diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
27 files changed, 10340 insertions, 4012 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 4058673fd853..e5d6f684437e 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -13,5 +13,7 @@ ice-y := ice_main.o \ ice_nvm.o \ ice_switch.o \ ice_sched.o \ + ice_lib.o \ ice_txrx.o \ ice_ethtool.o +ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 868f4a1d0f72..4c4b5717a627 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -28,6 +28,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_bridge.h> +#include <linux/avf/virtchnl.h> #include <net/ipv6.h> #include "ice_devids.h" #include "ice_type.h" @@ -35,17 +36,20 @@ #include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_virtchnl_pf.h" +#include "ice_sriov.h" extern const char ice_drv_ver[]; #define ICE_BAR0 0 #define ICE_DFLT_NUM_DESC 128 -#define ICE_MIN_NUM_DESC 8 -#define ICE_MAX_NUM_DESC 8160 #define ICE_REQ_DESC_MULTIPLE 32 +#define ICE_MIN_NUM_DESC ICE_REQ_DESC_MULTIPLE +#define ICE_MAX_NUM_DESC 8160 #define ICE_DFLT_TRAFFIC_CLASS BIT(0) #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) #define ICE_ETHTOOL_FWVER_LEN 32 #define ICE_AQ_LEN 64 +#define ICE_MBXQ_LEN 64 #define ICE_MIN_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_MAX_VSI_ALLOC 130 @@ -62,6 +66,15 @@ extern const char ice_drv_ver[]; #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff +#define ICE_INVAL_VFID 256 +#define ICE_MAX_VF_COUNT 256 +#define ICE_MAX_QS_PER_VF 256 +#define ICE_MIN_QS_PER_VF 1 +#define ICE_DFLT_QS_PER_VF 4 +#define ICE_MAX_BASE_QS_PER_VF 16 +#define ICE_MAX_INTR_PER_VF 65 +#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) +#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -122,7 +135,8 @@ struct ice_sw { enum ice_state { __ICE_DOWN, __ICE_NEEDS_RESTART, - __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */ + __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ + __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ __ICE_GLOBR_REQ, /* set by driver and peers */ @@ -131,10 +145,24 @@ enum ice_state { __ICE_EMPR_RECV, /* set by OICR handler */ __ICE_SUSPENDED, /* set on module remove path */ __ICE_RESET_FAILED, /* set by reset/rebuild */ + /* When checking for the PF to be in a nominal operating state, the + * bits that are grouped at the beginning of the list need to be + * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will + * be checked. If you need to add a bit into consideration for nominal + * operating state, it must be added before + * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position + * without appropriate consideration. + */ + __ICE_STATE_NOMINAL_CHECK_BITS, __ICE_ADMINQ_EVENT_PENDING, + __ICE_MAILBOXQ_EVENT_PENDING, + __ICE_MDD_EVENT_PENDING, + __ICE_VFLR_EVENT_PENDING, __ICE_FLTR_OVERFLOW_PROMISC, + __ICE_VF_DIS, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, + __ICE_SERVICE_DIS, __ICE_STATE_NBITS /* must be last */ }; @@ -168,7 +196,8 @@ struct ice_vsi { u32 rx_buf_failed; u32 rx_page_failed; int num_q_vectors; - int base_vector; + int sw_base_vector; /* Irq base for OS reserved vectors */ + int hw_base_vector; /* HW (absolute) index of a vector */ enum ice_vsi_type type; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ @@ -176,6 +205,8 @@ struct ice_vsi { /* Interrupt thresholds */ u16 work_lmt; + s16 vf_id; /* VF ID for SR-IOV VSIs */ + /* RSS config */ u16 rss_table_size; /* HW RSS table size */ u16 rss_size; /* Allocated RSS queues */ @@ -225,21 +256,39 @@ struct ice_q_vector { u8 num_ring_tx; /* total number of tx rings in vector */ u8 num_ring_rx; /* total number of rx rings in vector */ char name[ICE_INT_NAME_STR_LEN]; + /* in usecs, need to use ice_intrl_to_usecs_reg() before writing this + * value to the device + */ + u8 intrl; } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { ICE_FLAG_MSIX_ENA, ICE_FLAG_FLTR_SYNC, ICE_FLAG_RSS_ENA, + ICE_FLAG_SRIOV_ENA, + ICE_FLAG_SRIOV_CAPABLE, ICE_PF_FLAGS_NBITS /* must be last */ }; struct ice_pf { struct pci_dev *pdev; + + /* OS reserved IRQ details */ struct msix_entry *msix_entries; - struct ice_res_tracker *irq_tracker; + struct ice_res_tracker *sw_irq_tracker; + + /* HW reserved Interrupts for this PF */ + struct ice_res_tracker *hw_irq_tracker; + struct ice_vsi **vsi; /* VSIs created by the driver */ struct ice_sw *first_sw; /* first switch created by firmware */ + /* Virtchnl/SR-IOV config info */ + struct ice_vf *vf; + int num_alloc_vfs; /* actual number of VFs allocated */ + u16 num_vfs_supported; /* num VFs supported for this PF */ + u16 num_vf_qps; /* num queue pairs per VF */ + u16 num_vf_msix; /* num vectors per VF */ DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS); DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS); @@ -252,9 +301,11 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ u32 msg_enable; u32 hw_csum_rx_error; - u32 oicr_idx; /* Other interrupt cause vector index */ + u32 sw_oicr_idx; /* Other interrupt cause SW vector index */ + u32 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ + u32 hw_oicr_idx; /* Other interrupt cause vector HW index */ + u32 num_avail_hw_msix; /* remaining HW MSIX vectors left unclaimed */ u32 num_lan_msix; /* Total MSIX vectors for base driver */ - u32 num_avail_msix; /* remaining MSIX vectors left unclaimed */ u16 num_lan_tx; /* num lan tx queues setup */ u16 num_lan_rx; /* num lan rx queues setup */ u16 q_left_tx; /* remaining num tx queues left unclaimed */ @@ -270,6 +321,9 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded; /* has previous stats been loaded */ + u32 tx_timeout_count; + unsigned long tx_timeout_last_recovery; + u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; }; @@ -286,8 +340,8 @@ struct ice_netdev_priv { static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi, struct ice_q_vector *q_vector) { - u32 vector = (vsi && q_vector) ? vsi->base_vector + q_vector->v_idx : - ((struct ice_pf *)hw->back)->oicr_idx; + u32 vector = (vsi && q_vector) ? vsi->hw_base_vector + q_vector->v_idx : + ((struct ice_pf *)hw->back)->hw_oicr_idx; int itr = ICE_ITR_NONE; u32 val; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index a0614f472658..6653555f55dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -87,6 +87,8 @@ struct ice_aqc_list_caps { /* Device/Function buffer entry, repeated per reported capability */ struct ice_aqc_list_caps_elem { __le16 cap; +#define ICE_AQC_CAPS_SRIOV 0x0012 +#define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 #define ICE_AQC_CAPS_RSS 0x0040 #define ICE_AQC_CAPS_RXQS 0x0041 @@ -443,6 +445,8 @@ struct ice_aqc_vsi_props { u8 reserved[24]; }; +#define ICE_MAX_NUM_RECIPES 64 + /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ struct ice_aqc_sw_rules { @@ -734,6 +738,10 @@ struct ice_aqc_add_elem { struct ice_aqc_txsched_elem_data generic[1]; }; +struct ice_aqc_get_elem { + struct ice_aqc_txsched_elem_data generic[1]; +}; + struct ice_aqc_get_topo_elem { struct ice_aqc_txsched_topo_grp_info_hdr hdr; struct ice_aqc_txsched_elem_data @@ -771,9 +779,8 @@ struct ice_aqc_layer_props { u8 chunk_size; __le16 max_device_nodes; __le16 max_pf_nodes; - u8 rsvd0[2]; - __le16 max_shared_rate_lmtr; - __le16 max_children; + u8 rsvd0[4]; + __le16 max_sibl_grp_sz; __le16 max_cir_rl_profiles; __le16 max_eir_rl_profiles; __le16 max_srl_profiles; @@ -919,9 +926,11 @@ struct ice_aqc_set_phy_cfg_data { u8 caps; #define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0) #define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1) -#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) -#define ICE_AQ_PHY_ENA_LINK BIT(3) -#define ICE_AQ_PHY_ENA_ATOMIC_LINK BIT(5) +#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) +#define ICE_AQ_PHY_ENA_LINK BIT(3) +#define ICE_AQ_PHY_ENA_AUTO_LINK_UPDT BIT(5) +#define ICE_AQ_PHY_ENA_LESM BIT(6) +#define ICE_AQ_PHY_ENA_AUTO_FEC BIT(7) u8 low_power_ctrl; __le16 eee_cap; /* Value from ice_aqc_get_phy_caps */ __le16 eeer_value; @@ -1068,6 +1077,19 @@ struct ice_aqc_nvm { __le32 addr_low; }; +/** + * Send to PF command (indirect 0x0801) id is only used by PF + * + * Send to VF command (indirect 0x0802) id is only used by PF + * + */ +struct ice_aqc_pf_vf_msg { + __le32 id; + u32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { #define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) @@ -1203,6 +1225,84 @@ struct ice_aqc_dis_txq { struct ice_aqc_dis_txq_item qgrps[1]; }; +/* Configure Firmware Logging Command (indirect 0xFF09) + * Logging Information Read Response (indirect 0xFF10) + * Note: The 0xFF10 command has no input parameters. + */ +struct ice_aqc_fw_logging { + u8 log_ctrl; +#define ICE_AQC_FW_LOG_AQ_EN BIT(0) +#define ICE_AQC_FW_LOG_UART_EN BIT(1) + u8 rsvd0; + u8 log_ctrl_valid; /* Not used by 0xFF10 Response */ +#define ICE_AQC_FW_LOG_AQ_VALID BIT(0) +#define ICE_AQC_FW_LOG_UART_VALID BIT(1) + u8 rsvd1[5]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_fw_logging_mod { + ICE_AQC_FW_LOG_ID_GENERAL = 0, + ICE_AQC_FW_LOG_ID_CTRL, + ICE_AQC_FW_LOG_ID_LINK, + ICE_AQC_FW_LOG_ID_LINK_TOPO, + ICE_AQC_FW_LOG_ID_DNL, + ICE_AQC_FW_LOG_ID_I2C, + ICE_AQC_FW_LOG_ID_SDP, + ICE_AQC_FW_LOG_ID_MDIO, + ICE_AQC_FW_LOG_ID_ADMINQ, + ICE_AQC_FW_LOG_ID_HDMA, + ICE_AQC_FW_LOG_ID_LLDP, + ICE_AQC_FW_LOG_ID_DCBX, + ICE_AQC_FW_LOG_ID_DCB, + ICE_AQC_FW_LOG_ID_NETPROXY, + ICE_AQC_FW_LOG_ID_NVM, + ICE_AQC_FW_LOG_ID_AUTH, + ICE_AQC_FW_LOG_ID_VPD, + ICE_AQC_FW_LOG_ID_IOSF, + ICE_AQC_FW_LOG_ID_PARSER, + ICE_AQC_FW_LOG_ID_SW, + ICE_AQC_FW_LOG_ID_SCHEDULER, + ICE_AQC_FW_LOG_ID_TXQ, + ICE_AQC_FW_LOG_ID_RSVD, + ICE_AQC_FW_LOG_ID_POST, + ICE_AQC_FW_LOG_ID_WATCHDOG, + ICE_AQC_FW_LOG_ID_TASK_DISPATCH, + ICE_AQC_FW_LOG_ID_MNG, + ICE_AQC_FW_LOG_ID_MAX, +}; + +/* This is the buffer for both of the logging commands. + * The entry array size depends on the datalen parameter in the descriptor. + * There will be a total of datalen / 2 entries. + */ +struct ice_aqc_fw_logging_data { + __le16 entry[1]; +#define ICE_AQC_FW_LOG_ID_S 0 +#define ICE_AQC_FW_LOG_ID_M (0xFFF << ICE_AQC_FW_LOG_ID_S) + +#define ICE_AQC_FW_LOG_CONF_SUCCESS 0 /* Used by response */ +#define ICE_AQC_FW_LOG_CONF_BAD_INDX BIT(12) /* Used by response */ + +#define ICE_AQC_FW_LOG_EN_S 12 +#define ICE_AQC_FW_LOG_EN_M (0xF << ICE_AQC_FW_LOG_EN_S) +#define ICE_AQC_FW_LOG_INFO_EN BIT(12) /* Used by command */ +#define ICE_AQC_FW_LOG_INIT_EN BIT(13) /* Used by command */ +#define ICE_AQC_FW_LOG_FLOW_EN BIT(14) /* Used by command */ +#define ICE_AQC_FW_LOG_ERR_EN BIT(15) /* Used by command */ +}; + +/* Get/Clear FW Log (indirect 0xFF11) */ +struct ice_aqc_get_clear_fw_log { + u8 flags; +#define ICE_AQC_FW_LOG_CLEAR BIT(0) +#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL BIT(1) + u8 rsvd1[7]; + __le32 addr_high; + __le32 addr_low; +}; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -1247,11 +1347,15 @@ struct ice_aq_desc { struct ice_aqc_query_txsched_res query_sched_res; struct ice_aqc_add_move_delete_elem add_move_delete_elem; struct ice_aqc_nvm nvm; + struct ice_aqc_pf_vf_msg virt; struct ice_aqc_get_set_rss_lut get_set_rss_lut; struct ice_aqc_get_set_rss_key get_set_rss_key; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; struct ice_aqc_add_get_update_free_vsi vsi_cmd; + struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; + struct ice_aqc_fw_logging fw_logging; + struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; struct ice_aqc_get_link_status get_link_status; @@ -1325,6 +1429,7 @@ enum ice_adminq_opc { /* transmit scheduler commands */ ice_aqc_opc_get_dflt_topo = 0x0400, ice_aqc_opc_add_sched_elems = 0x0401, + ice_aqc_opc_get_sched_elems = 0x0404, ice_aqc_opc_suspend_sched_elems = 0x0409, ice_aqc_opc_resume_sched_elems = 0x040A, ice_aqc_opc_delete_sched_elems = 0x040F, @@ -1340,6 +1445,10 @@ enum ice_adminq_opc { /* NVM commands */ ice_aqc_opc_nvm_read = 0x0701, + /* PF/VF mailbox commands */ + ice_mbx_opc_send_msg_to_pf = 0x0801, + ice_mbx_opc_send_msg_to_vf = 0x0802, + /* RSS commands */ ice_aqc_opc_set_rss_key = 0x0B02, ice_aqc_opc_set_rss_lut = 0x0B03, @@ -1349,6 +1458,9 @@ enum ice_adminq_opc { /* TX queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + + /* debug commands */ + ice_aqc_opc_fw_logging = 0xFF09, }; #endif /* _ICE_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 661beea6af79..8cd6a2401fd9 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -7,16 +7,16 @@ #define ICE_PF_RESET_WAIT_COUNT 200 -#define ICE_NIC_FLX_ENTRY(hw, mdid, idx) \ - wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(ICE_RXDID_FLEX_NIC), \ +#define ICE_PROG_FLEX_ENTRY(hw, rxdid, mdid, idx) \ + wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(rxdid), \ ((ICE_RX_OPC_MDID << \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \ (((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M)) -#define ICE_NIC_FLX_FLG_ENTRY(hw, flg_0, flg_1, flg_2, flg_3, idx) \ - wr32((hw), GLFLXP_RXDID_FLAGS(ICE_RXDID_FLEX_NIC, idx), \ +#define ICE_PROG_FLG_ENTRY(hw, rxdid, flg_0, flg_1, flg_2, flg_3, idx) \ + wr32((hw), GLFLXP_RXDID_FLAGS(rxdid, idx), \ (((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \ GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \ (((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \ @@ -43,6 +43,23 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) } /** + * ice_dev_onetime_setup - Temporary HW/FW workarounds + * @hw: pointer to the HW structure + * + * This function provides temporary workarounds for certain issues + * that are expected to be fixed in the HW/FW. + */ +void ice_dev_onetime_setup(struct ice_hw *hw) +{ + /* configure Rx - set non pxe mode */ + wr32(hw, GLLAN_RCTL_0, 0x1); + +#define MBX_PF_VT_PFALLOC 0x00231E80 + /* set VFs per PF */ + wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF)); +} + +/** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure * @@ -125,7 +142,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, * * Returns the various PHY capabilities supported on the Port (0x0600) */ -static enum ice_status +enum ice_status ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *pcaps, struct ice_sq_cd *cd) @@ -218,7 +235,7 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi) * * Get Link Status (0x607). Returns the link status of the adapter. */ -enum ice_status +static enum ice_status ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_link_status *link, struct ice_sq_cd *cd) { @@ -290,30 +307,85 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, } /** - * ice_init_flex_parser - initialize rx flex parser + * ice_init_flex_flags * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID * - * Function to initialize flex descriptors + * Function to initialize Rx flex flags */ -static void ice_init_flex_parser(struct ice_hw *hw) +static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id) { u8 idx = 0; - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_LOW, 0); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_HIGH, 1); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_LOWER, 2); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_HIGH, 3); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_FRG, ICE_RXFLG_UDP_GRE, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_FIN, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_SYN, ICE_RXFLG_RST, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, - ICE_RXFLG_EVLAN_x8100, ICE_RXFLG_EVLAN_x9100, - idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_VLAN_x8100, ICE_RXFLG_TNL_VLAN, - ICE_RXFLG_TNL_MAC, ICE_RXFLG_TNL0, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + /* Flex-flag fields (0-2) are programmed with FLG64 bits with layout: + * flexiflags0[5:0] - TCP flags, is_packet_fragmented, is_packet_UDP_GRE + * flexiflags1[3:0] - Not used for flag programming + * flexiflags2[7:0] - Tunnel and VLAN types + * 2 invalid fields in last index + */ + switch (prof_id) { + /* Rx flex flags are currently programmed for the NIC profiles only. + * Different flag bit programming configurations can be added per + * profile as needed. + */ + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_FRG, + ICE_RXFLG_UDP_GRE, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_FIN, idx++); + /* flex flag 1 is not used for flexi-flag programming, skipping + * these four FLG64 bits. + */ + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_SYN, ICE_RXFLG_RST, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_EVLAN_x8100, + ICE_RXFLG_EVLAN_x9100, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_VLAN_x8100, + ICE_RXFLG_TNL_VLAN, ICE_RXFLG_TNL_MAC, + ICE_RXFLG_TNL0, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Flag programming for profile ID %d not supported\n", + prof_id); + } +} + +/** + * ice_init_flex_flds + * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID + * + * Function to initialize flex descriptors + */ +static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id) +{ + enum ice_flex_rx_mdid mdid; + + switch (prof_id) { + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_LOW, 0); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_HIGH, 1); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_FLOW_ID_LOWER, 2); + + mdid = (prof_id == ICE_RXDID_FLEX_NIC_2) ? + ICE_RX_MDID_SRC_VSI : ICE_RX_MDID_FLOW_ID_HIGH; + + ICE_PROG_FLEX_ENTRY(hw, prof_id, mdid, 3); + + ice_init_flex_flags(hw, prof_id); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Field init for profile ID %d not supported\n", + prof_id); + } } /** @@ -333,20 +405,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) INIT_LIST_HEAD(&sw->vsi_list_map_head); - mutex_init(&sw->mac_list_lock); - INIT_LIST_HEAD(&sw->mac_list_head); - - mutex_init(&sw->vlan_list_lock); - INIT_LIST_HEAD(&sw->vlan_list_head); - - mutex_init(&sw->eth_m_list_lock); - INIT_LIST_HEAD(&sw->eth_m_list_head); - - mutex_init(&sw->promisc_list_lock); - INIT_LIST_HEAD(&sw->promisc_list_head); - - mutex_init(&sw->mac_vlan_list_lock); - INIT_LIST_HEAD(&sw->mac_vlan_list_head); + ice_init_def_sw_recp(hw); return 0; } @@ -360,20 +419,232 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) struct ice_switch_info *sw = hw->switch_info; struct ice_vsi_list_map_info *v_pos_map; struct ice_vsi_list_map_info *v_tmp_map; + struct ice_sw_recipe *recps; + u8 i; list_for_each_entry_safe(v_pos_map, v_tmp_map, &sw->vsi_list_map_head, list_entry) { list_del(&v_pos_map->list_entry); devm_kfree(ice_hw_to_dev(hw), v_pos_map); } + recps = hw->switch_info->recp_list; + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + + recps[i].root_rid = i; + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } + ice_rm_all_sw_replay_rule_info(hw); + devm_kfree(ice_hw_to_dev(hw), sw->recp_list); + devm_kfree(ice_hw_to_dev(hw), sw); +} - mutex_destroy(&sw->mac_list_lock); - mutex_destroy(&sw->vlan_list_lock); - mutex_destroy(&sw->eth_m_list_lock); - mutex_destroy(&sw->promisc_list_lock); - mutex_destroy(&sw->mac_vlan_list_lock); +#define ICE_FW_LOG_DESC_SIZE(n) (sizeof(struct ice_aqc_fw_logging_data) + \ + (((n) - 1) * sizeof(((struct ice_aqc_fw_logging_data *)0)->entry))) +#define ICE_FW_LOG_DESC_SIZE_MAX \ + ICE_FW_LOG_DESC_SIZE(ICE_AQC_FW_LOG_ID_MAX) - devm_kfree(ice_hw_to_dev(hw), sw); +/** + * ice_cfg_fw_log - configure FW logging + * @hw: pointer to the hw struct + * @enable: enable certain FW logging events if true, disable all if false + * + * This function enables/disables the FW logging via Rx CQ events and a UART + * port based on predetermined configurations. FW logging via the Rx CQ can be + * enabled/disabled for individual PF's. However, FW logging via the UART can + * only be enabled/disabled for all PFs on the same device. + * + * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in + * hw->fw_log need to be set accordingly, e.g. based on user-provided input, + * before initializing the device. + * + * When re/configuring FW logging, callers need to update the "cfg" elements of + * the hw->fw_log.evnts array with the desired logging event configurations for + * modules of interest. When disabling FW logging completely, the callers can + * just pass false in the "enable" parameter. On completion, the function will + * update the "cur" element of the hw->fw_log.evnts array with the resulting + * logging event configurations of the modules that are being re/configured. FW + * logging modules that are not part of a reconfiguration operation retain their + * previous states. + * + * Before resetting the device, it is recommended that the driver disables FW + * logging before shutting down the control queue. When disabling FW logging + * ("enable" = false), the latest configurations of FW logging events stored in + * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after + * a device reset. + * + * When enabling FW logging to emit log messages via the Rx CQ during the + * device's initialization phase, a mechanism alternative to interrupt handlers + * needs to be used to extract FW log messages from the Rx CQ periodically and + * to prevent the Rx CQ from being full and stalling other types of control + * messages from FW to SW. Interrupts are typically disabled during the device's + * initialization phase. + */ +static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) +{ + struct ice_aqc_fw_logging_data *data = NULL; + struct ice_aqc_fw_logging *cmd; + enum ice_status status = 0; + u16 i, chgs = 0, len = 0; + struct ice_aq_desc desc; + u8 actv_evnts = 0; + void *buf = NULL; + + if (!hw->fw_log.cq_en && !hw->fw_log.uart_en) + return 0; + + /* Disable FW logging only when the control queue is still responsive */ + if (!enable && + (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq))) + return 0; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging); + cmd = &desc.params.fw_logging; + + /* Indicate which controls are valid */ + if (hw->fw_log.cq_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID; + + if (hw->fw_log.uart_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID; + + if (enable) { + /* Fill in an array of entries with FW logging modules and + * logging events being reconfigured. + */ + for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { + u16 val; + + /* Keep track of enabled event types */ + actv_evnts |= hw->fw_log.evnts[i].cfg; + + if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur) + continue; + + if (!data) { + data = devm_kzalloc(ice_hw_to_dev(hw), + ICE_FW_LOG_DESC_SIZE_MAX, + GFP_KERNEL); + if (!data) + return ICE_ERR_NO_MEMORY; + } + + val = i << ICE_AQC_FW_LOG_ID_S; + val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S; + data->entry[chgs++] = cpu_to_le16(val); + } + + /* Only enable FW logging if at least one module is specified. + * If FW logging is currently enabled but all modules are not + * enabled to emit log messages, disable FW logging altogether. + */ + if (actv_evnts) { + /* Leave if there is effectively no change */ + if (!chgs) + goto out; + + if (hw->fw_log.cq_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN; + + if (hw->fw_log.uart_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN; + + buf = data; + len = ICE_FW_LOG_DESC_SIZE(chgs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } + } + + status = ice_aq_send_cmd(hw, &desc, buf, len, NULL); + if (!status) { + /* Update the current configuration to reflect events enabled. + * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW + * logging mode is enabled for the device. They do not reflect + * actual modules being enabled to emit log messages. So, their + * values remain unchanged even when all modules are disabled. + */ + u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX; + + hw->fw_log.actv_evnts = actv_evnts; + for (i = 0; i < cnt; i++) { + u16 v, m; + + if (!enable) { + /* When disabling all FW logging events as part + * of device's de-initialization, the original + * configurations are retained, and can be used + * to reconfigure FW logging later if the device + * is re-initialized. + */ + hw->fw_log.evnts[i].cur = 0; + continue; + } + + v = le16_to_cpu(data->entry[i]); + m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S; + hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg; + } + } + +out: + if (data) + devm_kfree(ice_hw_to_dev(hw), data); + + return status; +} + +/** + * ice_output_fw_log + * @hw: pointer to the hw struct + * @desc: pointer to the AQ message descriptor + * @buf: pointer to the buffer accompanying the AQ message + * + * Formats a FW Log message and outputs it via the standard driver logs. + */ +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) +{ + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg Start ]\n"); + ice_debug_array(hw, ICE_DBG_AQ_MSG, 16, 1, (u8 *)buf, + le16_to_cpu(desc->datalen)); + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg End ]\n"); +} + +/** + * ice_get_itr_intrl_gran - determine int/intrl granularity + * @hw: pointer to the hw struct + * + * Determines the itr/intrl granularities based on the maximum aggregate + * bandwidth according to the device's configuration during power-on. + */ +static enum ice_status ice_get_itr_intrl_gran(struct ice_hw *hw) +{ + u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) & + GL_PWR_MODE_CTL_CAR_MAX_BW_M) >> + GL_PWR_MODE_CTL_CAR_MAX_BW_S; + + switch (max_agg_bw) { + case ICE_MAX_AGG_BW_200G: + case ICE_MAX_AGG_BW_100G: + case ICE_MAX_AGG_BW_50G: + hw->itr_gran = ICE_ITR_GRAN_ABOVE_25; + hw->intrl_gran = ICE_INTRL_GRAN_ABOVE_25; + break; + case ICE_MAX_AGG_BW_25G: + hw->itr_gran = ICE_ITR_GRAN_MAX_25; + hw->intrl_gran = ICE_INTRL_GRAN_MAX_25; + break; + default: + ice_debug(hw, ICE_DBG_INIT, + "Failed to determine itr/intrl granularity\n"); + return ICE_ERR_CFG; + } + + return 0; } /** @@ -400,16 +671,19 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) return status; - /* set these values to minimum allowed */ - hw->itr_gran_200 = ICE_ITR_GRAN_MIN_200; - hw->itr_gran_100 = ICE_ITR_GRAN_MIN_100; - hw->itr_gran_50 = ICE_ITR_GRAN_MIN_50; - hw->itr_gran_25 = ICE_ITR_GRAN_MIN_25; + status = ice_get_itr_intrl_gran(hw); + if (status) + return status; status = ice_init_all_ctrlq(hw); if (status) goto err_unroll_cqinit; + /* Enable FW logging. Not fatal if this fails. */ + status = ice_cfg_fw_log(hw, true); + if (status) + ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n"); + status = ice_clear_pf_cfg(hw); if (status) goto err_unroll_cqinit; @@ -472,10 +746,19 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; + /* need a valid SW entry point to build a Tx tree */ + if (!hw->sw_entry_point_layer) { + ice_debug(hw, ICE_DBG_SCHED, "invalid sw entry point\n"); + status = ICE_ERR_CFG; + goto err_unroll_sched; + } + status = ice_init_fltr_mgmt_struct(hw); if (status) goto err_unroll_sched; + ice_dev_onetime_setup(hw); + /* Get MAC information */ /* A single port can report up to two (LAN and WoL) addresses */ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, @@ -494,7 +777,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_flex_parser(hw); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2); return 0; @@ -515,15 +799,18 @@ err_unroll_cqinit: */ void ice_deinit_hw(struct ice_hw *hw) { + ice_cleanup_fltr_mgmt_struct(hw); + ice_sched_cleanup_all(hw); - ice_shutdown_all_ctrlq(hw); if (hw->port_info) { devm_kfree(ice_hw_to_dev(hw), hw->port_info); hw->port_info = NULL; } - ice_cleanup_fltr_mgmt_struct(hw); + /* Attempt to disable FW logging before shutting down control queues */ + ice_cfg_fw_log(hw, false); + ice_shutdown_all_ctrlq(hw); } /** @@ -652,6 +939,8 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) ice_debug(hw, ICE_DBG_INIT, "GlobalR requested\n"); val = GLGEN_RTRIG_GLOBR_M; break; + default: + return ICE_ERR_PARAM; } val |= rd32(hw, GLGEN_RTRIG); @@ -904,7 +1193,22 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) * @timeout: the maximum time in ms that the driver may hold the resource * @cd: pointer to command details structure or NULL * - * requests common resource using the admin queue commands (0x0008) + * Requests common resource using the admin queue commands (0x0008). + * When attempting to acquire the Global Config Lock, the driver can + * learn of three states: + * 1) ICE_SUCCESS - acquired lock, and can perform download package + * 2) ICE_ERR_AQ_ERROR - did not get lock, driver should fail to load + * 3) ICE_ERR_AQ_NO_WORK - did not get lock, but another driver has + * successfully downloaded the package; the driver does + * not have to download the package and can continue + * loading + * + * Note that if the caller is in an acquire lock, perform action, release lock + * phase of operation, it is possible that the FW may detect a timeout and issue + * a CORER. In this case, the driver will receive a CORER interrupt and will + * have to determine its cause. The calling thread that is handling this flow + * will likely get an error propagated back to it indicating the Download + * Package, Update Package or the Release Resource AQ commands timed out. */ static enum ice_status ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, @@ -922,13 +1226,43 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, cmd_resp->res_id = cpu_to_le16(res); cmd_resp->access_type = cpu_to_le16(access); cmd_resp->res_number = cpu_to_le32(sdp_number); + cmd_resp->timeout = cpu_to_le32(*timeout); + *timeout = 0; status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + /* The completion specifies the maximum time in ms that the driver * may hold the resource in the Timeout field. - * If the resource is held by someone else, the command completes with - * busy return value and the timeout field indicates the maximum time - * the current owner of the resource has to free it. + */ + + /* Global config lock response utilizes an additional status field. + * + * If the Global config lock resource is held by some other driver, the + * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field + * and the timeout field indicates the maximum time the current owner + * of the resource has to free it. + */ + if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) { + if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return 0; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_IN_PROG) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return ICE_ERR_AQ_ERROR; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_DONE) { + return ICE_ERR_AQ_NO_WORK; + } + + /* invalid FW response, force a timeout immediately */ + *timeout = 0; + return ICE_ERR_AQ_ERROR; + } + + /* If the resource is held by some other driver, the command completes + * with a busy return value and the timeout field indicates the maximum + * time the current owner of the resource has to free it. */ if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY) *timeout = le32_to_cpu(cmd_resp->timeout); @@ -967,30 +1301,28 @@ ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number, * @hw: pointer to the HW structure * @res: resource id * @access: access type (read or write) + * @timeout: timeout in milliseconds * * This function will attempt to acquire the ownership of a resource. */ enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access) + enum ice_aq_res_access_type access, u32 timeout) { #define ICE_RES_POLLING_DELAY_MS 10 u32 delay = ICE_RES_POLLING_DELAY_MS; + u32 time_left = timeout; enum ice_status status; - u32 time_left = 0; - u32 timeout; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - /* An admin queue return code of ICE_AQ_RC_EEXIST means that another - * driver has previously acquired the resource and performed any - * necessary updates; in this case the caller does not obtain the - * resource and has no further work to do. + /* A return code of ICE_ERR_AQ_NO_WORK means that another driver has + * previously acquired the resource and performed any necessary updates; + * in this case the caller does not obtain the resource and has no + * further work to do. */ - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { - status = ICE_ERR_AQ_NO_WORK; + if (status == ICE_ERR_AQ_NO_WORK) goto ice_acquire_res_exit; - } if (status) ice_debug(hw, ICE_DBG_RES, @@ -1003,11 +1335,9 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, timeout = (timeout > delay) ? timeout - delay : 0; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { + if (status == ICE_ERR_AQ_NO_WORK) /* lock free, but no work to do */ - status = ICE_ERR_AQ_NO_WORK; break; - } if (!status) /* lock acquired */ @@ -1095,6 +1425,28 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, u16 cap = le16_to_cpu(cap_resp->cap); switch (cap) { + case ICE_AQC_CAPS_SRIOV: + caps->sr_iov_1_1 = (number == 1); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: SR-IOV = %d\n", caps->sr_iov_1_1); + break; + case ICE_AQC_CAPS_VF: + if (dev_p) { + dev_p->num_vfs_exposed = number; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs exposed = %d\n", + dev_p->num_vfs_exposed); + } else if (func_p) { + func_p->num_allocd_vfs = number; + func_p->vf_base_id = logical_id; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs allocated = %d\n", + func_p->num_allocd_vfs); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VF base_id = %d\n", + func_p->vf_base_id); + } + break; case ICE_AQC_CAPS_VSI: if (dev_p) { dev_p->num_vsi_allocd_to_host = number; @@ -1171,7 +1523,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, * @hw: pointer to the hw struct * @buf: a virtual buffer to hold the capabilities * @buf_size: Size of the virtual buffer - * @data_size: Size of the returned data, or buf size needed if AQ err==ENOMEM + * @cap_count: cap count needed if AQ err==ENOMEM * @opc: capabilities type to discover - pass in the command opcode * @cd: pointer to command details structure or NULL * @@ -1179,7 +1531,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, * the firmware. */ static enum ice_status -ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u16 *data_size, +ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { struct ice_aqc_list_caps *cmd; @@ -1197,59 +1549,75 @@ ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u16 *data_size, status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); if (!status) ice_parse_caps(hw, buf, le32_to_cpu(cmd->count), opc); - *data_size = le16_to_cpu(desc.datalen); - + else if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOMEM) + *cap_count = le32_to_cpu(cmd->count); return status; } /** - * ice_get_caps - get info about the HW + * ice_discover_caps - get info about the HW * @hw: pointer to the hardware structure + * @opc: capabilities type to discover - pass in the command opcode */ -enum ice_status ice_get_caps(struct ice_hw *hw) +static enum ice_status ice_discover_caps(struct ice_hw *hw, + enum ice_adminq_opc opc) { enum ice_status status; - u16 data_size = 0; + u32 cap_count; u16 cbuf_len; u8 retries; /* The driver doesn't know how many capabilities the device will return * so the buffer size required isn't known ahead of time. The driver * starts with cbuf_len and if this turns out to be insufficient, the - * device returns ICE_AQ_RC_ENOMEM and also the buffer size it needs. - * The driver then allocates the buffer of this size and retries the - * operation. So it follows that the retry count is 2. + * device returns ICE_AQ_RC_ENOMEM and also the cap_count it needs. + * The driver then allocates the buffer based on the count and retries + * the operation. So it follows that the retry count is 2. */ #define ICE_GET_CAP_BUF_COUNT 40 #define ICE_GET_CAP_RETRY_COUNT 2 - cbuf_len = ICE_GET_CAP_BUF_COUNT * - sizeof(struct ice_aqc_list_caps_elem); - + cap_count = ICE_GET_CAP_BUF_COUNT; retries = ICE_GET_CAP_RETRY_COUNT; do { void *cbuf; + cbuf_len = (u16)(cap_count * + sizeof(struct ice_aqc_list_caps_elem)); cbuf = devm_kzalloc(ice_hw_to_dev(hw), cbuf_len, GFP_KERNEL); if (!cbuf) return ICE_ERR_NO_MEMORY; - status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &data_size, - ice_aqc_opc_list_func_caps, NULL); + status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &cap_count, + opc, NULL); devm_kfree(ice_hw_to_dev(hw), cbuf); if (!status || hw->adminq.sq_last_status != ICE_AQ_RC_ENOMEM) break; /* If ENOMEM is returned, try again with bigger buffer */ - cbuf_len = data_size; } while (--retries); return status; } /** + * ice_get_caps - get info about the HW + * @hw: pointer to the hardware structure + */ +enum ice_status ice_get_caps(struct ice_hw *hw) +{ + enum ice_status status; + + status = ice_discover_caps(hw, ice_aqc_opc_list_dev_caps); + if (!status) + status = ice_discover_caps(hw, ice_aqc_opc_list_func_caps); + + return status; +} + +/** * ice_aq_manage_mac_write - manage MAC address write command * @hw: pointer to the hw struct * @mac_addr: MAC address to be written as LAA/LAA+WoL/Port address @@ -1307,6 +1675,110 @@ void ice_clear_pxe_mode(struct ice_hw *hw) } /** + * ice_get_link_speed_based_on_phy_type - returns link speed + * @phy_type_low: lower part of phy_type + * + * This helper function will convert a phy_type_low to its corresponding link + * speed. + * Note: In the structure of phy_type_low, there should be one bit set, as + * this function will convert one phy type to its speed. + * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + */ +static u16 +ice_get_link_speed_based_on_phy_type(u64 phy_type_low) +{ + u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + + switch (phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + case ICE_PHY_TYPE_LOW_100M_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_100MB; + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + case ICE_PHY_TYPE_LOW_1000BASE_KX: + case ICE_PHY_TYPE_LOW_1G_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_1000MB; + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + case ICE_PHY_TYPE_LOW_2500BASE_X: + case ICE_PHY_TYPE_LOW_2500BASE_KX: + speed_phy_type_low = ICE_AQ_LINK_SPEED_2500MB; + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + speed_phy_type_low = ICE_AQ_LINK_SPEED_5GB; + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10GBASE_SR: + case ICE_PHY_TYPE_LOW_10GBASE_LR: + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_10GB; + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_25G_AUI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_25GB; + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB; + break; + default: + speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + + return speed_phy_type_low; +} + +/** + * ice_update_phy_type + * @phy_type_low: pointer to the lower part of phy_type + * @link_speeds_bitmap: targeted link speeds bitmap + * + * Note: For the link_speeds_bitmap structure, you can check it at + * [ice_aqc_get_link_status->link_speed]. Caller can pass in + * link_speeds_bitmap include multiple speeds. + * + * The value of phy_type_low will present a certain link speed. This helper + * function will turn on bits in the phy_type_low based on the value of + * link_speeds_bitmap input parameter. + */ +void ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap) +{ + u16 speed = ICE_AQ_LINK_SPEED_UNKNOWN; + u64 pt_low; + int index; + + /* We first check with low part of phy_type */ + for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) { + pt_low = BIT_ULL(index); + speed = ice_get_link_speed_based_on_phy_type(pt_low); + + if (link_speeds_bitmap & speed) + *phy_type_low |= BIT_ULL(index); + } +} + +/** * ice_aq_set_phy_cfg * @hw: pointer to the hw struct * @lport: logical port number @@ -1318,19 +1790,18 @@ void ice_clear_pxe_mode(struct ice_hw *hw) * mode as the PF may not have the privilege to set some of the PHY Config * parameters. This status will be indicated by the command response (0x0601). */ -static enum ice_status +enum ice_status ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd) { - struct ice_aqc_set_phy_cfg *cmd; struct ice_aq_desc desc; if (!cfg) return ICE_ERR_PARAM; - cmd = &desc.params.set_phy; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg); - cmd->lport_num = lport; + desc.params.set_phy.lport_num = lport; + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd); } @@ -1339,8 +1810,7 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, * ice_update_link_info - update status of the HW network link * @pi: port info structure of the interested logical port */ -static enum ice_status -ice_update_link_info(struct ice_port_info *pi) +enum ice_status ice_update_link_info(struct ice_port_info *pi) { struct ice_aqc_get_phy_caps_data *pcaps; struct ice_phy_info *phy_info; @@ -1379,12 +1849,12 @@ out: * ice_set_fc * @pi: port information structure * @aq_failures: pointer to status code, specific to ice_set_fc routine - * @atomic_restart: enable automatic link update + * @ena_auto_link_update: enable automatic link update * * Set the requested flow control mode. */ enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { struct ice_aqc_set_phy_cfg_data cfg = { 0 }; struct ice_aqc_get_phy_caps_data *pcaps; @@ -1434,8 +1904,8 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) int retry_count, retry_max = 10; /* Auto restart link so settings take effect */ - if (atomic_restart) - cfg.caps |= ICE_AQ_PHY_ENA_ATOMIC_LINK; + if (ena_auto_link_update) + cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; /* Copy over all the old settings */ cfg.phy_type_low = pcaps->phy_type_low; cfg.low_power_ctrl = pcaps->low_power_ctrl; @@ -1535,33 +2005,6 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, } /** - * ice_aq_set_event_mask - * @hw: pointer to the hw struct - * @port_num: port number of the physical function - * @mask: event mask to be set - * @cd: pointer to command details structure or NULL - * - * Set event mask (0x0613) - */ -enum ice_status -ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, - struct ice_sq_cd *cd) -{ - struct ice_aqc_set_event_mask *cmd; - struct ice_aq_desc desc; - - cmd = &desc.params.set_event_mask; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask); - - cmd->lport_num = port_num; - - cmd->event_mask = cpu_to_le16(mask); - - return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); -} - -/** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure * @vsi_id: VSI FW index @@ -1654,7 +2097,7 @@ ice_aq_get_set_rss_lut_exit: /** * ice_aq_get_rss_lut * @hw: pointer to the hardware structure - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @lut_type: LUT table type * @lut: pointer to the LUT buffer provided by the caller * @lut_size: size of the LUT buffer @@ -1662,17 +2105,20 @@ ice_aq_get_set_rss_lut_exit: * get the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, - u16 lut_size) +ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, + u8 *lut, u16 lut_size) { - return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0, - false); + if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), + lut_type, lut, lut_size, 0, false); } /** * ice_aq_set_rss_lut * @hw: pointer to the hardware structure - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @lut_type: LUT table type * @lut: pointer to the LUT buffer provided by the caller * @lut_size: size of the LUT buffer @@ -1680,11 +2126,14 @@ ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, * set the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, - u16 lut_size) +ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, + u8 *lut, u16 lut_size) { - return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0, - true); + if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), + lut_type, lut, lut_size, 0, true); } /** @@ -1725,31 +2174,39 @@ ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, /** * ice_aq_get_rss_key * @hw: pointer to the hw struct - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @key: pointer to key info struct * * get the RSS key per VSI */ enum ice_status -ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *key) { - return __ice_aq_get_set_rss_key(hw, vsi_id, key, false); + if (!ice_is_vsi_valid(hw, vsi_handle) || !key) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), + key, false); } /** * ice_aq_set_rss_key * @hw: pointer to the hw struct - * @vsi_id: VSI FW index + * @vsi_handle: software VSI handle * @keys: pointer to key info struct * * set the RSS key per VSI */ enum ice_status -ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys) { - return __ice_aq_get_set_rss_key(hw, vsi_id, keys, true); + if (!ice_is_vsi_valid(hw, vsi_handle) || !keys) + return ICE_ERR_PARAM; + + return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), + keys, true); } /** @@ -1820,6 +2277,8 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, * @num_qgrps: number of groups in the list * @qg_list: the list of groups to disable * @buf_size: the total size of the qg_list buffer in bytes + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * Disable LAN Tx queue (0x0C31) @@ -1827,6 +2286,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, static enum ice_status ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *qg_list, u16 buf_size, + enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { struct ice_aqc_dis_txqs *cmd; @@ -1836,14 +2296,45 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, cmd = &desc.params.dis_txqs; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs); - if (!qg_list) + /* qg_list can be NULL only in VM/VF reset flow */ + if (!qg_list && !rst_src) return ICE_ERR_PARAM; if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS) return ICE_ERR_PARAM; - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + cmd->num_entries = num_qgrps; + cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) & + ICE_AQC_Q_DIS_TIMEOUT_M); + + switch (rst_src) { + case ICE_VM_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET; + cmd->vmvf_and_timeout |= + cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_VF_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET; + /* In this case, FW expects vmvf_num to be absolute VF id */ + cmd->vmvf_and_timeout |= + cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) & + ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_NO_RESET: + default: + break; + } + + /* If no queue group info, we are in a reset flow. Issue the AQ */ + if (!qg_list) + goto do_aq; + + /* set RD bit to indicate that command buffer is provided by the driver + * and it needs to be read by the firmware + */ + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + for (i = 0; i < num_qgrps; ++i) { /* Calculate the size taken up by the queue IDs in this group */ sz += qg_list[i].num_qs * sizeof(qg_list[i].q_id); @@ -1859,6 +2350,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, if (buf_size != sz) return ICE_ERR_PARAM; +do_aq: return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd); } @@ -2088,7 +2580,7 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /** * ice_ena_vsi_txq * @pi: port information structure - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * @tc: tc number * @num_qgrps: Number of added queue groups * @buf: list of queue groups to be added @@ -2098,7 +2590,7 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) * This function adds one lan q */ enum ice_status -ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, +ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd) { @@ -2115,15 +2607,19 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, hw = pi->hw; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + mutex_lock(&pi->sched_lock); /* find a parent node */ - parent = ice_sched_get_free_qparent(pi, vsi_id, tc, + parent = ice_sched_get_free_qparent(pi, vsi_handle, tc, ICE_SCHED_NODE_OWNER_LAN); if (!parent) { status = ICE_ERR_PARAM; goto ena_txq_exit; } + buf->parent_teid = parent->info.node_teid; node.parent_teid = parent->info.node_teid; /* Mark that the values in the "generic" section as valid. The default @@ -2161,13 +2657,16 @@ ena_txq_exit: * @num_queues: number of queues * @q_ids: pointer to the q_id array * @q_teids: pointer to queue node teids + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * This function removes queues and their corresponding nodes in SW DB */ enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cd) + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cd) { enum ice_status status = ICE_ERR_DOES_NOT_EXIST; struct ice_aqc_dis_txq_item qg_list; @@ -2176,6 +2675,15 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return ICE_ERR_CFG; + /* if queue is disabled already yet the disable queue command has to be + * sent to complete the VF reset, then call ice_aq_dis_lan_txq without + * any queue information + */ + + if (!num_queues && rst_src) + return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src, vmvf_num, + NULL); + mutex_lock(&pi->sched_lock); for (i = 0; i < num_queues; i++) { @@ -2188,7 +2696,8 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, qg_list.num_qs = 1; qg_list.q_id[0] = cpu_to_le16(q_ids[i]); status = ice_aq_dis_lan_txq(pi->hw, 1, &qg_list, - sizeof(qg_list), cd); + sizeof(qg_list), rst_src, vmvf_num, + cd); if (status) break; @@ -2201,7 +2710,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, /** * ice_cfg_vsi_qs - configure the new/exisiting VSI queues * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_bitmap: TC bitmap * @maxqs: max queues array per TC * @owner: lan or rdma @@ -2209,7 +2718,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, * This function adds/updates the VSI queues per TC. */ static enum ice_status -ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *maxqs, u8 owner) { enum ice_status status = 0; @@ -2218,6 +2727,9 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return ICE_ERR_CFG; + if (!ice_is_vsi_valid(pi->hw, vsi_handle)) + return ICE_ERR_PARAM; + mutex_lock(&pi->sched_lock); for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { @@ -2225,7 +2737,7 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, if (!ice_sched_get_tc_node(pi, i)) continue; - status = ice_sched_cfg_vsi(pi, vsi_id, i, maxqs[i], owner, + status = ice_sched_cfg_vsi(pi, vsi_handle, i, maxqs[i], owner, ice_is_tc_ena(tc_bitmap, i)); if (status) break; @@ -2238,16 +2750,140 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, /** * ice_cfg_vsi_lan - configure VSI lan queues * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_bitmap: TC bitmap * @max_lanqs: max lan queues array per TC * * This function adds/updates the VSI lan queues per TC. */ enum ice_status -ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs) { - return ice_cfg_vsi_qs(pi, vsi_id, tc_bitmap, max_lanqs, + return ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, max_lanqs, ICE_SCHED_NODE_OWNER_LAN); } + +/** + * ice_replay_pre_init - replay pre initialization + * @hw: pointer to the hw struct + * + * Initializes required config data for VSI, FD, ACL, and RSS before replay. + */ +static enum ice_status