf_idx++) { + if (vf_idx == vf) + continue; + for (idx = 0; idx < RTE_DIM(vfinfo[vf_idx].tx_rate); + idx++) + total_rate += vfinfo[vf_idx].tx_rate[idx]; + } + } else + return -EINVAL; + + /* Store tx_rate for this vf. */ + for (idx = 0; idx < nb_q_per_pool; idx++) { + if (((uint64_t)0x1 << idx) & q_msk) { + if (vfinfo[vf].tx_rate[idx] != tx_rate) + vfinfo[vf].tx_rate[idx] = tx_rate; + total_rate += tx_rate; + } + } + + if (total_rate > dev->data->dev_link.link_speed) { + /* + * Reset stored TX rate of the VF if it causes exceed + * link speed. */ memset(vfinfo[vf].tx_rate, 0, sizeof(vfinfo[vf].tx_rate)); return -EINVAL; @@ -3785,9 +5061,18 @@ ixgbevf_remove_mac_addr(struct rte_eth_dev *dev, uint32_t index) } } +static void +ixgbevf_set_default_mac_addr(struct rte_eth_dev *dev, struct ether_addr *addr) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + hw->mac.ops.set_rar(hw, 0, (void *)addr, 0, 0); +} + #define MAC_TYPE_FILTER_SUP(type) do {\ if ((type) != ixgbe_mac_82599EB && (type) != ixgbe_mac_X540 &&\ - (type) != ixgbe_mac_X550)\ + (type) != ixgbe_mac_X550 && (type) != ixgbe_mac_X550EM_x &&\ + (type) != ixgbe_mac_X550EM_a)\ return -ENOTSUP;\ } while (0) @@ -4502,6 +5787,9 @@ ixgbe_dev_filter_ctrl(struct rte_eth_dev *dev, case RTE_ETH_FILTER_FDIR: ret = ixgbe_fdir_ctrl_func(dev, filter_op, arg); break; + case RTE_ETH_FILTER_L2_TUNNEL: + ret = ixgbe_dev_l2_tunnel_filter_handle(dev, filter_op, arg); + break; default: PMD_DRV_LOG(WARNING, "Filter type (%d) not supported", filter_type); @@ -4525,8 +5813,8 @@ ixgbe_dev_addr_list_itr(__attribute__((unused)) struct ixgbe_hw *hw, static int ixgbe_dev_set_mc_addr_list(struct rte_eth_dev *dev, - struct ether_addr *mc_addr_set, - uint32_t nb_mc_addr) + struct ether_addr *mc_addr_set, + uint32_t nb_mc_addr) { struct ixgbe_hw *hw; u8 *mc_addr_list; @@ -4537,6 +5825,194 @@ ixgbe_dev_set_mc_addr_list(struct rte_eth_dev *dev, ixgbe_dev_addr_list_itr, TRUE); } +static uint64_t +ixgbe_read_systime_cyclecounter(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint64_t systime_cycles; + + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + /* SYSTIMEL stores ns and SYSTIMEH stores seconds. */ + systime_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_SYSTIML); + systime_cycles += (uint64_t)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) + * NSEC_PER_SEC; + break; + default: + systime_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_SYSTIML); + systime_cycles |= (uint64_t)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) + << 32; + } + + return systime_cycles; +} + +static uint64_t +ixgbe_read_rx_tstamp_cyclecounter(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint64_t rx_tstamp_cycles; + + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + /* RXSTMPL stores ns and RXSTMPH stores seconds. */ + rx_tstamp_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_RXSTMPL); + rx_tstamp_cycles += (uint64_t)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) + * NSEC_PER_SEC; + break; + default: + /* RXSTMPL stores ns and RXSTMPH stores seconds. */ + rx_tstamp_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_RXSTMPL); + rx_tstamp_cycles |= (uint64_t)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) + << 32; + } + + return rx_tstamp_cycles; +} + +static uint64_t +ixgbe_read_tx_tstamp_cyclecounter(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint64_t tx_tstamp_cycles; + + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + /* TXSTMPL stores ns and TXSTMPH stores seconds. */ + tx_tstamp_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_TXSTMPL); + tx_tstamp_cycles += (uint64_t)IXGBE_READ_REG(hw, IXGBE_TXSTMPH) + * NSEC_PER_SEC; + break; + default: + /* TXSTMPL stores ns and TXSTMPH stores seconds. */ + tx_tstamp_cycles = (uint64_t)IXGBE_READ_REG(hw, IXGBE_TXSTMPL); + tx_tstamp_cycles |= (uint64_t)IXGBE_READ_REG(hw, IXGBE_TXSTMPH) + << 32; + } + + return tx_tstamp_cycles; +} + +static void +ixgbe_start_timecounters(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; + struct rte_eth_link link; + uint32_t incval = 0; + uint32_t shift = 0; + + /* Get current link speed. */ + memset(&link, 0, sizeof(link)); + ixgbe_dev_link_update(dev, 1); + rte_ixgbe_dev_atomic_read_link_status(dev, &link); + + switch (link.link_speed) { + case ETH_LINK_SPEED_100: + incval = IXGBE_INCVAL_100; + shift = IXGBE_INCVAL_SHIFT_100; + break; + case ETH_LINK_SPEED_1000: + incval = IXGBE_INCVAL_1GB; + shift = IXGBE_INCVAL_SHIFT_1GB; + break; + case ETH_LINK_SPEED_10000: + default: + incval = IXGBE_INCVAL_10GB; + shift = IXGBE_INCVAL_SHIFT_10GB; + break; + } + + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + /* Independent of link speed. */ + incval = 1; + /* Cycles read will be interpreted as ns. */ + shift = 0; + /* Fall-through */ + case ixgbe_mac_X540: + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, incval); + break; + case ixgbe_mac_82599EB: + incval >>= IXGBE_INCVAL_SHIFT_82599; + shift -= IXGBE_INCVAL_SHIFT_82599; + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, + (1 << IXGBE_INCPER_SHIFT_82599) | incval); + break; + default: + /* Not supported. */ + return; + } + + memset(&adapter->systime_tc, 0, sizeof(struct rte_timecounter)); + memset(&adapter->rx_tstamp_tc, 0, sizeof(struct rte_timecounter)); + memset(&adapter->tx_tstamp_tc, 0, sizeof(struct rte_timecounter)); + + adapter->systime_tc.cc_mask = IXGBE_CYCLECOUNTER_MASK; + adapter->systime_tc.cc_shift = shift; + adapter->systime_tc.nsec_mask = (1ULL << shift) - 1; + + adapter->rx_tstamp_tc.cc_mask = IXGBE_CYCLECOUNTER_MASK; + adapter->rx_tstamp_tc.cc_shift = shift; + adapter->rx_tstamp_tc.nsec_mask = (1ULL << shift) - 1; + + adapter->tx_tstamp_tc.cc_mask = IXGBE_CYCLECOUNTER_MASK; + adapter->tx_tstamp_tc.cc_shift = shift; + adapter->tx_tstamp_tc.nsec_mask = (1ULL << shift) - 1; +} + +static int +ixgbe_timesync_adjust_time(struct rte_eth_dev *dev, int64_t delta) +{ + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; + + adapter->systime_tc.nsec += delta; + adapter->rx_tstamp_tc.nsec += delta; + adapter->tx_tstamp_tc.nsec += delta; + + return 0; +} + +static int +ixgbe_timesync_write_time(struct rte_eth_dev *dev, const struct timespec *ts) +{ + uint64_t ns; + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; + + ns = rte_timespec_to_ns(ts); + /* Set the timecounters to a new value. */ + adapter->systime_tc.nsec = ns; + adapter->rx_tstamp_tc.nsec = ns; + adapter->tx_tstamp_tc.nsec = ns; + + return 0; +} + +static int +ixgbe_timesync_read_time(struct rte_eth_dev *dev, struct timespec *ts) +{ + uint64_t ns, systime_cycles; + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; + + systime_cycles = ixgbe_read_systime_cyclecounter(dev); + ns = rte_timecounter_update(&adapter->systime_tc, systime_cycles); + *ts = rte_ns_to_timespec(ns); + + return 0; +} + static int ixgbe_timesync_enable(struct rte_eth_dev *dev) { @@ -4544,13 +6020,18 @@ ixgbe_timesync_enable(struct rte_eth_dev *dev) uint32_t tsync_ctl; uint32_t tsauxc; + /* Stop the timesync system time. */ + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, 0x0); + /* Reset the timesync system time value. */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0x0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0x0); + /* Enable system time for platforms where it isn't on by default. */ tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); tsauxc &= ~IXGBE_TSAUXC_DISABLE_SYSTIME; IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc); - /* Start incrementing the register used to timestamp PTP packets. */ - IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, IXGBE_TIMINCA_INIT); + ixgbe_start_timecounters(dev); /* Enable L2 filtering of IEEE1588/802.1AS Ethernet frame types. */ IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), @@ -4568,6 +6049,8 @@ ixgbe_timesync_enable(struct rte_eth_dev *dev) tsync_ctl |= IXGBE_TSYNCTXCTL_ENABLED; IXGBE_WRITE_REG(hw, IXGBE_TSYNCTXCTL, tsync_ctl); + IXGBE_WRITE_FLUSH(hw); + return 0; } @@ -4602,19 +6085,19 @@ ixgbe_timesync_read_rx_timestamp(struct rte_eth_dev *dev, uint32_t flags __rte_unused) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; uint32_t tsync_rxctl; - uint32_t rx_stmpl; - uint32_t rx_stmph; + uint64_t rx_tstamp_cycles; + uint64_t ns; tsync_rxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); if ((tsync_rxctl & IXGBE_TSYNCRXCTL_VALID) == 0) return -EINVAL; - rx_stmpl = IXGBE_READ_REG(hw, IXGBE_RXSTMPL); - rx_stmph = IXGBE_READ_REG(hw, IXGBE_RXSTMPH); - - timestamp->tv_sec = (uint64_t)(((uint64_t)rx_stmph << 32) | rx_stmpl); - timestamp->tv_nsec = 0; + rx_tstamp_cycles = ixgbe_read_rx_tstamp_cyclecounter(dev); + ns = rte_timecounter_update(&adapter->rx_tstamp_tc, rx_tstamp_cycles); + *timestamp = rte_ns_to_timespec(ns); return 0; } @@ -4624,21 +6107,1027 @@ ixgbe_timesync_read_tx_timestamp(struct rte_eth_dev *dev, struct timespec *timestamp) { struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_adapter *adapter = + (struct ixgbe_adapter *)dev->data->dev_private; uint32_t tsync_txctl; - uint32_t tx_stmpl; - uint32_t tx_stmph; + uint64_t tx_tstamp_cycles; + uint64_t ns; tsync_txctl = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL); if ((tsync_txctl & IXGBE_TSYNCTXCTL_VALID) == 0) return -EINVAL; - tx_stmpl = IXGBE_READ_REG(hw, IXGBE_TXSTMPL); - tx_stmph = IXGBE_READ_REG(hw, IXGBE_TXSTMPH); + tx_tstamp_cycles = ixgbe_read_tx_tstamp_cyclecounter(dev); + ns = rte_timecounter_update(&adapter->tx_tstamp_tc, tx_tstamp_cycles); + *timestamp = rte_ns_to_timespec(ns); - timestamp->tv_sec = (uint64_t)(((uint64_t)tx_stmph << 32) | tx_stmpl); - timestamp->tv_nsec = 0; + return 0; +} - return 0; +static int +ixgbe_get_reg_length(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + int count = 0; + int g_ind = 0; + const struct reg_info *reg_group; + const struct reg_info **reg_set = (hw->mac.type == ixgbe_mac_82598EB) ? + ixgbe_regs_mac_82598EB : ixgbe_regs_others; + + while ((reg_group = reg_set[g_ind++])) + count += ixgbe_regs_group_count(reg_group); + + return count; +} + +static int +ixgbevf_get_reg_length(struct rte_eth_dev *dev __rte_unused) +{ + int count = 0; + int g_ind = 0; + const struct reg_info *reg_group; + + while ((reg_group = ixgbevf_regs[g_ind++])) + count += ixgbe_regs_group_count(reg_group); + + return count; +} + +static int +ixgbe_get_regs(struct rte_eth_dev *dev, + struct rte_dev_reg_info *regs) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t *data = regs->data; + int g_ind = 0; + int count = 0; + const struct reg_info *reg_group; + const struct reg_info **reg_set = (hw->mac.type == ixgbe_mac_82598EB) ? + ixgbe_regs_mac_82598EB : ixgbe_regs_others; + + /* Support only full register dump */ + if ((regs->length == 0) || + (regs->length == (uint32_t)ixgbe_get_reg_length(dev))) { + regs->version = hw->mac.type << 24 | hw->revision_id << 16 | + hw->device_id; + while ((reg_group = reg_set[g_ind++])) + count += ixgbe_read_regs_group(dev, &data[count], + reg_group); + return 0; + } + + return -ENOTSUP; +} + +static int +ixgbevf_get_regs(struct rte_eth_dev *dev, + struct rte_dev_reg_info *regs) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t *data = regs->data; + int g_ind = 0; + int count = 0; + const struct reg_info *reg_group; + + /* Support only full register dump */ + if ((regs->length == 0) || + (regs->length == (uint32_t)ixgbevf_get_reg_length(dev))) { + regs->version = hw->mac.type << 24 | hw->revision_id << 16 | + hw->device_id; + while ((reg_group = ixgbevf_regs[g_ind++])) + count += ixgbe_read_regs_group(dev, &data[count], + reg_group); + return 0; + } + + return -ENOTSUP; +} + +static int +ixgbe_get_eeprom_length(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + /* Return unit is byte count */ + return hw->eeprom.word_size * 2; +} + +static int +ixgbe_get_eeprom(struct rte_eth_dev *dev, + struct rte_dev_eeprom_info *in_eeprom) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + uint16_t *data = in_eeprom->data; + int first, length; + + first = in_eeprom->offset >> 1; + length = in_eeprom->length >> 1; + if ((first > hw->eeprom.word_size) || + ((first + length) > hw->eeprom.word_size)) + return -EINVAL; + + in_eeprom->magic = hw->vendor_id | (hw->device_id << 16); + + return eeprom->ops.read_buffer(hw, first, length, data); +} + +static int +ixgbe_set_eeprom(struct rte_eth_dev *dev, + struct rte_dev_eeprom_info *in_eeprom) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + uint16_t *data = in_eeprom->data; + int first, length; + + first = in_eeprom->offset >> 1; + length = in_eeprom->length >> 1; + if ((first > hw->eeprom.word_size) || + ((first + length) > hw->eeprom.word_size)) + return -EINVAL; + + in_eeprom->magic = hw->vendor_id | (hw->device_id << 16); + + return eeprom->ops.write_buffer(hw, first, length, data); +} + +uint16_t +ixgbe_reta_size_get(enum ixgbe_mac_type mac_type) { + switch (mac_type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + return ETH_RSS_RETA_SIZE_512; + case ixgbe_mac_X550_vf: + case ixgbe_mac_X550EM_x_vf: + case ixgbe_mac_X550EM_a_vf: + return ETH_RSS_RETA_SIZE_64; + default: + return ETH_RSS_RETA_SIZE_128; + } +} + +uint32_t +ixgbe_reta_reg_get(enum ixgbe_mac_type mac_type, uint16_t reta_idx) { + switch (mac_type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_X550EM_a: + if (reta_idx < ETH_RSS_RETA_SIZE_128) + return IXGBE_RETA(reta_idx >> 2); + else + return IXGBE_ERETA((reta_idx - ETH_RSS_RETA_SIZE_128) >> 2); + case ixgbe_mac_X550_vf: + case ixgbe_mac_X550EM_x_vf: + case ixgbe_mac_X550EM_a_vf: + return IXGBE_VFRETA(reta_idx >> 2); + default: + return IXGBE_RETA(reta_idx >> 2); + } +} + +uint32_t +ixgbe_mrqc_reg_get(enum ixgbe_mac_type mac_type) { + switch (mac_type) { + case ixgbe_mac_X550_vf: + case ixgbe_mac_X550EM_x_vf: + case ixgbe_mac_X550EM_a_vf: + return IXGBE_VFMRQC; + default: + return IXGBE_MRQC; + } +} + +uint32_t +ixgbe_rssrk_reg_get(enum ixgbe_mac_type mac_type, uint8_t i) { + switch (mac_type) { + case ixgbe_mac_X550_vf: + case ixgbe_mac_X550EM_x_vf: + case ixgbe_mac_X550EM_a_vf: + return IXGBE_VFRSSRK(i); + default: + return IXGBE_RSSRK(i); + } +} + +bool +ixgbe_rss_update_sp(enum ixgbe_mac_type mac_type) { + switch (mac_type) { + case ixgbe_mac_82599_vf: + case ixgbe_mac_X540_vf: + return 0; + default: + return 1; + } +} + +static int +ixgbe_dev_get_dcb_info(struct rte_eth_dev *dev, + struct rte_eth_dcb_info *dcb_info) +{ + struct ixgbe_dcb_config *dcb_config = + IXGBE_DEV_PRIVATE_TO_DCB_CFG(dev->data->dev_private); + struct ixgbe_dcb_tc_config *tc; + uint8_t i, j; + + if (dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_DCB_FLAG) + dcb_info->nb_tcs = dcb_config->num_tcs.pg_tcs; + else + dcb_info->nb_tcs = 1; + + if (dcb_config->vt_mode) { /* vt is enabled*/ + struct rte_eth_vmdq_dcb_conf *vmdq_rx_conf = + &dev->data->dev_conf.rx_adv_conf.vmdq_dcb_conf; + for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++) + dcb_info->prio_tc[i] = vmdq_rx_conf->dcb_tc[i]; + for (i = 0; i < vmdq_rx_conf->nb_queue_pools; i++) { + for (j = 0; j < dcb_info->nb_tcs; j++) { + dcb_info->tc_queue.tc_rxq[i][j].base = + i * dcb_info->nb_tcs + j; + dcb_info->tc_queue.tc_rxq[i][j].nb_queue = 1; + dcb_info->tc_queue.tc_txq[i][j].base = + i * dcb_info->nb_tcs + j; + dcb_info->tc_queue.tc_txq[i][j].nb_queue = 1; + } + } + } else { /* vt is disabled*/ + struct rte_eth_dcb_rx_conf *rx_conf = + &dev->data->dev_conf.rx_adv_conf.dcb_rx_conf; + for (i = 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++) + dcb_info->prio_tc[i] = rx_conf->dcb_tc[i]; + if (dcb_info->nb_tcs == ETH_4_TCS) { + for (i = 0; i < dcb_info->nb_tcs; i++) { + dcb_info->tc_queue.tc_rxq[0][i].base = i * 32; + dcb_info->tc_queue.tc_rxq[0][i].nb_queue = 16; + } + dcb_info->tc_queue.tc_txq[0][0].base = 0; + dcb_info->tc_queue.tc_txq[0][1].base = 64; + dcb_info->tc_queue.tc_txq[0][2].base = 96; + dcb_info->tc_queue.tc_txq[0][3].base = 112; + dcb_info->tc_queue.tc_txq[0][0].nb_queue = 64; + dcb_info->tc_queue.tc_txq[0][1].nb_queue = 32; + dcb_info->tc_queue.tc_txq[0][2].nb_queue = 16; + dcb_info->tc_queue.tc_txq[0][3].nb_queue = 16; + } else if (dcb_info->nb_tcs == ETH_8_TCS) { + for (i = 0; i < dcb_info->nb_tcs; i++) { + dcb_info->tc_queue.tc_rxq[0][i].base = i * 16; + dcb_info->tc_queue.tc_rxq[0][i].nb_queue = 16; + } + dcb_info->tc_queue.tc_txq[0][0].base = 0; + dcb_info->tc_queue.tc_txq[0][1].base = 32; + dcb_info->tc_queue.tc_txq[0][2].base = 64; + dcb_info->tc_queue.tc_txq[0][3].base = 80; + dcb_info->tc_queue.tc_txq[0][4].base = 96; + dcb_info->tc_queue.tc_txq[0][5].base = 104; + dcb_info->tc_queue.tc_txq[0][6].base = 112; + dcb_info->tc_queue.tc_txq[0][7].base = 120; + dcb_info->tc_queue.tc_txq[0][0].nb_queue = 32; + dcb_info->tc_queue.tc_txq[0][1].nb_queue = 32; + dcb_info->tc_queue.tc_txq[0][2].nb_queue = 16; + dcb_info->tc_queue.tc_txq[0][3].nb_queue = 16; + dcb_info->tc_queue.tc_txq[0][4].nb_queue = 8; + dcb_info->tc_queue.tc_txq[0][5].nb_queue = 8; + dcb_info->tc_queue.tc_txq[0][6].nb_queue = 8; + dcb_info->tc_queue.tc_txq[0][7].nb_queue = 8; + } + } + for (i = 0; i < dcb_info->nb_tcs; i++) { + tc = &dcb_config->tc_config[i]; + dcb_info->tc_bws[i] = tc->path[IXGBE_DCB_TX_CONFIG].bwg_percent; + } + return 0; +} + +/* Update e-tag ether type */ +static int +ixgbe_update_e_tag_eth_type(struct ixgbe_hw *hw, + uint16_t ether_type) +{ + uint32_t etag_etype; + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + etag_etype = IXGBE_READ_REG(hw, IXGBE_ETAG_ETYPE); + etag_etype &= ~IXGBE_ETAG_ETYPE_MASK; + etag_etype |= ether_type; + IXGBE_WRITE_REG(hw, IXGBE_ETAG_ETYPE, etag_etype); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/* Config l2 tunnel ether type */ +static int +ixgbe_dev_l2_tunnel_eth_type_conf(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (l2_tunnel == NULL) + return -EINVAL; + + switch (l2_tunnel->l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_update_e_tag_eth_type(hw, l2_tunnel->ether_type); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Enable e-tag tunnel */ +static int +ixgbe_e_tag_enable(struct ixgbe_hw *hw) +{ + uint32_t etag_etype; + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + etag_etype = IXGBE_READ_REG(hw, IXGBE_ETAG_ETYPE); + etag_etype |= IXGBE_ETAG_ETYPE_VALID; + IXGBE_WRITE_REG(hw, IXGBE_ETAG_ETYPE, etag_etype); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/* Enable l2 tunnel */ +static int +ixgbe_dev_l2_tunnel_enable(struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_enable(hw); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Disable e-tag tunnel */ +static int +ixgbe_e_tag_disable(struct ixgbe_hw *hw) +{ + uint32_t etag_etype; + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + etag_etype = IXGBE_READ_REG(hw, IXGBE_ETAG_ETYPE); + etag_etype &= ~IXGBE_ETAG_ETYPE_VALID; + IXGBE_WRITE_REG(hw, IXGBE_ETAG_ETYPE, etag_etype); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/* Disable l2 tunnel */ +static int +ixgbe_dev_l2_tunnel_disable(struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_disable(hw); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +static int +ixgbe_e_tag_filter_del(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t i, rar_entries; + uint32_t rar_low, rar_high; + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + rar_entries = ixgbe_get_num_rx_addrs(hw); + + for (i = 1; i < rar_entries; i++) { + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(i)); + rar_low = IXGBE_READ_REG(hw, IXGBE_RAL(i)); + if ((rar_high & IXGBE_RAH_AV) && + (rar_high & IXGBE_RAH_ADTYPE) && + ((rar_low & IXGBE_RAL_ETAG_FILTER_MASK) == + l2_tunnel->tunnel_id)) { + IXGBE_WRITE_REG(hw, IXGBE_RAL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_RAH(i), 0); + + ixgbe_clear_vmdq(hw, i, IXGBE_CLEAR_VMDQ_ALL); + + return ret; + } + } + + return ret; +} + +static int +ixgbe_e_tag_filter_add(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + uint32_t i, rar_entries; + uint32_t rar_low, rar_high; + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + /* One entry for one tunnel. Try to remove potential existing entry. */ + ixgbe_e_tag_filter_del(dev, l2_tunnel); + + rar_entries = ixgbe_get_num_rx_addrs(hw); + + for (i = 1; i < rar_entries; i++) { + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(i)); + if (rar_high & IXGBE_RAH_AV) { + continue; + } else { + ixgbe_set_vmdq(hw, i, l2_tunnel->pool); + rar_high = IXGBE_RAH_AV | IXGBE_RAH_ADTYPE; + rar_low = l2_tunnel->tunnel_id; + + IXGBE_WRITE_REG(hw, IXGBE_RAL(i), rar_low); + IXGBE_WRITE_REG(hw, IXGBE_RAH(i), rar_high); + + return ret; + } + } + + PMD_INIT_LOG(NOTICE, "The table of E-tag forwarding rule is full." + " Please remove a rule before adding a new one."); + return -EINVAL; +} + +/* Add l2 tunnel filter */ +static int +ixgbe_dev_l2_tunnel_filter_add(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + + switch (l2_tunnel->l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_filter_add(dev, l2_tunnel); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Delete l2 tunnel filter */ +static int +ixgbe_dev_l2_tunnel_filter_del(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + + switch (l2_tunnel->l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_filter_del(dev, l2_tunnel); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/** + * ixgbe_dev_l2_tunnel_filter_handle - Handle operations for l2 tunnel filter. + * @dev: pointer to rte_eth_dev structure + * @filter_op:operation will be taken. + * @arg: a pointer to specific structure corresponding to the filter_op + */ +static int +ixgbe_dev_l2_tunnel_filter_handle(struct rte_eth_dev *dev, + enum rte_filter_op filter_op, + void *arg) +{ + int ret = 0; + + if (filter_op == RTE_ETH_FILTER_NOP) + return 0; + + if (arg == NULL) { + PMD_DRV_LOG(ERR, "arg shouldn't be NULL for operation %u.", + filter_op); + return -EINVAL; + } + + switch (filter_op) { + case RTE_ETH_FILTER_ADD: + ret = ixgbe_dev_l2_tunnel_filter_add + (dev, + (struct rte_eth_l2_tunnel_conf *)arg); + break; + case RTE_ETH_FILTER_DELETE: + ret = ixgbe_dev_l2_tunnel_filter_del + (dev, + (struct rte_eth_l2_tunnel_conf *)arg); + break; + default: + PMD_DRV_LOG(ERR, "unsupported operation %u.", filter_op); + ret = -EINVAL; + break; + } + return ret; +} + +static int +ixgbe_e_tag_forwarding_en_dis(struct rte_eth_dev *dev, bool en) +{ + int ret = 0; + uint32_t ctrl; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + ctrl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + ctrl &= ~IXGBE_VT_CTL_POOLING_MODE_MASK; + if (en) + ctrl |= IXGBE_VT_CTL_POOLING_MODE_ETAG; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, ctrl); + + return ret; +} + +/* Enable l2 tunnel forwarding */ +static int +ixgbe_dev_l2_tunnel_forwarding_enable + (struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_forwarding_en_dis(dev, 1); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Disable l2 tunnel forwarding */ +static int +ixgbe_dev_l2_tunnel_forwarding_disable + (struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_forwarding_en_dis(dev, 0); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +static int +ixgbe_e_tag_insertion_en_dis(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel, + bool en) +{ + int ret = 0; + uint32_t vmtir, vmvir; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (l2_tunnel->vf_id >= dev->pci_dev->max_vfs) { + PMD_DRV_LOG(ERR, + "VF id %u should be less than %u", + l2_tunnel->vf_id, + dev->pci_dev->max_vfs); + return -EINVAL; + } + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + if (en) + vmtir = l2_tunnel->tunnel_id; + else + vmtir = 0; + + IXGBE_WRITE_REG(hw, IXGBE_VMTIR(l2_tunnel->vf_id), vmtir); + + vmvir = IXGBE_READ_REG(hw, IXGBE_VMVIR(l2_tunnel->vf_id)); + vmvir &= ~IXGBE_VMVIR_TAGA_MASK; + if (en) + vmvir |= IXGBE_VMVIR_TAGA_ETAG_INSERT; + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(l2_tunnel->vf_id), vmvir); + + return ret; +} + +/* Enable l2 tunnel tag insertion */ +static int +ixgbe_dev_l2_tunnel_insertion_enable(struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + + switch (l2_tunnel->l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_insertion_en_dis(dev, l2_tunnel, 1); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Disable l2 tunnel tag insertion */ +static int +ixgbe_dev_l2_tunnel_insertion_disable + (struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel) +{ + int ret = 0; + + switch (l2_tunnel->l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_insertion_en_dis(dev, l2_tunnel, 0); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +static int +ixgbe_e_tag_stripping_en_dis(struct rte_eth_dev *dev, + bool en) +{ + int ret = 0; + uint32_t qde; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + qde = IXGBE_READ_REG(hw, IXGBE_QDE); + if (en) + qde |= IXGBE_QDE_STRIP_TAG; + else + qde &= ~IXGBE_QDE_STRIP_TAG; + qde &= ~IXGBE_QDE_READ; + qde |= IXGBE_QDE_WRITE; + IXGBE_WRITE_REG(hw, IXGBE_QDE, qde); + + return ret; +} + +/* Enable l2 tunnel tag stripping */ +static int +ixgbe_dev_l2_tunnel_stripping_enable + (struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_stripping_en_dis(dev, 1); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Disable l2 tunnel tag stripping */ +static int +ixgbe_dev_l2_tunnel_stripping_disable + (struct rte_eth_dev *dev, + enum rte_eth_tunnel_type l2_tunnel_type) +{ + int ret = 0; + + switch (l2_tunnel_type) { + case RTE_L2_TUNNEL_TYPE_E_TAG: + ret = ixgbe_e_tag_stripping_en_dis(dev, 0); + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Enable/disable l2 tunnel offload functions */ +static int +ixgbe_dev_l2_tunnel_offload_set + (struct rte_eth_dev *dev, + struct rte_eth_l2_tunnel_conf *l2_tunnel, + uint32_t mask, + uint8_t en) +{ + int ret = 0; + + if (l2_tunnel == NULL) + return -EINVAL; + + ret = -EINVAL; + if (mask & ETH_L2_TUNNEL_ENABLE_MASK) { + if (en) + ret = ixgbe_dev_l2_tunnel_enable( + dev, + l2_tunnel->l2_tunnel_type); + else + ret = ixgbe_dev_l2_tunnel_disable( + dev, + l2_tunnel->l2_tunnel_type); + } + + if (mask & ETH_L2_TUNNEL_INSERTION_MASK) { + if (en) + ret = ixgbe_dev_l2_tunnel_insertion_enable( + dev, + l2_tunnel); + else + ret = ixgbe_dev_l2_tunnel_insertion_disable( + dev, + l2_tunnel); + } + + if (mask & ETH_L2_TUNNEL_STRIPPING_MASK) { + if (en) + ret = ixgbe_dev_l2_tunnel_stripping_enable( + dev, + l2_tunnel->l2_tunnel_type); + else + ret = ixgbe_dev_l2_tunnel_stripping_disable( + dev, + l2_tunnel->l2_tunnel_type); + } + + if (mask & ETH_L2_TUNNEL_FORWARDING_MASK) { + if (en) + ret = ixgbe_dev_l2_tunnel_forwarding_enable( + dev, + l2_tunnel->l2_tunnel_type); + else + ret = ixgbe_dev_l2_tunnel_forwarding_disable( + dev, + l2_tunnel->l2_tunnel_type); + } + + return ret; +} + +static int +ixgbe_update_vxlan_port(struct ixgbe_hw *hw, + uint16_t port) +{ + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, port); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/* There's only one register for VxLAN UDP port. + * So, we cannot add several ports. Will update it. + */ +static int +ixgbe_add_vxlan_port(struct ixgbe_hw *hw, + uint16_t port) +{ + if (port == 0) { + PMD_DRV_LOG(ERR, "Add VxLAN port 0 is not allowed."); + return -EINVAL; + } + + return ixgbe_update_vxlan_port(hw, port); +} + +/* We cannot delete the VxLAN port. For there's a register for VxLAN + * UDP port, it must have a value. + * So, will reset it to the original value 0. + */ +static int +ixgbe_del_vxlan_port(struct ixgbe_hw *hw, + uint16_t port) +{ + uint16_t cur_port; + + cur_port = (uint16_t)IXGBE_READ_REG(hw, IXGBE_VXLANCTRL); + + if (cur_port != port) { + PMD_DRV_LOG(ERR, "Port %u does not exist.", port); + return -EINVAL; + } + + return ixgbe_update_vxlan_port(hw, 0); +} + +/* Add UDP tunneling port */ +static int +ixgbe_dev_udp_tunnel_port_add(struct rte_eth_dev *dev, + struct rte_eth_udp_tunnel *udp_tunnel) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + if (udp_tunnel == NULL) + return -EINVAL; + + switch (udp_tunnel->prot_type) { + case RTE_TUNNEL_TYPE_VXLAN: + ret = ixgbe_add_vxlan_port(hw, udp_tunnel->udp_port); + break; + + case RTE_TUNNEL_TYPE_GENEVE: + case RTE_TUNNEL_TYPE_TEREDO: + PMD_DRV_LOG(ERR, "Tunnel type is not supported now."); + ret = -EINVAL; + break; + + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* Remove UDP tunneling port */ +static int +ixgbe_dev_udp_tunnel_port_del(struct rte_eth_dev *dev, + struct rte_eth_udp_tunnel *udp_tunnel) +{ + int ret = 0; + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + if (hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_X550EM_a) { + return -ENOTSUP; + } + + if (udp_tunnel == NULL) + return -EINVAL; + + switch (udp_tunnel->prot_type) { + case RTE_TUNNEL_TYPE_VXLAN: + ret = ixgbe_del_vxlan_port(hw, udp_tunnel->udp_port); + break; + case RTE_TUNNEL_TYPE_GENEVE: + case RTE_TUNNEL_TYPE_TEREDO: + PMD_DRV_LOG(ERR, "Tunnel type is not supported now."); + ret = -EINVAL; + break; + default: + PMD_DRV_LOG(ERR, "Invalid tunnel type"); + ret = -EINVAL; + break; + } + + return ret; +} + +/* ixgbevf_update_xcast_mode - Update Multicast mode + * @hw: pointer to the HW structure + * @netdev: pointer to net device structure + * @xcast_mode: new multicast mode + * + * Updates the Multicast Mode of VF. + */ +static int ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, + int xcast_mode) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + u32 msgbuf[2]; + s32 err; + + switch (hw->api_version) { + case ixgbe_mbox_api_12: + break; + default: + return -EOPNOTSUPP; + } + + msgbuf[0] = IXGBE_VF_UPDATE_XCAST_MODE; + msgbuf[1] = xcast_mode; + + err = mbx->ops.write_posted(hw, msgbuf, 2, 0); + if (err) + return err; + + err = mbx->ops.read_posted(hw, msgbuf, 2, 0); + if (err) + return err; + + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + if (msgbuf[0] == (IXGBE_VF_UPDATE_XCAST_MODE | IXGBE_VT_MSGTYPE_NACK)) + return -EPERM; + + return 0; +} + +static void +ixgbevf_dev_allmulticast_enable(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + ixgbevf_update_xcast_mode(hw, IXGBEVF_XCAST_MODE_ALLMULTI); +} + +static void +ixgbevf_dev_allmulticast_disable(struct rte_eth_dev *dev) +{ + struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); + + ixgbevf_update_xcast_mode(hw, IXGBEVF_XCAST_MODE_NONE); } static struct rte_driver rte_ixgbe_driver = {