ice_replay_pre_init(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + /* Delete old entries from replay filter list head if there is any */ + ice_rm_all_sw_replay_rule_info(hw); + /* In start of replay, move entries into replay_rules list, it + * will allow adding rules entries back to filt_rules list, + * which is operational list. + */ + for (i = 0; i < ICE_SW_LKUP_LAST; i++) + list_replace_init(&sw->recp_list[i].filt_rules, + &sw->recp_list[i].filt_replay_rules); + + return 0; +} + +/** + * ice_replay_vsi - replay VSI configuration + * @hw: pointer to the hw struct + * @vsi_handle: driver VSI handle + * + * Restore all VSI configuration after reset. It is required to call this + * function with main VSI first. + */ +enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle) +{ + enum ice_status status; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + /* Replay pre-initialization if there is any */ + if (vsi_handle == ICE_MAIN_VSI_HANDLE) { + status = ice_replay_pre_init(hw); + if (status) + return status; + } + + /* Replay per VSI all filters */ + status = ice_replay_vsi_all_fltr(hw, vsi_handle); + return status; +} + +/** + * ice_replay_post - post replay configuration cleanup + * @hw: pointer to the hw struct + * + * Post replay cleanup. + */ +void ice_replay_post(struct ice_hw *hw) +{ + /* Delete old entries from replay filter list head */ + ice_rm_all_sw_replay_rule_info(hw); +} + +/** + * ice_stat_update40 - read 40 bit stat from the chip and update stat values + * @hw: ptr to the hardware info + * @hireg: high 32 bit HW register to read from + * @loreg: low 32 bit HW register to read from + * @prev_stat_loaded: bool to specify if previous stats are loaded + * @prev_stat: ptr to previous loaded stat value + * @cur_stat: ptr to current stat value + */ +void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, + bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat) +{ + u64 new_data; + + new_data = rd32(hw, loreg); + new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; + + /* device stats are not reset at PFR, they likely will not be zeroed + * when the driver starts. So save the first values read and use them as + * offsets to be subtracted from the raw values in order to report stats + * that count from zero. + */ + if (!prev_stat_loaded) + *prev_stat = new_data; + if (new_data >= *prev_stat) + *cur_stat = new_data - *prev_stat; + else + /* to manage the potential roll-over */ + *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; + *cur_stat &= 0xFFFFFFFFFFULL; +} + +/** + * ice_stat_update32 - read 32 bit stat from the chip and update stat values + * @hw: ptr to the hardware info + * @reg: HW register to read from + * @prev_stat_loaded: bool to specify if previous stats are loaded + * @prev_stat: ptr to previous loaded stat value + * @cur_stat: ptr to current stat value + */ +void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat) +{ + u32 new_data; + + new_data = rd32(hw, reg); + + /* device stats are not reset at PFR, they likely will not be zeroed + * when the driver starts. So save the first values read and use them as + * offsets to be subtracted from the raw values in order to report stats + * that count from zero. + */ + if (!prev_stat_loaded) + *prev_stat = new_data; + if (new_data >= *prev_stat) + *cur_stat = new_data - *prev_stat; + else + /* to manage the potential roll-over */ + *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; +} diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 9a5519130af1..cf760c24a6aa 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -7,6 +7,7 @@ #include "ice.h" #include "ice_type.h" #include "ice_switch.h" +#include <linux/avf/virtchnl.h> void ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf, u16 buf_len); @@ -21,9 +22,10 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending); enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up); +enum ice_status ice_update_link_info(struct ice_port_info *pi); enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access); + enum ice_aq_res_access_type access, u32 timeout); void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res); enum ice_status ice_init_nvm(struct ice_hw *hw); enum ice_status @@ -32,22 +34,26 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_sq_cd *cd); void ice_clear_pxe_mode(struct ice_hw *hw); enum ice_status ice_get_caps(struct ice_hw *hw); + +void ice_dev_onetime_setup(struct ice_hw *hw); + enum ice_status ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, +ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, u16 lut_size); enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, +ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, u16 lut_size); enum ice_status -ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); enum ice_status -ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id, +ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); + bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); @@ -58,29 +64,43 @@ enum ice_status ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); + +enum ice_status +ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, + struct ice_aqc_get_phy_caps_data *caps, + struct ice_sq_cd *cd); +void +ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap); enum ice_status ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); enum ice_status ice_clear_pf_cfg(struct ice_hw *hw); enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart); +ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, + struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd); +enum ice_status +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, + bool ena_auto_link_update); + enum ice_status ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd); enum ice_status -ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, - struct ice_link_status *link, struct ice_sq_cd *cd); -enum ice_status -ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, - struct ice_sq_cd *cd); -enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cmd_details); + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cmd_details); enum ice_status -ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap, +ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs); enum ice_status -ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, +ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); +void ice_replay_post(struct ice_hw *hw); +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); +void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, + bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 62be72fdc8f3..84c967294eaf 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -33,6 +33,36 @@ static void ice_adminq_init_regs(struct ice_hw *hw) } /** + * ice_mailbox_init_regs - Initialize Mailbox registers + * @hw: pointer to the hardware structure + * + * This assumes the alloc_sq and alloc_rq functions have already been called + */ +static void ice_mailbox_init_regs(struct ice_hw *hw) +{ + struct ice_ctl_q_info *cq = &hw->mailboxq; + + /* set head and tail registers in our local struct */ + cq->sq.head = PF_MBX_ATQH; + cq->sq.tail = PF_MBX_ATQT; + cq->sq.len = PF_MBX_ATQLEN; + cq->sq.bah = PF_MBX_ATQBAH; + cq->sq.bal = PF_MBX_ATQBAL; + cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M; + cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M; + cq->sq.head_mask = PF_MBX_ATQH_ATQH_M; + + cq->rq.head = PF_MBX_ARQH; + cq->rq.tail = PF_MBX_ARQT; + cq->rq.len = PF_MBX_ARQLEN; + cq->rq.bah = PF_MBX_ARQBAH; + cq->rq.bal = PF_MBX_ARQBAL; + cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M; + cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M; + cq->rq.head_mask = PF_MBX_ARQH_ARQH_M; +} + +/** * ice_check_sq_alive * @hw: pointer to the hw struct * @cq: pointer to the specific Control queue @@ -518,22 +548,31 @@ shutdown_sq_out: /** * ice_aq_ver_check - Check the reported AQ API version. - * @fw_branch: The "branch" of FW, typically describes the device type - * @fw_major: The major version of the FW API - * @fw_minor: The minor version increment of the FW API + * @hw: pointer to the hardware structure * * Checks if the driver should load on a given AQ API version. * * Return: 'true' iff the driver should attempt to load. 'false' otherwise. */ -static bool ice_aq_ver_check(u8 fw_branch, u8 fw_major, u8 fw_minor) +static bool ice_aq_ver_check(struct ice_hw *hw) { - if (fw_branch != EXP_FW_API_VER_BRANCH) - return false; - if (fw_major != EXP_FW_API_VER_MAJOR) - return false; - if (fw_minor != EXP_FW_API_VER_MINOR) + if (hw->api_maj_ver > EXP_FW_API_VER_MAJOR) { + /* Major API version is newer than expected, don't load */ + dev_warn(ice_hw_to_dev(hw), + "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); return false; + } else if (hw->api_maj_ver == EXP_FW_API_VER_MAJOR) { + if (hw->api_min_ver > (EXP_FW_API_VER_MINOR + 2)) + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); + else if ((hw->api_min_ver + 2) < EXP_FW_API_VER_MINOR) + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + } else { + /* Major API version is older than expected, log a warning */ + dev_info(ice_hw_to_dev(hw), + "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + } return true; } @@ -588,8 +627,7 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) if (status) goto init_ctrlq_free_rq; - if (!ice_aq_ver_check(hw->api_branch, hw->api_maj_ver, - hw->api_min_ver)) { + if (!ice_aq_ver_check(hw)) { status = ICE_ERR_FW_API_VER; goto init_ctrlq_free_rq; } @@ -597,11 +635,11 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) return 0; init_ctrlq_free_rq: - if (cq->rq.head) { + if (cq->rq.count) { ice_shutdown_rq(hw, cq); mutex_destroy(&cq->rq_lock); } - if (cq->sq.head) { + if (cq->sq.count) { ice_shutdown_sq(hw, cq); mutex_destroy(&cq->sq_lock); } @@ -631,6 +669,10 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) ice_adminq_init_regs(hw); cq = &hw->adminq; break; + case ICE_CTL_Q_MAILBOX: + ice_mailbox_init_regs(hw); + cq = &hw->mailboxq; + break; default: return ICE_ERR_PARAM; } @@ -688,7 +730,12 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) if (ret_code) return ret_code; - return ice_init_check_adminq(hw); + ret_code = ice_init_check_adminq(hw); + if (ret_code) + return ret_code; + + /* Init Mailbox queue */ + return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** @@ -706,15 +753,18 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) if (ice_check_sq_alive(hw, cq)) ice_aq_q_shutdown(hw, true); break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + break; default: return; } - if (cq->sq.head) { + if (cq->sq.count) { ice_shutdown_sq(hw, cq); mutex_destroy(&cq->sq_lock); } - if (cq->rq.head) { + if (cq->rq.count) { ice_shutdown_rq(hw, cq); mutex_destroy(&cq->rq_lock); } @@ -728,6 +778,8 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { /* Shutdown FW admin queue */ ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + /* Shutdown PF-VF Mailbox */ + ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** @@ -806,6 +858,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, u16 retval = 0; u32 val = 0; + /* if reset is in progress return a soft error */ + if (hw->reset_ongoing) + return ICE_ERR_RESET_ONGOING; mutex_lock(&cq->sq_lock); cq->sq_last_status = ICE_AQ_RC_OK; @@ -847,7 +902,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use); if (cd) - memcpy(details, cd, sizeof(*details)); + *details = *cd; else memset(details, 0, sizeof(*details)); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index ea02b89243e2..0038a4109c99 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -8,6 +8,7 @@ /* Maximum buffer lengths for all control queue types */ #define ICE_AQ_MAX_BUF_LEN 4096 +#define ICE_MBXQ_MAX_BUF_LEN 4096 #define ICE_CTL_Q_DESC(R, i) \ (&(((struct ice_aq_desc *)((R).desc_buf.va))[i])) @@ -18,16 +19,16 @@ /* Defines that help manage the driver vs FW API checks. * Take a look at ice_aq_ver_check in ice_controlq.c for actual usage. - * */ #define EXP_FW_API_VER_BRANCH 0x00 -#define EXP_FW_API_VER_MAJOR 0x00 -#define EXP_FW_API_VER_MINOR 0x01 +#define EXP_FW_API_VER_MAJOR 0x01 +#define EXP_FW_API_VER_MINOR 0x03 /* Different control queue types: These are mainly for SW consumption. */ enum ice_ctl_q { ICE_CTL_Q_UNKNOWN = 0, ICE_CTL_Q_ADMIN, + ICE_CTL_Q_MAILBOX, }; /* Control Queue default settings */ diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 0e14d7215a6e..f8d5c661d0ba 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -5,15 +5,11 @@ #define _ICE_DEVIDS_H_ /* Device IDs */ -/* Intel(R) Ethernet Controller C810 for backplane */ -#define ICE_DEV_ID_C810_BACKPLANE 0x1591 -/* Intel(R) Ethernet Controller C810 for QSFP */ -#define ICE_DEV_ID_C810_QSFP 0x1592 -/* Intel(R) Ethernet Controller C810 for SFP */ -#define ICE_DEV_ID_C810_SFP 0x1593 -/* Intel(R) Ethernet Controller C810/X557-AT 10GBASE-T */ -#define ICE_DEV_ID_C810_10G_BASE_T 0x1594 -/* Intel(R) Ethernet Controller C810 1GbE */ -#define ICE_DEV_ID_C810_SGMII 0x1595 +/* Intel(R) Ethernet Controller E810-C for backplane */ +#define ICE_DEV_ID_E810C_BACKPLANE 0x1591 +/* Intel(R) Ethernet Controller E810-C for QSFP */ +#define ICE_DEV_ID_E810C_QSFP 0x1592 +/* Intel(R) Ethernet Controller E810-C for SFP */ +#define ICE_DEV_ID_E810C_SFP 0x1593 #endif /* _ICE_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index c71a9b528d6d..96923580f2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -332,58 +332,473 @@ ice_get_ethtool_stats(struct net_device *netdev, } } -static int -ice_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *ks) +/** + * ice_phy_type_to_ethtool - convert the phy_types to ethtool link modes + * @netdev: network interface device structure + * @ks: ethtool link ksettings struct to fill out + */ +static void ice_phy_type_to_ethtool(struct net_device *netdev, + struct ethtool_link_ksettings *ks) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; - bool link_up; + u64 phy_types_low; hw_link_info = &vsi->port_info->phy.link_info; - link_up = hw_link_info->link_info & ICE_AQ_LINK_UP; + phy_types_low = vsi->port_info->phy.phy_type_low; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); + + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_100M_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1G_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_SX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_LX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_X || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_DA || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_SR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_SR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_SR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseSR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_LR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseLR4_Full); + } - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 10000baseT_Full); + /* Autoneg PHY types */ + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); + } +} - /* set speed and duplex */ - if (link_up) { - switch (hw_link_info->link_speed) { - case ICE_AQ_LINK_SPEED_100MB: - ks->base.speed = SPEED_100; - break; - case ICE_AQ_LINK_SPEED_2500MB: - ks->base.speed = SPEED_2500; - break; - case ICE_AQ_LINK_SPEED_5GB: - ks->base.speed = SPEED_5000; - break; - case ICE_AQ_LINK_SPEED_10GB: - ks->base.speed = SPEED_10000; - break; - case ICE_AQ_LINK_SPEED_25GB: - ks->base.speed = SPEED_25000; - break; - case ICE_AQ_LINK_SPEED_40GB: - ks->base.speed = SPEED_40000; - break; - default: - ks->base.speed = SPEED_UNKNOWN; - break; - } +#define TEST_SET_BITS_TIMEOUT 50 +#define TEST_SET_BITS_SLEEP_MAX 2000 +#define TEST_SET_BITS_SLEEP_MIN 1000 - ks->base.duplex = DUPLEX_FULL; - } else { - ks->base.speed = SPEED_UNKNOWN; - ks->base.duplex = DUPLEX_UNKNOWN; +/** + * ice_get_settings_link_up - Get Link settings for when link is up + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + */ +static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks, + struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings cap_ksettings; + struct ice_link_status *link_info; + struct ice_vsi *vsi = np->vsi; + bool unrecog_phy_low = false; + + link_info = &vsi->port_info->phy.link_info; + + /* Initialize supported and advertised settings based on phy settings */ + switch (link_info->phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_100M_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1G_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_X: + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_SR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + break; + default: + unrecog_phy_low = true; + } + + if (unrecog_phy_low) { + /* if we got here and link is up something bad is afoot */ + netdev_info(netdev, "WARNING: Unrecognized PHY_Low (0x%llx).\n", + (u64)link_info->phy_type_low); } + /* Now that we've worked out everything that could be supported by the + * current PHY type, get what is supported by the NVM and intersect + * them to get what is truly supported + */ + memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings)); + ice_phy_type_to_ethtool(netdev, &cap_ksettings); + ethtool_intersect_link_masks(ks, &cap_ksettings); + + switch (link_info->link_speed) { + case ICE_AQ_LINK_SPEED_40GB: + ks->base.speed = SPEED_40000; + break; + case ICE_AQ_LINK_SPEED_25GB: + ks->base.speed = SPEED_25000; + break; + case ICE_AQ_LINK_SPEED_20GB: + ks->base.speed = SPEED_20000; + break; + case ICE_AQ_LINK_SPEED_10GB: + ks->base.speed = SPEED_10000; + break; + case ICE_AQ_LINK_SPEED_5GB: + ks->base.speed = SPEED_5000; + break; + case ICE_AQ_LINK_SPEED_2500MB: + ks->base.speed = SPEED_2500; + break; + case ICE_AQ_LINK_SPEED_1000MB: + ks->base.speed = SPEED_1000; + break; + case ICE_AQ_LINK_SPEED_100MB: + ks->base.speed = SPEED_100; + break; + default: + netdev_info(netdev, + "WARNING: Unrecognized link_speed (0x%x).\n", + link_info->link_speed); + break; + } + ks->base.duplex = DUPLEX_FULL; +} + +/** + * ice_get_settings_link_down - Get the Link settings when link is down + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + * + * Reports link settings that can be determined when link is down + */ +static void +ice_get_settings_link_down(struct ethtool_link_ksettings *ks, + struct net_device __always_unused *netdev) +{ + /* link is down and the driver needs to fall back on + * supported phy types to figure out what info to display + */ + ice_phy_type_to_ethtool(netdev, ks); + + /* With no link, speed and duplex are unknown */ + ks->base.speed = SPEED_UNKNOWN; + ks->base.duplex = DUPLEX_UNKNOWN; +} + +/** + * ice_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Reports speed/duplex settings based on media_type + */ +static int ice_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ks) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_link_status *hw_link_info; + struct ice_vsi *vsi = np->vsi; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); + hw_link_info = &vsi->port_info->phy.link_info; + + /* set speed and duplex */ + if (hw_link_info->link_info & ICE_AQ_LINK_UP) + ice_get_settings_link_up(ks, netdev); + else + ice_get_settings_link_down(ks, netdev); + /* set autoneg settings */ - ks->base.autoneg = ((hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ks->base.autoneg = (hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; /* set media type settings */ switch (vsi->port_info->phy.media_type) { @@ -442,6 +857,311 @@ ice_get_link_ksettings(struct net_device *netdev, } /** + * ice_ksettings_find_adv_link_speed - Find advertising link speed + * @ks: ethtool ksettings + */ +static u16 +ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) +{ + u16 adv_link_speed = 0; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 100baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 5000baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_5GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseLR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_25GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseCR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseSR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseLR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseKR4_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_40GB; + + return adv_link_speed; +} + +/** + * ice_setup_autoneg + * @p: port info + * @ks: ethtool_link_ksettings + * @config: configuration that will be sent down to FW + * @autoneg_enabled: autonegotiation is enabled or not + * @autoneg_changed: will there a change in autonegotiation + * @netdev: network interface device structure + * + * Setup PHY autonegotiation feature + */ +static int +ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks, + struct ice_aqc_set_phy_cfg_data *config, + u8 autoneg_enabled, u8 *autoneg_changed, + struct net_device *netdev) +{ + int err = 0; + + *autoneg_changed = 0; + + /* Check autoneg */ + if (autoneg_enabled == AUTONEG_ENABLE) { + /* If autoneg was not already enabled */ + if (!(p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)) { + /* If autoneg is not supported, return error */ + if (!ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg not supported on this phy.\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } else { + /* If autoneg is currently enabled */ + if (p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) { + /* If autoneg is supported 10GBASE_T is the only phy + * that can disable it, so otherwise return error + */ + if (ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps &= ~ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } + + return err; +} + +/** + * ice_set_link_ksettings - Set Speed and Duplex + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Set speed/duplex per media_types advertised/forced + */ +static int ice_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ks) +{ + u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings safe_ks, copy_ks; + struct ice_aqc_get_phy_caps_data *abilities; + u16 adv_link_speed, curr_link_speed, idx; + struct ice_aqc_set_phy_cfg_data config; + struct ice_pf *pf = np->vsi->back; + struct ice_port_info *p; + u8 autoneg_changed = 0; + enum ice_status status; + u64 phy_type_low; + int err = 0; + bool linkup; + + p = np->vsi->port_info; + + if (!p) + return -EOPNOTSUPP; + + /* Check if this is lan vsi */ + for (idx = 0 ; idx < pf->num_alloc_vsi ; idx++) { + if (pf->vsi[idx]->type == ICE_VSI_PF) { + if (np->vsi != pf->vsi[idx]) + return -EOPNOTSUPP; + break; + } + } + + if (p->phy.media_type != ICE_MEDIA_BASET && + p->phy.media_type != ICE_MEDIA_FIBER && + p->phy.media_type != ICE_MEDIA_BACKPLANE && + p->phy.media_type != ICE_MEDIA_DA && + p->phy.link_info.link_info & ICE_AQ_LINK_UP) + return -EOPNOTSUPP; + + /* copy the ksettings to copy_ks to avoid modifying the original */ + memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings)); + + /* save autoneg out of ksettings */ + autoneg = copy_ks.base.autoneg; + + memset(&safe_ks, 0, sizeof(safe_ks)); + + /* Get link modes supported by hardware.*/ + ice_phy_type_to_ethtool(netdev, &safe_ks); + + /* and check against modes requested by user. + * Return an error if unsupported mode was set. + */ + if (!bitmap_subset(copy_ks.link_modes.advertising, + safe_ks.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; + + /* get our own copy of the bits to check against */ + memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings)); + safe_ks.base.cmd = copy_ks.base.cmd; + safe_ks.base.link_mode_masks_nwords = + copy_ks.base.link_mode_masks_nwords; + ice_get_link_ksettings(netdev, &safe_ks); + + /* set autoneg back to what it currently is */ + copy_ks.base.autoneg = safe_ks.base.autoneg; + /* we don't compare the speed */ + copy_ks.base.speed = safe_ks.base.speed; + + /* If copy_ks.base and safe_ks.base are not the same now, then they are + * trying to set something that we do not support. + */ + if (memcmp(©_ks.base, &safe_ks.base, + sizeof(struct ethtool_link_settings))) + return -EOPNOTSUPP; + + while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(TEST_SET_BITS_SLEEP_MIN, TEST_SET_BITS_SLEEP_MAX); + } + + abilities = devm_kzalloc(&pf->pdev->dev, sizeof(*abilities), + GFP_KERNEL); + if (!abilities) + return -ENOMEM; + + /* Get the current phy config */ + status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_SW_CFG, abilities, + NULL); + if (status) { + err = -EAGAIN; + goto done; + } + + /* Copy abilities to config in case autoneg is not set below */ + memset(&config, 0, sizeof(struct ice_aqc_set_phy_cfg_data)); + config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE; + if (abilities->caps & ICE_AQC_PHY_AN_MODE) + config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + + /* Check autoneg */ + err = ice_setup_autoneg(p, &safe_ks, &config, autoneg, &autoneg_changed, + netdev); + + if (err) + goto done; + + /* Call to get the current link speed */ + p->phy.get_link_info = true; + status = ice_get_link_status(p, &linkup); + if (status) { + err = -EAGAIN; + goto done; + } + + curr_link_speed = p->phy.link_info.link_speed; + adv_link_speed = ice_ksettings_find_adv_link_speed(ks); + + /* If speed didn't get set, set it to what it currently is. + * This is needed because if advertise is 0 (as it is when autoneg + * is disabled) then speed won't get set. + */ + if (!adv_link_speed) + adv_link_speed = curr_link_speed; + + /* Convert the advertise link speeds to their corresponded PHY_TYPE */ + ice_update_phy_type(&phy_type_low, adv_link_speed); + + if (!autoneg_changed && adv_link_speed == curr_link_speed) { + netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); + goto done; + } + + /* copy over the rest of the abilities */ + config.low_power_ctrl = abilities->low_power_ctrl; + config.eee_cap = abilities->eee_cap; + config.eeer_value = abilities->eeer_value; + config.link_fec_opt = abilities->link_fec_options; + + /* save the requested speeds */ + p->phy.link_info.req_speeds = adv_link_speed; + + /* set link and auto negotiation so changes take effect */ + config.caps |= ICE_AQ_PHY_ENA_LINK; + + if (phy_type_low) { + config.phy_type_low = cpu_to_le64(phy_type_low) & + abilities->phy_type_low; + } else { + err = -EAGAIN; + netdev_info(netdev, "Nothing changed. No PHY_TYPE is corresponded to advertised link speed.\n"); + goto done; + } + + /* If link is up put link down */ + if (p->phy.link_info.link_info & ICE_AQ_LINK_UP) { + /* Tell the OS link is going down, the link will go + * back up when fw says it is ready asynchronously + */ + ice_print_link_msg(np->vsi, false); + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + } + + /* make the aq call */ + status = ice_aq_set_phy_cfg(&pf->hw, lport, &config, NULL); + if (status) { + netdev_info(netdev, "Set phy config failed,\n"); + err = -EAGAIN; + } + +done: + devm_kfree(&pf->pdev->dev, abilities); + clear_bit(__ICE_CFG_BUSY, pf->state); + + return err; +} + +/** * ice_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -478,9 +1198,11 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) ring->tx_max_pending = ICE_MAX_NUM_DESC; ring->rx_pending = vsi->rx_rings[0]->count; ring->tx_pending = vsi->tx_rings[0]->count; - ring->rx_mini_pending = ICE_MIN_NUM_DESC; + + /* Rx mini and jumbo rings are not supported */ ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; + ring->rx_mini_pending = 0; ring->rx_jumbo_pending = 0; } @@ -498,14 +1220,23 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) ring->tx_pending < ICE_MIN_NUM_DESC || ring->rx_pending > ICE_MAX_NUM_DESC || ring->rx_pending < ICE_MIN_NUM_DESC) { - netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d]\n", + netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n", ring->tx_pending, ring->rx_pending, - ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC); + ICE_MIN_NUM_DESC, ICE_MAX_NUM_DESC, + ICE_REQ_DESC_MULTIPLE); return -EINVAL; } new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); + if (new_tx_cnt != ring->tx_pending) + netdev_info(netdev, + "Requested Tx descriptor count rounded up to %d\n", + new_tx_cnt); new_rx_cnt = ALIGN(ring->rx_pending, ICE_REQ_DESC_MULTIPLE); + if (new_rx_cnt != ring->rx_pending) + netdev_info(netdev, + "Requested Rx descriptor count rounded up to %d\n", + new_rx_cnt); /* if nothing to do return success */ if (new_tx_cnt == vsi->tx_rings[0]->count && @@ -933,6 +1664,7 @@ static int ice_set_rxfh(struct net_device *netdev, const u32 *indir, static const struct ethtool_ops ice_ethtool_ops = { .get_link_ksettings = ice_get_link_ksettings, + .set_link_ksettings = ice_set_link_ksettings, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 6076fc87df9d..5fdea6ec7675 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -6,251 +6,331 @@ #ifndef _ICE_HW_AUTOGEN_H_ #define _ICE_HW_AUTOGEN_H_ -#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) -#define PF_FW_ARQBAH 0x00080180 -#define PF_FW_ARQBAL 0x00080080 -#define PF_FW_ARQH 0x00080380 -#define PF_FW_ARQH_ARQH_S 0 -#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, PF_FW_ARQH_ARQH_S) -#define PF_FW_ARQLEN 0x00080280 -#define PF_FW_ARQLEN_ARQLEN_S 0 -#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, PF_FW_ARQLEN_ARQLEN_S) -#define PF_FW_ARQLEN_ARQVFE_S 28 -#define PF_FW_ARQLEN_ARQVFE_M BIT(PF_FW_ARQLEN_ARQVFE_S) -#define PF_FW_ARQLEN_ARQOVFL_S 29 -#define PF_FW_ARQLEN_ARQOVFL_M BIT(PF_FW_ARQLEN_ARQOVFL_S) -#define PF_FW_ARQLEN_ARQCRIT_S 30 -#define PF_FW_ARQLEN_ARQCRIT_M BIT(PF_FW_ARQLEN_ARQCRIT_S) -#define PF_FW_ARQLEN_ARQENABLE_S 31 -#define PF_FW_ARQLEN_ARQENABLE_M BIT(PF_FW_ARQLEN_ARQENABLE_S) -#define PF_FW_ARQT 0x00080480 -#define PF_FW_ATQBAH 0x00080100 -#define PF_FW_ATQBAL 0x00080000 -#define PF_FW_ATQH 0x00080300 -#define PF_FW_ATQH_ATQH_S 0 -#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, PF_FW_ATQH_ATQH_S) -#define PF_FW_ATQLEN 0x00080200 -#define PF_FW_ATQLEN_ATQLEN_S 0 -#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, PF_FW_ATQLEN_ATQLEN_S) -#define PF_FW_ATQLEN_ATQVFE_S 28 -#define PF_FW_ATQLEN_ATQVFE_M BIT(PF_FW_ATQLEN_ATQVFE_S) -#define PF_FW_ATQLEN_ATQOVFL_S 29 -#define PF_FW_ATQLEN_ATQOVFL_M BIT(PF_FW_ATQLEN_ATQOVFL_S) -#define PF_FW_ATQLEN_ATQCRIT_S 30 -#define PF_FW_ATQLEN_ATQCRIT_M BIT(PF_FW_ATQLEN_ATQCRIT_S) -#define PF_FW_ATQLEN_ATQENABLE_S 31 -#define PF_FW_ATQLEN_ATQENABLE_M BIT(PF_FW_ATQLEN_ATQENABLE_S) -#define PF_FW_ATQT 0x00080400 - +#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) +#define PF_FW_ARQBAH 0x00080180 +#define PF_FW_ARQBAL 0x00080080 +#define PF_FW_ARQH 0x00080380 +#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN 0x00080280 +#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN_ARQVFE_M BIT(28) +#define PF_FW_ARQLEN_ARQOVFL_M BIT(29) +#define PF_FW_ARQLEN_ARQCRIT_M BIT(30) +#define PF_FW_ARQLEN_ARQENABLE_M BIT(31) +#define PF_FW_ARQT 0x00080480 +#define PF_FW_ATQBAH 0x00080100 +#define PF_FW_ATQBAL 0x00080000 +#define PF_FW_ATQH 0x00080300 +#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN 0x00080200 +#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN_ATQVFE_M BIT(28) +#define PF_FW_ATQLEN_ATQOVFL_M BIT(29) +#define PF_FW_ATQLEN_ATQCRIT_M BIT(30) +#define PF_FW_ATQLEN_ATQENABLE_M BIT(31) +#define PF_FW_ATQT 0x00080400 +#define PF_MBX_ARQBAH 0x0022E400 +#define PF_MBX_ARQBAL 0x0022E380 +#define PF_MBX_ARQH 0x0022E500 +#define PF_MBX_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN 0x0022E480 +#define PF_MBX_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN_ARQENABLE_M BIT(31) +#define PF_MBX_ARQT 0x0022E580 +#define PF_MBX_ATQBAH 0x0022E180 +#define PF_MBX_ATQBAL 0x0022E100 +#define PF_MBX_ATQH 0x0022E280 +#define PF_MBX_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN 0x0022E200 +#define PF_MBX_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN_ATQENABLE_M BIT(31) +#define PF_MBX_ATQT 0x0022E300 #define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S 8 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, 8) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S 16 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, 16) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S 24 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, 24) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_1(_i) (0x0045c900 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_2(_i) (0x0045ca00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_3(_i) (0x0045cb00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S) - -#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) -#define QRXFLXP_CNTXT_RXDID_IDX_S 0 -#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, QRXFLXP_CNTXT_RXDID_IDX_S) -#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 -#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, QRXFLXP_CNTXT_RXDID_PRIO_S) -#define QRXFLXP_CNTXT_TS_S 11 -#define QRXFLXP_CNTXT_TS_M BIT(QRXFLXP_CNTXT_TS_S) -#define GLGEN_RSTAT 0x000B8188 -#define GLGEN_RSTAT_DEVSTATE_S 0 -#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, GLGEN_RSTAT_DEVSTATE_S) -#define GLGEN_RSTCTL 0x000B8180 -#define GLGEN_RSTCTL_GRSTDEL_S 0 -#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) -#define GLGEN_RSTAT_RESET_TYPE_S 2 -#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, GLGEN_RSTAT_RESET_TYPE_S) -#define GLGEN_RTRIG 0x000B8190 -#define GLGEN_RTRIG_CORER_S 0 -#define GLGEN_RTRIG_CORER_M BIT(GLGEN_RTRIG_CORER_S) -#define GLGEN_RTRIG_GLOBR_S 1 -#define GLGEN_RTRIG_GLOBR_M BIT(GLGEN_RTRIG_GLOBR_S) -#define GLGEN_STAT 0x000B612C -#define PFGEN_CTRL 0x00091000 -#define PFGEN_CTRL_PFSWR_S 0 -#define PFGEN_CTRL_PFSWR_M BIT(PFGEN_CTRL_PFSWR_S) -#define PFGEN_STATE 0x00088000 -#define PRTGEN_STATUS 0x000B8100 -#define PFHMC_ERRORDATA 0x00520500 -#define PFHMC_ERRORINFO 0x00520400 -#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) -#define GLINT_DYN_CTL_INTENA_S 0 -#define GLINT_DYN_CTL_INTENA_M BIT(GLINT_DYN_CTL_INTENA_S) -#define GLINT_DYN_CTL_CLEARPBA_S 1 -#define GLINT_DYN_CTL_CLEARPBA_M BIT(GLINT_DYN_CTL_CLEARPBA_S) -#define GLINT_DYN_CTL_SWINT_TRIG_S 2 -#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(GLINT_DYN_CTL_SWINT_TRIG_S) -#define GLINT_DYN_CTL_ITR_INDX_S 3 -#define GLINT_DYN_CTL_SW_ITR_INDX_S 25 -#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S) -#define GLINT_DYN_CTL_INTENA_MSK_S 31 -#define GLINT_DYN_CTL_INTENA_MSK_M BIT(GLINT_DYN_CTL_INTENA_MSK_S) -#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) -#define PFINT_FW_CTL 0x0016C800 -#define PFINT_FW_CTL_MSIX_INDX_S 0 -#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_FW_CTL_MSIX_INDX_S) -#define PFINT_FW_CTL_ITR_INDX_S 11 -#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, PFINT_FW_CTL_ITR_INDX_S) -#define PFINT_FW_CTL_CAUSE_ENA_S 30 -#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S) -#define PFINT_OICR 0x0016CA00 -#define PFINT_OICR_ECC_ERR_S 16 -#define PFINT_OICR_ECC_ERR_M BIT(PFINT_OICR_ECC_ERR_S) -#define PFINT_OICR_MAL_DETECT_S 19 -#define PFINT_OICR_MAL_DETECT_M BIT(PFINT_OICR_MAL_DETECT_S) -#define PFINT_OICR_GRST_S 20 -#define PFINT_OICR_GRST_M BIT(PFINT_OICR_GRST_S) -#define PFINT_OICR_PCI_EXCEPTION_S 21 -#define PFINT_OICR_PCI_EXCEPTION_M BIT(PFINT_OICR_PCI_EXCEPTION_S) -#define PFINT_OICR_HMC_ERR_S 26 -#define PFINT_OICR_HMC_ERR_M BIT(PFINT_OICR_HMC_ERR_S) -#define PFINT_OICR_PE_CRITERR_S 28 -#define PFINT_OICR_PE_CRITERR_M BIT(PFINT_OICR_PE_CRITERR_S) -#define PFINT_OICR_CTL 0x0016CA80 -#define PFINT_OICR_CTL_MSIX_INDX_S 0 -#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_OICR_CTL_MSIX_INDX_S) -#define PFINT_OICR_CTL_ITR_INDX_S 11 -#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, PFINT_OICR_CTL_ITR_INDX_S) -#define PFINT_OICR_CTL_CAUSE_ENA_S 30 -#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(PFINT_OICR_CTL_CAUSE_ENA_S) -#define PFINT_OICR_ENA 0x0016C900 -#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) -#define QINT_RQCTL_MSIX_INDX_S 0 -#define QINT_RQCTL_ITR_INDX_S 11 -#define QINT_RQCTL_CAUSE_ENA_S 30 -#define QINT_RQCTL_CAUSE_ENA_M BIT(QINT_RQCTL_CAUSE_ENA_S) -#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) -#define QINT_TQCTL_MSIX_INDX_S 0 -#define QINT_TQCTL_ITR_INDX_S 11 -#define QINT_TQCTL_CAUSE_ENA_S 30 -#define QINT_TQCTL_CAUSE_ENA_M BIT(QINT_TQCTL_CAUSE_ENA_S) -#define GLLAN_RCTL_0 0x002941F8 -#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) -#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) -#define QRX_CTRL_MAX_INDEX 2047 -#define QRX_CTRL_QENA_REQ_S 0 -#define QRX_CTRL_QENA_REQ_M BIT(QRX_CTRL_QENA_REQ_S) -#define QRX_CTRL_QENA_STAT_S 2 -#define QRX_CTRL_QENA_STAT_M BIT(QRX_CTRL_QENA_STAT_S) -#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) -#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) -#define GLNVM_FLA 0x000B6108 -#define GLNVM_FLA_LOCKED_S 6 -#define GLNVM_FLA_LOCKED_M BIT(GLNVM_FLA_LOCKED_S) -#define GLNVM_GENS 0x000B6100 -#define GLNVM_GENS_SR_SIZE_S 5 -#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, GLNVM_GENS_SR_SIZE_S) -#define GLNVM_ULD 0x000B6008 -#define GLNVM_ULD_CORER_DONE_S 3 -#define GLNVM_ULD_CORER_DONE_M BIT(GLNVM_ULD_CORER_DONE_S) -#define GLNVM_ULD_GLOBR_DONE_S 4 -#define GLNVM_ULD_GLOBR_DONE_M BIT(GLNVM_ULD_GLOBR_DONE_S) -#define PF_FUNC_RID 0x0009E880 -#define PF_FUNC_RID_FUNC_NUM_S 0 -#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, PF_FUNC_RID_FUNC_NUM_S) -#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) -#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) -#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) -#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) -#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) -#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) -#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) -#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) -#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) -#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) -#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) -#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) -#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) -#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) -#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) -#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) -#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) -#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) -#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) -#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) -#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) -#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) -#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) -#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) -#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) -#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) -#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) -#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) -#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) -#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) -#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) -#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) -#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) -#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) -#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) -#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) -#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) -#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) -#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) -#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) -#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) -#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) -#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) -#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) -#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) -#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) -#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) -#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) -#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) -#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) -#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) -#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) -#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) -#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) -#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) -#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) -#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) -#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) -#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) -#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) -#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) -#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) -#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) -#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) -#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) -#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) -#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) -#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) -#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) -#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) -#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) -#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) -#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) -#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) -#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) -#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) -#define VSIQF_HKEY_MAX_INDEX 12 +#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, 30) +#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) +#define QRXFLXP_CNTXT_RXDID_IDX_S 0 +#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, 0) +#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 +#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, 8) +#define GLGEN_RSTAT 0x000B8188 +#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0) +#define GLGEN_RSTCTL 0x000B8180 +#define GLGEN_RSTCTL_GRSTDEL_S 0 +#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) +#define GLGEN_RSTAT_RESET_TYPE_S 2 +#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, 2) +#define GLGEN_RTRIG 0x000B8190 +#define GLGEN_RTRIG_CORER_M BIT(0) +#define GLGEN_RTRIG_GLOBR_M BIT(1) +#define GLGEN_STAT 0x000B612C +#define GLGEN_VFLRSTAT(_i) (0x00093A04 + ((_i) * 4)) +#define PFGEN_CTRL 0x00091000 +#define PFGEN_CTRL_PFSWR_M BIT(0) +#define PFGEN_STATE 0x00088000 +#define PRTGEN_STATUS 0x000B8100 +#define VFGEN_RSTAT(_VF) (0x00074000 + ((_VF) * 4)) +#define VPGEN_VFRSTAT(_VF) (0x00090800 + ((_VF) * 4)) +#define VPGEN_VFRSTAT_VFRD_M BIT(0) +#define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4)) +#define VPGEN_VFRTRIG_VFSWR_M BIT(0) +#define PFHMC_ERRORDATA 0x00520500 +#define PFHMC_ERRORINFO 0x00520400 +#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) +#define GLINT_DYN_CTL_INTENA_M BIT(0) +#define GLINT_DYN_CTL_CLEARPBA_M BIT(1) +#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(2) +#define GLINT_DYN_CTL_ITR_INDX_S 3 +#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) +#define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) +#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) +#define GLINT_RATE(_INT) (0x0015A000 + ((_INT) * 4)) +#define GLINT_RATE_INTRL_ENA_M BIT(6) +#define GLINT_VECT2FUNC(_INT) (0x00162000 + ((_INT) * 4)) +#define GLINT_VECT2FUNC_VF_NUM_S 0 +#define GLINT_VECT2FUNC_VF_NUM_M ICE_M(0xFF, 0) +#define GLINT_VECT2FUNC_PF_NUM_S 12 +#define GLINT_VECT2FUNC_PF_NUM_M ICE_M(0x7, 12) +#define GLINT_VECT2FUNC_IS_PF_S 16 +#define GLINT_VECT2FUNC_IS_PF_M BIT(16) +#define PFINT_FW_CTL 0x0016C800 +#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_FW_CTL_ITR_INDX_S 11 +#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_FW_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_MBX_CTL 0x0016B280 +#define PFINT_MBX_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_MBX_CTL_ITR_INDX_S 11 +#define PFINT_MBX_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_MBX_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR 0x0016CA00 +#define PFINT_OICR_ECC_ERR_M BIT(16) +#define PFINT_OICR_MAL_DETECT_M BIT(19) +#define PFINT_OICR_GRST_M BIT(20) +#define PFINT_OICR_PCI_EXCEPTION_M BIT(21) +#define PFINT_OICR_HMC_ERR_M BIT(26) +#define PFINT_OICR_PE_CRITERR_M BIT(28) +#define PFINT_OICR_VFLR_M BIT(29) +#define PFINT_OICR_CTL 0x0016CA80 +#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_OICR_CTL_ITR_INDX_S 11 +#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR_ENA 0x0016C900 +#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) +#define QINT_RQCTL_MSIX_INDX_S 0 +#define QINT_RQCTL_ITR_INDX_S 11 +#define QINT_RQCTL_CAUSE_ENA_M BIT(30) +#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) +#define QINT_TQCTL_MSIX_INDX_S 0 +#define QINT_TQCTL_ITR_INDX_S 11 +#define QINT_TQCTL_CAUSE_ENA_M BIT(30) +#define VPINT_ALLOC(_VF) (0x001D1000 + ((_VF) * 4)) +#define VPINT_ALLOC_FIRST_S 0 +#define VPINT_ALLOC_FIRST_M ICE_M(0x7FF, 0) +#define VPINT_ALLOC_LAST_S 12 +#define VPINT_ALLOC_LAST_M ICE_M(0x7FF, 12) +#define VPINT_ALLOC_VALID_M BIT(31) +#define VPINT_ALLOC_PCI(_VF) (0x0009D000 + ((_VF) * 4)) +#define VPINT_ALLOC_PCI_FIRST_S 0 +#define VPINT_ALLOC_PCI_FIRST_M ICE_M(0x7FF, 0) +#define VPINT_ALLOC_PCI_LAST_S 12 +#define VPINT_ALLOC_PCI_LAST_M ICE_M(0x7FF, 12) +#define VPINT_ALLOC_PCI_VALID_M BIT(31) +#define GLLAN_RCTL_0 0x002941F8 +#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) +#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) +#define QRX_CTRL_MAX_INDEX 2047 +#define QRX_CTRL_QENA_REQ_S 0 +#define QRX_CTRL_QENA_REQ_M BIT(0) +#define QRX_CTRL_QENA_STAT_S 2 +#define QRX_CTRL_QENA_STAT_M BIT(2) +#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) +#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) +#define QRX_TAIL_MAX_INDEX 2047 +#define QRX_TAIL_TAIL_S 0 +#define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0) +#define VPLAN_RX_QBASE(_VF) (0x00072000 + ((_VF) * 4)) +#define VPLAN_RX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_RX_QBASE_VFFIRSTQ_M ICE_M(0x7FF, 0) +#define VPLAN_RX_QBASE_VFNUMQ_S 16 +#define VPLAN_RX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_RXQ_MAPENA(_VF) (0x00073000 + ((_VF) * 4)) +#define VPLAN_RXQ_MAPENA_RX_ENA_M BIT(0) +#define VPLAN_TX_QBASE(_VF) (0x001D1800 + ((_VF) * 4)) +#define VPLAN_TX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_TX_QBASE_VFFIRSTQ_M ICE_M(0x3FFF, 0) +#define VPLAN_TX_QBASE_VFNUMQ_S 16 +#define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4)) +#define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0) +#define GL_MDET_RX 0x00294C00 +#define GL_MDET_RX_QNUM_S 0 +#define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_RX_VF_NUM_S 15 +#define GL_MDET_RX_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_RX_PF_NUM_S 23 +#define GL_MDET_RX_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_RX_MAL_TYPE_S 26 +#define GL_MDET_RX_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_RX_VALID_M BIT(31) +#define GL_MDET_TX_PQM 0x002D2E00 +#define GL_MDET_TX_PQM_PF_NUM_S 0 +#define GL_MDET_TX_PQM_PF_NUM_M ICE_M(0x7, 0) +#define GL_MDET_TX_PQM_VF_NUM_S 4 +#define GL_MDET_TX_PQM_VF_NUM_M ICE_M(0xFF, 4) +#define GL_MDET_TX_PQM_QNUM_S 12 +#define GL_MDET_TX_PQM_QNUM_M ICE_M(0x3FFF, 12) +#define GL_MDET_TX_PQM_MAL_TYPE_S 26 +#define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_PQM_VALID_M BIT(31) +#define GL_MDET_TX_TCLAN 0x000FC068 +#define GL_MDET_TX_TCLAN_QNUM_S 0 +#define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_TX_TCLAN_VF_NUM_S 15 +#define GL_MDET_TX_TCLAN_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_TX_TCLAN_PF_NUM_S 23 +#define GL_MDET_TX_TCLAN_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_TX_TCLAN_MAL_TYPE_S 26 +#define GL_MDET_TX_TCLAN_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_TCLAN_VALID_M BIT(31) +#define PF_MDET_RX 0x00294280 +#define PF_MDET_RX_VALID_M BIT(0) +#define PF_MDET_TX_PQM 0x002D2C80 +#define PF_MDET_TX_PQM_VALID_M BIT(0) +#define PF_MDET_TX_TCLAN 0x000FC000 +#define PF_MDET_TX_TCLAN_VALID_M BIT(0) +#define VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4)) +#define VP_MDET_RX_VALID_M BIT(0) +#define VP_MDET_TX_PQM(_VF) (0x002D2000 + ((_VF) * 4)) +#define VP_MDET_TX_PQM_VALID_M BIT(0) +#define VP_MDET_TX_TCLAN(_VF) (0x000FB800 + ((_VF) * 4)) +#define VP_MDET_TX_TCLAN_VALID_M BIT(0) +#define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4)) +#define VP_MDET_TX_TDPU_VALID_M BIT(0) +#define GLNVM_FLA 0x000B6108 +#define GLNVM_FLA_LOCKED_M BIT(6) +#define GLNVM_GENS 0x000B6100 +#define GLNVM_GENS_SR_SIZE_S 5 +#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5) +#define GLNVM_ULD 0x000B6008 +#define GLNVM_ULD_CORER_DONE_M BIT(3) +#define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define PF_FUNC_RID 0x0009E880 +#define PF_FUNC_RID_FUNC_NUM_S 0 +#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) +#define PF_PCI_CIAA 0x0009E580 +#define PF_PCI_CIAA_VF_NUM_S 12 +#define PF_PCI_CIAD 0x0009E500 +#define GL_PWR_MODE_CTL 0x000B820C +#define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 +#define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) +#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) +#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) +#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) +#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) +#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) +#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) +#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) +#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) +#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) +#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) +#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) +#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) +#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) +#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) +#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) +#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) +#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) +#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) +#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) +#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) +#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) +#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) +#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) +#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) +#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) +#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) +#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) +#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) +#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) +#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) +#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) +#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) +#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) +#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) +#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) +#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) +#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) +#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) +#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) +#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) +#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) +#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) +#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) +#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) +#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) +#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) +#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) +#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) +#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) +#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) +#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) +#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) +#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) +#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) +#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) +#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) +#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) +#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) +#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) +#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) +#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) +#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) +#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) +#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) +#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) +#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) +#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) +#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) +#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) +#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) +#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) +#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) +#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) +#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) +#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) +#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) +#define PF_VT_PFALLOC_HIF 0x0009DD80 +#define VSIQF_HKEY_MAX_INDEX 12 +#define VSIQF_HLUT_MAX_INDEX 15 +#define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) +#define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 068dbc740b76..7d2a66739e3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -188,23 +188,25 @@ struct ice_32b_rx_flex_desc_nic { * with a specific metadata (profile 7 reserved for HW) */ enum ice_rxdid { - ICE_RXDID_START = 0, - ICE_RXDID_LEGACY_0 = ICE_RXDID_START, - ICE_RXDID_LEGACY_1, - ICE_RXDID_FLX_START, - ICE_RXDID_FLEX_NIC = ICE_RXDID_FLX_START, - ICE_RXDID_FLX_LAST = 63, - ICE_RXDID_LAST = ICE_RXDID_FLX_LAST + ICE_RXDID_LEGACY_0 = 0, + ICE_RXDID_LEGACY_1 = 1, + ICE_RXDID_FLEX_NIC = 2, + ICE_RXDID_FLEX_NIC_2 = 6, + ICE_RXDID_HW = 7, + ICE_RXDID_LAST = 63, }; /* Receive Flex Descriptor Rx opcode values */ #define ICE_RX_OPC_MDID 0x01 /* Receive Descriptor MDID values */ -#define ICE_RX_MDID_FLOW_ID_LOWER 5 -#define ICE_RX_MDID_FLOW_ID_HIGH 6 -#define ICE_RX_MDID_HASH_LOW 56 -#define ICE_RX_MDID_HASH_HIGH 57 +enum ice_flex_rx_mdid { + ICE_RX_MDID_FLOW_ID_LOWER = 5, + ICE_RX_MDID_FLOW_ID_HIGH, + ICE_RX_MDID_SRC_VSI = 19, + ICE_RX_MDID_HASH_LOW = 56, + ICE_RX_MDID_HASH_HIGH, +}; /* Rx Flag64 packet flag bits */ enum ice_rx_flg64_bits { @@ -416,6 +418,7 @@ struct ice_tlan_ctx { u8 pf_num; u16 vmvf_num; u8 vmvf_type; +#define ICE_TLAN_CTX_VMVF_TYPE_VF 0 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ 1 #define ICE_TLAN_CTX_VMVF_TYPE_PF 2 u16 src_vsi; @@ -471,4 +474,16 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) { return ice_ptype_lkup[ptype]; } + +#define ICE_LINK_SPEED_UNKNOWN 0 +#define ICE_LINK_SPEED_10MBPS 10 +#define ICE_LINK_SPEED_100MBPS 100 +#define ICE_LINK_SPEED_1000MBPS 1000 +#define ICE_LINK_SPEED_2500MBPS 2500 +#define ICE_LINK_SPEED_5000MBPS 5000 +#define ICE_LINK_SPEED_10000MBPS 10000 +#define ICE_LINK_SPEED_20000MBPS 20000 +#define ICE_LINK_SPEED_25000MBPS 25000 +#define ICE_LINK_SPEED_40000MBPS 40000 + #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c new file mode 100644 index 000000000000..5bacad01f0c9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -0,0 +1,2620 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +/** + * ice_setup_rx_ctx - Configure a receive ring context + * @ring: The Rx ring to configure + * + * Configure the Rx descriptor ring in RLAN context. + */ +static int ice_setup_rx_ctx(struct ice_ring *ring) +{ + struct ice_vsi *vsi = ring->vsi; + struct ice_hw *hw = &vsi->back->hw; + u32 rxdid = ICE_RXDID_FLEX_NIC; + struct ice_rlan_ctx rlan_ctx; + u32 regval; + u16 pf_q; + int err; + + /* what is RX queue number in global space of 2K Rx queues */ + pf_q = vsi->rxq_map[ring->q_index]; + + /* clear the context structure first */ + memset(&rlan_ctx, 0, sizeof(rlan_ctx)); + + rlan_ctx.base = ring->dma >> 7; + + rlan_ctx.qlen = ring->count; + + /* Receive Packet Data Buffer Size. + * The Packet Data Buffer Size is defined in 128 byte units. + */ + rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + + /* use 32 byte descriptors */ + rlan_ctx.dsize = 1; + + /* Strip the Ethernet CRC bytes before the packet is posted to host + * memory. + */ + rlan_ctx.crcstrip = 1; + + /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ + rlan_ctx.l2tsel = 1; + + rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; + + /* This controls whether VLAN is stripped from inner headers + * The VLAN in the inner L2 header is stripped to the receive + * descriptor if enabled by this flag. + */ + rlan_ctx.showiv = 0; + + /* Max packet size for this queue - must not be set to a larger value + * than 5 x DBUF + */ + rlan_ctx.rxmax = min_t(u16, vsi->max_frame, + ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len); + + /* Rx queue threshold in units of 64 */ + rlan_ctx.lrxqthresh = 1; + + /* Enable Flexible Descriptors in the queue context which + * allows this driver to select a specific receive descriptor format + */ + if (vsi->type != ICE_VSI_VF) { + regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); + regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & + QRXFLXP_CNTXT_RXDID_IDX_M; + + /* increasing context priority to pick up profile id; + * default is 0x01; setting to 0x03 to ensure profile + * is programming if prev context is of same priority + */ + regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & + QRXFLXP_CNTXT_RXDID_PRIO_M; + + wr32(hw, QRXFLXP_CNTXT(pf_q), regval); + } + + /* Absolute queue number out of 2K needs to be passed */ + err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); + if (err) { + dev_err(&vsi->back->pdev->dev, + "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", + pf_q, err); + return -EIO; + } + + if (vsi->type == ICE_VSI_VF) + return 0; + + /* init queue specific tail register */ + ring->tail = hw->hw_addr + QRX_TAIL(pf_q); + writel(0, ring->tail); + ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); + + return 0; +} + +/** + * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance + * @ring: The Tx ring to configure + * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized + * @pf_q: queue index in the PF space + * + * Configure the Tx descriptor ring in TLAN context. + */ +static void +ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) +{ + struct ice_vsi *vsi = ring->vsi; + struct ice_hw *hw = &vsi->back->hw; + + tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S; + + tlan_ctx->port_num = vsi->port_info->lport; + + /* Transmit Queue Length */ + tlan_ctx->qlen = ring->count; + + /* PF number */ + tlan_ctx->pf_num = hw->pf_id; + + /* queue belongs to a specific VSI type + * VF / VM index should be programmed per vmvf_type setting: + * for vmvf_type = VF, it is VF number between 0-256 + * for vmvf_type = VM, it is VM number between 0-767 + * for PF or EMP this field should be set to zero + */ + switch (vsi->type) { + case ICE_VSI_PF: + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; + break; + case ICE_VSI_VF: + /* Firmware expects vmvf_num to be absolute VF id */ + tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id; + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; + break; + default: + return; + } + + /* make sure the context is associated with the right VSI */ + tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx); + + tlan_ctx->tso_ena = ICE_TX_LEGACY; + tlan_ctx->tso_qnum = pf_q; + + /* Legacy or Advanced Host Interface: + * 0: Advanced Host Interface + * 1: Legacy Host Interface + */ + tlan_ctx->legacy_int = ICE_TX_LEGACY; +} + +/** + * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled + * @pf: the PF being configured + * @pf_q: the PF queue + * @ena: enable or disable state of the queue + * + * This routine will wait for the given Rx queue of the PF to reach the + * enabled or disabled state. + * Returns -ETIMEDOUT in case of failing to reach the requested state after + * multiple retries; else will return 0 in case of success. + */ +static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) +{ + int i; + + for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) { + u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q)); + + if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) + break; + + usleep_range(10, 20); + } + if (i >= ICE_Q_WAIT_RETRY_LIMIT) + return -ETIMEDOUT; + + return 0; +} + +/** + * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings + * @vsi: the VSI being configured + * @ena: start or stop the Rx rings + */ +static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int i, j, ret = 0; + + for (i = 0; i < vsi->num_rxq; i++) { + int pf_q = vsi->rxq_map[i]; + u32 rx_reg; + + for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) { + rx_reg = rd32(hw, QRX_CTRL(pf_q)); + if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) == + ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) + continue; + + /* turn on/off the queue */ + if (ena) + rx_reg |= QRX_CTRL_QENA_REQ_M; + else + rx_reg &= ~QRX_CTRL_QENA_REQ_M; + wr32(hw, QRX_CTRL(pf_q), rx_reg); + + /* wait for the change to finish */ + ret = ice_pf_rxq_wait(pf, pf_q, ena); + if (ret) { + dev_err(&pf->pdev->dev, + "VSI idx %d Rx ring %d %sable timeout\n", + vsi->idx, pf_q, (ena ? "en" : "dis")); + break; + } + } + + return ret; +} + +/** + * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the VSI + * @vsi: VSI pointer + * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. + * + * On error: returns error code (negative) + * On success: returns 0 + */ +static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors) +{ + struct ice_pf *pf = vsi->back; + + /* allocate memory for both Tx and Rx ring pointers */ + vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, + sizeof(struct ice_ring *), GFP_KERNEL); + if (!vsi->tx_rings) + goto err_txrings; + + vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, + sizeof(struct ice_ring *), GFP_KERNEL); + if (!vsi->rx_rings) + goto err_rxrings; + + if (alloc_qvectors) { + /* allocate memory for q_vector pointers */ + vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, + vsi->num_q_vectors, + sizeof(struct ice_q_vector *), + GFP_KERNEL); + if (!vsi->q_vectors) + goto err_vectors; + } + + return 0; + +err_vectors: + devm_kfree(&pf->pdev->dev, vsi->rx_rings); +err_rxrings: + devm_kfree(&pf->pdev->dev, vsi->tx_rings); +err_txrings: + return -ENOMEM; +} + +/** + * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + */ +static void ice_vsi_set_num_qs(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + + switch (vsi->type) { + case ICE_VSI_PF: + vsi->alloc_txq = pf->num_lan_tx; + vsi->alloc_rxq = pf->num_lan_rx; + vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE); + vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); + break; + case ICE_VSI_VF: + vsi->alloc_txq = pf->num_vf_qps; + vsi->alloc_rxq = pf->num_vf_qps; + /* pf->num_vf_msix includes (VF miscellaneous vector + + * data queue interrupts). Since vsi->num_q_vectors is number + * of queues vectors, subtract 1 from the original vector + * count + */ + vsi->num_q_vectors = pf->num_vf_msix - 1; + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } +} + +/** + * ice_get_free_slot - get the next non-NULL location index in array + * @array: array to search + * @size: size of the array + * @curr: last known occupied index to be used as a search hint + * + * void * is being used to keep the functionality generic. This lets us use this + * function on any array of pointers. + */ +static int ice_get_free_slot(void *array, int size, int curr) +{ + int **tmp_array = (int **)array; + int next; + + if (curr < (size - 1) && !tmp_array[curr + 1]) { + next = curr + 1; + } else { + int i = 0; + + while ((i < size) && (tmp_array[i])) + i++; + if (i == size) + next = ICE_NO_VSI; + else + next = i; + } + return next; +} + +/** + * ice_vsi_delete - delete a VSI from the switch + * @vsi: pointer to VSI being removed + */ +void ice_vsi_delete(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_vsi_ctx ctxt; + enum ice_status status; + + if (vsi->type == ICE_VSI_VF) + ctxt.vf_num = vsi->vf_id; + ctxt.vsi_num = vsi->vsi_num; + + memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); + + status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL); + if (status) + dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", + vsi->vsi_num); +} + +/** + * ice_vsi_free_arrays - clean up VSI resources + * @vsi: pointer to VSI being cleared + * @free_qvectors: bool to specify if q_vectors should be deallocated + */ +static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors) +{ + struct ice_pf *pf = vsi->back; + + /* free the ring and vector containers */ + if (free_qvectors && vsi->q_vectors) { + devm_kfree(&pf->pdev->dev, vsi->q_vectors); + vsi->q_vectors = NULL; + } + if (vsi->tx_rings) { + devm_kfree(&pf->pdev->dev, vsi->tx_rings); + vsi->tx_rings = NULL; + } + if (vsi->rx_rings) { + devm_kfree(&pf->pdev->dev, vsi->rx_rings); + vsi->rx_rings = NULL; + } +} + +/** + * ice_vsi_clear - clean up and deallocate the provided VSI + * @vsi: pointer to VSI being cleared + * + * This deallocates the VSI's queue resources, removes it from the PF's + * VSI array if necessary, and deallocates the VSI + * + * Returns 0 on success, negative on failure + */ +int ice_vsi_clear(struct ice_vsi *vsi) +{ + struct ice_pf *pf = NULL; + + if (!vsi) + return 0; + + if (!vsi->back) + return -EINVAL; + + pf = vsi->back; + + if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { + dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n", + vsi->idx); + return -EINVAL; + } + + mutex_lock(&pf->sw_mutex); + /* updates the PF for this cleared VSI */ + + pf->vsi[vsi->idx] = NULL; + if (vsi->idx < pf->next_vsi) + pf->next_vsi = vsi->idx; + + ice_vsi_free_arrays(vsi, true); + mutex_unlock(&pf->sw_mutex); + devm_kfree(&pf->pdev->dev, vsi); + + return 0; +} + +/** + * ice_msix_clean_rings - MSIX mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a q_vector + */ +static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) +{ + struct ice_q_vector *q_vector = (struct ice_q_vector *)data; + + if (!q_vector->tx.ring && !q_vector->rx.ring) + return IRQ_HANDLED; + + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ice_vsi_alloc - Allocates the next available struct VSI in the PF + * @pf: board private structure + * @type: type of VSI + * + * returns a pointer to a VSI on success, NULL on failure. + */ +static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type) +{ + struct ice_vsi *vsi = NULL; + + /* Need to protect the allocation of the VSIs at the PF level */ + mutex_lock(&pf->sw_mutex); + + /* If we have already allocated our maximum number of VSIs, + * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index + * is available to be populated + */ + if (pf->next_vsi == ICE_NO_VSI) { + dev_dbg(&pf->pdev->dev, "out of VSI slots!\n"); + goto unlock_pf; + } + + vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL); + if (!vsi) + goto unlock_pf; + + vsi->type = type; + vsi->back = pf; + set_bit(__ICE_DOWN, vsi->state); + vsi->idx = pf->next_vsi; + vsi->work_lmt = ICE_DFLT_IRQ_WORK; + + ice_vsi_set_num_qs(vsi); + + switch (vsi->type) { + case ICE_VSI_PF: + if (ice_vsi_alloc_arrays(vsi, true)) + goto err_rings; + + /* Setup default MSIX irq handler for VSI */ + vsi->irq_handler = ice_msix_clean_rings; + break; + case ICE_VSI_VF: + if (ice_vsi_alloc_arrays(vsi, true)) + goto err_rings; + break; + default: + dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); + goto unlock_pf; + } + + /* fill VSI slot in the PF struct */ + pf->vsi[pf->next_vsi] = vsi; + + /* prepare pf->next_vsi for next use */ + pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, + pf->next_vsi); + goto unlock_pf; + +err_rings: + devm_kfree(&pf->pdev->dev, vsi); + vsi = NULL; +unlock_pf: + mutex_unlock(&pf->sw_mutex); + return vsi; +} + +/** + * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI + * @vsi: the VSI getting queues + * + * Return 0 on success and a negative value on error + */ +static int ice_vsi_get_qs_contig(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int offset, ret = 0; + + mutex_lock(&pf->avail_q_mutex); + /* look for contiguous block of queues for Tx */ + offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS, + 0, vsi->alloc_txq, 0); + if (offset < ICE_MAX_TXQS) { + int i; + + bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq); + for (i = 0; i < vsi->alloc_txq; i++) + vsi->txq_map[i] = i + offset; + } else { + ret = -ENOMEM; + vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER; + } + + /* look for contiguous block of queues for Rx */ + offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS, + 0, vsi->alloc_rxq, 0); + if (offset < ICE_MAX_RXQS) { + int i; + + bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq); + for (i = 0; i < vsi->alloc_rxq; i++) + vsi->rxq_map[i] = i + offset; + } else { + ret = -ENOMEM; + vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER; + } + mutex_unlock(&pf->avail_q_mutex); + + return ret; +} + +/** + * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI + * @vsi: the VSI getting queues + * + * Return 0 on success and a negative value on error + */ +static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i, index = 0; + + mutex_lock(&pf->avail_q_mutex); + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) { + for (i = 0; i < vsi->alloc_txq; i++) { + index = find_next_zero_bit(pf->avail_txqs, + ICE_MAX_TXQS, index); + if (index < ICE_MAX_TXQS) { + set_bit(index, pf->avail_txqs); + vsi->txq_map[i] = index; + } else { + goto err_scatter_tx; + } + } + } + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) { + for (i = 0; i < vsi->alloc_rxq; i++) { + index = find_next_zero_bit(pf->avail_rxqs, + ICE_MAX_RXQS, index); + if (index < ICE_MAX_RXQS) { + set_bit(index, pf->avail_rxqs); + vsi->rxq_map[i] = index; + } else { + goto err_scatter_rx; + } + } + } + + mutex_unlock(&pf->avail_q_mutex); + return 0; + +err_scatter_rx: + /* unflag any queues we have grabbed (i is failed position) */ + for (index = 0; index < i; index++) { + clear_bit(vsi->rxq_map[index], pf->avail_rxqs); + vsi->rxq_map[index] = 0; + } + i = vsi->alloc_txq; +err_scatter_tx: + /* i is either position of failed attempt or vsi->alloc_txq */ + for (index = 0; index < i; index++) { + clear_bit(vsi->txq_map[index], pf->avail_txqs); + vsi->txq_map[index] = 0; + } + + mutex_unlock(&pf->avail_q_mutex); + return -ENOMEM; +} + +/** + * ice_vsi_get_qs - Assign queues from PF to VSI + * @vsi: the VSI to assign queues to + * + * Returns 0 on success and a negative value on error + */ +static int ice_vsi_get_qs(struct ice_vsi *vsi) +{ + int ret = 0; + + vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG; + vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG; + + /* NOTE: ice_vsi_get_qs_contig() will set the Rx/Tx mapping + * modes individually to scatter if assigning contiguous queues + * to Rx or Tx fails + */ + ret = ice_vsi_get_qs_contig(vsi); + if (ret < 0) { + if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) + vsi->alloc_txq = max_t(u16, vsi->alloc_txq, + ICE_MAX_SCATTER_TXQS); + if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) + vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq, + ICE_MAX_SCATTER_RXQS); + ret = ice_vsi_get_qs_scatter(vsi); + } + + return ret; +} + +/** + * ice_vsi_put_qs - Release queues from VSI to PF + * @vsi: the VSI that is going to release queues + */ +void ice_vsi_put_qs(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i; + + mutex_lock(&pf->avail_q_mutex); + + for (i = 0; i < vsi->alloc_txq; i++) { + clear_bit(vsi->txq_map[i], pf->avail_txqs); + vsi->txq_map[i] = ICE_INVAL_Q_INDEX; + } + + for (i = 0; i < vsi->alloc_rxq; i++) { + clear_bit(vsi->rxq_map[i], pf->avail_rxqs); + vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; + } + + mutex_unlock(&pf->avail_q_mutex); +} + +/** + * ice_rss_clean - Delete RSS related VSI structures that hold user inputs + * @vsi: the VSI being removed + */ +static void ice_rss_clean(struct ice_vsi *vsi) +{ + struct ice_pf *pf; + + pf = vsi->back; + + if (vsi->rss_hkey_user) + devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user); + if (vsi->rss_lut_user) + devm_kfree(&pf->pdev->dev, vsi->rss_lut_user); +} + +/** + * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type + * @vsi: the VSI being configured + */ +static void ice_vsi_set_rss_params(struct ice_vsi *vsi) +{ + struct ice_hw_common_caps *cap; + struct ice_pf *pf = vsi->back; + + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + vsi->rss_size = 1; + return; + } + + cap = &pf->hw.func_caps.common_cap; + switch (vsi->type) { + case ICE_VSI_PF: + /* PF VSI will inherit RSS instance of PF */ + vsi->rss_table_size = cap->rss_table_size; + vsi->rss_size = min_t(int, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table + * For VSI_LUT, LUT size should be set to 64 bytes + */ + vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_size = min_t(int, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + break; + default: + dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } +} + +/** + * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI + * @ctxt: the VSI context being set + * + * This initializes a default VSI context for all sections except the Queues. + */ +static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) +{ + u32 table = 0; + + memset(&ctxt->info, 0, sizeof(ctxt->info)); + /* VSI's should be allocated from shared pool */ + ctxt->alloc_from_pool = true; + /* Src pruning enabled by default */ + ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; + /* Traffic from VSI can be sent to LAN */ + ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; + /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy + * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all + * packets untagged/tagged. + */ + ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & + ICE_AQ_VSI_VLAN_MODE_M) >> + ICE_AQ_VSI_VLAN_MODE_S); + /* Have 1:1 UP mapping for both ingress/egress tables */ + table |= ICE_UP_TABLE_TRANSLATE(0, 0); + table |= ICE_UP_TABLE_TRANSLATE(1, 1); + table |= ICE_UP_TABLE_TRANSLATE(2, 2); + table |= ICE_UP_TABLE_TRANSLATE(3, 3); + table |= ICE_UP_TABLE_TRANSLATE(4, 4); + table |= ICE_UP_TABLE_TRANSLATE(5, 5); + table |= ICE_UP_TABLE_TRANSLATE(6, 6); + table |= ICE_UP_TABLE_TRANSLATE(7, 7); + ctxt->info.ingress_table = cpu_to_le32(table); + ctxt->info.egress_table = cpu_to_le32(table); + /* Have 1:1 UP mapping for outer to inner UP table */ + ctxt->info.outer_up_table = cpu_to_le32(table); + /* No Outer tag support outer_tag_flags remains to zero */ +} + +/** + * ice_vsi_setup_q_map - Setup a VSI queue map + * @vsi: the VSI being configured + * @ctxt: VSI context structure + */ +static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) +{ + u16 offset = 0, qmap = 0, numq_tc; + u16 pow = 0, max_rss = 0, qcount; + u16 qcount_tx = vsi->alloc_txq; + u16 qcount_rx = vsi->alloc_rxq; + bool ena_tc0 = false; + int i; + + /* at least TC0 should be enabled by default */ + if (vsi->tc_cfg.numtc) { + if (!(vsi->tc_cfg.ena_tc & BIT(0))) + ena_tc0 = true; + } else { + ena_tc0 = true; + } + + if (ena_tc0) { + vsi->tc_cfg.numtc++; + vsi->tc_cfg.ena_tc |= 1; + } + + numq_tc = qcount_rx / vsi->tc_cfg.numtc; + + /* TC mapping is a function of the number of Rx queues assigned to the + * VSI for each traffic class and the offset of these queues. + * The first 10 bits are for queue offset for TC0, next 4 bits for no:of + * queues allocated to TC0. No:of queues is a power-of-2. + * + * If TC is not enabled, the queue offset is set to 0, and allocate one + * queue, this way, traffic for the given TC will be sent to the default + * queue. + * + * Setup number and offset of Rx queues for all TCs for the VSI + */ + + qcount = numq_tc; + /* qcount will change if RSS is enabled */ + if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { + if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) { + if (vsi->type == ICE_VSI_PF) + max_rss = ICE_MAX_LG_RSS_QS; + else + max_rss = ICE_MAX_SMALL_RSS_QS; + qcount = min_t(int, numq_tc, max_rss); + qcount = min_t(int, qcount, vsi->rss_size); + } + } + + /* find the (rounded up) power-of-2 of qcount */ + pow = order_base_2(qcount); + + for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) { + /* TC is not enabled */ + vsi->tc_cfg.tc_info[i].qoffset = 0; + vsi->tc_cfg.tc_info[i].qcount = 1; + ctxt->info.tc_mapping[i] = 0; + continue; + } + + /* TC is enabled */ + vsi->tc_cfg.tc_info[i].qoffset = offset; + vsi->tc_cfg.tc_info[i].qcount = qcount; + + qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & + ICE_AQ_VSI_TC_Q_OFFSET_M) | + ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & + ICE_AQ_VSI_TC_Q_NUM_M); + offset += qcount; + ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); + } + + vsi->num_txq = qcount_tx; + vsi->num_rxq = offset; + + if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { + dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); + /* since there is a chance that num_rxq could have been changed + * in the above for loop, make num_txq equal to num_rxq. + */ + vsi->num_txq = vsi->num_rxq; + } + + /* Rx queue mapping */ + ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); + /* q_mapping buffer holds the info for the first queue allocated for + * this VSI in the PF space and also the number of queues associated + * with this VSI. + */ + ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); + ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq); +} + +/** + * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI + * @ctxt: the VSI context being set + * @vsi: the VSI being configured + */ +static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) +{ + u8 lut_type, hash_type; + + switch (vsi->type) { + case ICE_VSI_PF: + /* PF VSI will inherit RSS instance of PF */ + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table which is a VSI LUT type */ + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + return; + } + + ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & + ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | + ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & + ICE_AQ_VSI_Q_OPT_RSS_HASH_M); +} + +/** + * ice_vsi_init - Create and initialize a VSI + * @vsi: the VSI being configured + * + * This initializes a VSI context depending on the VSI type to be added and + * passes it down to the add_vsi aq command to create a new VSI. + */ +static int ice_vsi_init(struct ice_vsi *vsi) +{ + struct ice_vsi_ctx ctxt = { 0 }; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int ret = 0; + + switch (vsi->type) { + case ICE_VSI_PF: + ctxt.flags = ICE_AQ_VSI_TYPE_PF; + break; + case ICE_VSI_VF: + ctxt.flags = ICE_AQ_VSI_TYPE_VF; + /* VF number here is the absolute VF number (0-255) */ + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id; + break; + default: + return -ENODEV; + } + + ice_set_dflt_vsi_ctx(&ctxt); + /* if the switch is in VEB mode, allow VSI loopback */ + if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB) + ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + + /* Set LUT type and HASH type if RSS is enabled */ + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_set_rss_vsi_ctx(&ctxt, vsi); + + ctxt.info.sw_id = vsi->port_info->sw_id; + ice_vsi_setup_q_map(vsi, &ctxt); + + ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Add VSI failed, err %d\n", ret); + return -EIO; + } + + /* keep context for update VSI operations */ + vsi->info = ctxt.info; + + /* record VSI number returned */ + vsi->vsi_num = ctxt.vsi_num; + + return ret; +} + +/** + * ice_free_q_vector - Free memory allocated for a specific interrupt vector + * @vsi: VSI having the memory freed + * @v_idx: index of the vector to be freed + */ +static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) +{ + struct ice_q_vector *q_vector; + struct ice_ring *ring; + + if (!vsi->q_vectors[v_idx]) { + dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n", + v_idx); + return; + } + q_vector = vsi->q_vectors[v_idx]; + + ice_for_each_ring(ring, q_vector->tx) + ring->q_vector = NULL; + ice_for_each_ring(ring, q_vector->rx) + ring->q_vector = NULL; + + /* only VSI with an associated netdev is set up with NAPI */ + if (vsi->netdev) + netif_napi_del(&q_vector->napi); + + devm_kfree(&vsi->back->pdev->dev, q_vector); + vsi->q_vectors[v_idx] = NULL; +} + +/** + * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors + * @vsi: the VSI having memory freed + */ +void ice_vsi_free_q_vectors(struct ice_vsi *vsi) +{ + int v_idx; + + for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) + ice_free_q_vector(vsi, v_idx); +} + +/** + * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector + * @vsi: the VSI being configured + * @v_idx: index of the vector in the VSI struct + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + */ +static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) +{ + struct ice_pf *pf = vsi->back; + struct ice_q_vector *q_vector; + + /* allocate q_vector */ + q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + q_vector->vsi = vsi; + q_vector->v_idx = v_idx; + if (vsi->type == ICE_VSI_VF) + goto out; + /* only set affinity_mask if the CPU is online */ + if (cpu_online(v_idx)) + cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + + /* This will not be called in the driver load path because the netdev + * will not be created yet. All other cases with register the NAPI + * handler here (i.e. resume, reset/rebuild, etc.) + */ + if (vsi->netdev) + netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, + NAPI_POLL_WEIGHT); + +out: + /* tie q_vector and VSI together */ + vsi->q_vectors[v_idx] = q_vector; + + return 0; +} + +/** + * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors + * @vsi: the VSI being configured + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + */ +static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int v_idx = 0, num_q_vectors; + int err; + + if (vsi->q_vectors[0]) { + dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n", + vsi->vsi_num); + return -EEXIST; + } + + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + num_q_vectors = vsi->num_q_vectors; + } else { + err = -EINVAL; + goto err_out; + } + + for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { + err = ice_vsi_alloc_q_vector(vsi, v_idx); + if (err) + goto err_out; + } + + return 0; + +err_out: + while (v_idx--) + ice_free_q_vector(vsi, v_idx); + + dev_err(&pf->pdev->dev, + "Failed to allocate %d q_vector for VSI %d, ret=%d\n", + vsi->num_q_vectors, vsi->vsi_num, err); + vsi->num_q_vectors = 0; + return err; +} + +/** + * ice_vsi_setup_vector_base - Set up the base vector for the given VSI + * @vsi: ptr to the VSI + * + * This should only be called after ice_vsi_alloc() which allocates the + * corresponding SW VSI structure and initializes num_queue_pairs for the + * newly allocated VSI. + * + * Returns 0 on success or negative on failure + */ +static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int num_q_vectors = 0; + + if (vsi->sw_base_vector || vsi->hw_base_vector) { + dev_dbg(&pf->pdev->dev, "VSI %d has non-zero HW base vector %d or SW base vector %d\n", + vsi->vsi_num, vsi->hw_base_vector, vsi->sw_base_vector); + return -EEXIST; + } + + if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + return -ENOENT; + + switch (vsi->type) { + case ICE_VSI_PF: + num_q_vectors = vsi->num_q_vectors; + /* reserve slots from OS requested IRQs */ + vsi->sw_base_vector = ice_get_res(pf, pf->sw_irq_tracker, + num_q_vectors, vsi->idx); + if (vsi->sw_base_vector < 0) { + dev_err(&pf->pdev->dev, + "Failed to get tracking for %d SW vectors for VSI %d, err=%d\n", + num_q_vectors, vsi->vsi_num, + vsi->sw_base_vector); + return -ENOENT; + } + pf->num_avail_sw_msix -= num_q_vectors; + + /* reserve slots from HW interrupts */ + vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, + num_q_vectors, vsi->idx); + break; + case ICE_VSI_VF: + /* take VF misc vector and data vectors into account */ + num_q_vectors = pf->num_vf_msix; + /* For VF VSI, reserve slots only from HW interrupts */ + vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, + num_q_vectors, vsi->idx); + break; + default: + dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", + vsi->type); + break; + } + + if (vsi->hw_base_vector < 0) { + dev_err(&pf->pdev->dev, + "Failed to get tracking for %d HW vectors for VSI %d, err=%d\n", + num_q_vectors, vsi->vsi_num, vsi->hw_base_vector); + if (vsi->type != ICE_VSI_VF) { + ice_free_res(vsi->back->sw_irq_tracker, + vsi->sw_base_vector, vsi->idx); + pf->num_avail_sw_msix += num_q_vectors; + } + return -ENOENT; + } + + pf->num_avail_hw_msix -= num_q_vectors; + + return 0; +} + +/** + * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI + * @vsi: the VSI having rings deallocated + */ +static void ice_vsi_clear_rings(struct ice_vsi *vsi) +{ + int i; + + if (vsi->tx_rings) { + for (i = 0; i < vsi->alloc_txq; i++) { + if (vsi->tx_rings[i]) { + kfree_rcu(vsi->tx_rings[i], rcu); + vsi->tx_rings[i] = NULL; + } + } + } + if (vsi->rx_rings) { + for (i = 0; i < vsi->alloc_rxq; i++) { + if (vsi->rx_rings[i]) { + kfree_rcu(vsi->rx_rings[i], rcu); + vsi->rx_rings[i] = NULL; + } + } + } +} + +/** + * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI + * @vsi: VSI which is having rings allocated + */ +static int ice_vsi_alloc_rings(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int i; + + /* Allocate tx_rings */ + for (i = 0; i < vsi->alloc_txq; i++) { + struct ice_ring *ring; + + /* allocate with kzalloc(), free with kfree_rcu() */ + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + + if (!ring) + goto err_out; + + ring->q_index = i; + ring->reg_idx = vsi->txq_map[i]; + ring->ring_active = false; + ring->vsi = vsi; + ring->dev = &pf->pdev->dev; + ring->count = vsi->num_desc; + vsi->tx_rings[i] = ring; + } + + /* Allocate rx_rings */ + for (i = 0; i < vsi->alloc_rxq; i++) { + struct ice_ring *ring; + + /* allocate with kzalloc(), free with kfree_rcu() */ + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_out; + + ring->q_index = i; + ring->reg_idx = vsi->rxq_map[i]; + ring->ring_active = false; + ring->vsi = vsi; + ring->netdev = vsi->netdev; + ring->dev = &pf->pdev->dev; + ring->count = vsi->num_desc; + vsi->rx_rings[i] = ring; + } + + return 0; + +err_out: + ice_vsi_clear_rings(vsi); + return -ENOMEM; +} + +/** + * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors + * @vsi: the VSI being configured + * + * This function maps descriptor rings to the queue-specific vectors allotted + * through the MSI-X enabling code. On a constrained vector budget, we map Tx + * and Rx rings to the vector as "efficiently" as possible. + */ +static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) +{ + int q_vectors = vsi->num_q_vectors; + int tx_rings_rem, rx_rings_rem; + int v_id; + + /* initially assigning remaining rings count to VSIs num queue value */ + tx_rings_rem = vsi->num_txq; + rx_rings_rem = vsi->num_rxq; + + for (v_id = 0; v_id < q_vectors; v_id++) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_id]; + int tx_rings_per_v, rx_rings_per_v, q_id, q_base; + + /* Tx rings mapping to vector */ + tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); + q_vector->num_ring_tx = tx_rings_per_v; + q_vector->tx.ring = NULL; + q_vector->tx.itr_idx = ICE_TX_ITR; + q_base = vsi->num_txq - tx_rings_rem; + + for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { + struct ice_ring *tx_ring = vsi->tx_rings[q_id]; + + tx_ring->q_vector = q_vector; + tx_ring->next = q_vector->tx.ring; + q_vector->tx.ring = tx_ring; + } + tx_rings_rem -= tx_rings_per_v; + + /* Rx rings mapping to vector */ + rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); + q_vector->num_ring_rx = rx_rings_per_v; + q_vector->rx.ring = NULL; + q_vector->rx.itr_idx = ICE_RX_ITR; + q_base = vsi->num_rxq - rx_rings_rem; + + for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { + struct ice_ring *rx_ring = vsi->rx_rings[q_id]; + + rx_ring->q_vector = q_vector; + rx_ring->next = q_vector->rx.ring; + q_vector->rx.ring = rx_ring; + } + rx_rings_rem -= rx_rings_per_v; + } +} + +/** + * ice_vsi_manage_rss_lut - disable/enable RSS + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is an enable or disable request + * + * In the event of disable request for RSS, this function will zero out RSS + * LUT, while in the event of enable request for RSS, it will reconfigure RSS + * LUT. + */ +int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) +{ + int err = 0; + u8 *lut; + + lut = devm_kzalloc(&vsi->back->pdev->dev, vsi->rss_table_size, + GFP_KERNEL); + if (!lut) + return -ENOMEM; + + if (ena) { + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + ice_fill_rss_lut(lut, vsi->rss_table_size, + vsi->rss_size); + } + + err = ice_set_rss(vsi, NULL, lut, vsi->rss_table_size); + devm_kfree(&vsi->back->pdev->dev, lut); + return err; +} + +/** + * ice_vsi_cfg_rss_lut_key - Configure RSS params for a VSI + * @vsi: VSI to be configured + */ +static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) +{ + u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE]; + struct ice_aqc_get_set_rss_keys *key; + struct ice_pf *pf = vsi->back; + enum ice_status status; + int err = 0; + u8 *lut; + + vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq); + + lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); + + status = ice_aq_set_rss_lut(&pf->hw, vsi->idx, vsi->rss_lut_type, lut, + vsi->rss_table_size); + + if (status) { + dev_err(&vsi->back->pdev->dev, + "set_rss_lut failed, error %d\n", status); + err = -EIO; + goto ice_vsi_cfg_rss_exit; + } + + key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto ice_vsi_cfg_rss_exit; + } + + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + else + netdev_rss_key_fill((void *)seed, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + memcpy(&key->standard_rss_key, seed, + ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); + + status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key); + + if (status) { + dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n", + status); + err = -EIO; + } + + devm_kfree(&pf->pdev->dev, key); +ice_vsi_cfg_rss_exit: + devm_kfree(&pf->pdev->dev, lut); + return err; +} + +/** + * ice_add_mac_to_list - Add a mac address filter entry to the list + * @vsi: the VSI to be forwarded to + * @add_list: pointer to the list which contains MAC filter entries + * @macaddr: the MAC address to be added. + * + * Adds mac address filter entry to the temp list + * + * Returns 0 on success or ENOMEM on failure. + */ +int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr) +{ + struct ice_fltr_list_entry *tmp; + struct ice_pf *pf = vsi->back; + + tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + + tmp->fltr_info.flag = ICE_FLTR_TX; + tmp->fltr_info.src_id = ICE_SRC_ID_VSI; + tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC; + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.vsi_handle = vsi->idx; + ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr); + + INIT_LIST_HEAD(&tmp->list_entry); + list_add(&tmp->list_entry, add_list); + + return 0; +} + +/** + * ice_update_eth_stats - Update VSI-specific ethernet statistics counters + * @vsi: the VSI to be updated + */ +void ice_update_eth_stats(struct ice_vsi *vsi) +{ + struct ice_eth_stats *prev_es, *cur_es; + struct ice_hw *hw = &vsi->back->hw; + u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ + + prev_es = &vsi->eth_stats_prev; + cur_es = &vsi->eth_stats; + + ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_bytes, + &cur_es->rx_bytes); + + ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_unicast, + &cur_es->rx_unicast); + + ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_multicast, + &cur_es->rx_multicast); + + ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->rx_broadcast, + &cur_es->rx_broadcast); + + ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_discards, &cur_es->rx_discards); + + ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_bytes, + &cur_es->tx_bytes); + + ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_unicast, + &cur_es->tx_unicast); + + ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_multicast, + &cur_es->tx_multicast); + + ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), + vsi->stat_offsets_loaded, &prev_es->tx_broadcast, + &cur_es->tx_broadcast); + + ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_errors, &cur_es->tx_errors); + + vsi->stat_offsets_loaded = true; +} + +/** + * ice_free_fltr_list - free filter lists helper + * @dev: pointer to the device struct + * @h: pointer to the list head to be freed + * + * Helper function to free filter lists previously created using + * ice_add_mac_to_list + */ +void ice_free_fltr_list(struct device *dev, struct list_head *h) +{ + struct ice_fltr_list_entry *e, *tmp; + + list_for_each_entry_safe(e, tmp, h, list_entry) { + list_del(&e->list_entry); + devm_kfree(dev, e); + } +} + +/** + * ice_vsi_add_vlan - Add VSI membership for given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be added + */ +int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid) +{ + struct ice_fltr_list_entry *tmp; + struct ice_pf *pf = vsi->back; + LIST_HEAD(tmp_add_list); + enum ice_status status; + int err = 0; + + tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.flag = ICE_FLTR_TX; + tmp->fltr_info.src_id = ICE_SRC_ID_VSI; + tmp->fltr_info.vsi_handle = vsi->idx; + tmp->fltr_info.l_data.vlan.vlan_id = vid; + + INIT_LIST_HEAD(&tmp->list_entry); + list_add(&tmp->list_entry, &tmp_add_list); + + status = ice_add_vlan(&pf->hw, &tmp_add_list); + if (status) { + err = -ENODEV; + dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n", + vid, vsi->vsi_num); + } + + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return err; +} + +/** + * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be removed + * + * Returns 0 on success and negative on failure + */ +int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) +{ + struct ice_fltr_list_entry *list; + struct ice_pf *pf = vsi->back; + LIST_HEAD(tmp_add_list); + int status = 0; + + list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); + if (!list) + return -ENOMEM; + + list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; + list->fltr_info.vsi_handle = vsi->idx; + list->fltr_info.fltr_act = ICE_FWD_TO_VSI; + list->fltr_info.l_data.vlan.vlan_id = vid; + list->fltr_info.flag = ICE_FLTR_TX; + list->fltr_info.src_id = ICE_SRC_ID_VSI; + + INIT_LIST_HEAD(&list->list_entry); + list_add(&list->list_entry, &tmp_add_list); + + if (ice_remove_vlan(&pf->hw, &tmp_add_list)) { + dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", + vid, vsi->vsi_num); + status = -EIO; + } + + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; +} + +/** + * ice_vsi_cfg_rxqs - Configure the VSI for Rx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Rx VSI for operation. + */ +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) +{ + int err = 0; + u16 i; + + if (vsi->type == ICE_VSI_VF) + goto setup_rings; + + if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN) + vsi->max_frame = vsi->netdev->mtu + + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + else + vsi->max_frame = ICE_RXBUF_2048; + + vsi->rx_buf_len = ICE_RXBUF_2048; +setup_rings: + /* set up individual rings */ + for (i = 0; i < vsi->num_rxq && !err; i++) + err = ice_setup_rx_ctx(vsi->rx_rings[i]); + + if (err) { + dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n"); + return -EIO; + } + return err; +} + +/** + * ice_vsi_cfg_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +int ice_vsi_cfg_txqs(struct ice_vsi *vsi) +{ + struct ice_aqc_add_tx_qgrp *qg_buf; + struct ice_aqc_add_txqs_perq *txq; + struct ice_pf *pf = vsi->back; + enum ice_status status; + u16 buf_len, i, pf_q; + int err = 0, tc = 0; + u8 num_q_grps; + + buf_len = sizeof(struct ice_aqc_add_tx_qgrp); + qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); + if (!qg_buf) + return -ENOMEM; + + if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) { + err = -EINVAL; + goto err_cfg_txqs; + } + qg_buf->num_txqs = 1; + num_q_grps = 1; + + /* set up and configure the Tx queues */ + ice_for_each_txq(vsi, i) { + struct ice_tlan_ctx tlan_ctx = { 0 }; + + pf_q = vsi->txq_map[i]; + ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q); + /* copy context contents into the qg_buf */ + qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); + ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, + ice_tlan_ctx_info); + + /* init queue specific tail reg. It is referred as transmit + * comm scheduler queue doorbell. + */ + vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); + status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, + num_q_grps, qg_buf, buf_len, NULL); + if (status) { + dev_err(&vsi->back->pdev->dev, + "Failed to set LAN Tx queue context, error: %d\n", + status); + err = -ENODEV; + goto err_cfg_txqs; + } + + /* Add Tx Queue TEID into the VSI Tx ring from the response + * This will complete configuring and enabling the queue. + */ + txq = &qg_buf->txqs[0]; + if (pf_q == le16_to_cpu(txq->txq_id)) + vsi->tx_rings[i]->txq_teid = + le32_to_cpu(txq->q_teid); + } +err_cfg_txqs: + devm_kfree(&pf->pdev->dev, qg_buf); + return err; +} + +/** + * ice_intrl_usec_to_reg - convert interrupt rate limit to register value + * @intrl: interrupt rate limit in usecs + * @gran: interrupt rate limit granularity in usecs + * + * This function converts a decimal interrupt rate limit in usecs to the format + * expected by firmware. + */ +static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) +{ + u32 val = intrl / gran; + + if (val) + return val | GLINT_RATE_INTRL_ENA_M; + return 0; +} + +/** + * ice_cfg_itr - configure the initial interrupt throttle values + * @hw: pointer to the HW structure + * @q_vector: interrupt vector that's being configured + * @vector: HW vector index to apply the interrupt throttling to + * + * Configure interrupt throttling values for the ring containers that are + * associated with the interrupt vector passed in. + */ +static void +ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector) +{ + u8 itr_gran = hw->itr_gran; + + if (q_vector->num_ring_rx) { + struct ice_ring_container *rc = &q_vector->rx; + + rc->itr = ITR_TO_REG(ICE_DFLT_RX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } + + if (q_vector->num_ring_tx) { + struct ice_ring_container *rc = &q_vector->tx; + + rc->itr = ITR_TO_REG(ICE_DFLT_TX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } +} + +/** + * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW + * @vsi: the VSI being configured + */ +void ice_vsi_cfg_msix(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + u16 vector = vsi->hw_base_vector; + struct ice_hw *hw = &pf->hw; + u32 txq = 0, rxq = 0; + int i, q; + + for (i = 0; i < vsi->num_q_vectors; i++, vector++) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + ice_cfg_itr(hw, q_vector, vector); + + wr32(hw, GLINT_RATE(vector), + ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); + + /* Both Transmit Queue Interrupt Cause Control register + * and Receive Queue Interrupt Cause control register + * expects MSIX_INDX field to be the vector index + * within the function space and not the absolute + * vector index across PF or across device. + * For SR-IOV VF VSIs queue vector index always starts + * with 1 since first vector index(0) is used for OICR + * in VF space. Since VMDq and other PF VSIs are within + * the PF function space, use the vector index that is + * tracked for this PF. + */ + for (q = 0; q < q_vector->num_ring_tx; q++) { + int itr_idx = q_vector->tx.itr_idx; + u32 val; + + if (vsi->type == ICE_VSI_VF) + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + ((i + 1) << QINT_TQCTL_MSIX_INDX_S); + else + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + (vector << QINT_TQCTL_MSIX_INDX_S); + wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); + txq++; + } + + for (q = 0; q < q_vector->num_ring_rx; q++) { + int itr_idx = q_vector->rx.itr_idx; + u32 val; + + if (vsi->type == ICE_VSI_VF) + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + ((i + 1) << QINT_RQCTL_MSIX_INDX_S); + else + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + (vector << QINT_RQCTL_MSIX_INDX_S); + wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); + rxq++; + } + } + + ice_flush(hw); +} + +/** + * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx + * @vsi: the VSI being changed + */ +int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + /* Here we are configuring the VSI to let the driver add VLAN tags by + * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag + * insertion happens in the Tx hot path, in ice_tx_map. + */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; + + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is a enable or disable request + */ +int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + /* Here we are configuring what the VSI should do with the VLAN tag in + * the Rx packet. We can either leave the tag in the packet or put it in + * the Rx descriptor. + */ + if (ena) { + /* Strip VLAN tag from Rx packet and put it in the desc */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; + } else { + /* Disable stripping. Leave tag in packet */ + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; + } + + /* Allow all packets untagged/tagged */ + ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; + + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", + ena, status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_start_rx_rings - start VSI's Rx rings + * @vsi: the VSI whose rings are to be started + * + * Returns 0 on success and a negative value on error + */ +int ice_vsi_start_rx_rings(struct ice_vsi *vsi) +{ + return ice_vsi_ctrl_rx_rings(vsi, true); +} + +/** + * ice_vsi_stop_rx_rings - stop VSI's Rx rings + * @vsi: the VSI + * + * Returns 0 on success and a negative value on error + */ +int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) +{ + return ice_vsi_ctrl_rx_rings(vsi, false); +} + +/** + * ice_vsi_stop_tx_rings - Disable Tx rings + * @vsi: the VSI being configured + * @rst_src: reset source + * @rel_vmvf_num: Relative id of VF/VM + */ +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u32 *q_teids, val; + u16 *q_ids, i; + int err = 0; + + if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) + return -EINVAL; + + q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids), + GFP_KERNEL); + if (!q_teids) + return -ENOMEM; + + q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids), + GFP_KERNEL); + if (!q_ids) { + err = -ENOMEM; + goto err_alloc_q_ids; + } + + /* set up the Tx queue list to be disabled */ + ice_for_each_txq(vsi, i) { + u16 v_idx; + + if (!vsi->tx_rings || !vsi->tx_rings[i]) { + err = -EINVAL; + goto err_out; + } + + q_ids[i] = vsi->txq_map[i]; + q_teids[i] = vsi->tx_rings[i]->txq_teid; + + /* clear cause_ena bit for disabled queues */ + val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx)); + val &= ~QINT_TQCTL_CAUSE_ENA_M; + wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val); + + /* software is expected to wait for 100 ns */ + ndelay(100); + + /* trigger a software interrupt for the vector associated to + * the queue to schedule NAPI handler + */ + v_idx = vsi->tx_rings[i]->q_vector->v_idx; + wr32(hw, GLINT_DYN_CTL(vsi->hw_base_vector + v_idx), + GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); + } + status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, + rst_src, rel_vmvf_num, NULL); + /* if the disable queue command was exercised during an active reset + * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as + * the reset operation disables queues at the hardware level anyway. + */ + if (status == ICE_ERR_RESET_ONGOING) { + dev_info(&pf->pdev->dev, + "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status) { + dev_err(&pf->pdev->dev, + "Failed to disable LAN Tx queues, error: %d\n", + status); + err = -ENODEV; + } + +err_out: + devm_kfree(&pf->pdev->dev, q_ids); + +err_alloc_q_ids: + devm_kfree(&pf->pdev->dev, q_teids); + + return err; +} + +/** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct device *dev; + int status; + + if (!vsi) + return -EINVAL; + + dev = &vsi->back->pdev->dev; + ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) { + ctxt->info.sec_flags |= + ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } else { + ctxt->info.sec_flags &= + ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n", + ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status, + vsi->back->hw.adminq.sq_last_status); + goto err_out; + } + + vsi->info.sec_flags = ctxt->info.sec_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + devm_kfree(dev, ctxt); + return 0; + +err_out: + devm_kfree(dev, ctxt); + return -EIO; +} + +/** + * ice_vsi_setup - Set up a VSI by a given type + * @pf: board private structure + * @pi: pointer to the port_info instance + * @type: VSI type + * @vf_id: defines VF id to which this VSI connects. This field is meant to be + * used only for ICE_VSI_VF VSI type. For other VSI types, should + * fill-in ICE_INVAL_VFID as input. + * + * This allocates the sw VSI structure and its queue resources. + * + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. + */ +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 vf_id) +{ + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct device *dev = &pf->pdev->dev; + struct ice_vsi *vsi; + int ret, i; + + vsi = ice_vsi_alloc(pf, type); + if (!vsi) { + dev_err(dev, "could not allocate VSI\n"); + return NULL; + } + + vsi->port_info = pi; + vsi->vsw = pf->first_sw; + if (vsi->type == ICE_VSI_VF) + vsi->vf_id = vf_id; + + if (ice_vsi_get_qs(vsi)) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_get_qs; + } + + /* set RSS capabilities */ + ice_vsi_set_rss_params(vsi); + + /* create the VSI */ + ret = ice_vsi_init(vsi); + if (ret) + goto unroll_get_qs; + + switch (vsi->type) { + case ICE_VSI_PF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto unroll_vsi_init; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto unroll_alloc_q_vector; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_vector_base; + + ice_vsi_map_rings_to_vectors(vsi); + + /* Do not exit if configuring RSS had an issue, at least + * receive traffic on first queue. Hence no need to capture + * return value + */ + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_vsi_cfg_rss_lut_key(vsi); + break; + case ICE_VSI_VF: + /* VF driver will take care of creating netdev for this type and + * map queues to vectors through Virtchnl, PF driver only + * creates a VSI and corresponding structures for bookkeeping + * purpose + */ + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto unroll_vsi_init; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + + /* Setup Vector base only during VF init phase or when VF asks + * for more vectors than assigned number. In all other cases, + * assign hw_base_vector to the value given earlier. + */ + if (test_bit(ICE_VF_STATE_CFG_INTR, pf->vf[vf_id].vf_states)) { + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto unroll_vector_base; + } else { + vsi->hw_base_vector = pf->vf[vf_id].first_vector_idx; + } + pf->q_left_tx -= vsi->alloc_txq; + pf->q_left_rx -= vsi->alloc_rxq; + break; + default: + /* if VSI type is not recognized, clean up the resources and + * exit + */ + goto unroll_vsi_init; + } + + ice_vsi_set_tc_cfg(vsi); + + /* configure VSI nodes based on number of queues and TC's */ + for (i = 0; i < vsi->tc_cfg.numtc; i++) + max_txqs[i] = vsi->num_txq; + + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n"); + goto unroll_vector_base; + } + + return vsi; + +unroll_vector_base: + /* reclaim SW interrupts back to the common pool */ + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + /* reclaim HW interrupt back to the common pool */ + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); + pf->num_avail_hw_msix += vsi->num_q_vectors; +unroll_alloc_q_vector: + ice_vsi_free_q_vectors(vsi); +unroll_vsi_init: + ice_vsi_delete(vsi); +unroll_get_qs: + ice_vsi_put_qs(vsi); + pf->q_left_tx += vsi->alloc_txq; + pf->q_left_rx += vsi->alloc_rxq; + ice_vsi_clear(vsi); + + return NULL; +} + +/** + * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW + * @vsi: the VSI being cleaned up + */ +static void ice_vsi_release_msix(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + u16 vector = vsi->hw_base_vector; + struct ice_hw *hw = &pf->hw; + u32 txq = 0; + u32 rxq = 0; + int i, q; + + for (i = 0; i < vsi->num_q_vectors; i++, vector++) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + wr32(hw, GLINT_ITR(ICE_IDX_ITR0, vector), 0); + wr32(hw, GLINT_ITR(ICE_IDX_ITR1, vector), 0); + for (q = 0; q < q_vector->num_ring_tx; q++) { + wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); + txq++; + } + + for (q = 0; q < q_vector->num_ring_rx; q++) { + wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0); + rxq++; + } + } + + ice_flush(hw); +} + +/** + * ice_vsi_free_irq - Free the IRQ association with the OS + * @vsi: the VSI being configured + */ +void ice_vsi_free_irq(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int base = vsi->sw_base_vector; + + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + int i; + + if (!vsi->q_vectors || !vsi->irqs_ready) + return; + + ice_vsi_release_msix(vsi); + if (vsi->type == ICE_VSI_VF) + return; + + vsi->irqs_ready = false; + for (i = 0; i < vsi->num_q_vectors; i++) { + u16 vector = i + base; + int irq_num; + + irq_num = pf->msix_entries[vector].vector; + + /* free only the irqs that were actually requested */ + if (!vsi->q_vectors[i] || + !(vsi->q_vectors[i]->num_ring_tx || + vsi->q_vectors[i]->num_ring_rx)) + continue; + + /* clear the affinity notifier in the IRQ descriptor */ + irq_set_affinity_notifier(irq_num, NULL); + + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(irq_num, NULL); + synchronize_irq(irq_num); + devm_free_irq(&pf->pdev->dev, irq_num, + vsi->q_vectors[i]); + } + } +} + +/** + * ice_vsi_free_tx_rings - Free Tx resources for VSI queues + * @vsi: the VSI having resources freed + */ +void ice_vsi_free_tx_rings(struct ice_vsi *vsi) +{ + int i; + + if (!vsi->tx_rings) + return; + + ice_for_each_txq(vsi, i) + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) + ice_free_tx_ring(vsi->tx_rings[i]); +} + +/** + * ice_vsi_free_rx_rings - Free Rx resources for VSI queues + * @vsi: the VSI having resources freed + */ +void ice_vsi_free_rx_rings(struct ice_vsi *vsi) +{ + int i; + + if (!vsi->rx_rings) + return; + + ice_for_each_rxq(vsi, i) + if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc) + ice_free_rx_ring(vsi->rx_rings[i]); +} + +/** + * ice_vsi_close - Shut down a VSI + * @vsi: the VSI being shut down + */ +void ice_vsi_close(struct ice_vsi *vsi) +{ + if (!test_and_set_bit(__ICE_DOWN, vsi->state)) + ice_down(vsi); + + ice_vsi_free_irq(vsi); + ice_vsi_free_tx_rings(vsi); + ice_vsi_free_rx_rings(vsi); +} + +/** + * ice_free_res - free a block of resources + * @res: pointer to the resource + * @index: starting index previously returned by ice_get_res + * @id: identifier to track owner + * + * Returns number of resources freed + */ +int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) +{ + int count = 0; + int i; + + if (!res || index >= res->num_entries) + return -EINVAL; + + id |= ICE_RES_VALID_BIT; + for (i = index; i < res->num_entries && res->list[i] == id; i++) { + res->list[i] = 0; + count++; + } + + return count; +} + +/** + * ice_search_res - Search the tracker for a block of resources + * @res: pointer to the resource + * @needed: size of the block needed + * @id: identifier to track owner + * + * Returns the base item index of the block, or -ENOMEM for error + */ +static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) +{ + int start = res->search_hint; + int end = start; + + if ((start + needed) > res->num_entries) + return -ENOMEM; + + id |= ICE_RES_VALID_BIT; + + do { + /* skip already allocated entries */ + if (res->list[end++] & ICE_RES_VALID_BIT) { + start = end; + if ((start + needed) > res->num_entries) + break; + } + + if (end == (start + needed)) { + int i = start; + + /* there was enough, so assign it to the requestor */ + while (i != end) + res->list[i++] = id; + + if (end == res->num_entries) + end = 0; + + res->search_hint = end; + return start; + } + } while (1); + + return -ENOMEM; +} + +/** + * ice_get_res - get a block of resources + * @pf: board private structure + * @res: pointer to the resource + * @needed: size of the block needed + * @id: identifier to track owner + * + * Returns the base item index of the block, or -ENOMEM for error + * The search_hint trick and lack of advanced fit-finding only works + * because we're highly likely to have all the same sized requests. + * Linear search time and any fragmentation should be minimal. + */ +int +ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) +{ + int ret; + + if (!res || !pf) + return -EINVAL; + + if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { + dev_err(&pf->pdev->dev, + "param err: needed=%d, num_entries = %d id=0x%04x\n", + needed, res->num_entries, id); + return -EINVAL; + } + + /* search based on search_hint */ + ret = ice_search_res(res, needed, id); + + if (ret < 0) { + /* previous search failed. Reset search hint and try again */ + res->search_hint = 0; + ret = ice_search_res(res, needed, id); + } + + return ret; +} + +/** + * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI + * @vsi: the VSI being un-configured + */ +void ice_vsi_dis_irq(struct ice_vsi *vsi) +{ + int base = vsi->sw_base_vector; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u32 val; + int i; + + /* disable interrupt causation from each queue */ + if (vsi->tx_rings) { + ice_for_each_txq(vsi, i) { + if (vsi->tx_rings[i]) { + u16 reg; + + reg = vsi->tx_rings[i]->reg_idx; + val = rd32(hw, QINT_TQCTL(reg)); + val &= ~QINT_TQCTL_CAUSE_ENA_M; + wr32(hw, QINT_TQCTL(reg), val); + } + } + } + + if (vsi->rx_rings) { + ice_for_each_rxq(vsi, i) { + if (vsi->rx_rings[i]) { + u16 reg; + + reg = vsi->rx_rings[i]->reg_idx; + val = rd32(hw, QINT_RQCTL(reg)); + val &= ~QINT_RQCTL_CAUSE_ENA_M; + wr32(hw, QINT_RQCTL(reg), val); + } + } + } + + /* disable each interrupt */ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { + for (i = vsi->hw_base_vector; + i < (vsi->num_q_vectors + vsi->hw_base_vector); i++) + wr32(hw, GLINT_DYN_CTL(i), 0); + + ice_flush(hw); + for (i = 0; i < vsi->num_q_vectors; i++) + synchronize_irq(pf->msix_entries[i + base].vector); + } +} + +/** + * ice_vsi_release - Delete a VSI and free its resources + * @vsi: the VSI being removed + * + * Returns 0 on success or < 0 on error + */ +int ice_vsi_release(struct ice_vsi *vsi) +{ + struct ice_pf *pf; + struct ice_vf *vf; + + if (!vsi->back) + return -ENODEV; + pf = vsi->back; + vf = &pf->vf[vsi->vf_id]; + /* do not unregister and free netdevs while driver is in the reset + * recovery pending state. Since reset/rebuild happens through PF + * service task workqueue, its not a good idea to unregister netdev + * that is associated to the PF that is running the work queue items + * currently. This is done to avoid check_flush_dependency() warning + * on this wq + */ + if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + unregister_netdev(vsi->netdev); + free_netdev(vsi->netdev); + vsi->netdev = NULL; + } + + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + ice_rss_clean(vsi); + + /* Disable VSI and free resources */ + ice_vsi_dis_irq(vsi); + ice_vsi_close(vsi); + + /* reclaim interrupt vectors back to PF */ + if (vsi->type != ICE_VSI_VF) { + /* reclaim SW interrupts back to the common pool */ + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, + vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + /* reclaim HW interrupts back to the common pool */ + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, + vsi->idx); + pf->num_avail_hw_msix += vsi->num_q_vectors; + } else if (test_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states)) { + /* Reclaim VF resources back only while freeing all VFs or + * vector reassignment is requested + */ + ice_free_res(vsi->back->hw_irq_tracker, vf->first_vector_idx, + vsi->idx); + pf->num_avail_hw_msix += pf->num_vf_msix; + } + + ice_remove_vsi_fltr(&pf->hw, vsi->idx); + ice_vsi_delete(vsi); + ice_vsi_free_q_vectors(vsi); + ice_vsi_clear_rings(vsi); + + ice_vsi_put_qs(vsi); + pf->q_left_tx += vsi->alloc_txq; + pf->q_left_rx += vsi->alloc_rxq; + + /* retain SW VSI data structure since it is needed to unregister and + * free VSI netdev when PF is not in reset recovery pending state,\ + * for ex: during rmmod. + */ + if (!ice_is_reset_in_progress(pf->state)) + ice_vsi_clear(vsi); + + return 0; +} + +/** + * ice_vsi_rebuild - Rebuild VSI after reset + * @vsi: VSI to be rebuild + * + * Returns 0 on success and negative value on failure + */ +int ice_vsi_rebuild(struct ice_vsi *vsi) +{ + u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + int ret, i; + + if (!vsi) + return -EINVAL; + + ice_vsi_free_q_vectors(vsi); + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); + vsi->sw_base_vector = 0; + vsi->hw_base_vector = 0; + ice_vsi_clear_rings(vsi); + ice_vsi_free_arrays(vsi, false); + ice_dev_onetime_setup(&vsi->back->hw); + ice_vsi_set_num_qs(vsi); + + /* Initialize VSI struct elements and create VSI in FW */ + ret = ice_vsi_init(vsi); + if (ret < 0) + goto err_vsi; + + ret = ice_vsi_alloc_arrays(vsi, false); + if (ret < 0) + goto err_vsi; + + switch (vsi->type) { + case ICE_VSI_PF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto err_rings; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto err_vectors; + + ice_vsi_map_rings_to_vectors(vsi); + break; + case ICE_VSI_VF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto err_rings; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto err_vectors; + + vsi->back->q_left_tx -= vsi->alloc_txq; + vsi->back->q_left_rx -= vsi->alloc_rxq; + break; + default: + break; + } + + ice_vsi_set_tc_cfg(vsi); + + /* configure VSI nodes based on number of queues and TC's */ + for (i = 0; i < vsi->tc_cfg.numtc; i++) + max_txqs[i] = vsi->num_txq; + + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed VSI lan queue config\n"); + goto err_vectors; + } + return 0; + +err_vectors: + ice_vsi_free_q_vectors(vsi); +err_rings: + if (vsi->netdev) { + vsi->current_netdev_flags = 0; + unregister_netdev(vsi->netdev); + free_netdev(vsi->netdev); + vsi->netdev = NULL; + } +err_vsi: + ice_vsi_clear(vsi); + set_bit(__ICE_RESET_FAILED, vsi->back->state); + return ret; +} + +/** + * ice_is_reset_in_progress - check for a reset in progress + * @state: pf state field + */ +bool ice_is_reset_in_progress(unsigned long *state) +{ + return test_bit(__ICE_RESET_OICR_RECV, state) || + test_bit(__ICE_PFR_REQ, state) || + test_bit(__ICE_CORER_REQ, state) || + test_bit(__ICE_GLOBR_REQ, state); +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h new file mode 100644 index 000000000000..3831b4f0960a --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_LIB_H_ +#define _ICE_LIB_H_ + +#include "ice.h" + +int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr); + +void ice_free_fltr_list(struct device *dev, struct list_head *h); + +void ice_update_eth_stats(struct ice_vsi *vsi); + +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); + +int ice_vsi_cfg_txqs(struct ice_vsi *vsi); + +void ice_vsi_cfg_msix(struct ice_vsi *vsi); + +int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid); + +int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid); + +int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi); + +int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena); + +int ice_vsi_start_rx_rings(struct ice_vsi *vsi); + +int ice_vsi_stop_rx_rings(struct ice_vsi *vsi); + +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num); + +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); + +void ice_vsi_delete(struct ice_vsi *vsi); + +int ice_vsi_clear(struct ice_vsi *vsi); + +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 vf_id); + +int ice_vsi_release(struct ice_vsi *vsi); + +void ice_vsi_close(struct ice_vsi *vsi); + +int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); + +int +ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); + +int ice_vsi_rebuild(struct ice_vsi *vsi); + +bool ice_is_reset_in_progress(unsigned long *state); + +void ice_vsi_free_q_vectors(struct ice_vsi *vsi); + +void ice_vsi_put_qs(struct ice_vsi *vsi); + +void ice_vsi_dis_irq(struct ice_vsi *vsi); + +void ice_vsi_free_irq(struct ice_vsi *vsi); + +void ice_vsi_free_rx_rings(struct ice_vsi *vsi); + +void ice_vsi_free_tx_rings(struct ice_vsi *vsi); + +int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); + +int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); + +#endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 3f047bb43348..05993451147a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6,8 +6,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "ice.h" +#include "ice_lib.h" -#define DRV_VERSION "ice-0.7.0-k" +#define DRV_VERSION "0.7.2-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY; @@ -15,7 +16,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static int debug = -1; @@ -31,173 +32,84 @@ static const struct net_device_ops ice_netdev_ops; static void ice_pf_dis_all_vsi(struct ice_pf *pf); static void ice_rebuild(struct ice_pf *pf); -static int ice_vsi_release(struct ice_vsi *vsi); + +static void ice_vsi_release_all(struct ice_pf *pf); static void ice_update_vsi_stats(struct ice_vsi *vsi); static void ice_update_pf_stats(struct ice_pf *pf); /** - * ice_get_free_slot - get the next non-NULL location index in array - * @array: array to search - * @size: size of the array - * @curr: last known occupied index to be used as a search hint - * - * void * is being used to keep the functionality generic. This lets us use this - * function on any array of pointers. + * ice_get_tx_pending - returns number of Tx descriptors not processed + * @ring: the ring of descriptors */ -static int ice_get_free_slot(void *array, int size, int curr) +static u32 ice_get_tx_pending(struct ice_ring *ring) { - int **tmp_array = (int **)array; - int next; + u32 head, tail; - if (curr < (size - 1) && !tmp_array[curr + 1]) { - next = curr + 1; - } else { - int i = 0; + head = ring->next_to_clean; + tail = readl(ring->tail); - while ((i < size) && (tmp_array[i])) - i++; - if (i == size) - next = ICE_NO_VSI; - else - next = i; - } - return next; + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + return 0; } /** - * ice_search_res - Search the tracker for a block of resources - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * Returns the base item index of the block, or -ENOMEM for error + * ice_check_for_hang_subtask - check for and recover hung queues + * @pf: pointer to PF struct */ -static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) +static void ice_check_for_hang_subtask(struct ice_pf *pf) { - int start = res->search_hint; - int end = start; - - id |= ICE_RES_VALID_BIT; + struct ice_vsi *vsi = NULL; + unsigned int i; + u32 v, v_idx; + int packets; - do { - /* skip already allocated entries */ - if (res->list[end++] & ICE_RES_VALID_BIT) { - start = end; - if ((start + needed) > res->num_entries) - break; + ice_for_each_vsi(pf, v) + if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) { + vsi = pf->vsi[v]; + break; } - if (end == (start + needed)) { - int i = start; + if (!vsi || test_bit(__ICE_DOWN, vsi->state)) + return; - /* there was enough, so assign it to the requestor */ - while (i != end) - res->list[i++] = id; + if (!(vsi->netdev && netif_carrier_ok(vsi->netdev))) + return; - if (end == res->num_entries) - end = 0; + for (i = 0; i < vsi->num_txq; i++) { + struct ice_ring *tx_ring = vsi->tx_rings[i]; + + if (tx_ring && tx_ring->desc) { + int itr = ICE_ITR_NONE; + + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.pkts & INT_MAX; + if (tx_ring->tx_stats.prev_pkt == packets) { + /* Trigger sw interrupt to revive the queue */ + v_idx = tx_ring->q_vector->v_idx; + wr32(&vsi->back->hw, + GLINT_DYN_CTL(vsi->hw_base_vector + v_idx), + (itr << GLINT_DYN_CTL_ITR_INDX_S) | + GLINT_DYN_CTL_SWINT_TRIG_M | + GLINT_DYN_CTL_INTENA_MSK_M); + continue; + } - res->search_hint = end; - return start; + /* Memory barrier between read of packet count and call + * to ice_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt = + ice_get_tx_pending(tx_ring) ? packets : -1; } - } while (1); - - return -ENOMEM; -} - -/** - * ice_get_res - get a block of resources - * @pf: board private structure - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or -ENOMEM for error - * The search_hint trick and lack of advanced fit-finding only works - * because we're highly likely to have all the same sized requests. - * Linear search time and any fragmentation should be minimal. - */ -static int -ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) -{ - int ret; - - if (!res || !pf) - return -EINVAL; - - if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { - dev_err(&pf->pdev->dev, - "param err: needed=%d, num_entries = %d id=0x%04x\n", - needed, res->num_entries, id); - return -EINVAL; - } - - /* search based on search_hint */ - ret = ice_search_res(res, needed, id); - - if (ret < 0) { - /* previous search failed. Reset search hint and try again */ - res->search_hint = 0; - ret = ice_search_res(res, needed, id); } - - return ret; -} - -/** - * ice_free_res - free a block of resources - * @res: pointer to the resource - * @index: starting index previously returned by ice_get_res - * @id: identifier to track owner - * Returns number of resources freed - */ -static int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) -{ - int count = 0; - int i; - - if (!res || index >= res->num_entries) - return -EINVAL; - - id |= ICE_RES_VALID_BIT; - for (i = index; i < res->num_entries && res->list[i] == id; i++) { - res->list[i] = 0; - count++; - } - - return count; -} - -/** - * ice_add_mac_to_list - Add a mac address filter entry to the list - * @vsi: the VSI to be forwarded to - * @add_list: pointer to the list which contains MAC filter entries - * @macaddr: the MAC address to be added. - * - * Adds mac address filter entry to the temp list - * - * Returns 0 on success or ENOMEM on failure. - */ -static int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, - const u8 *macaddr) -{ - struct ice_fltr_list_entry *tmp; - struct ice_pf *pf = vsi->back; - - tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - - tmp->fltr_info.flag = ICE_FLTR_TX; - tmp->fltr_info.src = vsi->vsi_num; - tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC; - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr); - - INIT_LIST_HEAD(&tmp->list_entry); - list_add(&tmp->list_entry, add_list); - - return 0; } /** @@ -243,24 +155,6 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) } /** - * ice_free_fltr_list - free filter lists helper - * @dev: pointer to the device struct - * @h: pointer to the list head to be freed - * - * Helper function to free filter lists previously created using - * ice_add_mac_to_list - */ -static void ice_free_fltr_list(struct device *dev, struct list_head *h) -{ - struct ice_fltr_list_entry *e, *tmp; - - list_for_each_entry_safe(e, tmp, h, list_entry) { - list_del(&e->list_entry); - devm_kfree(dev, e); - } -} - -/** * ice_vsi_fltr_changed - check if filter state changed * @vsi: VSI to be checked * @@ -359,7 +253,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags); if (vsi->current_netdev_flags & IFF_PROMISC) { /* Apply TX filter rule to get traffic from VMs */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true, + status = ice_cfg_dflt_vsi(hw, vsi->idx, true, ICE_FLTR_TX); if (status) { netdev_err(netdev, "Error setting default VSI %i tx rule\n", @@ -369,7 +263,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto out_promisc; } /* Apply RX filter rule to get traffic from wire */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true, + status = ice_cfg_dflt_vsi(hw, vsi->idx, true, ICE_FLTR_RX); if (status) { netdev_err(netdev, "Error setting default VSI %i rx rule\n", @@ -380,7 +274,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } } else { /* Clear TX filter rule to stop traffic from VMs */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false, + status = ice_cfg_dflt_vsi(hw, vsi->idx, false, ICE_FLTR_TX); if (status) { netdev_err(netdev, "Error clearing default VSI %i tx rule\n", @@ -389,8 +283,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) err = -EIO; goto out_promisc; } - /* Clear filter RX to remove traffic from wire */ - status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false, + /* Clear RX filter to remove traffic from wire */ + status = ice_cfg_dflt_vsi(hw, vsi->idx, false, ICE_FLTR_RX); if (status) { netdev_err(netdev, "Error clearing default VSI %i rx rule\n", @@ -438,15 +332,6 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf) } /** - * ice_is_reset_recovery_pending - schedule a reset - * @state: pf state field - */ -static bool ice_is_reset_recovery_pending(unsigned long int *state) -{ - return test_bit(__ICE_RESET_RECOVERY_PENDING, state); -} - -/** * ice_prepare_for_reset - prep for the core to reset * @pf: board private structure * @@ -456,23 +341,17 @@ static void ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - u32 v; - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - ice_remove_vsi_fltr(hw, pf->vsi[v]->vsi_num); - - dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); + /* Notify VFs of impending reset */ + if (ice_check_sq_alive(hw, &hw->mailboxq)) + ice_vc_notify_reset(pf); /* disable the VSIs and their queues that are not already DOWN */ - /* pf_dis_all_vsi modifies netdev structures -rtnl_lock needed */ ice_pf_dis_all_vsi(pf); - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - pf->vsi[v]->vsi_num = 0; - ice_shutdown_all_ctrlq(hw); + + set_bit(__ICE_PREPARED_FOR_RESET, pf->state); } /** @@ -489,27 +368,29 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); WARN_ON(in_interrupt()); - /* PFR is a bit of a special case because it doesn't result in an OICR - * interrupt. So for PFR, we prepare for reset, issue the reset and - * rebuild sequentially. - */ - if (reset_type == ICE_RESET_PFR) { - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - ice_prepare_for_reset(pf); - } + ice_prepare_for_reset(pf); /* trigger the reset */ if (ice_reset(hw, reset_type)) { dev_err(dev, "reset %d failed\n", reset_type); set_bit(__ICE_RESET_FAILED, pf->state); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_RESET_OICR_RECV, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); + clear_bit(__ICE_CORER_REQ, pf->state); + clear_bit(__ICE_GLOBR_REQ, pf->state); return; } + /* PFR is a bit of a special case because it doesn't result in an OICR + * interrupt. So for PFR, rebuild after the reset and clear the reset- + * associated state bits. + */ if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; ice_rebuild(pf); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); } } @@ -519,77 +400,60 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) */ static void ice_reset_subtask(struct ice_pf *pf) { - enum ice_reset_req reset_type; - - rtnl_lock(); + enum ice_reset_req reset_type = ICE_RESET_INVAL; /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an - * OICR interrupt. The OICR handler (ice_misc_intr) determines what - * type of reset happened and sets __ICE_RESET_RECOVERY_PENDING bit in - * pf->state. So if reset/recovery is pending (as indicated by this bit) - * we do a rebuild and return. + * OICR interrupt. The OICR handler (ice_misc_intr) determines what type + * of reset is pending and sets bits in pf->state indicating the reset + * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set + * prepare for pending reset if not already (for PF software-initiated + * global resets the software should already be prepared for it as + * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated + * by firmware or software on other PFs, that bit is not set so prepare + * for the reset now), poll for reset done, rebuild and return. */ - if (ice_is_reset_recovery_pending(pf->state)) { + if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) { clear_bit(__ICE_GLOBR_RECV, pf->state); clear_bit(__ICE_CORER_RECV, pf->state); - ice_prepare_for_reset(pf); + if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) + ice_prepare_for_reset(pf); /* make sure we are ready to rebuild */ - if (ice_check_reset(&pf->hw)) + if (ice_check_reset(&pf->hw)) { set_bit(__ICE_RESET_FAILED, pf->state); - else + } else { + /* done with reset. start rebuild */ + pf->hw.reset_ongoing = false; ice_rebuild(pf); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - goto unlock; + /* clear bit to resume normal operations, but + * ICE_NEEDS_RESTART bit is set incase rebuild failed + */ + clear_bit(__ICE_RESET_OICR_RECV, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(__ICE_PFR_REQ, pf->state); + clear_bit(__ICE_CORER_REQ, pf->state); + clear_bit(__ICE_GLOBR_REQ, pf->state); + } + + return; } /* No pending resets to finish processing. Check for new resets */ - if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state)) - reset_type = ICE_RESET_GLOBR; - else if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) - reset_type = ICE_RESET_CORER; - else if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) + if (test_bit(__ICE_PFR_REQ, pf->state)) reset_type = ICE_RESET_PFR; - else - goto unlock; + if (test_bit(__ICE_CORER_REQ, pf->state)) + reset_type = ICE_RESET_CORER; + if (test_bit(__ICE_GLOBR_REQ, pf->state)) + reset_type = ICE_RESET_GLOBR; + /* If no valid reset type requested just return */ + if (reset_type == ICE_RESET_INVAL) + return; - /* reset if not already down or resetting */ + /* reset if not already down or busy */ if (!test_bit(__ICE_DOWN, pf->state) && !test_bit(__ICE_CFG_BUSY, pf->state)) { ice_do_reset(pf, reset_type); } - -unlock: - rtnl_unlock(); -} - -/** - * ice_watchdog_subtask - periodic tasks not using event driven scheduling - * @pf: board private structure - */ -static void ice_watchdog_subtask(struct ice_pf *pf) -{ - int i; - - /* if interface is down do nothing */ - if (test_bit(__ICE_DOWN, pf->state) || - test_bit(__ICE_CFG_BUSY, pf->state)) - return; - - /* make sure we don't do these things too often */ - if (time_before(jiffies, - pf->serv_tmr_prev + pf->serv_tmr_period)) - return; - - pf->serv_tmr_prev = jiffies; - - /* Update the stats for active netdevs so the network stack - * can look at updated numbers whenever it cares to - */ - ice_update_pf_stats(pf); - for (i = 0; i < pf->num_alloc_vsi; i++) - if (pf->vsi[i] && pf->vsi[i]->netdev) - ice_update_vsi_stats(pf->vsi[i]); } /** @@ -662,36 +526,6 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } /** - * ice_init_link_events - enable/initialize link events - * @pi: pointer to the port_info instance - * - * Returns -EIO on failure, 0 on success - */ -static int ice_init_link_events(struct ice_port_info *pi) -{ - u16 mask; - - mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA | - ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL)); - - if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to set link event mask for port %d\n", - pi->lport); - return -EIO; - } - - if (ice_aq_get_link_info(pi, true, NULL, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to enable link events for port %d\n", - pi->lport); - return -EIO; - } - - return 0; -} - -/** * ice_vsi_link_event - update the vsi's netdev * @vsi: the vsi on which the link event occurred * @link_up: whether or not the vsi needs to be set up or down @@ -772,31 +606,41 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi) } } + ice_vc_notify_link_state(pf); + return 0; } /** - * ice_handle_link_event - handle link event via ARQ - * @pf: pf that the link event is associated with - * - * Return -EINVAL if port_info is null - * Return status on succes + * ice_watchdog_subtask - periodic tasks not using event driven scheduling + * @pf: board private structure */ -static int ice_handle_link_event(struct ice_pf *pf) +static void ice_watchdog_subtask(struct ice_pf *pf) { - struct ice_port_info *port_info; - int status; + int i; - port_info = pf->hw.port_info; - if (!port_info) - return -EINVAL; + /* if interface is down do nothing */ + if (test_bit(__ICE_DOWN, pf->state) || + test_bit(__ICE_CFG_BUSY, pf->state)) + return; - status = ice_link_event(pf, port_info); - if (status) - dev_dbg(&pf->pdev->dev, - "Could not process link event, error %d\n", status); + /* make sure we don't do these things too often */ + if (time_before(jiffies, + pf->serv_tmr_prev + pf->serv_tmr_period)) + return; - return status; + pf->serv_tmr_prev = jiffies; + + if (ice_link_event(pf, pf->hw.port_info)) + dev_dbg(&pf->pdev->dev, "ice_link_event failed\n"); + + /* Update the stats for active netdevs so the network stack + * can look at updated numbers whenever it cares to + */ + ice_update_pf_stats(pf); + for (i = 0; i < pf->num_alloc_vsi; i++) + if (pf->vsi[i] && pf->vsi[i]->netdev) + ice_update_vsi_stats(pf->vsi[i]); } /** @@ -822,6 +666,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) cq = &hw->adminq; qtype = "Admin"; break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + qtype = "Mailbox"; + break; default: dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n", q_type); @@ -898,10 +746,11 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) opcode = le16_to_cpu(event.desc.opcode); switch (opcode) { - case ice_aqc_opc_get_link_status: - if (ice_handle_link_event(pf)) - dev_err(&pf->pdev->dev, - "Could not handle link event\n"); + case ice_mbx_opc_send_msg_to_pf: + ice_vc_process_vf_msg(pf, &event); + break; + case ice_aqc_opc_fw_logging: + ice_output_fw_log(hw, &event.desc, event.msg_buf); break; default: dev_dbg(&pf->pdev->dev, @@ -959,6 +808,28 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) } /** + * ice_clean_mailboxq_subtask - clean the MailboxQ rings + * @pf: board private structure + */ +static void ice_clean_mailboxq_subtask(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state)) + return; + + if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX)) + return; + + clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); + + if (ice_ctrlq_pending(hw, &hw->mailboxq)) + __ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX); + + ice_flush(hw); +} + +/** * ice_service_task_schedule - schedule the service task to wake up * @pf: board private structure * @@ -966,8 +837,9 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) */ static void ice_service_task_schedule(struct ice_pf *pf) { - if (!test_bit(__ICE_DOWN, pf->state) && - !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state)) + if (!test_bit(__ICE_SERVICE_DIS, pf->state) && + !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) && + !test_bit(__ICE_NEEDS_RESTART, pf->state)) queue_work(ice_wq, &pf->serv_task); } @@ -985,6 +857,22 @@ static void ice_service_task_complete(struct ice_pf *pf) } /** + * ice_service_task_stop - stop service task and cancel works + * @pf: board private structure + */ +static void ice_service_task_stop(struct ice_pf *pf) +{ + set_bit(__ICE_SERVICE_DIS, pf->state); + + if (pf->serv_tmr.function) + del_timer_sync(&pf->serv_tmr); + if (pf->serv_task.func) + cancel_work_sync(&pf->serv_task); + + clear_bit(__ICE_SERVICE_SCHED, pf->state); +} + +/** * ice_service_timer - timer callback to schedule service task * @t: pointer to timer_list */ @@ -997,6 +885,160 @@ static void ice_service_timer(struct timer_list *t) } /** + * ice_handle_mdd_event - handle malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from service task. OICR interrupt handler indicates MDD event + */ +static void ice_handle_mdd_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + bool mdd_detected = false; + u32 reg; + int i; + + if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state)) + return; + + /* find what triggered the MDD event */ + reg = rd32(hw, GL_MDET_TX_PQM); + if (reg & GL_MDET_TX_PQM_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> + GL_MDET_TX_PQM_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >> + GL_MDET_TX_PQM_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >> + GL_MDET_TX_PQM_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >> + GL_MDET_TX_PQM_QNUM_S); + + if (netif_msg_tx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_PQM, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_TX_TCLAN); + if (reg & GL_MDET_TX_TCLAN_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> + GL_MDET_TX_TCLAN_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >> + GL_MDET_TX_TCLAN_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >> + GL_MDET_TX_TCLAN_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> + GL_MDET_TX_TCLAN_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_RX); + if (reg & GL_MDET_RX_VALID_M) { + u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >> + GL_MDET_RX_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >> + GL_MDET_RX_VF_NUM_S; + u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >> + GL_MDET_RX_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_RX_QNUM_M) >> + GL_MDET_RX_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_RX, 0xffffffff); + mdd_detected = true; + } + + if (mdd_detected) { + bool pf_mdd_detected = false; + + reg = rd32(hw, PF_MDET_TX_PQM); + if (reg & PF_MDET_TX_PQM_VALID_M) { + wr32(hw, PF_MDET_TX_PQM, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_TX_TCLAN); + if (reg & PF_MDET_TX_TCLAN_VALID_M) { + wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_RX); + if (reg & PF_MDET_RX_VALID_M) { + wr32(hw, PF_MDET_RX, 0xFFFF); + dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + /* Queue belongs to the PF initiate a reset */ + if (pf_mdd_detected) { + set_bit(__ICE_NEEDS_RESTART, pf->state); + ice_service_task_schedule(pf); + } + } + + /* see if one of the VFs needs to be reset */ + for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + struct ice_vf *vf = &pf->vf[i]; + + reg = rd32(hw, VP_MDET_TX_PQM(i)); + if (reg & VP_MDET_TX_PQM_VALID_M) { + wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TCLAN(i)); + if (reg & VP_MDET_TX_TCLAN_VALID_M) { + wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TDPU(i)); + if (reg & VP_MDET_TX_TDPU_VALID_M) { + wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_RX(i)); + if (reg & VP_MDET_RX_VALID_M) { + wr32(hw, VP_MDET_RX(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", + i); + } + + if (vf->num_mdd_events > ICE_DFLT_NUM_MDD_EVENTS_ALLOWED) { + dev_info(&pf->pdev->dev, + "Too many MDD events on VF %d, disabled\n", i); + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + } + } + + /* re-enable MDD interrupt cause */ + clear_bit(__ICE_MDD_EVENT_PENDING, pf->state); + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_MAL_DETECT_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); +} + +/** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct */ @@ -1010,16 +1052,21 @@ static void ice_service_task(struct work_struct *work) /* process reset requests first */ ice_reset_subtask(pf); - /* bail if a reset/recovery cycle is pending */ - if (ice_is_reset_recovery_pending(pf->state) || - test_bit(__ICE_SUSPENDED, pf->state)) { + /* bail if a reset/recovery cycle is pending or rebuild failed */ + if (ice_is_reset_in_progress(pf->state) || + test_bit(__ICE_SUSPENDED, pf->state) || + test_bit(__ICE_NEEDS_RESTART, pf->state)) { ice_service_task_complete(pf); return; } + ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); + ice_handle_mdd_event(pf); + ice_process_vflr_event(pf); ice_watchdog_subtask(pf); ice_clean_adminq_subtask(pf); + ice_clean_mailboxq_subtask(pf); /* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */ ice_service_task_complete(pf); @@ -1029,6 +1076,9 @@ static void ice_service_task(struct work_struct *work) * schedule the service task now. */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || + test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || + test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) || test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -1043,6 +1093,10 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) hw->adminq.num_sq_entries = ICE_AQ_LEN; hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN; hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN; + hw->mailboxq.num_rq_entries = ICE_MBXQ_LEN; + hw->mailboxq.num_sq_entries = ICE_MBXQ_LEN; + hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN; + hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN; } /** @@ -1073,57 +1127,6 @@ static void ice_irq_affinity_notify(struct irq_affinity_notify *notify, static void ice_irq_affinity_release(struct kref __always_unused *ref) {} /** - * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI - * @vsi: the VSI being un-configured - */ -static void ice_vsi_dis_irq(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int base = vsi->base_vector; - u32 val; - int i; - - /* disable interrupt causation from each queue */ - if (vsi->tx_rings) { - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i]) { - u16 reg; - - reg = vsi->tx_rings[i]->reg_idx; - val = rd32(hw, QINT_TQCTL(reg)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(reg), val); - } - } - } - - if (vsi->rx_rings) { - ice_for_each_rxq(vsi, i) { - if (vsi->rx_rings[i]) { - u16 reg; - - reg = vsi->rx_rings[i]->reg_idx; - val = rd32(hw, QINT_RQCTL(reg)); - val &= ~QINT_RQCTL_CAUSE_ENA_M; - wr32(hw, QINT_RQCTL(reg), val); - } - } - } - - /* disable each interrupt */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - for (i = vsi->base_vector; - i < (vsi->num_q_vectors + vsi->base_vector); i++) - wr32(hw, GLINT_DYN_CTL(i), 0); - - ice_flush(hw); - for (i = 0; i < vsi->num_q_vectors; i++) - synchronize_irq(pf->msix_entries[i + base].vector); - } -} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -1144,26 +1147,6 @@ static int ice_vsi_ena_irq(struct ice_vsi *vsi) } /** - * ice_vsi_delete - delete a VSI from the switch - * @vsi: pointer to VSI being removed - */ -static void ice_vsi_delete(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_vsi_ctx ctxt; - enum ice_status status; - - ctxt.vsi_num = vsi->vsi_num; - - memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); - - status = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); - if (status) - dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", - vsi->vsi_num); -} - -/** * ice_vsi_req_irq_msix - get MSI-X vectors from the OS for the VSI * @vsi: the VSI being configured * @basename: name for the vector @@ -1172,7 +1155,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) { int q_vectors = vsi->num_q_vectors; struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; + int base = vsi->sw_base_vector; int rx_int_idx = 0; int tx_int_idx = 0; int vector, err; @@ -1231,467 +1214,6 @@ free_q_irqs: } /** - * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type - * @vsi: the VSI being configured - */ -static void ice_vsi_set_rss_params(struct ice_vsi *vsi) -{ - struct ice_hw_common_caps *cap; - struct ice_pf *pf = vsi->back; - - if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - vsi->rss_size = 1; - return; - } - - cap = &pf->hw.func_caps.common_cap; - switch (vsi->type) { - case ICE_VSI_PF: - /* PF VSI will inherit RSS instance of PF */ - vsi->rss_table_size = cap->rss_table_size; - vsi->rss_size = min_t(int, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; - break; - default: - dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); - break; - } -} - -/** - * ice_vsi_setup_q_map - Setup a VSI queue map - * @vsi: the VSI being configured - * @ctxt: VSI context structure - */ -static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) -{ - u16 offset = 0, qmap = 0, numq_tc; - u16 pow = 0, max_rss = 0, qcount; - u16 qcount_tx = vsi->alloc_txq; - u16 qcount_rx = vsi->alloc_rxq; - bool ena_tc0 = false; - int i; - - /* at least TC0 should be enabled by default */ - if (vsi->tc_cfg.numtc) { - if (!(vsi->tc_cfg.ena_tc & BIT(0))) - ena_tc0 = true; - } else { - ena_tc0 = true; - } - - if (ena_tc0) { - vsi->tc_cfg.numtc++; - vsi->tc_cfg.ena_tc |= 1; - } - - numq_tc = qcount_rx / vsi->tc_cfg.numtc; - - /* TC mapping is a function of the number of Rx queues assigned to the - * VSI for each traffic class and the offset of these queues. - * The first 10 bits are for queue offset for TC0, next 4 bits for no:of - * queues allocated to TC0. No:of queues is a power-of-2. - * - * If TC is not enabled, the queue offset is set to 0, and allocate one - * queue, this way, traffic for the given TC will be sent to the default - * queue. - * - * Setup number and offset of Rx queues for all TCs for the VSI - */ - - /* qcount will change if RSS is enabled */ - if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { - if (vsi->type == ICE_VSI_PF) - max_rss = ICE_MAX_LG_RSS_QS; - else - max_rss = ICE_MAX_SMALL_RSS_QS; - - qcount = min_t(int, numq_tc, max_rss); - qcount = min_t(int, qcount, vsi->rss_size); - } else { - qcount = numq_tc; - } - - /* find the (rounded up) power-of-2 of qcount */ - pow = order_base_2(qcount); - - for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { - if (!(vsi->tc_cfg.ena_tc & BIT(i))) { - /* TC is not enabled */ - vsi->tc_cfg.tc_info[i].qoffset = 0; - vsi->tc_cfg.tc_info[i].qcount = 1; - ctxt->info.tc_mapping[i] = 0; - continue; - } - - /* TC is enabled */ - vsi->tc_cfg.tc_info[i].qoffset = offset; - vsi->tc_cfg.tc_info[i].qcount = qcount; - - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); - offset += qcount; - ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); - } - - vsi->num_txq = qcount_tx; - vsi->num_rxq = offset; - - /* Rx queue mapping */ - ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); - /* q_mapping buffer holds the info for the first queue allocated for - * this VSI in the PF space and also the number of queues associated - * with this VSI. - */ - ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); - ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq); -} - -/** - * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI - * @ctxt: the VSI context being set - * - * This initializes a default VSI context for all sections except the Queues. - */ -static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) -{ - u32 table = 0; - - memset(&ctxt->info, 0, sizeof(ctxt->info)); - /* VSI's should be allocated from shared pool */ - ctxt->alloc_from_pool = true; - /* Src pruning enabled by default */ - ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; - /* Traffic from VSI can be sent to LAN */ - ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; - - /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy - * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all - * packets untagged/tagged. - */ - ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & - ICE_AQ_VSI_VLAN_MODE_M) >> - ICE_AQ_VSI_VLAN_MODE_S); - - /* Have 1:1 UP mapping for both ingress/egress tables */ - table |= ICE_UP_TABLE_TRANSLATE(0, 0); - table |= ICE_UP_TABLE_TRANSLATE(1, 1); - table |= ICE_UP_TABLE_TRANSLATE(2, 2); - table |= ICE_UP_TABLE_TRANSLATE(3, 3); - table |= ICE_UP_TABLE_TRANSLATE(4, 4); - table |= ICE_UP_TABLE_TRANSLATE(5, 5); - table |= ICE_UP_TABLE_TRANSLATE(6, 6); - table |= ICE_UP_TABLE_TRANSLATE(7, 7); - ctxt->info.ingress_table = cpu_to_le32(table); - ctxt->info.egress_table = cpu_to_le32(table); - /* Have 1:1 UP mapping for outer to inner UP table */ - ctxt->info.outer_up_table = cpu_to_le32(table); - /* No Outer tag support outer_tag_flags remains to zero */ -} - -/** - * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI - * @ctxt: the VSI context being set - * @vsi: the VSI being configured - */ -static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) -{ - u8 lut_type, hash_type; - - switch (vsi->type) { - case ICE_VSI_PF: - /* PF VSI will inherit RSS instance of PF */ - lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - return; - } - - ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); -} - -/** - * ice_vsi_add - Create a new VSI or fetch preallocated VSI - * @vsi: the VSI being configured - * - * This initializes a VSI context depending on the VSI type to be added and - * passes it down to the add_vsi aq command to create a new VSI. - */ -static int ice_vsi_add(struct ice_vsi *vsi) -{ - struct ice_vsi_ctx ctxt = { 0 }; - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int ret = 0; - - switch (vsi->type) { - case ICE_VSI_PF: - ctxt.flags = ICE_AQ_VSI_TYPE_PF; - break; - default: - return -ENODEV; - } - - ice_set_dflt_vsi_ctx(&ctxt); - /* if the switch is in VEB mode, allow VSI loopback */ - if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB) - ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; - - /* Set LUT type and HASH type if RSS is enabled */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_set_rss_vsi_ctx(&ctxt, vsi); - - ctxt.info.sw_id = vsi->port_info->sw_id; - ice_vsi_setup_q_map(vsi, &ctxt); - - ret = ice_aq_add_vsi(hw, &ctxt, NULL); - if (ret) { - dev_err(&vsi->back->pdev->dev, - "Add VSI AQ call failed, err %d\n", ret); - return -EIO; - } - vsi->info = ctxt.info; - vsi->vsi_num = ctxt.vsi_num; - - return ret; -} - -/** - * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW - * @vsi: the VSI being cleaned up - */ -static void ice_vsi_release_msix(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - u16 vector = vsi->base_vector; - struct ice_hw *hw = &pf->hw; - u32 txq = 0; - u32 rxq = 0; - int i, q; - - for (i = 0; i < vsi->num_q_vectors; i++, vector++) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), 0); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), 0); - for (q = 0; q < q_vector->num_ring_tx; q++) { - wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - txq++; - } - - for (q = 0; q < q_vector->num_ring_rx; q++) { - wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0); - rxq++; - } - } - - ice_flush(hw); -} - -/** - * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI - * @vsi: the VSI having rings deallocated - */ -static void ice_vsi_clear_rings(struct ice_vsi *vsi) -{ - int i; - - if (vsi->tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) { - if (vsi->tx_rings[i]) { - kfree_rcu(vsi->tx_rings[i], rcu); - vsi->tx_rings[i] = NULL; - } - } - } - if (vsi->rx_rings) { - for (i = 0; i < vsi->alloc_rxq; i++) { - if (vsi->rx_rings[i]) { - kfree_rcu(vsi->rx_rings[i], rcu); - vsi->rx_rings[i] = NULL; - } - } - } -} - -/** - * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI - * @vsi: VSI which is having rings allocated - */ -static int ice_vsi_alloc_rings(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int i; - - /* Allocate tx_rings */ - for (i = 0; i < vsi->alloc_txq; i++) { - struct ice_ring *ring; - - /* allocate with kzalloc(), free with kfree_rcu() */ - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - - if (!ring) - goto err_out; - - ring->q_index = i; - ring->reg_idx = vsi->txq_map[i]; - ring->ring_active = false; - ring->vsi = vsi; - ring->netdev = vsi->netdev; - ring->dev = &pf->pdev->dev; - ring->count = vsi->num_desc; - - vsi->tx_rings[i] = ring; - } - - /* Allocate rx_rings */ - for (i = 0; i < vsi->alloc_rxq; i++) { - struct ice_ring *ring; - - /* allocate with kzalloc(), free with kfree_rcu() */ - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_out; - - ring->q_index = i; - ring->reg_idx = vsi->rxq_map[i]; - ring->ring_active = false; - ring->vsi = vsi; - ring->netdev = vsi->netdev; - ring->dev = &pf->pdev->dev; - ring->count = vsi->num_desc; - vsi->rx_rings[i] = ring; - } - - return 0; - -err_out: - ice_vsi_clear_rings(vsi); - return -ENOMEM; -} - -/** - * ice_vsi_free_irq - Free the irq association with the OS - * @vsi: the VSI being configured - */ -static void ice_vsi_free_irq(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; - - if (!vsi->q_vectors || !vsi->irqs_ready) - return; - - vsi->irqs_ready = false; - for (i = 0; i < vsi->num_q_vectors; i++) { - u16 vector = i + base; - int irq_num; - - irq_num = pf->msix_entries[vector].vector; - - /* free only the irqs that were actually requested */ - if (!vsi->q_vectors[i] || - !(vsi->q_vectors[i]->num_ring_tx || - vsi->q_vectors[i]->num_ring_rx)) - continue; - - /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); - synchronize_irq(irq_num); - devm_free_irq(&pf->pdev->dev, irq_num, - vsi->q_vectors[i]); - } - ice_vsi_release_msix(vsi); - } -} - -/** - * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW - * @vsi: the VSI being configured - */ -static void ice_vsi_cfg_msix(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - u16 vector = vsi->base_vector; - struct ice_hw *hw = &pf->hw; - u32 txq = 0, rxq = 0; - int i, q, itr; - u8 itr_gran; - - for (i = 0; i < vsi->num_q_vectors; i++, vector++) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - itr_gran = hw->itr_gran_200; - - if (q_vector->num_ring_rx) { - q_vector->rx.itr = - ITR_TO_REG(vsi->rx_rings[rxq]->rx_itr_setting, - itr_gran); - q_vector->rx.latency_range = ICE_LOW_LATENCY; - } - - if (q_vector->num_ring_tx) { - q_vector->tx.itr = - ITR_TO_REG(vsi->tx_rings[txq]->tx_itr_setting, - itr_gran); - q_vector->tx.latency_range = ICE_LOW_LATENCY; - } - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), q_vector->rx.itr); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), q_vector->tx.itr); - - /* Both Transmit Queue Interrupt Cause Control register - * and Receive Queue Interrupt Cause control register - * expects MSIX_INDX field to be the vector index - * within the function space and not the absolute - * vector index across PF or across device. - * For SR-IOV VF VSIs queue vector index always starts - * with 1 since first vector index(0) is used for OICR - * in VF space. Since VMDq and other PF VSIs are withtin - * the PF function space, use the vector index thats - * tracked for this PF. - */ - for (q = 0; q < q_vector->num_ring_tx; q++) { - u32 val; - - itr = ICE_TX_ITR; - val = QINT_TQCTL_CAUSE_ENA_M | - (itr << QINT_TQCTL_ITR_INDX_S) | - (vector << QINT_TQCTL_MSIX_INDX_S); - wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); - txq++; - } - - for (q = 0; q < q_vector->num_ring_rx; q++) { - u32 val; - - itr = ICE_RX_ITR; - val = QINT_RQCTL_CAUSE_ENA_M | - (itr << QINT_RQCTL_ITR_INDX_S) | - (vector << QINT_RQCTL_MSIX_INDX_S); - wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); - rxq++; - } - } - - ice_flush(hw); -} - -/** * ice_ena_misc_vector - enable the non-queue interrupts * @pf: board private structure */ @@ -1708,13 +1230,14 @@ static void ice_ena_misc_vector(struct ice_pf *pf) PFINT_OICR_MAL_DETECT_M | PFINT_OICR_GRST_M | PFINT_OICR_PCI_EXCEPTION_M | + PFINT_OICR_VFLR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_CRITERR_M); wr32(hw, PFINT_OICR_ENA, val); /* SW_ITR_IDX = 0, but don't change INTENA */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx), GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M); } @@ -1731,12 +1254,23 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) u32 oicr, ena_mask; set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); + set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); + if (oicr & PFINT_OICR_MAL_DETECT_M) { + ena_mask &= ~PFINT_OICR_MAL_DETECT_M; + set_bit(__ICE_MDD_EVENT_PENDING, pf->state); + } + if (oicr & PFINT_OICR_VFLR_M) { + ena_mask &= ~PFINT_OICR_VFLR_M; + set_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + } + if (oicr & PFINT_OICR_GRST_M) { u32 reset; + /* we have a reset warning */ ena_mask &= ~PFINT_OICR_GRST_M; reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >> @@ -1746,15 +1280,18 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) pf->corer_count++; else if (reset == ICE_RESET_GLOBR) pf->globr_count++; - else + else if (reset == ICE_RESET_EMPR) pf->empr_count++; + else + dev_dbg(&pf->pdev->dev, "Invalid reset type %d\n", + reset); /* If a reset cycle isn't already in progress, we set a bit in * pf->state so that the service task can start a reset/rebuild. * We also make note of which reset happened so that peer * devices/drivers can be informed. */ - if (!test_bit(__ICE_RESET_RECOVERY_PENDING, pf->state)) { + if (!test_and_set_bit(__ICE_RESET_OICR_RECV, pf->state)) { if (reset == ICE_RESET_CORER) set_bit(__ICE_CORER_RECV, pf->state); else if (reset == ICE_RESET_GLOBR) @@ -1762,7 +1299,20 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) else set_bit(__ICE_EMPR_RECV, pf->state); - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* There are couple of different bits at play here. + * hw->reset_ongoing indicates whether the hardware is + * in reset. This is set to true when a reset interrupt + * is received and set back to false after the driver + * has determined that the hardware is out of reset. + * + * __ICE_RESET_OICR_RECV in pf->state indicates + * that a post reset rebuild is required before the + * driver is operational again. This is set above. + * + * As this is the start of the reset/rebuild cycle, set + * both to indicate that. + */ + hw->reset_ongoing = true; } } @@ -1803,208 +1353,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } /** - * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors - * @vsi: the VSI being configured - * - * This function maps descriptor rings to the queue-specific vectors allotted - * through the MSI-X enabling code. On a constrained vector budget, we map Tx - * and Rx rings to the vector as "efficiently" as possible. - */ -static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) -{ - int q_vectors = vsi->num_q_vectors; - int tx_rings_rem, rx_rings_rem; - int v_id; - - /* initially assigning remaining rings count to VSIs num queue value */ - tx_rings_rem = vsi->num_txq; - rx_rings_rem = vsi->num_rxq; - - for (v_id = 0; v_id < q_vectors; v_id++) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_id]; - int tx_rings_per_v, rx_rings_per_v, q_id, q_base; - - /* Tx rings mapping to vector */ - tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); - q_vector->num_ring_tx = tx_rings_per_v; - q_vector->tx.ring = NULL; - q_base = vsi->num_txq - tx_rings_rem; - - for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { - struct ice_ring *tx_ring = vsi->tx_rings[q_id]; - - tx_ring->q_vector = q_vector; - tx_ring->next = q_vector->tx.ring; - q_vector->tx.ring = tx_ring; - } - tx_rings_rem -= tx_rings_per_v; - - /* Rx rings mapping to vector */ - rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); - q_vector->num_ring_rx = rx_rings_per_v; - q_vector->rx.ring = NULL; - q_base = vsi->num_rxq - rx_rings_rem; - - for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { - struct ice_ring *rx_ring = vsi->rx_rings[q_id]; - - rx_ring->q_vector = q_vector; - rx_ring->next = q_vector->rx.ring; - q_vector->rx.ring = rx_ring; - } - rx_rings_rem -= rx_rings_per_v; - } -} - -/** - * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - - switch (vsi->type) { - case ICE_VSI_PF: - vsi->alloc_txq = pf->num_lan_tx; - vsi->alloc_rxq = pf->num_lan_rx; - vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE); - vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - break; - } -} - -/** - * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi - * @vsi: VSI pointer - * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. - * - * On error: returns error code (negative) - * On success: returns 0 - */ -static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors) -{ - struct ice_pf *pf = vsi->back; - - /* allocate memory for both Tx and Rx ring pointers */ - vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, - sizeof(struct ice_ring *), GFP_KERNEL); - if (!vsi->tx_rings) - goto err_txrings; - - vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, - sizeof(struct ice_ring *), GFP_KERNEL); - if (!vsi->rx_rings) - goto err_rxrings; - - if (alloc_qvectors) { - /* allocate memory for q_vector pointers */ - vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, - vsi->num_q_vectors, - sizeof(struct ice_q_vector *), - GFP_KERNEL); - if (!vsi->q_vectors) - goto err_vectors; - } - - return 0; - -err_vectors: - devm_kfree(&pf->pdev->dev, vsi->rx_rings); -err_rxrings: - devm_kfree(&pf->pdev->dev, vsi->tx_rings); -err_txrings: - return -ENOMEM; -} - -/** - * ice_msix_clean_rings - MSIX mode Interrupt Handler - * @irq: interrupt number - * @data: pointer to a q_vector - */ -static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) -{ - struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - - if (!q_vector->tx.ring && !q_vector->rx.ring) - return IRQ_HANDLED; - - napi_schedule(&q_vector->napi); - - return IRQ_HANDLED; -} - -/** - * ice_vsi_alloc - Allocates the next available struct vsi in the PF - * @pf: board private structure - * @type: type of VSI - * - * returns a pointer to a VSI on success, NULL on failure. - */ -static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type) -{ - struct ice_vsi *vsi = NULL; - - /* Need to protect the allocation of the VSIs at the PF level */ - mutex_lock(&pf->sw_mutex); - - /* If we have already allocated our maximum number of VSIs, - * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index - * is available to be populated - */ - if (pf->next_vsi == ICE_NO_VSI) { - dev_dbg(&pf->pdev->dev, "out of VSI slots!\n"); - goto unlock_pf; - } - - vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL); - if (!vsi) - goto unlock_pf; - - vsi->type = type; - vsi->back = pf; - set_bit(__ICE_DOWN, vsi->state); - vsi->idx = pf->next_vsi; - vsi->work_lmt = ICE_DFLT_IRQ_WORK; - - ice_vsi_set_num_qs(vsi); - - switch (vsi->type) { - case ICE_VSI_PF: - if (ice_vsi_alloc_arrays(vsi, true)) - goto err_rings; - - /* Setup default MSIX irq handler for VSI */ - vsi->irq_handler = ice_msix_clean_rings; - break; - default: - dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); - goto unlock_pf; - } - - /* fill VSI slot in the PF struct */ - pf->vsi[pf->next_vsi] = vsi; - - /* prepare pf->next_vsi for next use */ - pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, - pf->next_vsi); - goto unlock_pf; - -err_rings: - devm_kfree(&pf->pdev->dev, vsi); - vsi = NULL; -unlock_pf: - mutex_unlock(&pf->sw_mutex); - return vsi; -} - -/** * ice_free_irq_msix_misc - Unroll misc vector setup * @pf: board private structure */ @@ -2015,12 +1363,15 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) ice_flush(&pf->hw); if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) { - synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); + synchronize_irq(pf->msix_entries[pf->sw_oicr_idx].vector); devm_free_irq(&pf->pdev->dev, - pf->msix_entries[pf->oicr_idx].vector, pf); + pf->msix_entries[pf->sw_oicr_idx].vector, pf); } - ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + ice_free_res(pf->sw_irq_tracker, pf->sw_oicr_idx, ICE_RES_MISC_VEC_ID); + pf->num_avail_hw_msix += 1; + ice_free_res(pf->hw_irq_tracker, pf->hw_oicr_idx, ICE_RES_MISC_VEC_ID); } /** @@ -2047,42 +1398,61 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) * lost during reset. Note that this function is called only during * rebuild path and not while reset is in progress. */ - if (ice_is_reset_recovery_pending(pf->state)) + if (ice_is_reset_in_progress(pf->state)) goto skip_req_irq; - /* reserve one vector in irq_tracker for misc interrupts */ - oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); + /* reserve one vector in sw_irq_tracker for misc interrupts */ + oicr_idx = ice_get_res(pf, pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); if (oicr_idx < 0) return oicr_idx; - pf->oicr_idx = oicr_idx; + pf->num_avail_sw_msix -= 1; + pf->sw_oicr_idx = oicr_idx; + + /* reserve one vector in hw_irq_tracker for misc interrupts */ + oicr_idx = ice_get_res(pf, pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + if (oicr_idx < 0) { + ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + return oicr_idx; + } + pf->num_avail_hw_msix -= 1; + pf->hw_oicr_idx = oicr_idx; err = devm_request_irq(&pf->pdev->dev, - pf->msix_entries[pf->oicr_idx].vector, + pf->msix_entries[pf->sw_oicr_idx].vector, ice_misc_intr, 0, pf->int_name, pf); if (err) { dev_err(&pf->pdev->dev, "devm_request_irq for %s failed: %d\n", pf->int_name, err); - ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); + ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_sw_msix += 1; + ice_free_res(pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID); + pf->num_avail_hw_msix += 1; return err; } skip_req_irq: ice_ena_misc_vector(pf); - val = ((pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | + val = ((pf->hw_oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | PFINT_OICR_CTL_CAUSE_ENA_M); wr32(hw, PFINT_OICR_CTL, val); /* This enables Admin queue Interrupt causes */ - val = ((pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | + val = ((pf->hw_oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | PFINT_FW_CTL_CAUSE_ENA_M); wr32(hw, PFINT_FW_CTL, val); - itr_gran = hw->itr_gran_200; + /* This enables Mailbox queue Interrupt causes */ + val = ((pf->hw_oicr_idx & PFINT_MBX_CTL_MSIX_INDX_M) | + PFINT_MBX_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_MBX_CTL, val); + + itr_gran = hw->itr_gran; - wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx), + wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx), ITR_TO_REG(ICE_ITR_8K, itr_gran)); ice_flush(hw); @@ -2092,209 +1462,43 @@ skip_req_irq: } /** - * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI - * @vsi: the VSI getting queues - * - * Return 0 on success and a negative value on error + * ice_napi_del - Remove NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be removed */ -static int ice_vsi_get_qs_contig(struct ice_vsi *vsi) +static void ice_napi_del(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; - int offset, ret = 0; - - mutex_lock(&pf->avail_q_mutex); - /* look for contiguous block of queues for tx */ - offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS, - 0, vsi->alloc_txq, 0); - if (offset < ICE_MAX_TXQS) { - int i; - - bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq); - for (i = 0; i < vsi->alloc_txq; i++) - vsi->txq_map[i] = i + offset; - } else { - ret = -ENOMEM; - vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER; - } - - /* look for contiguous block of queues for rx */ - offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS, - 0, vsi->alloc_rxq, 0); - if (offset < ICE_MAX_RXQS) { - int i; - - bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq); - for (i = 0; i < vsi->alloc_rxq; i++) - vsi->rxq_map[i] = i + offset; - } else { - ret = -ENOMEM; - vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER; - } - mutex_unlock(&pf->avail_q_mutex); - - return ret; -} - -/** - * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI - * @vsi: the VSI getting queues - * - * Return 0 on success and a negative value on error - */ -static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int i, index = 0; - - mutex_lock(&pf->avail_q_mutex); - - if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) { - for (i = 0; i < vsi->alloc_txq; i++) { - index = find_next_zero_bit(pf->avail_txqs, - ICE_MAX_TXQS, index); - if (index < ICE_MAX_TXQS) { - set_bit(index, pf->avail_txqs); - vsi->txq_map[i] = index; - } else { - goto err_scatter_tx; - } - } - } - - if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) { - for (i = 0; i < vsi->alloc_rxq; i++) { - index = find_next_zero_bit(pf->avail_rxqs, - ICE_MAX_RXQS, index); - if (index < ICE_MAX_RXQS) { - set_bit(index, pf->avail_rxqs); - vsi->rxq_map[i] = index; - } else { - goto err_scatter_rx; - } - } - } - - mutex_unlock(&pf->avail_q_mutex); - return 0; + int v_idx; -err_scatter_rx: - /* unflag any queues we have grabbed (i is failed position) */ - for (index = 0; index < i; index++) { - clear_bit(vsi->rxq_map[index], pf->avail_rxqs); - vsi->rxq_map[index] = 0; - } - i = vsi->alloc_txq; -err_scatter_tx: - /* i is either position of failed attempt or vsi->alloc_txq */ - for (index = 0; index < i; index++) { - clear_bit(vsi->txq_map[index], pf->avail_txqs); - vsi->txq_map[index] = 0; - } + if (!vsi->netdev) + return; - mutex_unlock(&pf->avail_q_mutex); - return -ENOMEM; + for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) + netif_napi_del(&vsi->q_vectors[v_idx]->napi); } /** - * ice_vsi_get_qs - Assign queues from PF to VSI - * @vsi: the VSI to assign queues to + * ice_napi_add - register NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be registered * - * Returns 0 on success and a negative value on error + * This function is only called in the driver's load path. Registering the NAPI + * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, + * reset/rebuild, etc.) */ -static int ice_vsi_get_qs(struct ice_vsi *vsi) +static void ice_napi_add(struct ice_vsi *vsi) { - int ret = 0; - - vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG; - vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG; - - /* NOTE: ice_vsi_get_qs_contig() will set the rx/tx mapping - * modes individually to scatter if assigning contiguous queues - * to rx or tx fails - */ - ret = ice_vsi_get_qs_contig(vsi); - if (ret < 0) { - if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) - vsi->alloc_txq = max_t(u16, vsi->alloc_txq, - ICE_MAX_SCATTER_TXQS); - if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) - vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq, - ICE_MAX_SCATTER_RXQS); - ret = ice_vsi_get_qs_scatter(vsi); - } - - return ret; -} - -/** - * ice_vsi_put_qs - Release queues from VSI to PF - * @vsi: the VSI thats going to release queues - */ -static void ice_vsi_put_qs(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int i; - - mutex_lock(&pf->avail_q_mutex); - - for (i = 0; i < vsi->alloc_txq; i++) { - clear_bit(vsi->txq_map[i], pf->avail_txqs); - vsi->txq_map[i] = ICE_INVAL_Q_INDEX; - } - - for (i = 0; i < vsi->alloc_rxq; i++) { - clear_bit(vsi->rxq_map[i], pf->avail_rxqs); - vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; - } - - mutex_unlock(&pf->avail_q_mutex); -} - -/** - * ice_free_q_vector - Free memory allocated for a specific interrupt vector - * @vsi: VSI having the memory freed - * @v_idx: index of the vector to be freed - */ -static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) -{ - struct ice_q_vector *q_vector; - struct ice_ring *ring; + int v_idx; - if (!vsi->q_vectors[v_idx]) { - dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n", - v_idx); + if (!vsi->netdev) return; - } - q_vector = vsi->q_vectors[v_idx]; - - ice_for_each_ring(ring, q_vector->tx) - ring->q_vector = NULL; - ice_for_each_ring(ring, q_vector->rx) - ring->q_vector = NULL; - - /* only VSI with an associated netdev is set up with NAPI */ - if (vsi->netdev) - netif_napi_del(&q_vector->napi); - - devm_kfree(&vsi->back->pdev->dev, q_vector); - vsi->q_vectors[v_idx] = NULL; -} - -/** - * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors - * @vsi: the VSI having memory freed - */ -static void ice_vsi_free_q_vectors(struct ice_vsi *vsi) -{ - int v_idx; for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) - ice_free_q_vector(vsi, v_idx); + netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, + ice_napi_poll, NAPI_POLL_WEIGHT); } /** - * ice_cfg_netdev - Setup the netdev flags - * @vsi: the VSI being configured + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev * * Returns 0 on success, negative value on failure */ @@ -2307,6 +1511,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) struct ice_netdev_priv *np; struct net_device *netdev; u8 mac_addr[ETH_ALEN]; + int err; netdev = alloc_etherdev_mqs(sizeof(struct ice_netdev_priv), vsi->alloc_txq, vsi->alloc_rxq); @@ -2364,195 +1569,14 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = ICE_MAX_MTU; - return 0; -} - -/** - * ice_vsi_free_arrays - clean up vsi resources - * @vsi: pointer to VSI being cleared - * @free_qvectors: bool to specify if q_vectors should be deallocated - */ -static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors) -{ - struct ice_pf *pf = vsi->back; - - /* free the ring and vector containers */ - if (free_qvectors && vsi->q_vectors) { - devm_kfree(&pf->pdev->dev, vsi->q_vectors); - vsi->q_vectors = NULL; - } - if (vsi->tx_rings) { - devm_kfree(&pf->pdev->dev, vsi->tx_rings); - vsi->tx_rings = NULL; - } - if (vsi->rx_rings) { - devm_kfree(&pf->pdev->dev, vsi->rx_rings); - vsi->rx_rings = NULL; - } -} - -/** - * ice_vsi_clear - clean up and deallocate the provided vsi - * @vsi: pointer to VSI being cleared - * - * This deallocates the vsi's queue resources, removes it from the PF's - * VSI array if necessary, and deallocates the VSI - * - * Returns 0 on success, negative on failure - */ -static int ice_vsi_clear(struct ice_vsi *vsi) -{ - struct ice_pf *pf = NULL; - - if (!vsi) - return 0; - - if (!vsi->back) - return -EINVAL; - - pf = vsi->back; - - if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { - dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n", - vsi->idx); - return -EINVAL; - } - - mutex_lock(&pf->sw_mutex); - /* updates the PF for this cleared vsi */ - - pf->vsi[vsi->idx] = NULL; - if (vsi->idx < pf->next_vsi) - pf->next_vsi = vsi->idx; - - ice_vsi_free_arrays(vsi, true); - mutex_unlock(&pf->sw_mutex); - devm_kfree(&pf->pdev->dev, vsi); - - return 0; -} - -/** - * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector - * @vsi: the VSI being configured - * @v_idx: index of the vector in the vsi struct - * - * We allocate one q_vector. If allocation fails we return -ENOMEM. - */ -static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) -{ - struct ice_pf *pf = vsi->back; - struct ice_q_vector *q_vector; - - /* allocate q_vector */ - q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL); - if (!q_vector) - return -ENOMEM; - - q_vector->vsi = vsi; - q_vector->v_idx = v_idx; - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); - - if (vsi->netdev) - netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, - NAPI_POLL_WEIGHT); - /* tie q_vector and vsi together */ - vsi->q_vectors[v_idx] = q_vector; - - return 0; -} - -/** - * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors - * @vsi: the VSI being configured - * - * We allocate one q_vector per queue interrupt. If allocation fails we - * return -ENOMEM. - */ -static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int v_idx = 0, num_q_vectors; - int err; - - if (vsi->q_vectors[0]) { - dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n", - vsi->vsi_num); - return -EEXIST; - } - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - num_q_vectors = vsi->num_q_vectors; - } else { - err = -EINVAL; - goto err_out; - } - - for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - err = ice_vsi_alloc_q_vector(vsi, v_idx); - if (err) - goto err_out; - } - - return 0; - -err_out: - while (v_idx--) - ice_free_q_vector(vsi, v_idx); - - dev_err(&pf->pdev->dev, - "Failed to allocate %d q_vector for VSI %d, ret=%d\n", - vsi->num_q_vectors, vsi->vsi_num, err); - vsi->num_q_vectors = 0; - return err; -} - -/** - * ice_vsi_setup_vector_base - Set up the base vector for the given VSI - * @vsi: ptr to the VSI - * - * This should only be called after ice_vsi_alloc() which allocates the - * corresponding SW VSI structure and initializes num_queue_pairs for the - * newly allocated VSI. - * - * Returns 0 on success or negative on failure - */ -static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - int num_q_vectors = 0; - - if (vsi->base_vector) { - dev_dbg(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n", - vsi->vsi_num, vsi->base_vector); - return -EEXIST; - } - - if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - return -ENOENT; - - switch (vsi->type) { - case ICE_VSI_PF: - num_q_vectors = vsi->num_q_vectors; - break; - default: - dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", - vsi->type); - break; - } + err = register_netdev(vsi->netdev); + if (err) + return err; - if (num_q_vectors) - vsi->base_vector = ice_get_res(pf, pf->irq_tracker, - num_q_vectors, vsi->idx); + netif_carrier_off(vsi->netdev); - if (vsi->base_vector < 0) { - dev_err(&pf->pdev->dev, - "Failed to get tracking for %d vectors for VSI %d, err=%d\n", - num_q_vectors, vsi->vsi_num, vsi->base_vector); - return -ENOENT; - } + /* make sure transmit queues start off as stopped */ + netif_tx_stop_all_queues(vsi->netdev); return 0; } @@ -2572,327 +1596,17 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) } /** - * ice_vsi_cfg_rss - Configure RSS params for a VSI - * @vsi: VSI to be configured - */ -static int ice_vsi_cfg_rss(struct ice_vsi *vsi) -{ - u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE]; - struct ice_aqc_get_set_rss_keys *key; - struct ice_pf *pf = vsi->back; - enum ice_status status; - int err = 0; - u8 *lut; - - vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq); - - lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL); - if (!lut) - return -ENOMEM; - - if (vsi->rss_lut_user) - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); - else - ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); - - status = ice_aq_set_rss_lut(&pf->hw, vsi->vsi_num, vsi->rss_lut_type, - lut, vsi->rss_table_size); - - if (status) { - dev_err(&vsi->back->pdev->dev, - "set_rss_lut failed, error %d\n", status); - err = -EIO; - goto ice_vsi_cfg_rss_exit; - } - - key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL); - if (!key) { - err = -ENOMEM; - goto ice_vsi_cfg_rss_exit; - } - - if (vsi->rss_hkey_user) - memcpy(seed, vsi->rss_hkey_user, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - else - netdev_rss_key_fill((void *)seed, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - memcpy(&key->standard_rss_key, seed, - ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE); - - status = ice_aq_set_rss_key(&pf->hw, vsi->vsi_num, key); - - if (status) { - dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n", - status); - err = -EIO; - } - - devm_kfree(&pf->pdev->dev, key); -ice_vsi_cfg_rss_exit: - devm_kfree(&pf->pdev->dev, lut); - return err; -} - -/** - * ice_vsi_reinit_setup - return resource and reallocate resource for a VSI - * @vsi: pointer to the ice_vsi - * - * This reallocates the VSIs queue resources - * - * Returns 0 on success and negative value on failure - */ -static int ice_vsi_reinit_setup(struct ice_vsi *vsi) -{ - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - int ret, i; - - if (!vsi) - return -EINVAL; - - ice_vsi_free_q_vectors(vsi); - ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx); - vsi->base_vector = 0; - ice_vsi_clear_rings(vsi); - ice_vsi_free_arrays(vsi, false); - ice_vsi_set_num_qs(vsi); - - /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_add(vsi); - if (ret < 0) - goto err_vsi; - - ret = ice_vsi_alloc_arrays(vsi, false); - if (ret < 0) - goto err_vsi; - - switch (vsi->type) { - case ICE_VSI_PF: - if (!vsi->netdev) { - ret = ice_cfg_netdev(vsi); - if (ret) - goto err_rings; - - ret = register_netdev(vsi->netdev); - if (ret) - goto err_rings; - - netif_carrier_off(vsi->netdev); - netif_tx_stop_all_queues(vsi->netdev); - } - - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ice_vsi_map_rings_to_vectors(vsi); - break; - default: - break; - } - - ice_vsi_set_tc_cfg(vsi); - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; - - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num, - vsi->tc_cfg.ena_tc, max_txqs); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "Failed VSI lan queue config\n"); - goto err_vectors; - } - return 0; - -err_vectors: - ice_vsi_free_q_vectors(vsi); -err_rings: - if (vsi->netdev) { - vsi->current_netdev_flags = 0; - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_vsi: - ice_vsi_clear(vsi); - set_bit(__ICE_RESET_FAILED, vsi->back->state); - return ret; -} - -/** - * ice_vsi_setup - Set up a VSI by a given type + * ice_pf_vsi_setup - Set up a PF VSI * @pf: board private structure - * @type: VSI type * @pi: pointer to the port_info instance * - * This allocates the sw VSI structure and its queue resources. - * - * Returns pointer to the successfully allocated and configure VSI sw struct on - * success, otherwise returns NULL on failure. + * Returns pointer to the successfully allocated VSI sw struct on success, + * otherwise returns NULL on failure. */ static struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type, - struct ice_port_info *pi) -{ - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - struct device *dev = &pf->pdev->dev; - struct ice_vsi_ctx ctxt = { 0 }; - struct ice_vsi *vsi; - int ret, i; - - vsi = ice_vsi_alloc(pf, type); - if (!vsi) { - dev_err(dev, "could not allocate VSI\n"); - return NULL; - } - - vsi->port_info = pi; - vsi->vsw = pf->first_sw; - - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto err_get_qs; - } - - /* set RSS capabilities */ - ice_vsi_set_rss_params(vsi); - - /* create the VSI */ - ret = ice_vsi_add(vsi); - if (ret) - goto err_vsi; - - ctxt.vsi_num = vsi->vsi_num; - - switch (vsi->type) { - case ICE_VSI_PF: - ret = ice_cfg_netdev(vsi); - if (ret) - goto err_cfg_netdev; - - ret = register_netdev(vsi->netdev); - if (ret) - goto err_register_netdev; - - netif_carrier_off(vsi->netdev); - - /* make sure transmit queues start off as stopped */ - netif_tx_stop_all_queues(vsi->netdev); - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_msix; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_rings; - - ice_vsi_map_rings_to_vectors(vsi); - - /* Do not exit if configuring RSS had an issue, at least - * receive traffic on first queue. Hence no need to capture - * return value - */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_vsi_cfg_rss(vsi); - break; - default: - /* if vsi type is not recognized, clean up the resources and - * exit - */ - goto err_rings; - } - - ice_vsi_set_tc_cfg(vsi); - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; - - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num, - vsi->tc_cfg.ena_tc, max_txqs); - if (ret) { - dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n"); - goto err_rings; - } - - return vsi; - -err_rings: - ice_vsi_free_q_vectors(vsi); -err_msix: - if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(vsi->netdev); -err_register_netdev: - if (vsi->netdev) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_cfg_netdev: - ret = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); - if (ret) - dev_err(&vsi->back->pdev->dev, - "Free VSI AQ call failed, err %d\n", ret); -err_vsi: - ice_vsi_put_qs(vsi); -err_get_qs: - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; - ice_vsi_clear(vsi); - - return NULL; -} - -/** - * ice_vsi_add_vlan - Add vsi membership for given vlan - * @vsi: the vsi being configured - * @vid: vlan id to be added - */ -static int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid) +ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - struct ice_fltr_list_entry *tmp; - struct ice_pf *pf = vsi->back; - LIST_HEAD(tmp_add_list); - enum ice_status status; - int err = 0; - - tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.flag = ICE_FLTR_TX; - tmp->fltr_info.src = vsi->vsi_num; - tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - tmp->fltr_info.l_data.vlan.vlan_id = vid; - - INIT_LIST_HEAD(&tmp->list_entry); - list_add(&tmp->list_entry, &tmp_add_list); - - status = ice_add_vlan(&pf->hw, &tmp_add_list); - if (status) { - err = -ENODEV; - dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n", - vid, vsi->vsi_num); - } - - ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); - return err; + return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID); } /** @@ -2908,7 +1622,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret = 0; + int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -2919,6 +1633,13 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, if (vsi->info.pvid) return -EINVAL; + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) { + ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) + return ret; + } + /* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch @@ -2932,38 +1653,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, } /** - * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN - * @vsi: the VSI being configured - * @vid: VLAN id to be removed - */ -static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) -{ - struct ice_fltr_list_entry *list; - struct ice_pf *pf = vsi->back; - LIST_HEAD(tmp_add_list); - - list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); - if (!list) - return; - - list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; - list->fltr_info.fwd_id.vsi_id = vsi->vsi_num; - list->fltr_info.fltr_act = ICE_FWD_TO_VSI; - list->fltr_info.l_data.vlan.vlan_id = vid; - list->fltr_info.flag = ICE_FLTR_TX; - list->fltr_info.src = vsi->vsi_num; - - INIT_LIST_HEAD(&list->list_entry); - list_add(&list->list_entry, &tmp_add_list); - - if (ice_remove_vlan(&pf->hw, &tmp_add_list)) - dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", - vid, vsi->vsi_num); - - ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); -} - -/** * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload * @netdev: network interface to be adjusted * @proto: unused protocol @@ -2976,19 +1665,25 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + int status; if (vsi->info.pvid) return -EINVAL; - /* return code is ignored as there is nothing a user - * can do about failure to remove and a log message was - * already printed from the other function + /* Make sure ice_vsi_kill_vlan is successful before updating VLAN + * information */ - ice_vsi_kill_vlan(vsi, vid); + status = ice_vsi_kill_vlan(vsi, vid); + if (status) + return status; clear_bit(vid, vsi->active_vlans); - return 0; + /* Disable VLAN pruning when VLAN 0 is removed */ + if (unlikely(!vid)) + status = ice_cfg_vlan_pruning(vsi, false); + + return status; } /** @@ -3004,59 +1699,73 @@ static int ice_setup_pf_sw(struct ice_pf *pf) struct ice_vsi *vsi; int status = 0; - if (!ice_is_reset_recovery_pending(pf->state)) { - vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info); - if (!vsi) { - status = -ENOMEM; - goto error_exit; - } - } else { - vsi = pf->vsi[0]; - status = ice_vsi_reinit_setup(vsi); - if (status < 0) - return -EIO; + if (ice_is_reset_in_progress(pf->state)) + return -EBUSY; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + status = -ENOMEM; + goto unroll_vsi_setup; + } + + status = ice_cfg_netdev(vsi); + if (status) { + status = -ENODEV; + goto unroll_vsi_setup; } - /* tmp_add_list contains a list of MAC addresses for which MAC - * filters need to be programmed. Add the VSI's unicast MAC to - * this list + /* registering the NAPI handler requires both the queues and + * netdev to be created, which are done in ice_pf_vsi_setup() + * and ice_cfg_netdev() respectively */ + ice_napi_add(vsi); + + /* To add a MAC filter, first add the MAC to a list and then + * pass the list to ice_add_mac. + */ + + /* Add a unicast MAC filter so the VSI can get its packets */ status = ice_add_mac_to_list(vsi, &tmp_add_list, vsi->port_info->mac.perm_addr); if (status) - goto error_exit; + goto unroll_napi_add; /* VSI needs to receive broadcast traffic, so add the broadcast - * MAC address to the list. + * MAC address to the list as well. */ eth_broadcast_addr(broadcast); status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); if (status) - goto error_exit; + goto free_mac_list; /* program MAC filters for entries in tmp_add_list */ status = ice_add_mac(&pf->hw, &tmp_add_list); if (status) { dev_err(&pf->pdev->dev, "Could not add MAC filters\n"); status = -ENOMEM; - goto error_exit; + goto free_mac_list; } ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); return status; -error_exit: +free_mac_list: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); +unroll_napi_add: if (vsi) { - ice_vsi_free_q_vectors(vsi); - if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(vsi->netdev); + ice_napi_del(vsi); if (vsi->netdev) { + if (vsi->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; } + } +unroll_vsi_setup: + if (vsi) { + ice_vsi_free_q_vectors(vsi); ice_vsi_delete(vsi); ice_vsi_put_qs(vsi); pf->q_left_tx += vsi->alloc_txq; @@ -3097,10 +1806,7 @@ static void ice_determine_q_usage(struct ice_pf *pf) */ static void ice_deinit_pf(struct ice_pf *pf) { - if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); - if (pf->serv_task.func) - cancel_work_sync(&pf->serv_task); + ice_service_task_stop(pf); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->avail_q_mutex); } @@ -3113,6 +1819,15 @@ static void ice_init_pf(struct ice_pf *pf) { bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS); set_bit(ICE_FLAG_MSIX_ENA, pf->flags); +#ifdef CONFIG_PCI_IOV + if (pf->hw.func_caps.common_cap.sr_iov_1_1) { + struct ice_hw *hw = &pf->hw; + + set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); + pf->num_vfs_supported = min_t(int, hw->func_caps.num_allocd_vfs, + ICE_MAX_VF_COUNT); + } +#endif /* CONFIG_PCI_IOV */ mutex_init(&pf->sw_mutex); mutex_init(&pf->avail_q_mutex); @@ -3155,6 +1870,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) /* reserve vectors for LAN traffic */ pf->num_lan_msix = min_t(int, num_online_cpus(), v_left); v_budget += pf->num_lan_msix; + v_left -= pf->num_lan_msix; pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget, sizeof(struct msix_entry), GFP_KERNEL); @@ -3182,10 +1898,11 @@ static int ice_ena_msix_range(struct ice_pf *pf) "not enough vectors. requested = %d, obtained = %d\n", v_budget, v_actual); if (v_actual >= (pf->num_lan_msix + 1)) { - pf->num_avail_msix = v_actual - (pf->num_lan_msix + 1); + pf->num_avail_sw_msix = v_actual - + (pf->num_lan_msix + 1); } else if (v_actual >= 2) { pf->num_lan_msix = 1; - pf->num_avail_msix = v_actual - 2; + pf->num_avail_sw_msix = v_actual - 2; } else { pci_disable_msix(pf->pdev); err = -ERANGE; @@ -3218,12 +1935,32 @@ static void ice_dis_msix(struct ice_pf *pf) } /** + * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme + * @pf: board private structure + */ +static void ice_clear_interrupt_scheme(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + ice_dis_msix(pf); + + if (pf->sw_irq_tracker) { + devm_kfree(&pf->pdev->dev, pf->sw_irq_tracker); + pf->sw_irq_tracker = NULL; + } + + if (pf->hw_irq_tracker) { + devm_kfree(&pf->pdev->dev, pf->hw_irq_tracker); + pf->hw_irq_tracker = NULL; + } +} + +/** * ice_init_interrupt_scheme - Determine proper interrupt scheme * @pf: board private structure to initialize */ static int ice_init_interrupt_scheme(struct ice_pf *pf) { - int vectors = 0; + int vectors = 0, hw_vectors = 0; ssize_t size; if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) @@ -3237,30 +1974,31 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) /* set up vector assignment tracking */ size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors); - pf->irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); - if (!pf->irq_tracker) { + pf->sw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); + if (!pf->sw_irq_tracker) { ice_dis_msix(pf); return -ENOMEM; } - pf->irq_tracker->num_entries = vectors; + /* populate SW interrupts pool with number of OS granted IRQs. */ + pf->num_avail_sw_msix = vectors; + pf->sw_irq_tracker->num_entries = vectors; - return 0; -} + /* set up HW vector assignment tracking */ + hw_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; + size = sizeof(struct ice_res_tracker) + (sizeof(u16) * hw_vectors); -/** - * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme - * @pf: board private structure - */ -static void ice_clear_interrupt_scheme(struct ice_pf *pf) -{ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_dis_msix(pf); - - if (pf->irq_tracker) { - devm_kfree(&pf->pdev->dev, pf->irq_tracker); - pf->irq_tracker = NULL; + pf->hw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL); + if (!pf->hw_irq_tracker) { + ice_clear_interrupt_scheme(pf); + return -ENOMEM; } + + /* populate HW interrupts pool with number of HW supported irqs. */ + pf->num_avail_hw_msix = hw_vectors; + pf->hw_irq_tracker->num_entries = hw_vectors; + + return 0; } /** @@ -3307,6 +2045,8 @@ static int ice_probe(struct pci_dev *pdev, pf->pdev = pdev; pci_set_drvdata(pdev, pf); set_bit(__ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(__ICE_SERVICE_DIS, pf->state); hw = &pf->hw; hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; @@ -3364,6 +2104,9 @@ static int ice_probe(struct pci_dev *pdev, goto err_init_interrupt_unroll; } + /* Driver is mostly up */ + clear_bit(__ICE_DOWN, pf->state); + /* In case of MSIX we are going to setup the misc vector right here * to handle admin queue events etc. In case of legacy and MSI * the misc functionality and queue processing is combined in @@ -3386,7 +2129,11 @@ static int ice_probe(struct pci_dev *pdev, goto err_msix_misc_unroll; } - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + if (hw->evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; + pf->first_sw->pf = pf; /* record the sw_id available for later use */ @@ -3399,21 +2146,15 @@ static int ice_probe(struct pci_dev *pdev, goto err_alloc_sw_unroll; } - /* Driver is mostly up */ - clear_bit(__ICE_DOWN, pf->state); + clear_bit(__ICE_SERVICE_DIS, pf->state); /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); - err = ice_init_link_events(pf->hw.port_info); - if (err) { - dev_err(&pdev->dev, "ice_init_link_events failed: %d\n", err); - goto err_alloc_sw_unroll; - } - return 0; err_alloc_sw_unroll: + set_bit(__ICE_SERVICE_DIS, pf->state); set_bit(__ICE_DOWN, pf->state); devm_kfree(&pf->pdev->dev, pf->first_sw); err_msix_misc_unroll: @@ -3436,25 +2177,23 @@ err_exit_unroll: static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - int i = 0; - int err; + int i; if (!pf) return; set_bit(__ICE_DOWN, pf->state); + ice_service_task_stop(pf); - for (i = 0; i < pf->num_alloc_vsi; i++) { + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + ice_free_vfs(pf); + ice_vsi_release_all(pf); + ice_free_irq_msix_misc(pf); + ice_for_each_vsi(pf, i) { if (!pf->vsi[i]) continue; - - err = ice_vsi_release(pf->vsi[i]); - if (err) - dev_dbg(&pf->pdev->dev, "Failed to release VSI index %d (err %d)\n", - i, err); + ice_vsi_free_q_vectors(pf->vsi[i]); } - - ice_free_irq_msix_misc(pf); ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); @@ -3470,11 +2209,9 @@ static void ice_remove(struct pci_dev *pdev) * Class, Class Mask, private data (not used) } */ static const struct pci_device_id ice_pci_tbl[] = { - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SGMII), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, /* required last entry */ { 0, } }; @@ -3485,6 +2222,7 @@ static struct pci_driver ice_driver = { .id_table = ice_pci_tbl, .probe = ice_probe, .remove = ice_remove, + .sriov_configure = ice_sriov_configure, }; /** @@ -3500,7 +2238,7 @@ static int __init ice_module_init(void) pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver); pr_info("%s\n", ice_copyright); - ice_wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; @@ -3562,7 +2300,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) } if (test_bit(__ICE_DOWN, pf->state) || - ice_is_reset_recovery_pending(pf->state)) { + ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't set mac %pM. device not ready\n", mac); return -EBUSY; @@ -3722,78 +2460,6 @@ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], } /** - * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx - * @vsi: the vsi being changed - */ -static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) -{ - struct device *dev = &vsi->back->pdev->dev; - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx ctxt = { 0 }; - enum ice_status status; - - /* Here we are configuring the VSI to let the driver add VLAN tags by - * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag - * insertion happens in the Tx hot path, in ice_tx_map. - */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - ctxt.vsi_num = vsi->vsi_num; - - status = ice_aq_update_vsi(hw, &ctxt, NULL); - if (status) { - dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", - status, hw->adminq.sq_last_status); - return -EIO; - } - - vsi->info.vlan_flags = ctxt.info.vlan_flags; - return 0; -} - -/** - * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx - * @vsi: the vsi being changed - * @ena: boolean value indicating if this is a enable or disable request - */ -static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) -{ - struct device *dev = &vsi->back->pdev->dev; - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx ctxt = { 0 }; - enum ice_status status; - - /* Here we are configuring what the VSI should do with the VLAN tag in - * the Rx packet. We can either leave the tag in the packet or put it in - * the Rx descriptor. - */ - if (ena) { - /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; - } else { - /* Disable stripping. Leave tag in packet */ - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; - } - - /* Allow all packets untagged/tagged */ - ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - ctxt.vsi_num = vsi->vsi_num; - - status = ice_aq_update_vsi(hw, &ctxt, NULL); - if (status) { - dev_err(dev, "update VSI for VALN strip failed, ena = %d err %d aq_err %d\n", - ena, status, hw->adminq.sq_last_status); - return -EIO; - } - - vsi->info.vlan_flags = ctxt.info.vlan_flags; - return 0; -} - -/** * ice_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting @@ -3805,6 +2471,12 @@ static int ice_set_features(struct net_device *netdev, struct ice_vsi *vsi = np->vsi; int ret = 0; + if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH)) + ret = ice_vsi_manage_rss_lut(vsi, true); + else if (!(features & NETIF_F_RXHASH) && + netdev->features & NETIF_F_RXHASH) + ret = ice_vsi_manage_rss_lut(vsi, false); + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) ret = ice_vsi_manage_vlan_stripping(vsi, true); @@ -3863,248 +2535,6 @@ static int ice_restore_vlan(struct ice_vsi *vsi) } /** - * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance - * @ring: The Tx ring to configure - * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized - * @pf_q: queue index in the PF space - * - * Configure the Tx descriptor ring in TLAN context. - */ -static void -ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) -{ - struct ice_vsi *vsi = ring->vsi; - struct ice_hw *hw = &vsi->back->hw; - - tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S; - - tlan_ctx->port_num = vsi->port_info->lport; - - /* Transmit Queue Length */ - tlan_ctx->qlen = ring->count; - - /* PF number */ - tlan_ctx->pf_num = hw->pf_id; - - /* queue belongs to a specific VSI type - * VF / VM index should be programmed per vmvf_type setting: - * for vmvf_type = VF, it is VF number between 0-256 - * for vmvf_type = VM, it is VM number between 0-767 - * for PF or EMP this field should be set to zero - */ - switch (vsi->type) { - case ICE_VSI_PF: - tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; - break; - default: - return; - } - - /* make sure the context is associated with the right VSI */ - tlan_ctx->src_vsi = vsi->vsi_num; - - tlan_ctx->tso_ena = ICE_TX_LEGACY; - tlan_ctx->tso_qnum = pf_q; - - /* Legacy or Advanced Host Interface: - * 0: Advanced Host Interface - * 1: Legacy Host Interface - */ - tlan_ctx->legacy_int = ICE_TX_LEGACY; -} - -/** - * ice_vsi_cfg_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -static int ice_vsi_cfg_txqs(struct ice_vsi *vsi) -{ - struct ice_aqc_add_tx_qgrp *qg_buf; - struct ice_aqc_add_txqs_perq *txq; - struct ice_pf *pf = vsi->back; - enum ice_status status; - u16 buf_len, i, pf_q; - int err = 0, tc = 0; - u8 num_q_grps; - - buf_len = sizeof(struct ice_aqc_add_tx_qgrp); - qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - - if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) { - err = -EINVAL; - goto err_cfg_txqs; - } - qg_buf->num_txqs = 1; - num_q_grps = 1; - - /* set up and configure the tx queues */ - ice_for_each_txq(vsi, i) { - struct ice_tlan_ctx tlan_ctx = { 0 }; - - pf_q = vsi->txq_map[i]; - ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q); - /* copy context contents into the qg_buf */ - qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); - - /* init queue specific tail reg. It is referred as transmit - * comm scheduler queue doorbell. - */ - vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); - status = ice_ena_vsi_txq(vsi->port_info, vsi->vsi_num, tc, - num_q_grps, qg_buf, buf_len, NULL); - if (status) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Tx queue context, error: %d\n", - status); - err = -ENODEV; - goto err_cfg_txqs; - } - - /* Add Tx Queue TEID into the VSI tx ring from the response - * This will complete configuring and enabling the queue. - */ - txq = &qg_buf->txqs[0]; - if (pf_q == le16_to_cpu(txq->txq_id)) - vsi->tx_rings[i]->txq_teid = - le32_to_cpu(txq->q_teid); - } -err_cfg_txqs: - devm_kfree(&pf->pdev->dev, qg_buf); - return err; -} - -/** - * ice_setup_rx_ctx - Configure a receive ring context - * @ring: The Rx ring to configure - * - * Configure the Rx descriptor ring in RLAN context. - */ -static int ice_setup_rx_ctx(struct ice_ring *ring) -{ - struct ice_vsi *vsi = ring->vsi; - struct ice_hw *hw = &vsi->back->hw; - u32 rxdid = ICE_RXDID_FLEX_NIC; - struct ice_rlan_ctx rlan_ctx; - u32 regval; - u16 pf_q; - int err; - - /* what is RX queue number in global space of 2K rx queues */ - pf_q = vsi->rxq_map[ring->q_index]; - - /* clear the context structure first */ - memset(&rlan_ctx, 0, sizeof(rlan_ctx)); - - rlan_ctx.base = ring->dma >> ICE_RLAN_BASE_S; - - rlan_ctx.qlen = ring->count; - - /* Receive Packet Data Buffer Size. - * The Packet Data Buffer Size is defined in 128 byte units. - */ - rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; - - /* use 32 byte descriptors */ - rlan_ctx.dsize = 1; - - /* Strip the Ethernet CRC bytes before the packet is posted to host - * memory. - */ - rlan_ctx.crcstrip = 1; - - /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ - rlan_ctx.l2tsel = 1; - - rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; - rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; - rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; - - /* This controls whether VLAN is stripped from inner headers - * The VLAN in the inner L2 header is stripped to the receive - * descriptor if enabled by this flag. - */ - rlan_ctx.showiv = 0; - - /* Max packet size for this queue - must not be set to a larger value - * than 5 x DBUF - */ - rlan_ctx.rxmax = min_t(u16, vsi->max_frame, - ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len); - - /* Rx queue threshold in units of 64 */ - rlan_ctx.lrxqthresh = 1; - - /* Enable Flexible Descriptors in the queue context which - * allows this driver to select a specific receive descriptor format - */ - regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - /* increasing context priority to pick up profile id; - * default is 0x01; setting to 0x03 to ensure profile - * is programming if prev context is of same priority - */ - regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; - - wr32(hw, QRXFLXP_CNTXT(pf_q), regval); - - /* Absolute queue number out of 2K needs to be passed */ - err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); - if (err) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", - pf_q, err); - return -EIO; - } - - /* init queue specific tail register */ - ring->tail = hw->hw_addr + QRX_TAIL(pf_q); - writel(0, ring->tail); - ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); - - return 0; -} - -/** - * ice_vsi_cfg_rxqs - Configure the VSI for Rx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Rx VSI for operation. - */ -static int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) -{ - int err = 0; - u16 i; - - if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN) - vsi->max_frame = vsi->netdev->mtu + - ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - else - vsi->max_frame = ICE_RXBUF_2048; - - vsi->rx_buf_len = ICE_RXBUF_2048; - /* set up individual rings */ - for (i = 0; i < vsi->num_rxq && !err; i++) - err = ice_setup_rx_ctx(vsi->rx_rings[i]); - - if (err) { - dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n"); - return -EIO; - } - return err; -} - -/** * ice_vsi_cfg - Setup the VSI * @vsi: the VSI being configured * @@ -4129,200 +2559,6 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) } /** - * ice_vsi_stop_tx_rings - Disable Tx rings - * @vsi: the VSI being configured - */ -static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - enum ice_status status; - u32 *q_teids, val; - u16 *q_ids, i; - int err = 0; - - if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) - return -EINVAL; - - q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids), - GFP_KERNEL); - if (!q_teids) - return -ENOMEM; - - q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids), - GFP_KERNEL); - if (!q_ids) { - err = -ENOMEM; - goto err_alloc_q_ids; - } - - /* set up the tx queue list to be disabled */ - ice_for_each_txq(vsi, i) { - u16 v_idx; - - if (!vsi->tx_rings || !vsi->tx_rings[i]) { - err = -EINVAL; - goto err_out; - } - - q_ids[i] = vsi->txq_map[i]; - q_teids[i] = vsi->tx_rings[i]->txq_teid; - - /* clear cause_ena bit for disabled queues */ - val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val); - - /* software is expected to wait for 100 ns */ - ndelay(100); - - /* trigger a software interrupt for the vector associated to - * the queue to schedule napi handler - */ - v_idx = vsi->tx_rings[i]->q_vector->v_idx; - wr32(hw, GLINT_DYN_CTL(vsi->base_vector + v_idx), - GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); - } - status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, - NULL); - if (status) { - dev_err(&pf->pdev->dev, - "Failed to disable LAN Tx queues, error: %d\n", - status); - err = -ENODEV; - } - -err_out: - devm_kfree(&pf->pdev->dev, q_ids); - -err_alloc_q_ids: - devm_kfree(&pf->pdev->dev, q_teids); - - return err; -} - -/** - * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled - * @pf: the PF being configured - * @pf_q: the PF queue - * @ena: enable or disable state of the queue - * - * This routine will wait for the given Rx queue of the PF to reach the - * enabled or disabled state. - * Returns -ETIMEDOUT in case of failing to reach the requested state after - * multiple retries; else will return 0 in case of success. - */ -static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) -{ - int i; - - for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) { - u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q)); - - if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) - break; - - usleep_range(10, 20); - } - if (i >= ICE_Q_WAIT_RETRY_LIMIT) - return -ETIMEDOUT; - - return 0; -} - -/** - * ice_vsi_ctrl_rx_rings - Start or stop a VSI's rx rings - * @vsi: the VSI being configured - * @ena: start or stop the rx rings - */ -static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - int i, j, ret = 0; - - for (i = 0; i < vsi->num_rxq; i++) { - int pf_q = vsi->rxq_map[i]; - u32 rx_reg; - - for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) { - rx_reg = rd32(hw, QRX_CTRL(pf_q)); - if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) == - ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1)) - break; - usleep_range(1000, 2000); - } - - /* Skip if the queue is already in the requested state */ - if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) - continue; - - /* turn on/off the queue */ - if (ena) - rx_reg |= QRX_CTRL_QENA_REQ_M; - else - rx_reg &= ~QRX_CTRL_QENA_REQ_M; - wr32(hw, QRX_CTRL(pf_q), rx_reg); - - /* wait for the change to finish */ - ret = ice_pf_rxq_wait(pf, pf_q, ena); - if (ret) { - dev_err(&pf->pdev->dev, - "VSI idx %d Rx ring %d %sable timeout\n", - vsi->idx, pf_q, (ena ? "en" : "dis")); - break; - } - } - - return ret; -} - -/** - * ice_vsi_start_rx_rings - start VSI's rx rings - * @vsi: the VSI whose rings are to be started - * - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_start_rx_rings(struct ice_vsi *vsi) -{ - return ice_vsi_ctrl_rx_rings(vsi, true); -} - -/** - * ice_vsi_stop_rx_rings - stop VSI's rx rings - * @vsi: the VSI - * - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) -{ - return ice_vsi_ctrl_rx_rings(vsi, false); -} - -/** - * ice_vsi_stop_tx_rx_rings - stop VSI's tx and rx rings - * @vsi: the VSI - * Returns 0 on success and a negative value on error - */ -static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi) -{ - int err_tx, err_rx; - - err_tx = ice_vsi_stop_tx_rings(vsi); - if (err_tx) - dev_dbg(&vsi->back->pdev->dev, "Failed to disable Tx rings\n"); - - err_rx = ice_vsi_stop_rx_rings(vsi); - if (err_rx) - dev_dbg(&vsi->back->pdev->dev, "Failed to disable Rx rings\n"); - - if (err_tx || err_rx) - return -EIO; - - return 0; -} - -/** * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI * @vsi: the VSI being configured */ @@ -4419,122 +2655,6 @@ static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, } /** - * ice_stat_update40 - read 40 bit stat from the chip and update stat values - * @hw: ptr to the hardware info - * @hireg: high 32 bit HW register to read from - * @loreg: low 32 bit HW register to read from - * @prev_stat_loaded: bool to specify if previous stats are loaded - * @prev_stat: ptr to previous loaded stat value - * @cur_stat: ptr to current stat value - */ -static void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, - u64 *cur_stat) -{ - u64 new_data; - - new_data = rd32(hw, loreg); - new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; - - /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. - */ - if (!prev_stat_loaded) - *prev_stat = new_data; - if (likely(new_data >= *prev_stat)) - *cur_stat = new_data - *prev_stat; - else - /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; - *cur_stat &= 0xFFFFFFFFFFULL; -} - -/** - * ice_stat_update32 - read 32 bit stat from the chip and update stat values - * @hw: ptr to the hardware info - * @reg: HW register to read from - * @prev_stat_loaded: bool to specify if previous stats are loaded - * @prev_stat: ptr to previous loaded stat value - * @cur_stat: ptr to current stat value - */ -static void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, - u64 *prev_stat, u64 *cur_stat) -{ - u32 new_data; - - new_data = rd32(hw, reg); - - /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. - */ - if (!prev_stat_loaded) - *prev_stat = new_data; - if (likely(new_data >= *prev_stat)) - *cur_stat = new_data - *prev_stat; - else - /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; -} - -/** - * ice_update_eth_stats - Update VSI-specific ethernet statistics counters - * @vsi: the VSI to be updated - */ -static void ice_update_eth_stats(struct ice_vsi *vsi) -{ - struct ice_eth_stats *prev_es, *cur_es; - struct ice_hw *hw = &vsi->back->hw; - u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ - - prev_es = &vsi->eth_stats_prev; - cur_es = &vsi->eth_stats; - - ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_bytes, - &cur_es->rx_bytes); - - ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_unicast, - &cur_es->rx_unicast); - - ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_multicast, - &cur_es->rx_multicast); - - ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_broadcast, - &cur_es->rx_broadcast); - - ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, - &prev_es->rx_discards, &cur_es->rx_discards); - - ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_bytes, - &cur_es->tx_bytes); - - ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_unicast, - &cur_es->tx_unicast); - - ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_multicast, - &cur_es->tx_multicast); - - ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_broadcast, - &cur_es->tx_broadcast); - - ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, - &prev_es->tx_errors, &cur_es->tx_errors); - - vsi->stat_offsets_loaded = true; -} - -/** * ice_update_vsi_ring_stats - Update VSI stats counters * @vsi: the VSI to be updated */ @@ -4827,7 +2947,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, err; + int i, tx_err, rx_err; /* Caller of this function is expected to set the * vsi->state __ICE_DOWN bit @@ -4838,7 +2958,18 @@ int ice_down(struct ice_vsi *vsi) } ice_vsi_dis_irq(vsi); - err = ice_vsi_stop_tx_rx_rings(vsi); + tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0); + if (tx_err) + netdev_err(vsi->netdev, + "Failed stop Tx rings, VSI %d error %d\n", + vsi->vsi_num, tx_err); + + rx_err = ice_vsi_stop_rx_rings(vsi); + if (rx_err) + netdev_err(vsi->netdev, + "Failed stop Rx rings, VSI %d error %d\n", + vsi->vsi_num, rx_err); + ice_napi_disable_all(vsi); ice_for_each_txq(vsi, i) @@ -4847,10 +2978,14 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (err) - netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", + if (tx_err || rx_err) { + netdev_err(vsi->netdev, + "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); - return err; + return -EIO; + } + + return 0; } /** @@ -4870,6 +3005,7 @@ static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) } ice_for_each_txq(vsi, i) { + vsi->tx_rings[i]->netdev = vsi->netdev; err = ice_setup_tx_ring(vsi->tx_rings[i]); if (err) break; @@ -4895,6 +3031,7 @@ static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } ice_for_each_rxq(vsi, i) { + vsi->rx_rings[i]->netdev = vsi->netdev; err = ice_setup_rx_ring(vsi->rx_rings[i]); if (err) break; @@ -4922,38 +3059,6 @@ static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename) } /** - * ice_vsi_free_tx_rings - Free Tx resources for VSI queues - * @vsi: the VSI having resources freed - */ -static void ice_vsi_free_tx_rings(struct ice_vsi *vsi) -{ - int i; - - if (!vsi->tx_rings) - return; - - ice_for_each_txq(vsi, i) - if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) - ice_free_tx_ring(vsi->tx_rings[i]); -} - -/** - * ice_vsi_free_rx_rings - Free Rx resources for VSI queues - * @vsi: the VSI having resources freed - */ -static void ice_vsi_free_rx_rings(struct ice_vsi *vsi) -{ - int i; - - if (!vsi->rx_rings) - return; - - ice_for_each_rxq(vsi, i) - if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc) - ice_free_rx_ring(vsi->rx_rings[i]); -} - -/** * ice_vsi_open - Called when a network interface is made active * @vsi: the VSI to open * @@ -5014,78 +3119,26 @@ err_setup_tx: } /** - * ice_vsi_close - Shut down a VSI - * @vsi: the VSI being shut down + * ice_vsi_release_all - Delete all VSIs + * @pf: PF from which all VSIs are being removed */ -static void ice_vsi_close(struct ice_vsi *vsi) +static void ice_vsi_release_all(struct ice_pf *pf) { - if (!test_and_set_bit(__ICE_DOWN, vsi->state)) - ice_down(vsi); - - ice_vsi_free_irq(vsi); - ice_vsi_free_tx_rings(vsi); - ice_vsi_free_rx_rings(vsi); -} + int err, i; -/** - * ice_rss_clean - Delete RSS related VSI structures that hold user inputs - * @vsi: the VSI being removed - */ -static void ice_rss_clean(struct ice_vsi *vsi) -{ - struct ice_pf *pf; - - pf = vsi->back; - - if (vsi->rss_hkey_user) - devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user); - if (vsi->rss_lut_user) - devm_kfree(&pf->pdev->dev, vsi->rss_lut_user); -} - -/** - * ice_vsi_release - Delete a VSI and free its resources - * @vsi: the VSI being removed - * - * Returns 0 on success or < 0 on error - */ -static int ice_vsi_release(struct ice_vsi *vsi) -{ - struct ice_pf *pf; + if (!pf->vsi) + return; - if (!vsi->back) - return -ENODEV; - pf = vsi->back; + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (!pf->vsi[i]) + continue; - if (vsi->netdev) { - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; + err = ice_vsi_release(pf->vsi[i]); + if (err) + dev_dbg(&pf->pdev->dev, + "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", + i, err, pf->vsi[i]->vsi_num); } - - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_rss_clean(vsi); - - /* Disable VSI and free resources */ - ice_vsi_dis_irq(vsi); - ice_vsi_close(vsi); - - /* reclaim interrupt vectors back to PF */ - ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_msix += vsi->num_q_vectors; - - ice_remove_vsi_fltr(&pf->hw, vsi->vsi_num); - ice_vsi_delete(vsi); - ice_vsi_free_q_vectors(vsi); - ice_vsi_clear_rings(vsi); - - ice_vsi_put_qs(vsi); - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; - - ice_vsi_clear(vsi); - - return 0; } /** @@ -5099,28 +3152,37 @@ static void ice_dis_vsi(struct ice_vsi *vsi) set_bit(__ICE_NEEDS_RESTART, vsi->state); - if (vsi->netdev && netif_running(vsi->netdev) && - vsi->type == ICE_VSI_PF) - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - - ice_vsi_close(vsi); + if (vsi->type == ICE_VSI_PF && vsi->netdev) { + if (netif_running(vsi->netdev)) { + rtnl_lock(); + vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + rtnl_unlock(); + } else { + ice_vsi_close(vsi); + } + } } /** * ice_ena_vsi - resume a VSI * @vsi: the VSI being resume */ -static void ice_ena_vsi(struct ice_vsi *vsi) +static int ice_ena_vsi(struct ice_vsi *vsi) { - if (!test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) - return; + int err = 0; - if (vsi->netdev && netif_running(vsi->netdev)) - vsi->netdev->netdev_ops->ndo_open(vsi->netdev); - else if (ice_vsi_open(vsi)) - /* this clears the DOWN bit */ - dev_dbg(&vsi->back->pdev->dev, "Failed open VSI 0x%04X on switch 0x%04X\n", - vsi->vsi_num, vsi->vsw->sw_id); + if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state) && + vsi->netdev) { + if (netif_running(vsi->netdev)) { + rtnl_lock(); + err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev); + rtnl_unlock(); + } else { + err = ice_vsi_open(vsi); + } + } + + return err; } /** @@ -5140,13 +3202,89 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf) * ice_pf_ena_all_vsi - Resume all VSIs on a PF * @pf: the PF */ -static void ice_pf_ena_all_vsi(struct ice_pf *pf) +static int ice_pf_ena_all_vsi(struct ice_pf *pf) { int v; ice_for_each_vsi(pf, v) if (pf->vsi[v]) - ice_ena_vsi(pf->vsi[v]); + if (ice_ena_vsi(pf->vsi[v])) + return -EIO; + + return 0; +} + +/** + * ice_vsi_rebuild_all - rebuild all VSIs in pf + * @pf: the PF + */ +static int ice_vsi_rebuild_all(struct ice_pf *pf) +{ + int i; + + /* loop through pf->vsi array and reinit the VSI if found */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + int err; + + if (!pf->vsi[i]) + continue; + + /* VF VSI rebuild isn't supported yet */ + if (pf->vsi[i]->type == ICE_VSI_VF) + continue; + + err = ice_vsi_rebuild(pf->vsi[i]); + if (err) { + dev_err(&pf->pdev->dev, + "VSI at index %d rebuild failed\n", + pf->vsi[i]->idx); + return err; + } + + dev_info(&pf->pdev->dev, + "VSI at index %d rebuilt. vsi_num = 0x%x\n", + pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + } + + return 0; +} + +/** + * ice_vsi_replay_all - replay all VSIs configuration in the PF + * @pf: the PF + */ +static int ice_vsi_replay_all(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + enum ice_status ret; + int i; + + /* loop through pf->vsi array and replay the VSI if found */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (!pf->vsi[i]) + continue; + + ret = ice_replay_vsi(hw, pf->vsi[i]->idx); + if (ret) { + dev_err(&pf->pdev->dev, + "VSI at index %d replay failed %d\n", + pf->vsi[i]->idx, ret); + return -EIO; + } + + /* Re-map HW VSI number, using VSI handle that has been + * previously validated in ice_replay_vsi() call above + */ + pf->vsi[i]->vsi_num = ice_get_hw_vsi_num(hw, pf->vsi[i]->idx); + + dev_info(&pf->pdev->dev, + "VSI at index %d filter replayed successfully - vsi_num %i\n", + pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + } + + /* Clean up replay filter after successful re-configuration */ + ice_replay_post(hw); + return 0; } /** @@ -5168,13 +3306,13 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_init_all_ctrlq(hw); if (ret) { dev_err(dev, "control queues init failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ret = ice_clear_pf_cfg(hw); if (ret) { dev_err(dev, "clear PF configuration failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ice_clear_pxe_mode(hw); @@ -5182,14 +3320,34 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_get_caps(hw); if (ret) { dev_err(dev, "ice_get_caps failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } - /* basic nic switch setup */ - err = ice_setup_pf_sw(pf); + err = ice_sched_init_port(hw->port_info); + if (err) + goto err_sched_init_port; + + /* reset search_hint of irq_trackers to 0 since interrupts are + * reclaimed and could be allocated from beginning during VSI rebuild + */ + pf->sw_irq_tracker->search_hint = 0; + pf->hw_irq_tracker->search_hint = 0; + + err = ice_vsi_rebuild_all(pf); if (err) { - dev_err(dev, "ice_setup_pf_sw failed\n"); - goto fail_reset; + dev_err(dev, "ice_vsi_rebuild_all failed\n"); + goto err_vsi_rebuild; + } + + err = ice_update_link_info(hw->port_info); + if (err) + dev_err(&pf->pdev->dev, "Get link status error %d\n", err); + + /* Replay all VSIs Configuration, including filters after reset */ + if (ice_vsi_replay_all(pf)) { + dev_err(&pf->pdev->dev, + "error replaying VSI configurations with switch filter rules\n"); + goto err_vsi_rebuild; } /* start misc vector */ @@ -5197,20 +3355,36 @@ static void ice_rebuild(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "misc vector setup failed: %d\n", err); - goto fail_reset; + goto err_vsi_rebuild; } } /* restart the VSIs that were rebuilt and running before the reset */ - ice_pf_ena_all_vsi(pf); + err = ice_pf_ena_all_vsi(pf); + if (err) { + dev_err(&pf->pdev->dev, "error enabling VSIs\n"); + /* no need to disable VSIs in tear down path in ice_rebuild() + * since its already taken care in ice_vsi_open() + */ + goto err_vsi_rebuild; + } + ice_reset_all_vfs(pf, true); + /* if we get here, reset flow is successful */ + clear_bit(__ICE_RESET_FAILED, pf->state); return; -fail_reset: +err_vsi_rebuild: + ice_vsi_release_all(pf); +err_sched_init_port: + ice_sched_cleanup_all(hw); +err_init_ctrlq: ice_shutdown_all_ctrlq(hw); set_bit(__ICE_RESET_FAILED, pf->state); clear_recovery: - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* set this bit in PF state to control service task scheduling */ + set_bit(__ICE_NEEDS_RESTART, pf->state); + dev_err(dev, "Rebuild failed, unload and reload driver\n"); } /** @@ -5243,7 +3417,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) } /* if a reset is in progress, wait for some time for it to complete */ do { - if (ice_is_reset_recovery_pending(pf->state)) { + if (ice_is_reset_in_progress(pf->state)) { count++; usleep_range(1000, 2000); } else { @@ -5299,7 +3473,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) struct ice_aqc_get_set_rss_keys *buf = (struct ice_aqc_get_set_rss_keys *)seed; - status = ice_aq_set_rss_key(hw, vsi->vsi_num, buf); + status = ice_aq_set_rss_key(hw, vsi->idx, buf); if (status) { dev_err(&pf->pdev->dev, @@ -5310,8 +3484,8 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } if (lut) { - status = ice_aq_set_rss_lut(hw, vsi->vsi_num, - vsi->rss_lut_type, lut, lut_size); + status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type, + lut, lut_size); if (status) { dev_err(&pf->pdev->dev, "Cannot set RSS lut, err %d aq_err %d\n", @@ -5342,7 +3516,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) struct ice_aqc_get_set_rss_keys *buf = (struct ice_aqc_get_set_rss_keys *)seed; - status = ice_aq_get_rss_key(hw, vsi->vsi_num, buf); + status = ice_aq_get_rss_key(hw, vsi->idx, buf); if (status) { dev_err(&pf->pdev->dev, "Cannot get RSS key, err %d aq_err %d\n", @@ -5352,8 +3526,8 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } if (lut) { - status = ice_aq_get_rss_lut(hw, vsi->vsi_num, - vsi->rss_lut_type, lut, lut_size); + status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type, + lut, lut_size); if (status) { dev_err(&pf->pdev->dev, "Cannot get RSS lut, err %d aq_err %d\n", @@ -5366,6 +3540,232 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } /** + * ice_bridge_getlink - Get the hardware bridge mode + * @skb: skb buff + * @pid: process id + * @seq: RTNL message seq + * @dev: the netdev being configured + * @filter_mask: filter mask passed in + * @nlflags: netlink flags passed in + * + * Return the bridge mode (VEB/VEPA) + */ +static int +ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, int nlflags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u16 bmode; + + bmode = pf->first_sw->bridge_mode; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bmode, 0, 0, nlflags, + filter_mask, NULL); +} + +/** + * ice_vsi_update_bridge_mode - Update VSI for switching bridge mode (VEB/VEPA) + * @vsi: Pointer to VSI structure + * @bmode: Hardware bridge mode (VEB/VEPA) + * + * Returns 0 on success, negative on failure + */ +static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_aqc_vsi_props *vsi_props; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + vsi_props = &vsi->info; + ctxt.info = vsi->info; + + if (bmode == BRIDGE_MODE_VEB) + /* change from VEPA to VEB mode */ + ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + else + /* change from VEB to VEPA mode */ + ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", + bmode, status, hw->adminq.sq_last_status); + return -EIO; + } + /* Update sw flags for book keeping */ + vsi_props->sw_flags = ctxt.info.sw_flags; + + return 0; +} + +/** + * ice_bridge_setlink - Set the hardware bridge mode + * @dev: the netdev being configured + * @nlh: RTNL message + * @flags: bridge setlink flags + * + * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is + * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if + * not already set for all VSIs connected to this switch. And also update the + * unicast switch filter rules for the corresponding switch of the netdev. + */ +static int +ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 __always_unused flags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_pf *pf = np->vsi->back; + struct nlattr *attr, *br_spec; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + struct ice_sw *pf_sw; + int rem, v, err = 0; + + pf_sw = pf->first_sw; + /* find the attribute in the netlink message */ + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + + nla_for_each_nested(attr, br_spec, rem) { + __u16 mode; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + mode = nla_get_u16(attr); + if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) + return -EINVAL; + /* Continue if bridge mode is not being flipped */ + if (mode == pf_sw->bridge_mode) + continue; + /* Iterates through the PF VSI list and update the loopback + * mode of the VSI + */ + ice_for_each_vsi(pf, v) { + if (!pf->vsi[v]) + continue; + err = ice_vsi_update_bridge_mode(pf->vsi[v], mode); + if (err) + return err; + } + + hw->evb_veb = (mode == BRIDGE_MODE_VEB); + /* Update the unicast switch filter rules for the corresponding + * switch of the netdev + */ + status = ice_update_sw_rule_bridge_mode(hw); + if (status) { + netdev_err(dev, "update SW_RULE for bridge mode failed, = %d err %d aq_err %d\n", + mode, status, hw->adminq.sq_last_status); + /* revert hw->evb_veb */ + hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); + return -EIO; + } + + pf_sw->bridge_mode = mode; + } + + return 0; +} + +/** + * ice_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + */ +static void ice_tx_timeout(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_ring *tx_ring = NULL; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u32 head, val = 0, i; + int hung_queue = -1; + + pf->tx_timeout_count++; + + /* find the stopped queue the same way the stack does */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + unsigned long trans_start; + + q = netdev_get_tx_queue(netdev, i); + trans_start = q->trans_start; + if (netif_xmit_stopped(q) && + time_after(jiffies, + (trans_start + netdev->watchdog_timeo))) { + hung_queue = i; + break; + } + } + + if (i == netdev->num_tx_queues) { + netdev_info(netdev, "tx_timeout: no netdev hung queue found\n"); + } else { + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_txq; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (hung_queue == + vsi->tx_rings[i]->q_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + } + + /* Reset recovery level if enough time has elapsed after last timeout. + * Also ensure no new reset action happens before next timeout period. + */ + if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ * 20))) + pf->tx_timeout_recovery_level = 1; + else if (time_before(jiffies, (pf->tx_timeout_last_recovery + + netdev->watchdog_timeo))) + return; + + if (tx_ring) { + head = tx_ring->next_to_clean; + /* Read interrupt register */ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + val = rd32(&pf->hw, + GLINT_DYN_CTL(tx_ring->q_vector->v_idx + + tx_ring->vsi->hw_base_vector)); + + netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + vsi->vsi_num, hung_queue, tx_ring->next_to_clean, + head, tx_ring->next_to_use, + readl(tx_ring->tail), val); + } + + pf->tx_timeout_last_recovery = jiffies; + netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n", + pf->tx_timeout_recovery_level, hung_queue); + + switch (pf->tx_timeout_recovery_level) { + case 1: + set_bit(__ICE_PFR_REQ, pf->state); + break; + case 2: + set_bit(__ICE_CORER_REQ, pf->state); + break; + case 3: + set_bit(__ICE_GLOBR_REQ, pf->state); + break; + default: + netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n"); + set_bit(__ICE_DOWN, pf->state); + set_bit(__ICE_NEEDS_RESTART, vsi->state); + set_bit(__ICE_SERVICE_DIS, pf->state); + break; + } + + ice_service_task_schedule(pf); + pf->tx_timeout_recovery_level++; +} + +/** * ice_open - Called when a network interface becomes active * @netdev: network interface device structure * @@ -5383,6 +3783,11 @@ static int ice_open(struct net_device *netdev) struct ice_vsi *vsi = np->vsi; int err; + if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) { + netdev_err(netdev, "driver needs to be unloaded and reloaded\n"); + return -EIO; + } + netif_carrier_off(netdev); err = ice_vsi_open(vsi); @@ -5473,9 +3878,18 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, + .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, + .ndo_set_vf_mac = ice_set_vf_mac, + .ndo_get_vf_config = ice_get_vf_cfg, + .ndo_set_vf_trust = ice_set_vf_trust, + .ndo_set_vf_vlan = ice_set_vf_port_vlan, + .ndo_set_vf_link_state = ice_set_vf_link_state, .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, .ndo_set_features = ice_set_features, + .ndo_bridge_getlink = ice_bridge_getlink, + .ndo_bridge_setlink = ice_bridge_setlink, .ndo_fdb_add = ice_fdb_add, .ndo_fdb_del = ice_fdb_del, + .ndo_tx_timeout = ice_tx_timeout, }; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 295a8cd87fc1..3274c543283c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -137,7 +137,7 @@ ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access) if (hw->nvm.blank_nvm_mode) return 0; - return ice_acquire_res(hw, ICE_NVM_RES_ID, access); + return ice_acquire_res(hw, ICE_NVM_RES_ID, access, ICE_NVM_TIMEOUT); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index eeae199469b6..7cc8aa18a22b 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -17,7 +17,6 @@ ice_sched_add_root_node(struct ice_port_info *pi, { struct ice_sched_node *root; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -28,8 +27,8 @@ ice_sched_add_root_node(struct ice_port_info *pi, if (!root) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[0].max_children); - root->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + /* coverity[suspicious_sizeof] */ + root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], sizeof(*root), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); @@ -86,6 +85,62 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid) } /** + * ice_aq_query_sched_elems - query scheduler elements + * @hw: pointer to the hw struct + * @elems_req: number of elements to query + * @buf: pointer to buffer + * @buf_size: buffer size in bytes + * @elems_ret: returns total number of elements returned + * @cd: pointer to command details structure or NULL + * + * Query scheduling elements (0x0404) + */ +static enum ice_status +ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, + struct ice_aqc_get_elem *buf, u16 buf_size, + u16 *elems_ret, struct ice_sq_cd *cd) +{ + struct ice_aqc_get_cfg_elem *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.get_update_elem; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sched_elems); + cmd->num_elem_req = cpu_to_le16(elems_req); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (!status && elems_ret) + *elems_ret = le16_to_cpu(cmd->num_elem_resp); + + return status; +} + +/** + * ice_sched_query_elem - query element information from hw + * @hw: pointer to the hw struct + * @node_teid: node teid to be queried + * @buf: buffer to element information + * + * This function queries HW element information + */ +static enum ice_status +ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, + struct ice_aqc_get_elem *buf) +{ + u16 buf_size, num_elem_ret = 0; + enum ice_status status; + + buf_size = sizeof(*buf); + memset(buf, 0, buf_size); + buf->generic[0].node_teid = cpu_to_le32(node_teid); + status = ice_aq_query_sched_elems(hw, 1, buf, buf_size, &num_elem_ret, + NULL); + if (status || num_elem_ret != 1) + ice_debug(hw, ICE_DBG_SCHED, "query element failed\n"); + return status; +} + +/** * ice_sched_add_node - Insert the Tx scheduler node in SW DB * @pi: port information structure * @layer: Scheduler layer of the node @@ -98,9 +153,10 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_aqc_txsched_elem_data *info) { struct ice_sched_node *parent; + struct ice_aqc_get_elem elem; struct ice_sched_node *node; + enum ice_status status; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -117,12 +173,20 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, return ICE_ERR_PARAM; } + /* query the current node information from FW before additing it + * to the SW DB + */ + status = ice_sched_query_elem(hw, le32_to_cpu(info->node_teid), &elem); + if (status) + return status; + node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[layer].max_children); - if (max_children) { - node->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + if (hw->max_children[layer]) { + /* coverity[suspicious_sizeof] */ + node->children = devm_kcalloc(ice_hw_to_dev(hw), + hw->max_children[layer], sizeof(*node), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); @@ -134,7 +198,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, node->parent = parent; node->tx_sched_layer = layer; parent->children[parent->num_children++] = node; - memcpy(&node->info, info, sizeof(*info)); + memcpy(&node->info, &elem.generic[0], sizeof(node->info)); return 0; } @@ -192,14 +256,17 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; + buf->hdr.parent_teid = parent->info.node_teid; buf->hdr.num_elems = cpu_to_le16(num_nodes); for (i = 0; i < num_nodes; i++) buf->teid[i] = cpu_to_le32(node_teids[i]); + status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size, &num_groups_removed, NULL); if (status || num_groups_removed != 1) ice_debug(hw, ICE_DBG_SCHED, "remove elements failed\n"); + devm_kfree(ice_hw_to_dev(hw), buf); return status; } @@ -532,9 +599,7 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, static void ice_sched_clear_tx_topo(struct ice_port_info *pi) { struct ice_sched_agg_info *agg_info; - struct ice_sched_vsi_info *vsi_elem; struct ice_sched_agg_info *atmp; - struct ice_sched_vsi_info *tmp; struct ice_hw *hw; if (!pi) @@ -553,13 +618,6 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi) } } - /* remove the vsi list */ - list_for_each_entry_safe(vsi_elem, tmp, &pi->vsi_info_list, - list_entry) { - list_del(&vsi_elem->list_entry); - devm_kfree(ice_hw_to_dev(hw), vsi_elem); - } - if (pi->root) { ice_free_sched_node(pi, pi->root); pi->root = NULL; @@ -592,13 +650,16 @@ static void ice_sched_clear_port(struct ice_port_info *pi) */ void ice_sched_cleanup_all(struct ice_hw *hw) { - if (!hw || !hw->port_info) + if (!hw) return; - if (hw->layer_info) + if (hw->layer_info) { devm_kfree(ice_hw_to_dev(hw), hw->layer_info); + hw->layer_info = NULL; + } - ice_sched_clear_port(hw->port_info); + if (hw->port_info) + ice_sched_clear_port(hw->port_info); hw->num_tx_sched_layers = 0; hw->num_tx_sched_phys_layers = 0; @@ -607,31 +668,6 @@ void ice_sched_cleanup_all(struct ice_hw *hw) } /** - * ice_sched_create_vsi_info_entry - create an empty new VSI entry - * @pi: port information structure - * @vsi_id: VSI Id - * - * This function creates a new VSI entry and adds it to list - */ -static struct ice_sched_vsi_info * -ice_sched_create_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id) -{ - struct ice_sched_vsi_info *vsi_elem; - - if (!pi) - return NULL; - - vsi_elem = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*vsi_elem), - GFP_KERNEL); - if (!vsi_elem) - return NULL; - - list_add(&vsi_elem->list_entry, &pi->vsi_info_list); - vsi_elem->vsi_id = vsi_id; - return vsi_elem; -} - -/** * ice_sched_add_elems - add nodes to hw and SW DB * @pi: port information structure * @tc_node: pointer to the branch node @@ -671,9 +707,13 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, ICE_AQC_ELEM_VALID_EIR; buf->generic[i].data.generic = 0; buf->generic[i].data.cir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); buf->generic[i].data.eir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); } status = ice_aq_add_sched_elems(hw, 1, buf, buf_size, @@ -697,7 +737,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, teid = le32_to_cpu(buf->generic[i].node_teid); new_node = ice_sched_find_node_by_teid(parent, teid); - if (!new_node) { ice_debug(hw, ICE_DBG_SCHED, "Node is missing for teid =%d\n", teid); @@ -710,7 +749,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, /* add it to previous node sibling pointer */ /* Note: siblings are not linked across branches */ prev = ice_sched_get_first_node(hw, tc_node, layer); - if (prev && prev != new_node) { while (prev->sibling) prev = prev->sibling; @@ -760,8 +798,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, return ICE_ERR_PARAM; /* max children per node per layer */ - max_child_nodes = - le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children); + max_child_nodes = hw->max_children[parent->tx_sched_layer]; /* current number of children + required nodes exceed max children ? */ if ((parent->num_children + num_nodes) > max_child_nodes) { @@ -851,78 +888,6 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) } /** - * ice_sched_get_num_nodes_per_layer - Get the total number of nodes per layer - * @pi: pointer to the port info struct - * @layer: layer number - * - * This function calculates the number of nodes present in the scheduler tree - * including all the branches for a given layer - */ -static u16 -ice_sched_get_num_nodes_per_layer(struct ice_port_info *pi, u8 layer) -{ - struct ice_hw *hw; - u16 num_nodes = 0; - u8 i; - - if (!pi) - return num_nodes; - - hw = pi->hw; - - /* Calculate the number of nodes for all TCs */ - for (i = 0; i < pi->root->num_children; i++) { - struct ice_sched_node *tc_node, *node; - - tc_node = pi->root->children[i]; - - /* Get the first node */ - node = ice_sched_get_first_node(hw, tc_node, layer); - if (!node) - continue; - - /* count the siblings */ - while (node) { - num_nodes++; - node = node->sibling; - } - } - - return num_nodes; -} - -/** - * ice_sched_val_max_nodes - check max number of nodes reached or not - * @pi: port information structure - * @new_num_nodes_per_layer: pointer to the new number of nodes array - * - * This function checks whether the scheduler tree layers have enough space to - * add new nodes - */ -static enum ice_status -ice_sched_validate_for_max_nodes(struct ice_port_info *pi, - u16 *new_num_nodes_per_layer) -{ - struct ice_hw *hw = pi->hw; - u8 i, qg_layer; - u16 num_nodes; - - qg_layer = ice_sched_get_qgrp_layer(hw); - - /* walk through all the layers from SW entry point to qgroup layer */ - for (i = hw->sw_entry_point_layer; i <= qg_layer; i++) { - num_nodes = ice_sched_get_num_nodes_per_layer(pi, i); - if (num_nodes + new_num_nodes_per_layer[i] > - le16_to_cpu(hw->layer_info[i].max_pf_nodes)) { - ice_debug(hw, ICE_DBG_SCHED, - "max nodes reached for layer = %d\n", i); - return ICE_ERR_CFG; - } - } - return 0; -} - -/** * ice_rm_dflt_leaf_node - remove the default leaf node in the tree * @pi: port information structure * @@ -1003,14 +968,12 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) hw = pi->hw; /* Query the Default Topology from FW */ - buf = devm_kcalloc(ice_hw_to_dev(hw), ICE_TXSCHED_MAX_BRANCHES, - sizeof(*buf), GFP_KERNEL); + buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; /* Query default scheduling tree topology */ - status = ice_aq_get_dflt_topo(hw, pi->lport, buf, - sizeof(*buf) * ICE_TXSCHED_MAX_BRANCHES, + status = ice_aq_get_dflt_topo(hw, pi->lport, buf, ICE_AQ_MAX_BUF_LEN, &num_branches, NULL); if (status) goto err_init_port; @@ -1075,7 +1038,6 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) pi->port_state = ICE_SCHED_PORT_STATE_READY; mutex_init(&pi->sched_lock); INIT_LIST_HEAD(&pi->agg_list); - INIT_LIST_HEAD(&pi->vsi_info_list); err_init_port: if (status && pi->root) { @@ -1097,6 +1059,8 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) { struct ice_aqc_query_txsched_res_resp *buf; enum ice_status status = 0; + __le16 max_sibl; + u8 i; if (hw->layer_info) return status; @@ -1115,7 +1079,20 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) hw->flattened_layers = buf->sched_props.flattening_bitmap; hw->max_cgds = buf->sched_props.max_pf_cgds; - hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, + /* max sibling group size of current layer refers to the max children + * of the below layer node. + * layer 1 node max children will be layer 2 max sibling group size + * layer 2 node max children will be layer 3 max sibling group size + * and so on. This array will be populated from root (index 0) to + * qgroup layer 7. Leaf node has no children. + */ + for (i = 0; i < hw->num_tx_sched_layers; i++) { + max_sibl = buf->layer_props[i].max_sibl_grp_sz; + hw->max_children[i] = le16_to_cpu(max_sibl); + } + + hw->layer_info = (struct ice_aqc_layer_props *) + devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, (hw->num_tx_sched_layers * sizeof(*hw->layer_info)), GFP_KERNEL); @@ -1130,27 +1107,6 @@ sched_query_out: } /** - * ice_sched_get_vsi_info_entry - Get the vsi entry list for given vsi_id - * @pi: port information structure - * @vsi_id: vsi id - * - * This function retrieves the vsi list for the given vsi id - */ -static struct ice_sched_vsi_info * -ice_sched_get_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id) -{ - struct ice_sched_vsi_info *list_elem; - - if (!pi) - return NULL; - - list_for_each_entry(list_elem, &pi->vsi_info_list, list_entry) - if (list_elem->vsi_id == vsi_id) - return list_elem; - return NULL; -} - -/** * ice_sched_find_node_in_subtree - Find node in part of base node subtree * @hw: pointer to the hw struct * @base: pointer to the base node @@ -1186,30 +1142,28 @@ ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base, /** * ice_sched_get_free_qparent - Get a free lan or rdma q group node * @pi: port information structure - * @vsi_id: vsi id + * @vsi_handle: software VSI handle * @tc: branch number * @owner: lan or rdma * * This function retrieves a free lan or rdma q group node */ struct ice_sched_node * -ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, +ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner) { struct ice_sched_node *vsi_node, *qgrp_node = NULL; - struct ice_sched_vsi_info *list_elem; + struct ice_vsi_ctx *vsi_ctx; u16 max_children; u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); - max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children); - - list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!list_elem) - goto lan_q_exit; - - vsi_node = list_elem->vsi_node[tc]; + max_children = pi->hw->max_children[qgrp_layer]; + vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); + if (!vsi_ctx) + return NULL; + vsi_node = vsi_ctx->sched.vsi_node[tc]; /* validate invalid VSI id */ if (!vsi_node) goto lan_q_exit; @@ -1233,14 +1187,14 @@ lan_q_exit: * ice_sched_get_vsi_node - Get a VSI node based on VSI id * @hw: pointer to the hw struct * @tc_node: pointer to the TC node - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * * This function retrieves a VSI node for a given VSI id from a given * TC branch */ static struct ice_sched_node * ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node, - u16 vsi_id) + u16 vsi_handle) { struct ice_sched_node *node; u8 vsi_layer; @@ -1250,7 +1204,7 @@ ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node, /* Check whether it already exists */ while (node) { - if (node->vsi_id == vsi_id) + if (node->vsi_handle == vsi_handle) return node; node = node->sibling; } @@ -1278,10 +1232,8 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) /* calculate num nodes from q group to VSI layer */ for (i = qgl; i > vsil; i--) { - u16 max_children = le16_to_cpu(hw->layer_info[i].max_children); - /* round to the next integer if there is a remainder */ - num = DIV_ROUND_UP(num, max_children); + num = DIV_ROUND_UP(num, hw->max_children[i]); /* need at least one node */ num_nodes[i] = num ? num : 1; @@ -1291,7 +1243,7 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) /** * ice_sched_add_vsi_child_nodes - add VSI child nodes to tree * @pi: port information structure - * @vsi_id: VSI id + * @vsi_handle: software VSI handle * @tc_node: pointer to the TC node * @num_nodes: pointer to the num nodes that needs to be added per layer * @owner: node owner (lan or rdma) @@ -1300,7 +1252,7 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) * lan and rdma separately. */ static enum ice_status -ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, +ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes, u8 owner) { @@ -1311,16 +1263,13 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u16 num_added = 0; u8 i, qgl, vsil; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); - parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + parent = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); for (i = vsil + 1; i <= qgl; i++) { if (!parent) return ICE_ERR_CFG; + status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, @@ -1398,8 +1347,8 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *node; - u16 max_child; - u8 i, vsil; + u8 vsil; + int i; vsil = ice_sched_get_vsi_layer(hw); for (i = vsil; i >= hw->sw_entry_point_layer; i--) @@ -1412,12 +1361,10 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /* If intermediate nodes are reached max children * then add a new one. */ - node = ice_sched_get_first_node(hw, tc_node, i); - max_child = le16_to_cpu(hw->layer_info[i].max_children); - + node = ice_sched_get_first_node(hw, tc_node, (u8)i); /* scan all the siblings */ while (node) { - if (node->num_children < max_child) + if (node->num_children < hw->max_children[i]) break; node = node->sibling; } @@ -1431,7 +1378,7 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /** * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc_node: pointer to TC node * @num_nodes: pointer to num nodes array * @@ -1439,7 +1386,7 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, * VSI, its parent and intermediate nodes in below layers */ static enum ice_status -ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, +ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *parent = tc_node; @@ -1451,10 +1398,6 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, if (!pi) return ICE_ERR_PARAM; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - vsil = ice_sched_get_vsi_layer(pi->hw); for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) { status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, @@ -1477,21 +1420,22 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, return ICE_ERR_CFG; if (i == vsil) - parent->vsi_id = vsi_id; + parent->vsi_handle = vsi_handle; } + return 0; } /** * ice_sched_add_vsi_to_topo - add a new VSI into tree * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * * This function adds a new VSI into scheduler tree */ static enum ice_status -ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) +ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) { u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; struct ice_sched_node *tc_node; @@ -1505,13 +1449,14 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) ice_sched_calc_vsi_support_nodes(hw, tc_node, num_nodes); /* add vsi supported nodes to tc subtree */ - return ice_sched_add_vsi_support_nodes(pi, vsi_id, tc_node, num_nodes); + return ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node, + num_nodes); } /** * ice_sched_update_vsi_child_nodes - update VSI child nodes * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * @new_numqs: new number of max queues * @owner: owner of this subtree @@ -1519,14 +1464,14 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc) * This function updates the VSI child nodes based on the number of queues */ static enum ice_status -ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, - u16 new_numqs, u8 owner) +ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, + u8 tc, u16 new_numqs, u8 owner) { u16 prev_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; u16 new_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; struct ice_sched_node *vsi_node; struct ice_sched_node *tc_node; - struct ice_sched_vsi_info *vsi; + struct ice_vsi_ctx *vsi_ctx; enum ice_status status = 0; struct ice_hw *hw = pi->hw; u16 prev_numqs; @@ -1536,16 +1481,16 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, if (!tc_node) return ICE_ERR_CFG; - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); if (!vsi_node) return ICE_ERR_CFG; - vsi = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!vsi) - return ICE_ERR_CFG; + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; if (owner == ICE_SCHED_NODE_OWNER_LAN) - prev_numqs = vsi->max_lanq[tc]; + prev_numqs = vsi_ctx->sched.max_lanq[tc]; else return ICE_ERR_PARAM; @@ -1570,13 +1515,13 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++) new_num_nodes[i] -= prev_num_nodes[i]; - status = ice_sched_add_vsi_child_nodes(pi, vsi_id, tc_node, + status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node, new_num_nodes, owner); if (status) return status; } - vsi->max_lanq[tc] = new_numqs; + vsi_ctx->sched.max_lanq[tc] = new_numqs; return status; } @@ -1584,7 +1529,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, /** * ice_sched_cfg_vsi - configure the new/exisiting VSI * @pi: port information structure - * @vsi_id: VSI Id + * @vsi_handle: software VSI handle * @tc: TC number * @maxqs: max number of queues * @owner: lan or rdma @@ -1595,25 +1540,21 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, * disabled then suspend the VSI if it is not already. */ enum ice_status -ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, +ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable) { struct ice_sched_node *vsi_node, *tc_node; - struct ice_sched_vsi_info *vsi; + struct ice_vsi_ctx *vsi_ctx; enum ice_status status = 0; struct ice_hw *hw = pi->hw; tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) return ICE_ERR_PARAM; - - vsi = ice_sched_get_vsi_info_entry(pi, vsi_id); - if (!vsi) - vsi = ice_sched_create_vsi_info_entry(pi, vsi_id); - if (!vsi) - return ICE_ERR_NO_MEMORY; - - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); /* suspend the VSI if tc is not enabled */ if (!enable) { @@ -1630,18 +1571,26 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, /* TC is enabled, if it is a new VSI then add it to the tree */ if (!vsi_node) { - status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc); + status = ice_sched_add_vsi_to_topo(pi, vsi_handle, tc); if (status) return status; - vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); + + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle); if (!vsi_node) return ICE_ERR_CFG; - vsi->vsi_node[tc] = vsi_node; + + vsi_ctx->sched.vsi_node[tc] = vsi_node; vsi_node->in_use = true; + /* invalidate the max queues whenever VSI gets added first time + * into the scheduler tree (boot or after reset). We need to + * recreate the child nodes all the time in these cases. + */ + vsi_ctx->sched.max_lanq[tc] = 0; } /* update the VSI child nodes */ - status = ice_sched_update_vsi_child_nodes(pi, vsi_id, tc, maxqs, owner); + status = ice_sched_update_vsi_child_nodes(pi, vsi_handle, tc, maxqs, + owner); if (status) return status; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index badadcc120d3..5dc9cfa04c58 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -12,7 +12,6 @@ struct ice_sched_agg_vsi_info { struct list_head list_entry; DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS); - u16 vsi_id; }; struct ice_sched_agg_info { @@ -35,9 +34,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node); struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc); struct ice_sched_node * -ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, +ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner); enum ice_status -ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, +ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c new file mode 100644 index 000000000000..027eba4e13f8 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_adminq_cmd.h" +#include "ice_sriov.h" + +/** + * ice_aq_send_msg_to_vf + * @hw: pointer to the hardware structure + * @vfid: VF ID to send msg + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cd: pointer to command details + * + * Send message to VF driver (0x0802) using mailbox + * queue and asynchronously sending message via + * ice_sq_send_cmd() function + */ +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd) +{ + struct ice_aqc_pf_vf_msg *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf); + + cmd = &desc.params.virt; + cmd->id = cpu_to_le32(vfid); + + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + + if (msglen) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); +} + +/** + * ice_conv_link_speed_to_virtchnl + * @adv_link_support: determines the format of the returned link speed + * @link_speed: variable containing the link_speed to be converted + * + * Convert link speed supported by HW to link speed supported by virtchnl. + * If adv_link_support is true, then return link speed in Mbps. Else return + * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller + * needs to cast back to an enum virtchnl_link_speed in the case where + * adv_link_support is false, but when adv_link_support is true the caller can + * expect the speed in Mbps. + */ +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) +{ + u32 speed; + + if (adv_link_support) + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + speed = ICE_LINK_SPEED_10MBPS; + break; + case ICE_AQ_LINK_SPEED_100MB: + speed = ICE_LINK_SPEED_100MBPS; + break; + case ICE_AQ_LINK_SPEED_1000MB: + speed = ICE_LINK_SPEED_1000MBPS; + break; + case ICE_AQ_LINK_SPEED_2500MB: + speed = ICE_LINK_SPEED_2500MBPS; + break; + case ICE_AQ_LINK_SPEED_5GB: + speed = ICE_LINK_SPEED_5000MBPS; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = ICE_LINK_SPEED_10000MBPS; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = ICE_LINK_SPEED_20000MBPS; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = ICE_LINK_SPEED_25000MBPS; + break; + case ICE_AQ_LINK_SPEED_40GB: + speed = ICE_LINK_SPEED_40000MBPS; + break; + default: + speed = ICE_LINK_SPEED_UNKNOWN; + break; + } + else + /* Virtchnl speeds are not defined for every speed supported in + * the hardware. To maintain compatibility with older AVF + * drivers, while reporting the speed the new speed values are + * resolved to the closest known virtchnl speeds + */ + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + case ICE_AQ_LINK_SPEED_100MB: + speed = (u32)VIRTCHNL_LINK_SPEED_100MB; + break; + case ICE_AQ_LINK_SPEED_1000MB: + case ICE_AQ_LINK_SPEED_2500MB: + case ICE_AQ_LINK_SPEED_5GB: + speed = (u32)VIRTCHNL_LINK_SPEED_1GB; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = (u32)VIRTCHNL_LINK_SPEED_10GB; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = (u32)VIRTCHNL_LINK_SPEED_20GB; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = (u32)VIRTCHNL_LINK_SPEED_25GB; + break; + case ICE_AQ_LINK_SPEED_40GB: + /* fall through */ + speed = (u32)VIRTCHNL_LINK_SPEED_40GB; + break; + default: + speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; + break; + } + + return speed; +} diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h new file mode 100644 index 000000000000..3d78a0795138 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_SRIOV_H_ +#define _ICE_SRIOV_H_ + +#include "ice_common.h" + +#ifdef CONFIG_PCI_IOV +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd); + +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +#else /* CONFIG_PCI_IOV */ +static inline enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, + u16 __always_unused vfid, u32 __always_unused v_opcode, + u32 __always_unused v_retval, u8 __always_unused *msg, + u16 __always_unused msglen, + struct ice_sq_cd __always_unused *cd) +{ + return 0; +} + +static inline u32 +ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, + u16 __always_unused link_speed) +{ + return 0; +} + +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h index 9a95c4ffd7d7..f49f299ddf2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ b/drivers/net/ethernet/intel/ice/ice_status.h @@ -6,6 +6,9 @@ /* Error Codes */ enum ice_status { + ICE_SUCCESS = 0, + + /* Generic codes : Range -1..-49 */ ICE_ERR_PARAM = -1, ICE_ERR_NOT_IMPL = -2, ICE_ERR_NOT_READY = -3, @@ -20,6 +23,7 @@ enum ice_status { ICE_ERR_ALREADY_EXISTS = -14, ICE_ERR_DOES_NOT_EXIST = -15, ICE_ERR_MAX_LIMIT = -17, + ICE_ERR_RESET_ONGOING = -18, ICE_ERR_BUF_TOO_SHORT = -52, ICE_ERR_NVM_BLANK_MODE = -53, ICE_ERR_AQ_ERROR = -100, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6b7ec2ae5ad6..33403f39f1b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -86,6 +86,36 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, } /** + * ice_init_def_sw_recp - initialize the recipe book keeping tables + * @hw: pointer to the hw struct + * + * Allocate memory for the entire recipe table and initialize the structures/ + * entries corresponding to basic recipes. + */ +enum ice_status +ice_init_def_sw_recp(struct ice_hw *hw) +{ + struct ice_sw_recipe *recps; + u8 i; + + recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES, + sizeof(struct ice_sw_recipe), GFP_KERNEL); + if (!recps) + return ICE_ERR_NO_MEMORY; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + recps[i].root_rid = i; + INIT_LIST_HEAD(&recps[i].filt_rules); + INIT_LIST_HEAD(&recps[i].filt_replay_rules); + mutex_init(&recps[i].filt_rule_lock); + } + + hw->switch_info->recp_list = recps; + + return 0; +} + +/** * ice_aq_get_sw_cfg - get switch configuration * @hw: pointer to the hardware structure * @buf: pointer to the result buffer @@ -140,23 +170,24 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp *buf, * * Add a VSI context to the hardware (0x0210) */ -enum ice_status +static enum ice_status ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *res; struct ice_aqc_add_get_update_free_vsi *cmd; - enum ice_status status; struct ice_aq_desc desc; + enum ice_status status; cmd = &desc.params.vsi_cmd; - res = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + res = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi); if (!vsi_ctx->alloc_from_pool) cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + cmd->vf_id = vsi_ctx->vf_num; cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags); @@ -175,6 +206,42 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** + * ice_aq_free_vsi + * @hw: pointer to the hw struct + * @vsi_ctx: pointer to a VSI context struct + * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources + * @cd: pointer to command details structure or NULL + * + * Free VSI context info from hardware (0x0213) + */ +static enum ice_status +ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_update_free_vsi_resp *resp; + struct ice_aqc_add_get_update_free_vsi *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.vsi_cmd; + resp = &desc.params.add_update_free_vsi_res; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); + + cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + if (keep_vsi_alloc) + cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) { + vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); + vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); + } + + return status; +} + +/** * ice_aq_update_vsi * @hw: pointer to the hw struct * @vsi_ctx: pointer to a VSI context struct @@ -182,7 +249,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, * * Update VSI context in the hardware (0x0211) */ -enum ice_status +static enum ice_status ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { @@ -192,7 +259,7 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, enum ice_status status; cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + resp = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi); @@ -212,42 +279,162 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** - * ice_aq_free_vsi + * ice_is_vsi_valid - check whether the VSI is valid or not + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * check whether the VSI is valid or not + */ +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) +{ + return vsi_handle < ICE_MAX_VSI && hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_get_hw_vsi_num - return the hw VSI number + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the hw VSI number + * Caution: call this function only if VSI is valid (ice_is_vsi_valid) + */ +u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) +{ + return hw->vsi_ctx[vsi_handle]->vsi_num; +} + +/** + * ice_get_vsi_ctx - return the VSI context entry for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the VSI context entry for a given VSI handle + */ +struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + return (vsi_handle >= ICE_MAX_VSI) ? NULL : hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_save_vsi_ctx - save the VSI context for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * @vsi: VSI context pointer + * + * save the VSI context entry for a given VSI handle + */ +static void ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, + struct ice_vsi_ctx *vsi) +{ + hw->vsi_ctx[vsi_handle] = vsi; +} + +/** + * ice_clear_vsi_ctx - clear the VSI context entry + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * clear the VSI context entry + */ +static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + struct ice_vsi_ctx *vsi; + + vsi = ice_get_vsi_ctx(hw, vsi_handle); + if (vsi) { + devm_kfree(ice_hw_to_dev(hw), vsi); + hw->vsi_ctx[vsi_handle] = NULL; + } +} + +/** + * ice_add_vsi - add VSI context to the hardware and VSI handle list * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle provided by drivers * @vsi_ctx: pointer to a VSI context struct - * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources * @cd: pointer to command details structure or NULL * - * Get VSI context info from hardware (0x0213) + * Add a VSI context to the hardware also add it into the VSI handle list. + * If this function gets called after reset for existing VSIs then update + * with the new HW VSI number in the corresponding VSI handle list entry. */ enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd) +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd) { - struct ice_aqc_add_update_free_vsi_resp *resp; - struct ice_aqc_add_get_update_free_vsi *cmd; - struct ice_aq_desc desc; + struct ice_vsi_ctx *tmp_vsi_ctx; enum ice_status status; - cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); + if (vsi_handle >= ICE_MAX_VSI) + return ICE_ERR_PARAM; + status = ice_aq_add_vsi(hw, vsi_ctx, cd); + if (status) + return status; + tmp_vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!tmp_vsi_ctx) { + /* Create a new vsi context */ + tmp_vsi_ctx = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*tmp_vsi_ctx), GFP_KERNEL); + if (!tmp_vsi_ctx) { + ice_aq_free_vsi(hw, vsi_ctx, false, cd); + return ICE_ERR_NO_MEMORY; + } + *tmp_vsi_ctx = *vsi_ctx; + ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx); + } else { + /* update with new HW VSI num */ + if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num) + tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num; + } - cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); - if (keep_vsi_alloc) - cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); + return status; +} - status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); - if (!status) { - vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); - vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); - } +/** + * ice_free_vsi- free VSI context from hardware and VSI handle list + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle + * @vsi_ctx: pointer to a VSI context struct + * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources + * @cd: pointer to command details structure or NULL + * + * Free VSI context info from hardware as well as from VSI handle list + */ +enum ice_status +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) +{ + enum ice_status status; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); + status = ice_aq_free_vsi(hw, vsi_ctx, keep_vsi_alloc, cd); + if (!status) + ice_clear_vsi_ctx(hw, vsi_handle); return status; } /** + * ice_update_vsi + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle + * @vsi_ctx: pointer to a VSI context struct + * @cd: pointer to command details structure or NULL + * + * Update VSI context in the hardware + */ +enum ice_status +ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd) +{ + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); + return ice_aq_update_vsi(hw, vsi_ctx, cd); +} + +/** * ice_aq_alloc_free_vsi_list * @hw: pointer to the hw struct * @vsi_list_id: VSI list id returned or used for lookup @@ -464,10 +651,12 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc) { u16 vlan_id = ICE_MAX_VLAN_ID + 1; - u8 eth_hdr[DUMMY_ETH_HDR_LEN]; void *daddr = NULL; + u16 eth_hdr_sz; + u8 *eth_hdr; u32 act = 0; __be16 *off; + u8 q_rgn; if (opc == ice_aqc_opc_remove_sw_rules) { s_rule->pdata.lkup_tx_rx.act = 0; @@ -477,13 +666,16 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, return; } + eth_hdr_sz = sizeof(dummy_eth_header); + eth_hdr = s_rule->pdata.lkup_tx_rx.hdr; + /* initialize the ether header with a dummy header */ - memcpy(eth_hdr, dummy_eth_header, sizeof(dummy_eth_header)); + memcpy(eth_hdr, dummy_eth_header, eth_hdr_sz); ice_fill_sw_info(hw, f_info); switch (f_info->fltr_act) { case ICE_FWD_TO_VSI: - act |= (f_info->fwd_id.vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & + act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | @@ -503,14 +695,19 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & ICE_SINGLE_ACT_Q_INDEX_M; break; + case ICE_DROP_PACKET: + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | + ICE_SINGLE_ACT_VALID_BIT; + break; case ICE_FWD_TO_QGRP: + q_rgn = f_info->qgrp_size > 0 ? + (u8)ilog2(f_info->qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->qgrp_size << ICE_SINGLE_ACT_Q_REGION_S) & + act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & ICE_SINGLE_ACT_Q_REGION_M; break; - case ICE_DROP_PACKET: - act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP; - break; default: return; } @@ -536,7 +733,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, daddr = f_info->l_data.ethertype_mac.mac_addr; /* fall-through */ case ICE_SW_LKUP_ETHERTYPE: - off = (__be16 *)ð_hdr[ICE_ETH_ETHTYPE_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); *off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype); break; case ICE_SW_LKUP_MAC_VLAN: @@ -563,18 +760,16 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); if (daddr) - ether_addr_copy(ð_hdr[ICE_ETH_DA_OFFSET], daddr); + ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr); if (!(vlan_id > ICE_MAX_VLAN_ID)) { - off = (__be16 *)ð_hdr[ICE_ETH_VLAN_TCI_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET); *off = cpu_to_be16(vlan_id); } /* Create the switch rule with the final dummy Ethernet header */ if (opc != ice_aqc_opc_update_sw_rules) - s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(sizeof(eth_hdr)); - - memcpy(s_rule->pdata.lkup_tx_rx.hdr, eth_hdr, sizeof(eth_hdr)); + s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(eth_hdr_sz); } /** @@ -601,8 +796,8 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, enum ice_status status; u16 lg_act_size; u16 rules_size; - u16 vsi_info; u32 act; + u16 id; if (m_ent->fltr_info.lkup_type != ICE_SW_LKUP_MAC) return ICE_ERR_PARAM; @@ -628,12 +823,11 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /* First action VSI forwarding or VSI list forwarding depending on how * many VSIs */ - vsi_info = (m_ent->vsi_count > 1) ? - m_ent->fltr_info.fwd_id.vsi_list_id : - m_ent->fltr_info.fwd_id.vsi_id; + id = (m_ent->vsi_count > 1) ? m_ent->fltr_info.fwd_id.vsi_list_id : + m_ent->fltr_info.fwd_id.hw_vsi_id; act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT; - act |= (vsi_info << ICE_LG_ACT_VSI_LIST_ID_S) & + act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M; if (m_ent->vsi_count > 1) act |= ICE_LG_ACT_VSI_LIST; @@ -686,15 +880,15 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /** * ice_create_vsi_list_map * @hw: pointer to the hardware structure - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: num VSI in the array + * @vsi_handle_arr: array of VSI handles to set in the VSI mapping + * @num_vsi: number of VSI handles in the array * @vsi_list_id: VSI list id generated as part of allocate resource * * Helper function to create a new entry of VSI list id to VSI mapping * using the given VSI list id */ static struct ice_vsi_list_map_info * -ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id) { struct ice_switch_info *sw = hw->switch_info; @@ -706,9 +900,9 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, return NULL; v_map->vsi_list_id = vsi_list_id; - + v_map->ref_cnt = 1; for (i = 0; i < num_vsi; i++) - set_bit(vsi_array[i], v_map->vsi_map); + set_bit(vsi_handle_arr[i], v_map->vsi_map); list_add(&v_map->list_entry, &sw->vsi_list_map_head); return v_map; @@ -717,8 +911,8 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, /** * ice_update_vsi_list_rule * @hw: pointer to the hardware structure - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: num VSI in the array + * @vsi_handle_arr: array of VSI handles to form a VSI list + * @num_vsi: number of VSI handles in the array * @vsi_list_id: VSI list id generated as part of allocate resource * @remove: Boolean value to indicate if this is a remove action * @opc: switch rules population command type - pass in the command opcode @@ -728,7 +922,7 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, * using the given VSI list id */ static enum ice_status -ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id, bool remove, enum ice_adminq_opc opc, enum ice_sw_lkup_type lkup_type) { @@ -759,9 +953,15 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) return ICE_ERR_NO_MEMORY; - - for (i = 0; i < num_vsi; i++) - s_rule->pdata.vsi_list.vsi[i] = cpu_to_le16(vsi_array[i]); + for (i = 0; i < num_vsi; i++) { + if (!ice_is_vsi_valid(hw, vsi_handle_arr[i])) { + status = ICE_ERR_PARAM; + goto exit; + } + /* AQ call requires hw_vsi_id(s) */ + s_rule->pdata.vsi_list.vsi[i] = + cpu_to_le16(ice_get_hw_vsi_num(hw, vsi_handle_arr[i])); + } s_rule->type = cpu_to_le16(type); s_rule->pdata.vsi_list.number_vsi = cpu_to_le16(num_vsi); @@ -769,6 +969,7 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opc, NULL); +exit: devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } @@ -776,21 +977,16 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, /** * ice_create_vsi_list_rule - Creates and populates a VSI list rule * @hw: pointer to the hw struct - * @vsi_array: array of VSIs to form a VSI list - * @num_vsi: number of VSIs in the array + * @vsi_handle_arr: array of VSI handles to form a VSI list + * @num_vsi: number of VSI handles in the array * @vsi_list_id: stores the ID of the VSI list to be created * @lkup_type: switch rule filter's lookup type */ static enum ice_status -ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, +ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type) { enum ice_status status; - int i; - - for (i = 0; i < num_vsi; i++) - if (vsi_array[i] >= ICE_MAX_VSI) - return ICE_ERR_OUT_OF_RANGE; status = ice_aq_alloc_free_vsi_list(hw, vsi_list_id, lkup_type, ice_aqc_opc_alloc_res); @@ -798,9 +994,9 @@ ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi, return status; /* Update the newly created VSI list to include the specified VSIs */ - return ice_update_vsi_list_rule(hw, vsi_array, num_vsi, *vsi_list_id, - false, ice_aqc_opc_add_sw_rules, - lkup_type); + return ice_update_vsi_list_rule(hw, vsi_handle_arr, num_vsi, + *vsi_list_id, false, + ice_aqc_opc_add_sw_rules, lkup_type); } /** @@ -816,10 +1012,10 @@ static enum ice_status ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { - struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *fm_entry; struct ice_aqc_sw_rules_elem *s_rule; enum ice_sw_lkup_type l_type; + struct ice_sw_recipe *recp; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -860,31 +1056,9 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, * calls remove filter AQ command */ l_type = fm_entry->fltr_info.lkup_type; - if (l_type == ICE_SW_LKUP_MAC) { - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); - } else if (l_type == ICE_SW_LKUP_VLAN) { - mutex_lock(&sw->vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->vlan_list_head); - mutex_unlock(&sw->vlan_list_lock); - } else if (l_type == ICE_SW_LKUP_ETHERTYPE || - l_type == ICE_SW_LKUP_ETHERTYPE_MAC) { - mutex_lock(&sw->eth_m_list_lock); - list_add(&fm_entry->list_entry, &sw->eth_m_list_head); - mutex_unlock(&sw->eth_m_list_lock); - } else if (l_type == ICE_SW_LKUP_PROMISC || - l_type == ICE_SW_LKUP_PROMISC_VLAN) { - mutex_lock(&sw->promisc_list_lock); - list_add(&fm_entry->list_entry, &sw->promisc_list_head); - mutex_unlock(&sw->promisc_list_lock); - } else if (fm_entry->fltr_info.lkup_type == ICE_SW_LKUP_MAC_VLAN) { - mutex_lock(&sw->mac_vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_vlan_list_head); - mutex_unlock(&sw->mac_vlan_list_lock); - } else { - status = ICE_ERR_NOT_IMPL; - } + recp = &hw->switch_info->recp_list[l_type]; + list_add(&fm_entry->list_entry, &recp->filt_rules); + ice_create_pkt_fwd_rule_exit: devm_kfree(ice_hw_to_dev(hw), s_rule); return status; @@ -893,19 +1067,15 @@ ice_create_pkt_fwd_rule_exit: /** * ice_update_pkt_fwd_rule * @hw: pointer to the hardware structure - * @rule_id: rule of previously created switch rule to update - * @vsi_list_id: VSI list id to be updated with - * @f_info: ice_fltr_info to pull other information for switch rule + * @f_info: filter information for switch rule * * Call AQ command to update a previously created switch rule with a * VSI list id */ static enum ice_status -ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, - struct ice_fltr_info f_info) +ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) { struct ice_aqc_sw_rules_elem *s_rule; - struct ice_fltr_info tmp_fltr; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -913,14 +1083,9 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, if (!s_rule) return ICE_ERR_NO_MEMORY; - tmp_fltr = f_info; - tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; - tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules); - ice_fill_sw_rule(hw, &tmp_fltr, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(rule_id); + s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(f_info->fltr_rule_id); /* Update switch rule with new rule set to forward VSI list */ status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, @@ -931,7 +1096,48 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, } /** - * ice_handle_vsi_list_mgmt + * ice_update_sw_rule_bridge_mode + * @hw: pointer to the hw struct + * + * Updates unicast switch filter rules based on VEB/VEPA mode + */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; + struct list_head *rule_head; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; + + mutex_lock(rule_lock); + list_for_each_entry(fm_entry, rule_head, list_entry) { + struct ice_fltr_info *fi = &fm_entry->fltr_info; + u8 *addr = fi->l_data.mac.mac_addr; + + /* Update unicast Tx rules to reflect the selected + * VEB/VEPA mode + */ + if ((fi->flag & ICE_FLTR_TX) && is_unicast_ether_addr(addr) && + (fi->fltr_act == ICE_FWD_TO_VSI || + fi->fltr_act == ICE_FWD_TO_VSI_LIST || + fi->fltr_act == ICE_FWD_TO_Q || + fi->fltr_act == ICE_FWD_TO_QGRP)) { + status = ice_update_pkt_fwd_rule(hw, fi); + if (status) + break; + } + } + + mutex_unlock(rule_lock); + + return status; +} + +/** + * ice_add_update_vsi_list * @hw: pointer to the hardware structure * @m_entry: pointer to current filter management list entry * @cur_fltr: filter information from the book keeping entry @@ -952,10 +1158,10 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, * using the update switch rule command */ static enum ice_status -ice_handle_vsi_list_mgmt(struct ice_hw *hw, - struct ice_fltr_mgmt_list_entry *m_entry, - struct ice_fltr_info *cur_fltr, - struct ice_fltr_info *new_fltr) +ice_add_update_vsi_list(struct ice_hw *hw, + struct ice_fltr_mgmt_list_entry *m_entry, + struct ice_fltr_info *cur_fltr, + struct ice_fltr_info *new_fltr) { enum ice_status status = 0; u16 vsi_list_id = 0; @@ -975,34 +1181,36 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, * a part of a VSI list. So, create a VSI list with the old and * new VSIs. */ - u16 vsi_id_arr[2]; - u16 fltr_rule; + struct ice_fltr_info tmp_fltr; + u16 vsi_handle_arr[2]; /* A rule already exists with the new VSI being added */ - if (cur_fltr->fwd_id.vsi_id == new_fltr->fwd_id.vsi_id) + if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id) return ICE_ERR_ALREADY_EXISTS; - vsi_id_arr[0] = cur_fltr->fwd_id.vsi_id; - vsi_id_arr[1] = new_fltr->fwd_id.vsi_id; - status = ice_create_vsi_list_rule(hw, &vsi_id_arr[0], 2, + vsi_handle_arr[0] = cur_fltr->vsi_handle; + vsi_handle_arr[1] = new_fltr->vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, &vsi_list_id, new_fltr->lkup_type); if (status) return status; - fltr_rule = cur_fltr->fltr_rule_id; + tmp_fltr = *new_fltr; + tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; /* Update the previous switch rule of "MAC forward to VSI" to * "MAC fwd to VSI list" */ - status = ice_update_pkt_fwd_rule(hw, fltr_rule, vsi_list_id, - *new_fltr); + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); if (status) return status; cur_fltr->fwd_id.vsi_list_id = vsi_list_id; cur_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; m_entry->vsi_list_info = - ice_create_vsi_list_map(hw, &vsi_id_arr[0], 2, + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, vsi_list_id); /* If this entry was large action then the large action needs @@ -1014,11 +1222,11 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, m_entry->sw_marker_id, m_entry->lg_act_idx); } else { - u16 vsi_id = new_fltr->fwd_id.vsi_id; + u16 vsi_handle = new_fltr->vsi_handle; enum ice_adminq_opc opcode; /* A rule already exists with the new VSI being added */ - if (test_bit(vsi_id, m_entry->vsi_list_info->vsi_map)) + if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) return 0; /* Update the previously created VSI list set with @@ -1027,12 +1235,12 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, vsi_list_id = cur_fltr->fwd_id.vsi_list_id; opcode = ice_aqc_opc_update_sw_rules; - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, - false, opcode, + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, + vsi_list_id, false, opcode, new_fltr->lkup_type); /* update VSI list mapping info with new VSI id */ if (!status) - set_bit(vsi_id, m_entry->vsi_list_info->vsi_map); + set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map); } if (!status) m_entry->vsi_count++; @@ -1040,54 +1248,313 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, } /** - * ice_find_mac_entry + * ice_find_rule_entry - Search a rule entry * @hw: pointer to the hardware structure - * @mac_addr: MAC address to search for + * @recp_id: lookup type for which the specified rule needs to be searched + * @f_info: rule information * - * Helper function to search for a MAC entry using a given MAC address - * Returns pointer to the entry if found. + * Helper function to search for a given rule entry + * Returns pointer to entry storing the rule if found */ static struct ice_fltr_mgmt_list_entry * -ice_find_mac_entry(struct ice_hw *hw, u8 *mac_addr) +ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) { - struct ice_fltr_mgmt_list_entry *m_list_itr, *mac_ret = NULL; + struct ice_fltr_mgmt_list_entry *list_itr, *ret = NULL; struct ice_switch_info *sw = hw->switch_info; - - mutex_lock(&sw->mac_list_lock); - list_for_each_entry(m_list_itr, &sw->mac_list_head, list_entry) { - u8 *buf = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; - - if (ether_addr_equal(buf, mac_addr)) { - mac_ret = m_list_itr; + struct list_head *list_head; + + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data, + sizeof(f_info->l_data)) && + f_info->flag == list_itr->fltr_info.flag) { + ret = list_itr; break; } } - mutex_unlock(&sw->mac_list_lock); - return mac_ret; + return ret; +} + +/** + * ice_find_vsi_list_entry - Search VSI list map with VSI count 1 + * @hw: pointer to the hardware structure + * @recp_id: lookup type for which VSI lists needs to be searched + * @vsi_handle: VSI handle to be found in VSI list + * @vsi_list_id: VSI list id found containing vsi_handle + * + * Helper function to search a VSI list with single entry containing given VSI + * handle element. This can be extended further to search VSI list with more + * than 1 vsi_count. Returns pointer to VSI list entry if found. + */ +static struct ice_vsi_list_map_info * +ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, + u16 *vsi_list_id) +{ + struct ice_vsi_list_map_info *map_info = NULL; + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_itr; + struct list_head *list_head; + + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { + map_info = list_itr->vsi_list_info; + if (test_bit(vsi_handle, map_info->vsi_map)) { + *vsi_list_id = map_info->vsi_list_id; + return map_info; + } + } + } + return NULL; } /** - * ice_add_shared_mac - Add one MAC shared filter rule + * ice_add_rule_internal - add rule for a given lookup type * @hw: pointer to the hardware structure + * @recp_id: lookup type (recipe id) for which rule has to be added * @f_entry: structure containing MAC forwarding information * - * Adds or updates the book keeping list for the MAC addresses + * Adds or updates the rule lists for a given recipe */ static enum ice_status -ice_add_shared_mac(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) +ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) { + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *m_entry; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; - new_fltr = &f_entry->fltr_info; + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); + + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; - m_entry = ice_find_mac_entry(hw, &new_fltr->l_data.mac.mac_addr[0]); - if (!m_entry) + mutex_lock(rule_lock); + new_fltr = &f_entry->fltr_info; + if (new_fltr->flag & ICE_FLTR_RX) + new_fltr->src = hw->port_info->lport; + else if (new_fltr->flag & ICE_FLTR_TX) + new_fltr->src = f_entry->fltr_info.fwd_id.hw_vsi_id; + + m_entry = ice_find_rule_entry(hw, recp_id, new_fltr); + if (!m_entry) { + mutex_unlock(rule_lock); return ice_create_pkt_fwd_rule(hw, f_entry); + } cur_fltr = &m_entry->fltr_info; + status = ice_add_update_vsi_list(hw, m_entry, cur_fltr, new_fltr); + mutex_unlock(rule_lock); - return ice_handle_vsi_list_mgmt(hw, m_entry, cur_fltr, new_fltr); + return status; +} + +/** + * ice_remove_vsi_list_rule + * @hw: pointer to the hardware structure + * @vsi_list_id: VSI list id generated as part of allocate resource + * @lkup_type: switch rule filter lookup type + * + * The VSI list should be emptied before this function is called to remove the + * VSI list. + */ +static enum ice_status +ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, + enum ice_sw_lkup_type lkup_type) +{ + struct ice_aqc_sw_rules_elem *s_rule; + enum ice_status status; + u16 s_rule_size; + + s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); + s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); + s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); + + /* Free the vsi_list resource that we allocated. It is assumed that the + * list is empty at this point. + */ + status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, + ice_aqc_opc_free_res); + + devm_kfree(ice_hw_to_dev(hw), s_rule); + return status; +} + +/** + * ice_rem_update_vsi_list + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle of the VSI to remove + * @fm_list: filter management entry for which the VSI list management needs to + * be done + */ +static enum ice_status +ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, + struct ice_fltr_mgmt_list_entry *fm_list) +{ + enum ice_sw_lkup_type lkup_type; + enum ice_status status = 0; + u16 vsi_list_id; + + if (fm_list->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST || + fm_list->vsi_count == 0) + return ICE_ERR_PARAM; + + /* A rule with the VSI being removed does not exist */ + if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) + return ICE_ERR_DOES_NOT_EXIST; + + lkup_type = fm_list->fltr_info.lkup_type; + vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id; + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + fm_list->vsi_count--; + clear_bit(vsi_handle, fm_list->vsi_list_info->vsi_map); + + if (fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) { + struct ice_fltr_info tmp_fltr_info = fm_list->fltr_info; + struct ice_vsi_list_map_info *vsi_list_info = + fm_list->vsi_list_info; + u16 rem_vsi_handle; + + rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (!ice_is_vsi_valid(hw, rem_vsi_handle)) + return ICE_ERR_OUT_OF_RANGE; + + /* Make sure VSI list is empty before removing it below */ + status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, + vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + tmp_fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + tmp_fltr_info.vsi_handle = rem_vsi_handle; + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr_info); + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n", + tmp_fltr_info.fwd_id.hw_vsi_id, status); + return status; + } + + fm_list->fltr_info = tmp_fltr_info; + } + + if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) || + (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) { + struct ice_vsi_list_map_info *vsi_list_info = + fm_list->vsi_list_info; + + /* Remove the VSI list since it is no longer used */ + status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to remove VSI list %d, error %d\n", + vsi_list_id, status); + return status; + } + + list_del(&vsi_list_info->list_entry); + devm_kfree(ice_hw_to_dev(hw), vsi_list_info); + fm_list->vsi_list_info = NULL; + } + + return status; +} + +/** + * ice_remove_rule_internal - Remove a filter rule of a given type + * @hw: pointer to the hardware structure + * @recp_id: recipe id for which the rule needs to removed + * @f_entry: rule entry containing filter information + */ +static enum ice_status +ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_elem; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; + bool remove_rule = false; + u16 vsi_handle; + + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); + + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; + mutex_lock(rule_lock); + list_elem = ice_find_rule_entry(hw, recp_id, &f_entry->fltr_info); + if (!list_elem) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } + + if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) { + remove_rule = true; + } else if (!list_elem->vsi_list_info) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } else { + if (list_elem->vsi_list_info->ref_cnt > 1) + list_elem->vsi_list_info->ref_cnt--; + vsi_handle = f_entry->fltr_info.vsi_handle; + status = ice_rem_update_vsi_list(hw, vsi_handle, list_elem); + if (status) + goto exit; + /* if vsi count goes to zero after updating the vsi list */ + if (list_elem->vsi_count == 0) + remove_rule = true; + } + + if (remove_rule) { + /* Remove the lookup rule */ + struct ice_aqc_sw_rules_elem *s_rule; + + s_rule = devm_kzalloc(ice_hw_to_dev(hw), + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, + GFP_KERNEL); + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto exit; + } + + ice_fill_sw_rule(hw, &list_elem->fltr_info, s_rule, + ice_aqc_opc_remove_sw_rules); + + status = ice_aq_sw_rules(hw, s_rule, + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, + ice_aqc_opc_remove_sw_rules, NULL); + if (status) + goto exit; + + /* Remove a book keeping from the list */ + devm_kfree(ice_hw_to_dev(hw), s_rule); + + list_del(&list_elem->list_entry); + devm_kfree(ice_hw_to_dev(hw), list_elem); + } +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1106,7 +1573,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_aqc_sw_rules_elem *s_rule, *r_iter; struct ice_fltr_list_entry *m_list_itr; + struct list_head *rule_head; u16 elem_sent, total_elem_left; + struct ice_switch_info *sw; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; u16 num_unicast = 0; u16 s_rule_size; @@ -1114,48 +1584,73 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) if (!m_list || !hw) return ICE_ERR_PARAM; + s_rule = NULL; + sw = hw->switch_info; + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry(m_list_itr, m_list, list_entry) { u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; + u16 vsi_handle; + u16 hw_vsi_id; - if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC) + m_list_itr->fltr_info.flag = ICE_FLTR_TX; + vsi_handle = m_list_itr->fltr_info.vsi_handle; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + m_list_itr->fltr_info.fwd_id.hw_vsi_id = hw_vsi_id; + /* update the src in case it is vsi num */ + if (m_list_itr->fltr_info.src_id != ICE_SRC_ID_VSI) return ICE_ERR_PARAM; - if (is_zero_ether_addr(add)) + m_list_itr->fltr_info.src = hw_vsi_id; + if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || + is_zero_ether_addr(add)) return ICE_ERR_PARAM; if (is_unicast_ether_addr(add) && !hw->ucast_shared) { /* Don't overwrite the unicast address */ - if (ice_find_mac_entry(hw, add)) + mutex_lock(rule_lock); + if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC, + &m_list_itr->fltr_info)) { + mutex_unlock(rule_lock); return ICE_ERR_ALREADY_EXISTS; + } + mutex_unlock(rule_lock); num_unicast++; } else if (is_multicast_ether_addr(add) || (is_unicast_ether_addr(add) && hw->ucast_shared)) { - status = ice_add_shared_mac(hw, m_list_itr); - if (status) { - m_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - m_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + m_list_itr->status = + ice_add_rule_internal(hw, ICE_SW_LKUP_MAC, + m_list_itr); + if (m_list_itr->status) + return m_list_itr->status; } } + mutex_lock(rule_lock); /* Exit if no suitable entries were found for adding bulk switch rule */ - if (!num_unicast) - return 0; + if (!num_unicast) { + status = 0; + goto ice_add_mac_exit; + } + + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; /* Allocate switch rule buffer for the bulk update for unicast */ s_rule_size = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto ice_add_mac_exit; + } r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - if (is_unicast_ether_addr(addr)) { - ice_fill_sw_rule(hw, &m_list_itr->fltr_info, - r_iter, ice_aqc_opc_add_sw_rules); + if (is_unicast_ether_addr(mac_addr)) { + ice_fill_sw_rule(hw, &m_list_itr->fltr_info, r_iter, + ice_aqc_opc_add_sw_rules); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } @@ -1183,11 +1678,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; - struct ice_switch_info *sw = hw->switch_info; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; struct ice_fltr_mgmt_list_entry *fm_entry; - if (is_unicast_ether_addr(addr)) { + if (is_unicast_ether_addr(mac_addr)) { f_info->fltr_rule_id = le16_to_cpu(r_iter->pdata.lkup_tx_rx.index); f_info->fltr_act = ICE_FWD_TO_VSI; @@ -1203,46 +1697,21 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) /* The book keeping entries will get removed when * base driver calls remove filter AQ command */ - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); + list_add(&fm_entry->list_entry, rule_head); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } } ice_add_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); + mutex_unlock(rule_lock); + if (s_rule) + devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } /** - * ice_find_vlan_entry - * @hw: pointer to the hardware structure - * @vlan_id: VLAN id to search for - * - * Helper function to search for a VLAN entry using a given VLAN id - * Returns pointer to the entry if found. - */ -static struct ice_fltr_mgmt_list_entry * -ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) -{ - struct ice_fltr_mgmt_list_entry *vlan_list_itr, *vlan_ret = NULL; - struct ice_switch_info *sw = hw->switch_info; - - mutex_lock(&sw->vlan_list_lock); - list_for_each_entry(vlan_list_itr, &sw->vlan_list_head, list_entry) - if (vlan_list_itr->fltr_info.l_data.vlan.vlan_id == vlan_id) { - vlan_ret = vlan_list_itr; - break; - } - - mutex_unlock(&sw->vlan_list_lock); - return vlan_ret; -} - -/** * ice_add_vlan_internal - Add one VLAN based filter rule * @hw: pointer to the hardware structure * @f_entry: filter entry containing one VLAN information @@ -1250,53 +1719,150 @@ ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) static enum ice_status ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { - struct ice_fltr_info *new_fltr, *cur_fltr; + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *v_list_itr; - u16 vlan_id; + struct ice_fltr_info *new_fltr, *cur_fltr; + enum ice_sw_lkup_type lkup_type; + u16 vsi_list_id = 0, vsi_handle; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; + + if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) + return ICE_ERR_PARAM; + f_entry->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); new_fltr = &f_entry->fltr_info; + /* VLAN id should only be 12 bits */ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID) return ICE_ERR_PARAM; - vlan_id = new_fltr->l_data.vlan.vlan_id; - v_list_itr = ice_find_vlan_entry(hw, vlan_id); + if (new_fltr->src_id != ICE_SRC_ID_VSI) + return ICE_ERR_PARAM; + + new_fltr->src = new_fltr->fwd_id.hw_vsi_id; + lkup_type = new_fltr->lkup_type; + vsi_handle = new_fltr->vsi_handle; + rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; + mutex_lock(rule_lock); + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { - u16 vsi_id = ICE_VSI_INVAL_ID; - enum ice_status status; - u16 vsi_list_id = 0; + struct ice_vsi_list_map_info *map_info = NULL; if (new_fltr->fltr_act == ICE_FWD_TO_VSI) { - enum ice_sw_lkup_type lkup_type = new_fltr->lkup_type; - - /* All VLAN pruning rules use a VSI list. - * Convert the action to forwarding to a VSI list. + /* All VLAN pruning rules use a VSI list. Check if + * there is already a VSI list containing VSI that we + * want to add. If found, use the same vsi_list_id for + * this new VLAN rule or else create a new list. */ - vsi_id = new_fltr->fwd_id.vsi_id; - status = ice_create_vsi_list_rule(hw, &vsi_id, 1, - &vsi_list_id, - lkup_type); - if (status) - return status; + map_info = ice_find_vsi_list_entry(hw, ICE_SW_LKUP_VLAN, + vsi_handle, + &vsi_list_id); + if (!map_info) { + status = ice_create_vsi_list_rule(hw, + &vsi_handle, + 1, + &vsi_list_id, + lkup_type); + if (status) + goto exit; + } + /* Convert the action to forwarding to a VSI list. */ new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; new_fltr->fwd_id.vsi_list_id = vsi_list_id; } status = ice_create_pkt_fwd_rule(hw, f_entry); - if (!status && vsi_id != ICE_VSI_INVAL_ID) { - v_list_itr = ice_find_vlan_entry(hw, vlan_id); - if (!v_list_itr) - return ICE_ERR_DOES_NOT_EXIST; - v_list_itr->vsi_list_info = - ice_create_vsi_list_map(hw, &vsi_id, 1, - vsi_list_id); + if (!status) { + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, + new_fltr); + if (!v_list_itr) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } + /* reuse VSI list for new rule and increment ref_cnt */ + if (map_info) { + v_list_itr->vsi_list_info = map_info; + map_info->ref_cnt++; + } else { + v_list_itr->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle, + 1, vsi_list_id); + } } + } else if (v_list_itr->vsi_list_info->ref_cnt == 1) { + /* Update existing VSI list to add new VSI id only if it used + * by one VLAN rule. + */ + cur_fltr = &v_list_itr->fltr_info; + status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr, + new_fltr); + } else { + /* If VLAN rule exists and VSI list being used by this rule is + * referenced by more than 1 VLAN rule. Then create a new VSI + * list appending previous VSI with new VSI and update existing + * VLAN rule to point to new VSI list id + */ + struct ice_fltr_info tmp_fltr; + u16 vsi_handle_arr[2]; + u16 cur_handle; - return status; + /* Current implementation only supports reusing VSI list with + * one VSI count. We should never hit below condition + */ + if (v_list_itr->vsi_count > 1 && + v_list_itr->vsi_list_info->ref_cnt > 1) { + ice_debug(hw, ICE_DBG_SW, + "Invalid configuration: Optimization to reuse VSI list with more than one VSI is not being done yet\n"); + status = ICE_ERR_CFG; + goto exit; + } + + cur_handle = + find_first_bit(v_list_itr->vsi_list_info->vsi_map, + ICE_MAX_VSI); + + /* A rule already exists with the new VSI being added */ + if (cur_handle == vsi_handle) { + status = ICE_ERR_ALREADY_EXISTS; + goto exit; + } + + vsi_handle_arr[0] = cur_handle; + vsi_handle_arr[1] = vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, + &vsi_list_id, lkup_type); + if (status) + goto exit; + + tmp_fltr = v_list_itr->fltr_info; + tmp_fltr.fltr_rule_id = v_list_itr->fltr_info.fltr_rule_id; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + /* Update the previous switch rule to a new VSI list which + * includes current VSI thats requested + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) + goto exit; + + /* before overriding VSI list map info. decrement ref_cnt of + * previous VSI list + */ + v_list_itr->vsi_list_info->ref_cnt--; + + /* now update to newly created list */ + v_list_itr->fltr_info.fwd_id.vsi_list_id = vsi_list_id; + v_list_itr->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, + vsi_list_id); + v_list_itr->vsi_count++; } - cur_fltr = &v_list_itr->fltr_info; - return ice_handle_vsi_list_mgmt(hw, v_list_itr, cur_fltr, new_fltr); +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1313,335 +1879,58 @@ ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) return ICE_ERR_PARAM; list_for_each_entry(v_list_itr, v_list, list_entry) { - enum ice_status status; - if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN) return ICE_ERR_PARAM; - - status = ice_add_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + v_list_itr->fltr_info.flag = ICE_FLTR_TX; + v_list_itr->status = ice_add_vlan_internal(hw, v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } return 0; } /** - * ice_remove_vsi_list_rule + * ice_rem_sw_rule_info * @hw: pointer to the hardware structure - * @vsi_list_id: VSI list id generated as part of allocate resource - * @lkup_type: switch rule filter lookup type + * @rule_head: pointer to the switch list structure that we want to delete */ -static enum ice_status -ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, - enum ice_sw_lkup_type lkup_type) -{ - struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; - u16 s_rule_size; - - s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); - s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); - s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); - /* FW expects number of VSIs in vsi_list resource to be 0 for clear - * command. Since memory is zero'ed out during initialization, it's not - * necessary to explicitly initialize the variable to 0. - */ - - status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (!status) - /* Free the vsi_list resource that we allocated */ - status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, - ice_aqc_opc_free_res); - - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_handle_rem_vsi_list_mgmt - * @hw: pointer to the hardware structure - * @vsi_id: ID of the VSI to remove - * @fm_list_itr: filter management entry for which the VSI list management - * needs to be done - */ -static enum ice_status -ice_handle_rem_vsi_list_mgmt(struct ice_hw *hw, u16 vsi_id, - struct ice_fltr_mgmt_list_entry *fm_list_itr) +static void +ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) { - struct ice_switch_info *sw = hw->switch_info; - enum ice_status status = 0; - enum ice_sw_lkup_type lkup_type; - bool is_last_elem = true; - bool conv_list = false; - bool del_list = false; - u16 vsi_list_id; - - lkup_type = fm_list_itr->fltr_info.lkup_type; - vsi_list_id = fm_list_itr->fltr_info.fwd_id.vsi_list_id; - - if (fm_list_itr->vsi_count > 1) { - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, - true, - ice_aqc_opc_update_sw_rules, - lkup_type); - if (status) - return status; - fm_list_itr->vsi_count--; - is_last_elem = false; - clear_bit(vsi_id, fm_list_itr->vsi_list_info->vsi_map); - } - - /* For non-VLAN rules that forward packets to a VSI list, convert them - * to forwarding packets to a VSI if there is only one VSI left in the - * list. Unused lists are then removed. - * VLAN rules need to use VSI lists even with only one VSI. - */ - if (fm_list_itr->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST) { - if (lkup_type == ICE_SW_LKUP_VLAN) { - del_list = is_last_elem; - } else if (fm_list_itr->vsi_count == 1) { - conv_list = true; - del_list = true; - } - } - - if (del_list) { - /* Remove the VSI list since it is no longer used */ - struct ice_vsi_list_map_info *vsi_list_info = - fm_list_itr->vsi_list_info; + if (!list_empty(rule_head)) { + struct ice_fltr_mgmt_list_entry *entry; + struct ice_fltr_mgmt_list_entry *tmp; - status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); - if (status) - return status; - - if (conv_list) { - u16 rem_vsi_id; - - rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, - ICE_MAX_VSI); - - /* Error out when the expected last element is not in - * the VSI list map - */ - if (rem_vsi_id == ICE_MAX_VSI) - return ICE_ERR_OUT_OF_RANGE; - - /* Change the list entry action from VSI_LIST to VSI */ - fm_list_itr->fltr_info.fltr_act = ICE_FWD_TO_VSI; - fm_list_itr->fltr_info.fwd_id.vsi_id = rem_vsi_id; + list_for_each_entry_safe(entry, tmp, rule_head, list_entry) { + list_del(&entry->list_entry); + devm_kfree(ice_hw_to_dev(hw), entry); } - - list_del(&vsi_list_info->list_entry); - devm_kfree(ice_hw_to_dev(hw), vsi_list_info); - fm_list_itr->vsi_list_info = NULL; - } - - if (conv_list) { - /* Convert the rule's forward action to forwarding packets to - * a VSI - */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = - cpu_to_le16(fm_list_itr->fltr_info.fltr_rule_id); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, - ice_aqc_opc_update_sw_rules, NULL); - devm_kfree(ice_hw_to_dev(hw), s_rule); - if (status) - return status; } - - if (is_last_elem) { - /* Remove the lookup rule */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_remove_sw_rules); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (status) - return status; - - /* Remove a book keeping entry from the MAC address list */ - mutex_lock(&sw->mac_list_lock); - list_del(&fm_list_itr->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), fm_list_itr); - devm_kfree(ice_hw_to_dev(hw), s_rule); - } - return status; -} - -/** - * ice_remove_mac_entry - * @hw: pointer to the hardware structure - * @f_entry: structure containing MAC forwarding information - */ -static enum ice_status -ice_remove_mac_entry(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) -{ - struct ice_fltr_mgmt_list_entry *m_entry; - u16 vsi_id; - u8 *add; - - add = &f_entry->fltr_info.l_data.mac.mac_addr[0]; - - m_entry = ice_find_mac_entry(hw, add); - if (!m_entry) - return ICE_ERR_PARAM; - - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, m_entry); } /** - * ice_remove_mac - remove a MAC address based filter rule + * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure - * @m_list: list of MAC addresses and forwarding information - * - * This function removes either a MAC filter rule or a specific VSI from a - * VSI list for a multicast MAC address. - * - * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by - * ice_add_mac. Caller should be aware that this call will only work if all - * the entries passed into m_list were added previously. It will not attempt to - * do a partial remove of entries that were found. - */ -enum ice_status -ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) -{ - struct ice_aqc_sw_rules_elem *s_rule, *r_iter; - u8 s_rule_size = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; - struct ice_switch_info *sw = hw->switch_info; - struct ice_fltr_mgmt_list_entry *m_entry; - struct ice_fltr_list_entry *m_list_itr; - u16 elem_sent, total_elem_left; - enum ice_status status = 0; - u16 num_unicast = 0; - - if (!m_list) - return ICE_ERR_PARAM; - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr) && !hw->ucast_shared) - num_unicast++; - else if (is_multicast_ether_addr(addr) || - (is_unicast_ether_addr(addr) && hw->ucast_shared)) - ice_remove_mac_entry(hw, m_list_itr); - } - - /* Exit if no unicast addresses found. Multicast switch rules - * were added individually - */ - if (!num_unicast) - return 0; - - /* Allocate switch rule buffer for the bulk update for unicast */ - s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - r_iter = s_rule; - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) { - status = ICE_ERR_DOES_NOT_EXIST; - goto ice_remove_mac_exit; - } - - ice_fill_sw_rule(hw, &m_entry->fltr_info, - r_iter, ice_aqc_opc_remove_sw_rules); - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - } - - /* Call AQ bulk switch rule update for all unicast addresses */ - r_iter = s_rule; - /* Call AQ switch rule in AQ_MAX chunk */ - for (total_elem_left = num_unicast; total_elem_left > 0; - total_elem_left -= elem_sent) { - struct ice_aqc_sw_rules_elem *entry = r_iter; - - elem_sent = min(total_elem_left, - (u16)(ICE_AQ_MAX_BUF_LEN / s_rule_size)); - status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size, - elem_sent, ice_aqc_opc_remove_sw_rules, - NULL); - if (status) - break; - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) - return ICE_ERR_OUT_OF_RANGE; - mutex_lock(&sw->mac_list_lock); - list_del(&m_entry->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), m_entry); - } - } - -ice_remove_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_cfg_dflt_vsi - add filter rule to set/unset given VSI as default - * VSI for the switch (represented by swid) - * @hw: pointer to the hardware structure - * @vsi_id: number of VSI to set as default + * @vsi_handle: VSI handle to set as default * @set: true to add the above mentioned switch rule, false to remove it * @direction: ICE_FLTR_RX or ICE_FLTR_TX + * + * add filter rule to set/unset given VSI as default VSI for the switch + * (represented by swid) */ enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) +ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) { struct ice_aqc_sw_rules_elem *s_rule; struct ice_fltr_info f_info; enum ice_adminq_opc opcode; enum ice_status status; u16 s_rule_size; + u16 hw_vsi_id; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE : ICE_SW_RULE_RX_TX_NO_HDR_SIZE; @@ -1654,15 +1943,17 @@ ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) f_info.lkup_type = ICE_SW_LKUP_DFLT; f_info.flag = direction; f_info.fltr_act = ICE_FWD_TO_VSI; - f_info.fwd_id.vsi_id = vsi_id; + f_info.fwd_id.hw_vsi_id = hw_vsi_id; if (f_info.flag & ICE_FLTR_RX) { f_info.src = hw->port_info->lport; + f_info.src_id = ICE_SRC_ID_LPORT; if (!set) f_info.fltr_rule_id = hw->port_info->dflt_rx_vsi_rule_id; } else if (f_info.flag & ICE_FLTR_TX) { - f_info.src = vsi_id; + f_info.src_id = ICE_SRC_ID_VSI; + f_info.src = hw_vsi_id; if (!set) f_info.fltr_rule_id = hw->port_info->dflt_tx_vsi_rule_id; @@ -1682,10 +1973,10 @@ ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) u16 index = le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); if (f_info.flag & ICE_FLTR_TX) { - hw->port_info->dflt_tx_vsi_num = vsi_id; + hw->port_info->dflt_tx_vsi_num = hw_vsi_id; hw->port_info->dflt_tx_vsi_rule_id = index; } else if (f_info.flag & ICE_FLTR_RX) { - hw->port_info->dflt_rx_vsi_num = vsi_id; + hw->port_info->dflt_rx_vsi_num = hw_vsi_id; hw->port_info->dflt_rx_vsi_rule_id = index; } } else { @@ -1704,26 +1995,38 @@ out: } /** - * ice_remove_vlan_internal - Remove one VLAN based filter rule + * ice_remove_mac - remove a MAC address based filter rule * @hw: pointer to the hardware structure - * @f_entry: filter entry containing one VLAN information + * @m_list: list of MAC addresses and forwarding information + * + * This function removes either a MAC filter rule or a specific VSI from a + * VSI list for a multicast MAC address. + * + * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by + * ice_add_mac. Caller should be aware that this call will only work if all + * the entries passed into m_list were added previously. It will not attempt to + * do a partial remove of entries that were found. */ -static enum ice_status -ice_remove_vlan_internal(struct ice_hw *hw, - struct ice_fltr_list_entry *f_entry) +enum ice_status +ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_fltr_info *new_fltr; - struct ice_fltr_mgmt_list_entry *v_list_elem; - u16 vsi_id; + struct ice_fltr_list_entry *list_itr, *tmp; - new_fltr = &f_entry->fltr_info; - - v_list_elem = ice_find_vlan_entry(hw, new_fltr->l_data.vlan.vlan_id); - if (!v_list_elem) + if (!m_list) return ICE_ERR_PARAM; - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, v_list_elem); + list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { + enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_MAC) + return ICE_ERR_PARAM; + list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_MAC, + list_itr); + if (list_itr->status) + return list_itr->status; + } + return 0; } /** @@ -1734,131 +2037,169 @@ ice_remove_vlan_internal(struct ice_hw *hw, enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { - struct ice_fltr_list_entry *v_list_itr; - enum ice_status status = 0; + struct ice_fltr_list_entry *v_list_itr, *tmp; if (!v_list || !hw) return ICE_ERR_PARAM; - list_for_each_entry(v_list_itr, v_list, list_entry) { - status = ice_remove_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) { + enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_VLAN) + return ICE_ERR_PARAM; + v_list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_VLAN, + v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } - return status; + return 0; +} + +/** + * ice_vsi_uses_fltr - Determine if given VSI uses specified filter + * @fm_entry: filter entry to inspect + * @vsi_handle: VSI handle to compare with filter info + */ +static bool +ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) +{ + return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && + fm_entry->fltr_info.vsi_handle == vsi_handle) || + (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); +} + +/** + * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle to remove filters from + * @vsi_list_head: pointer to the list to add entry to + * @fi: pointer to fltr_info of filter entry to copy & add + * + * Helper function, used when creating a list of filters to remove from + * a specific VSI. The entry added to vsi_list_head is a COPY of the + * original filter entry, with the exception of fltr_info.fltr_act and + * fltr_info.fwd_id fields. These are set such that later logic can + * extract which VSI to remove the fltr from, and pass on that information. + */ +static enum ice_status +ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, + struct list_head *vsi_list_head, + struct ice_fltr_info *fi) +{ + struct ice_fltr_list_entry *tmp; + + /* this memory is freed up in the caller function + * once filters for this VSI are removed + */ + tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + tmp->fltr_info = *fi; + + /* Overwrite these fields to indicate which VSI to remove filter from, + * so find and remove logic can extract the information from the + * list entries. Note that original entries will still have proper + * values. + */ + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.vsi_handle = vsi_handle; + tmp->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + + list_add(&tmp->list_entry, vsi_list_head); + + return 0; } /** * ice_add_to_vsi_fltr_list - Add VSI filters to the list * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from * @lkup_list_head: pointer to the list that has certain lookup type filters - * @vsi_list_head: pointer to the list pertaining to VSI with vsi_id + * @vsi_list_head: pointer to the list pertaining to VSI with vsi_handle + * + * Locates all filters in lkup_list_head that are used by the given VSI, + * and adds COPIES of those entries to vsi_list_head (intended to be used + * to remove the listed filters). + * Note that this means all entries in vsi_list_head must be explicitly + * deallocated by the caller when done with list. */ static enum ice_status -ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, +ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct list_head *lkup_list_head, struct list_head *vsi_list_head) { struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; /* check to make sure VSI id is valid and within boundary */ - if (vsi_id >= - (sizeof(fm_entry->vsi_list_info->vsi_map) * BITS_PER_BYTE - 1)) + if (!ice_is_vsi_valid(hw, vsi_handle)) return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { struct ice_fltr_info *fi; fi = &fm_entry->fltr_info; - if ((fi->fltr_act == ICE_FWD_TO_VSI && - fi->fwd_id.vsi_id == vsi_id) || - (fi->fltr_act == ICE_FWD_TO_VSI_LIST && - (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))) { - struct ice_fltr_list_entry *tmp; - - /* this memory is freed up in the caller function - * ice_remove_vsi_lkup_fltr() once filters for - * this VSI are removed - */ - tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), - GFP_KERNEL); - if (!tmp) - return ICE_ERR_NO_MEMORY; + if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle)) + continue; - memcpy(&tmp->fltr_info, fi, sizeof(*fi)); - - /* Expected below fields to be set to ICE_FWD_TO_VSI and - * the particular VSI id since we are only removing this - * one VSI - */ - if (fi->fltr_act == ICE_FWD_TO_VSI_LIST) { - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi_id; - } - - list_add(&tmp->list_entry, vsi_list_head); - } + status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle, + vsi_list_head, fi); + if (status) + return status; } - return 0; + return status; } /** * ice_remove_vsi_lkup_fltr - Remove lookup type filters for a VSI * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from * @lkup: switch rule filter lookup type */ static void -ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, +ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, enum ice_sw_lkup_type lkup) { struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_list_entry *fm_entry; struct list_head remove_list_head; + struct list_head *rule_head; struct ice_fltr_list_entry *tmp; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status; INIT_LIST_HEAD(&remove_list_head); + rule_lock = &sw->recp_list[lkup].filt_rule_lock; + rule_head = &sw->recp_list[lkup].filt_rules; + mutex_lock(rule_lock); + status = ice_add_to_vsi_fltr_list(hw, vsi_handle, rule_head, + &remove_list_head); + mutex_unlock(rule_lock); + if (status) + return; + switch (lkup) { case ICE_SW_LKUP_MAC: - mutex_lock(&sw->mac_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->mac_list_head, - &remove_list_head); - mutex_unlock(&sw->mac_list_lock); - if (!status) { - ice_remove_mac(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_mac(hw, &remove_list_head); break; case ICE_SW_LKUP_VLAN: - mutex_lock(&sw->vlan_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->vlan_list_head, - &remove_list_head); - mutex_unlock(&sw->vlan_list_lock); - if (!status) { - ice_remove_vlan(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_vlan(hw, &remove_list_head); break; case ICE_SW_LKUP_MAC_VLAN: case ICE_SW_LKUP_ETHERTYPE: case ICE_SW_LKUP_ETHERTYPE_MAC: case ICE_SW_LKUP_PROMISC: - case ICE_SW_LKUP_PROMISC_VLAN: case ICE_SW_LKUP_DFLT: - ice_debug(hw, ICE_DBG_SW, - "Remove filters for this lookup type hasn't been implemented yet\n"); + case ICE_SW_LKUP_PROMISC_VLAN: + case ICE_SW_LKUP_LAST: + default: + ice_debug(hw, ICE_DBG_SW, "Unsupported lookup type %d\n", lkup); break; } - return; -free_fltr_list: list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) { list_del(&fm_entry->list_entry); devm_kfree(ice_hw_to_dev(hw), fm_entry); @@ -1868,16 +2209,121 @@ free_fltr_list: /** * ice_remove_vsi_fltr - Remove all filters for a VSI * @hw: pointer to the hardware structure - * @vsi_id: ID of VSI to remove filters from + * @vsi_handle: VSI handle to remove filters from + */ +void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle) +{ + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC_VLAN); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_VLAN); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_DFLT); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE_MAC); + ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC_VLAN); +} + +/** + * ice_replay_vsi_fltr - Replay filters for requested VSI + * @hw: pointer to the hardware structure + * @vsi_handle: driver VSI handle + * @recp_id: Recipe id for which rules need to be replayed + * @list_head: list for which filters need to be replayed + * + * Replays the filter of recipe recp_id for a VSI represented via vsi_handle. + * It is required to pass valid VSI handle. + */ +static enum ice_status +ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, + struct list_head *list_head) +{ + struct ice_fltr_mgmt_list_entry *itr; + enum ice_status status = 0; + u16 hw_vsi_id; + + if (list_empty(list_head)) + return status; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + + list_for_each_entry(itr, list_head, list_entry) { + struct ice_fltr_list_entry f_entry; + + f_entry.fltr_info = itr->fltr_info; + if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN && + itr->fltr_info.vsi_handle == vsi_handle) { + /* update the src in case it is vsi num */ + if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI) + f_entry.fltr_info.src = hw_vsi_id; + status = ice_add_rule_internal(hw, recp_id, &f_entry); + if (status) + goto end; + continue; + } + if (!itr->vsi_list_info || + !test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) + continue; + /* Clearing it so that the logic can add it back */ + clear_bit(vsi_handle, itr->vsi_list_info->vsi_map); + f_entry.fltr_info.vsi_handle = vsi_handle; + f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; + /* update the src in case it is vsi num */ + if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI) + f_entry.fltr_info.src = hw_vsi_id; + if (recp_id == ICE_SW_LKUP_VLAN) + status = ice_add_vlan_internal(hw, &f_entry); + else + status = ice_add_rule_internal(hw, recp_id, &f_entry); + if (status) + goto end; + } +end: + return status; +} + +/** + * ice_replay_vsi_all_fltr - replay all filters stored in bookkeeping lists + * @hw: pointer to the hardware structure + * @vsi_handle: driver VSI handle + * + * Replays filters for requested VSI via vsi_handle. */ -void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id) +enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle) { - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC_VLAN); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_VLAN); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_DFLT); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE_MAC); - ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC_VLAN); + struct ice_switch_info *sw = hw->switch_info; + enum ice_status status = 0; + u8 i; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct list_head *head; + + head = &sw->recp_list[i].filt_replay_rules; + status = ice_replay_vsi_fltr(hw, vsi_handle, i, head); + if (status) + return status; + } + return status; +} + +/** + * ice_rm_all_sw_replay_rule_info - deletes filter replay rules + * @hw: pointer to the hw struct + * + * Deletes the filter replay rules. + */ +void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + if (!sw) + return; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + if (!list_empty(&sw->recp_list[i].filt_replay_rules)) { + struct list_head *l_head; + + l_head = &sw->recp_list[i].filt_replay_rules; + ice_rem_sw_rule_info(hw, l_head); + } + } } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 9b8ec128ee31..b88d96a1ef69 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -17,7 +17,9 @@ struct ice_vsi_ctx { u16 vsis_unallocated; u16 flags; struct ice_aqc_vsi_props info; + struct ice_sched_vsi_info sched; u8 alloc_from_pool; + u8 vf_num; }; enum ice_sw_fwd_act_type { @@ -39,6 +41,15 @@ enum ice_sw_lkup_type { ICE_SW_LKUP_DFLT = 5, ICE_SW_LKUP_ETHERTYPE_MAC = 8, ICE_SW_LKUP_PROMISC_VLAN = 9, + ICE_SW_LKUP_LAST +}; + +/* type of filter src id */ +enum ice_src_id { + ICE_SRC_ID_UNKNOWN = 0, + ICE_SRC_ID_VSI, + ICE_SRC_ID_QUEUE, + ICE_SRC_ID_LPORT, }; struct ice_fltr_info { @@ -55,6 +66,7 @@ struct ice_fltr_info { /* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */ u16 src; + enum ice_src_id src_id; union { struct { @@ -76,7 +88,10 @@ struct ice_fltr_info { u16 ethertype; u8 mac_addr[ETH_ALEN]; /* optional */ } ethertype_mac; - } l_data; + } l_data; /* Make sure to zero out the memory of l_data before using + * it or only set the data associated with lookup match + * rest everything should be zero + */ /* Depending on filter action */ union { @@ -84,12 +99,16 @@ struct ice_fltr_info { * queue id in case of ICE_FWD_TO_QGRP. */ u16 q_id:11; - u16 vsi_id:10; + u16 hw_vsi_id:10; u16 vsi_list_id:10; } fwd_id; + /* Sw VSI handle */ + u16 vsi_handle; + /* Set to num_queues if action is ICE_FWD_TO_QGRP. This field - * determines the range of queues the packet needs to be forwarded to + * determines the range of queues the packet needs to be forwarded to. + * Note that qgrp_size must be set to a power of 2. */ u8 qgrp_size; @@ -98,29 +117,52 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_sw_recipe { + struct list_head l_entry; + + /* To protect modification of filt_rule list + * defined below + */ + struct mutex filt_rule_lock; + + /* List of type ice_fltr_mgmt_list_entry */ + struct list_head filt_rules; + struct list_head filt_replay_rules; + + /* linked list of type recipe_list_entry */ + struct list_head rg_list; + /* linked list of type ice_sw_fv_list_entry*/ + struct list_head fv_list; + struct ice_aqc_recipe_data_elem *r_buf; + u8 recp_count; + u8 root_rid; + u8 num_profs; + u8 *prof_ids; + + /* recipe bitmap: what all recipes makes this recipe */ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); +}; + /* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list id */ struct ice_vsi_list_map_info { struct list_head list_entry; DECLARE_BITMAP(vsi_map, ICE_MAX_VSI); u16 vsi_list_id; -}; - -enum ice_sw_fltr_status { - ICE_FLTR_STATUS_NEW = 0, - ICE_FLTR_STATUS_FW_SUCCESS, - ICE_FLTR_STATUS_FW_FAIL, + /* counter to track how many rules are reusing this VSI list */ + u16 ref_cnt; }; struct ice_fltr_list_entry { struct list_head list_entry; - enum ice_sw_fltr_status status; + enum ice_status status; struct ice_fltr_info fltr_info; }; /* This defines an entry in the list that maintains MAC or VLAN membership * to HW list mapping, since multiple VSIs can subscribe to the same MAC or * VLAN. As an optimization the VSI list should be created only when a - * second VSI becomes a subscriber to the VLAN address. + * second VSI becomes a subscriber to the same MAC address. VSI lists are always + * used for VLAN membership. */ struct ice_fltr_mgmt_list_entry { /* back pointer to VSI list id to VSI list mapping */ @@ -138,24 +180,33 @@ struct ice_fltr_mgmt_list_entry { /* VSI related commands */ enum ice_status -ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - struct ice_sq_cd *cd); +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd); enum ice_status -ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - struct ice_sq_cd *cd); +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd); enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd); - +ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd); +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); +struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id); +void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction); +ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction); + +enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); +u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); +bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); + +enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); +void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 6481e3d86374..5dae968d853e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -251,6 +251,7 @@ int ice_setup_tx_ring(struct ice_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt = -1; return 0; err: diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 31bc998fe200..1d0f58bd389b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -71,6 +71,7 @@ struct ice_txq_stats { u64 restart_q; u64 tx_busy; u64 tx_linearize; + int prev_pkt; /* negative if no pending Tx descriptors */ }; struct ice_rxq_stats { @@ -103,10 +104,17 @@ enum ice_rx_dtype { #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 #define ICE_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define ICE_ITR_8K 0x003E +#define ICE_ITR_8K 125 +#define ICE_ITR_20K 50 +#define ICE_DFLT_TX_ITR ICE_ITR_20K +#define ICE_DFLT_RX_ITR ICE_ITR_20K +/* apply ITR granularity translation to program the register. itr_gran is either + * 2 or 4 usecs so we need to divide by 2 first then shift by that value + */ +#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> \ + ((itr_gran) / 2)) -/* apply ITR HW granularity translation to program the HW registers */ -#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> (itr_gran)) +#define ICE_DFLT_INTRL 0 /* Legacy or Advanced Mode Queue */ #define ICE_TX_ADVANCED 0 @@ -128,14 +136,6 @@ struct ice_ring { u16 q_index; /* Queue number of ring */ u32 txq_teid; /* Added Tx queue TEID */ - /* high bit set means dynamic, use accessor routines to read/write. - * hardware supports 2us/1us resolution for the ITR registers. - * these values always store the USER setting, and must be converted - * before programming to a register. - */ - u16 rx_itr_setting; - u16 tx_itr_setting; - u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -172,6 +172,7 @@ struct ice_ring_container { unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_pkts; /* total packets processed this int */ enum ice_latency_range latency_range; + int itr_idx; /* index in the interrupt vector */ u16 itr; }; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 97c366e0ca59..12f9432abf11 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,9 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) return test_bit(tc, (unsigned long *)&bitmap); } +/* Driver always calls main vsi_handle first */ +#define ICE_MAIN_VSI_HANDLE 0 + /* debug masks - set these bits in hw->debug_mask to control output */ #define ICE_DBG_INIT BIT_ULL(1) #define ICE_DBG_LINK BIT_ULL(4) @@ -34,10 +37,15 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) enum ice_aq_res_ids { ICE_NVM_RES_ID = 1, ICE_SPD_RES_ID, - ICE_GLOBAL_CFG_LOCK_RES_ID, - ICE_CHANGE_LOCK_RES_ID + ICE_CHANGE_LOCK_RES_ID, + ICE_GLOBAL_CFG_LOCK_RES_ID }; +/* FW update timeout definitions are in milliseconds */ +#define ICE_NVM_TIMEOUT 180000 +#define ICE_CHANGE_LOCK_TIMEOUT 1000 +#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 3000 + enum ice_aq_res_access_type { ICE_RES_READ = 1, ICE_RES_WRITE @@ -76,6 +84,7 @@ enum ice_media_type { enum ice_vsi_type { ICE_VSI_PF = 0, + ICE_VSI_VF, }; struct ice_link_status { @@ -95,6 +104,15 @@ struct ice_link_status { u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE]; }; +/* Different reset sources for which a disable queue AQ call has to be made in + * order to clean the TX scheduler as a part of the reset + */ +enum ice_disq_rst_src { + ICE_NO_RESET = 0, + ICE_VM_RESET, + ICE_VF_RESET, +}; + /* PHY info such as phy_type, etc... */ struct ice_phy_info { struct ice_link_status link_info; @@ -119,6 +137,9 @@ struct ice_hw_common_caps { /* Max MTU for function or device */ u16 max_mtu; + /* Virtualization support */ + u8 sr_iov_1_1; /* SR-IOV enabled */ + /* RSS related capabilities */ u16 rss_table_size; /* 512 for PFs and 64 for VFs */ u8 rss_table_entry_width; /* RSS Entry width in bits */ @@ -127,12 +148,15 @@ struct ice_hw_common_caps { /* Function specific capabilities */ struct ice_hw_func_caps { struct ice_hw_common_caps common_cap; + u32 num_allocd_vfs; /* Number of allocated VFs */ + u32 vf_base_id; /* Logical ID of the first VF */ u32 guaranteed_num_vsi; }; /* Device wide capabilities */ struct ice_hw_dev_caps { struct ice_hw_common_caps common_cap; + u32 num_vfs_exposed; /* Total number of VFs exposed */ u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ }; @@ -142,11 +166,18 @@ struct ice_mac_info { u8 perm_addr[ETH_ALEN]; }; -/* Various RESET request, These are not tied with HW reset types */ +/* Reset types used to determine which kind of reset was requested. These + * defines match what the RESET_TYPE field of the GLGEN_RSTAT register. + * ICE_RESET_PFR does not match any RESET_TYPE field in the GLGEN_RSTAT register + * because its reset source is different than the other types listed. + */ enum ice_reset_req { - ICE_RESET_PFR = 0, + ICE_RESET_POR = 0, + ICE_RESET_INVAL = 0, ICE_RESET_CORER = 1, ICE_RESET_GLOBR = 2, + ICE_RESET_EMPR = 3, + ICE_RESET_PFR = 4, }; /* Bus parameters */ @@ -180,7 +211,7 @@ struct ice_sched_node { struct ice_sched_node **children; struct ice_aqc_txsched_elem_data info; u32 agg_id; /* aggregator group id */ - u16 vsi_id; + u16 vsi_handle; u8 in_use; /* suspended or in use */ u8 tx_sched_layer; /* Logical Layer (1-9) */ u8 num_children; @@ -204,6 +235,7 @@ enum ice_agg_type { }; #define ICE_SCHED_DFLT_RL_PROF_ID 0 +#define ICE_SCHED_DFLT_BW_WT 1 /* vsi type list entry to locate corresponding vsi/ag nodes */ struct ice_sched_vsi_info { @@ -238,8 +270,6 @@ struct ice_port_info { struct ice_mac_info mac; struct ice_phy_info phy; struct mutex sched_lock; /* protect access to TXSched tree */ - struct ice_sched_tx_policy sched_policy; - struct list_head vsi_info_list; struct list_head agg_list; /* lists all aggregator */ u8 lport; #define ICE_LPORT_MASK 0xff @@ -247,19 +277,26 @@ struct ice_port_info { }; struct ice_switch_info { - /* Switch VSI lists to MAC/VLAN translation */ - struct mutex mac_list_lock; /* protect MAC list */ - struct list_head mac_list_head; - struct mutex vlan_list_lock; /* protect VLAN list */ - struct list_head vlan_list_head; - struct mutex eth_m_list_lock; /* protect ethtype list */ - struct list_head eth_m_list_head; - struct mutex promisc_list_lock; /* protect promisc mode list */ - struct list_head promisc_list_head; - struct mutex mac_vlan_list_lock; /* protect MAC-VLAN list */ - struct list_head mac_vlan_list_head; - struct list_head vsi_list_map_head; + struct ice_sw_recipe *recp_list; +}; + +/* FW logging configuration */ +struct ice_fw_log_evnt { + u8 cfg : 4; /* New event enables to configure */ + u8 cur : 4; /* Current/active event enables */ +}; + +struct ice_fw_log_cfg { + u8 cq_en : 1; /* FW logging is enabled via the control queue */ + u8 uart_en : 1; /* FW logging is enabled via UART for all PFs */ + u8 actv_evnts; /* Cumulation of currently enabled log events */ + +#define ICE_FW_LOG_EVNT_INFO (ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_INIT (ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_FLOW (ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_ERR (ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S) + struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX]; }; /* Port hardware description */ @@ -286,8 +323,11 @@ struct ice_hw { u8 flattened_layers; u8 max_cgds; u8 sw_entry_point_layer; + u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; + struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI]; u8 evb_veb; /* true for VEB, false for VEPA */ + u8 reset_ongoing; /* true if hw is in reset, false otherwise */ struct ice_bus_info bus; struct ice_nvm_info nvm; struct ice_hw_dev_caps dev_caps; /* device capabilities */ @@ -297,6 +337,7 @@ struct ice_hw { /* Control Queue info */ struct ice_ctl_q_info adminq; + struct ice_ctl_q_info mailboxq; u8 api_branch; /* API branch version */ u8 api_maj_ver; /* API major version */ @@ -308,16 +349,27 @@ struct ice_hw { u8 fw_patch; /* firmware patch version */ u32 fw_build; /* firmware build number */ - /* minimum allowed value for different speeds */ -#define ICE_ITR_GRAN_MIN_200 1 -#define ICE_ITR_GRAN_MIN_100 1 -#define ICE_ITR_GRAN_MIN_50 2 -#define ICE_ITR_GRAN_MIN_25 4 + struct ice_fw_log_cfg fw_log; + +/* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL + * register. Used for determining the itr/intrl granularity during + * initialization. + */ +#define ICE_MAX_AGG_BW_200G 0x0 +#define ICE_MAX_AGG_BW_100G 0X1 +#define ICE_MAX_AGG_BW_50G 0x2 +#define ICE_MAX_AGG_BW_25G 0x3 + /* ITR granularity for different speeds */ +#define ICE_ITR_GRAN_ABOVE_25 2 +#define ICE_ITR_GRAN_MAX_25 4 /* ITR granularity in 1 us */ - u8 itr_gran_200; - u8 itr_gran_100; - u8 itr_gran_50; - u8 itr_gran_25; + u8 itr_gran; + /* INTRL granularity for different speeds */ +#define ICE_INTRL_GRAN_ABOVE_25 4 +#define ICE_INTRL_GRAN_MAX_25 8 + /* INTRL granularity in 1 us */ + u8 intrl_gran; + u8 ucast_shared; /* true if VSIs can share unicast addr */ }; @@ -391,4 +443,7 @@ struct ice_hw_port_stats { #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 #define ICE_SR_WORDS_IN_1KB 512 +/* Hash redirection LUT for VSI - maximum array size */ +#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4) + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c new file mode 100644 index 000000000000..45f10f8f01dc --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -0,0 +1,2675 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +/** + * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF + * @pf: pointer to the PF structure + * @v_opcode: operation code + * @v_retval: return value + * @msg: pointer to the msg buffer + * @msglen: msg length + */ +static void +ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf = pf->vf; + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++, vf++) { + /* Not all vfs are enabled so skip the ones that are not */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + continue; + + /* Ignore return value on purpose - a given VF may fail, but + * we need to keep going and send to all of them + */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg, + msglen, NULL); + } +} + +/** + * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_* + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + int ice_link_speed, bool link_up) +{ + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { + pfe->event_data.link_event_adv.link_status = link_up; + /* Speed in Mbps */ + pfe->event_data.link_event_adv.link_speed = + ice_conv_link_speed_to_virtchnl(true, ice_link_speed); + } else { + pfe->event_data.link_event.link_status = link_up; + /* Legacy method for virtchnl link speeds */ + pfe->event_data.link_event.link_speed = + (enum virtchnl_link_speed) + ice_conv_link_speed_to_virtchnl(false, ice_link_speed); + } +} + +/** + * ice_set_pfe_link_forced - Force the virtchnl_pf_event link speed/status + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + bool link_up) +{ + u16 link_speed; + + if (link_up) + link_speed = ICE_AQ_LINK_SPEED_40GB; + else + link_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + + ice_set_pfe_link(vf, pfe, link_speed, link_up); +} + +/** + * ice_vc_notify_vf_link_state - Inform a VF of link status + * @vf: pointer to the VF structure + * + * send a link status message to a single VF + */ +static void ice_vc_notify_vf_link_state(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + + hw = &pf->hw; + ls = &hw->port_info->phy.link_info; + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info & + ICE_AQ_LINK_UP); + + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); +} + +/** + * ice_get_vf_vector - get VF interrupt vector register offset + * @vf_msix: number of MSIx vector per VF on a PF + * @vf_id: VF identifier + * @i: index of MSIx vector + */ +static u32 ice_get_vf_vector(int vf_msix, int vf_id, int i) +{ + return ((i == 0) ? VFINT_DYN_CTLN(vf_id) : + VFINT_DYN_CTLN(((vf_msix - 1) * (vf_id)) + (i - 1))); +} + +/** + * ice_free_vf_res - Free a VF's resources + * @vf: pointer to the VF info + */ +static void ice_free_vf_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + int i, pf_vf_msix; + + /* First, disable VF's configuration API to prevent OS from + * accessing the VF's VSI after it's freed or invalidated. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* free vsi & disconnect it from the parent uplink */ + if (vf->lan_vsi_idx) { + ice_vsi_release(pf->vsi[vf->lan_vsi_idx]); + vf->lan_vsi_idx = 0; + vf->lan_vsi_num = 0; + vf->num_mac = 0; + } + + pf_vf_msix = pf->num_vf_msix; + /* Disable interrupts so that VF starts in a known state */ + for (i = 0; i < pf_vf_msix; i++) { + u32 reg_idx; + + reg_idx = ice_get_vf_vector(pf_vf_msix, vf->vf_id, i); + wr32(&pf->hw, reg_idx, VFINT_DYN_CTLN_CLEARPBA_M); + ice_flush(&pf->hw); + } + /* reset some of the state variables keeping track of the resources */ + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); +} + +/***********************enable_vf routines*****************************/ + +/** + * ice_dis_vf_mappings + * @vf: pointer to the VF structure + */ +static void ice_dis_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + + wr32(hw, VPINT_ALLOC(vf->vf_id), 0); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); + + first = vf->first_vector_idx; + last = first + pf->num_vf_msix - 1; + for (v = first; v <= last; v++) { + u32 reg; + + reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & + GLINT_VECT2FUNC_IS_PF_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); +} + +/** + * ice_free_vfs - Free all VFs + * @pf: pointer to the PF structure + */ +void ice_free_vfs(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int tmp, i; + + if (!pf->vf) + return; + + while (test_and_set_bit(__ICE_VF_DIS, pf->state)) + usleep_range(1000, 2000); + + /* Avoid wait time by stopping all VFs at the same time */ + for (i = 0; i < pf->num_alloc_vfs; i++) { + if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states)) + continue; + + /* stop rings without wait time */ + ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx], + ICE_NO_RESET, i); + ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]); + + clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); + } + + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + + tmp = pf->num_alloc_vfs; + pf->num_vf_qps = 0; + pf->num_alloc_vfs = 0; + for (i = 0; i < tmp; i++) { + if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + /* disable VF qp mappings */ + ice_dis_vf_mappings(&pf->vf[i]); + + /* Set this state so that assigned VF vectors can be + * reclaimed by PF for reuse in ice_vsi_release(). No + * need to clear this bit since pf->vf array is being + * freed anyways after this for loop + */ + set_bit(ICE_VF_STATE_CFG_INTR, pf->vf[i].vf_states); + ice_free_vf_res(&pf->vf[i]); + } + } + + devm_kfree(&pf->pdev->dev, pf->vf); + pf->vf = NULL; + + /* This check is for when the driver is unloaded while VFs are + * assigned. Setting the number of VFs to 0 through sysfs is caught + * before this function ever gets called. + */ + if (!pci_vfs_assigned(pf->pdev)) { + int vf_id; + + /* Acknowledge VFLR for all VFs. Without this, VFs will fail to + * work correctly when SR-IOV gets re-enabled. + */ + for (vf_id = 0; vf_id < tmp; vf_id++) { + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + } + } + clear_bit(__ICE_VF_DIS, pf->state); + clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); +} + +/** + * ice_trigger_vf_reset - Reset a VF on HW + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. + */ +static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + u32 reg, reg_idx, bit_idx; + struct ice_hw *hw; + int vf_abs_id, i; + + hw = &pf->hw; + vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* Inform VF that it is no longer active, as a warning */ + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * in ice_alloc_vf_res(), when it's safe again to access VF's VSI. + * It's normally disabled in ice_free_vf_res(), but it's safer + * to do it earlier to give some time to finish to any VF config + * functions that may still be running at this point. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* In the case of a VFLR, the HW has already reset the VF and we + * just need to clean up, so don't hit the VFRTRIG register. + */ + if (!is_vflr) { + /* reset VF using VPGEN_VFRTRIG reg */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg |= VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + } + /* clear the VFLR bit in GLGEN_VFLRSTAT */ + reg_idx = (vf_abs_id) / 32; + bit_idx = (vf_abs_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + ice_flush(hw); + + wr32(hw, PF_PCI_CIAA, + VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); + for (i = 0; i < 100; i++) { + reg = rd32(hw, PF_PCI_CIAD); + if ((reg & VF_TRANS_PENDING_M) != 0) + dev_err(&pf->pdev->dev, + "VF %d PCI transactions stuck\n", vf->vf_id); + udelay(1); + } +} + +/** + * ice_vsi_set_pvid - Set port VLAN id for the VSI + * @vsi: the VSI being changed + * @vid: the VLAN id to set as a PVID + */ +static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ICE_AQ_VSI_PVLAN_INSERT_PVID | + ICE_AQ_VSI_VLAN_EMOD_STR; + ctxt.info.pvid = cpu_to_le16(vid); + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_info(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.pvid = ctxt.info.pvid; + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_kill_pvid - Remove port VLAN id from the VSI + * @vsi: the VSI being changed + */ +static int ice_vsi_kill_pvid(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + + if (ice_vsi_manage_vlan_stripping(vsi, false)) { + dev_err(&pf->pdev->dev, "Error removing Port VLAN on VSI %i\n", + vsi->vsi_num); + return -ENODEV; + } + + vsi->info.pvid = 0; + return 0; +} + +/** + * ice_vf_vsi_setup - Set up a VF VSI + * @pf: board private structure + * @pi: pointer to the port_info instance + * @vf_id: defines VF id to which this VSI connects. + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi * +ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_VF, vf_id); +} + +/** + * ice_alloc_vsi_res - Setup VF VSI and its resources + * @vf: pointer to the VF structure + * + * Returns 0 on success, negative value on failure + */ +static int ice_alloc_vsi_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + LIST_HEAD(tmp_add_list); + u8 broadcast[ETH_ALEN]; + struct ice_vsi *vsi; + int status = 0; + + vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id); + + if (!vsi) { + dev_err(&pf->pdev->dev, "Failed to create VF VSI\n"); + return -ENOMEM; + } + + vf->lan_vsi_idx = vsi->idx; + vf->lan_vsi_num = vsi->vsi_num; + + /* first vector index is the VFs OICR index */ + vf->first_vector_idx = vsi->hw_base_vector; + /* Since hw_base_vector holds the vector where data queue interrupts + * starts, increment by 1 since VFs allocated vectors include OICR intr + * as well. + */ + vsi->hw_base_vector += 1; + + /* Check if port VLAN exist before, and restore it accordingly */ + if (vf->port_vlan_id) + ice_vsi_set_pvid(vsi, vf->port_vlan_id); + + eth_broadcast_addr(broadcast); + + status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); + if (status) + goto ice_alloc_vsi_res_exit; + + if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) { + status = ice_add_mac_to_list(vsi, &tmp_add_list, + vf->dflt_lan_addr.addr); + if (status) + goto ice_alloc_vsi_res_exit; + } + + status = ice_add_mac(&pf->hw, &tmp_add_list); + if (status) + dev_err(&pf->pdev->dev, "could not add mac filters\n"); + + /* Clear this bit after VF initialization since we shouldn't reclaim + * and reassign interrupts for synchronous or asynchronous VFR events. + * We don't want to reconfigure interrupts since AVF driver doesn't + * expect vector assignment to be changed unless there is a request for + * more vectors. + */ + clear_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states); +ice_alloc_vsi_res_exit: + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; +} + +/** + * ice_alloc_vf_res - Allocate VF resources + * @vf: pointer to the VF structure + */ +static int ice_alloc_vf_res(struct ice_vf *vf) +{ + int status; + + /* setup VF VSI and necessary resources */ + status = ice_alloc_vsi_res(vf); + if (status) + goto ice_alloc_vf_res_exit; + + if (vf->trusted) + set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + else + clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + + /* VF is now completely initialized */ + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + + return status; + +ice_alloc_vf_res_exit: + ice_free_vf_res(vf); + return status; +} + +/** + * ice_ena_vf_mappings + * @vf: pointer to the VF structure + * + * Enable VF vectors and queues allocation by writing the details into + * respective registers. + */ +static void ice_ena_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + int abs_vf_id; + u32 reg; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + first = vf->first_vector_idx; + last = (first + pf->num_vf_msix) - 1; + abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* VF Vector allocation */ + reg = (((first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) | + ((last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) | + VPINT_ALLOC_VALID_M); + wr32(hw, VPINT_ALLOC(vf->vf_id), reg); + + reg = (((first << VPINT_ALLOC_PCI_FIRST_S) & VPINT_ALLOC_PCI_FIRST_M) | + ((last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) | + VPINT_ALLOC_PCI_VALID_M); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); + /* map the interrupts to its functions */ + for (v = first; v <= last; v++) { + reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & + GLINT_VECT2FUNC_VF_NUM_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + /* set regardless of mapping mode */ + wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M); + + /* VF Tx queues allocation */ + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { + /* set the VF PF Tx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & + VPLAN_TX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & + VPLAN_TX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + } + + /* set regardless of mapping mode */ + wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M); + + /* VF Rx queues allocation */ + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { + /* set the VF PF Rx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & + VPLAN_RX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & + VPLAN_RX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); + } +} + +/** + * ice_determine_res + * @pf: pointer to the PF structure + * @avail_res: available resources in the PF structure + * @max_res: maximum resources that can be given per VF + * @min_res: minimum resources that can be given per VF + * + * Returns non-zero value if resources (queues/vectors) are available or + * returns zero if PF cannot accommodate for all num_alloc_vfs. + */ +static int +ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res) +{ + bool checked_min_res = false; + int res; + + /* start by checking if PF can assign max number of resources for + * all num_alloc_vfs. + * if yes, return number per VF + * If no, divide by 2 and roundup, check again + * repeat the loop till we reach a point where even minimum resources + * are not available, in that case return 0 + */ + res = max_res; + while ((res >= min_res) && !checked_min_res) { + int num_all_res; + + num_all_res = pf->num_alloc_vfs * res; + if (num_all_res <= avail_res) + return res; + + if (res == min_res) + checked_min_res = true; + + res = DIV_ROUND_UP(res, 2); + } + return 0; +} + +/** + * ice_check_avail_res - check if vectors and queues are available + * @pf: pointer to the PF structure + * + * This function is where we calculate actual number of resources for VF VSIs, + * we don't reserve ahead of time during probe. Returns success if vectors and + * queues resources are available, otherwise returns error code + */ +static int ice_check_avail_res(struct ice_pf *pf) +{ + u16 num_msix, num_txq, num_rxq; + + if (!pf->num_alloc_vfs) + return -EINVAL; + + /* Grab from HW interrupts common pool + * Note: By the time the user decides it needs more vectors in a VF + * its already too late since one must decide this prior to creating the + * VF interface. So the best we can do is take a guess as to what the + * user might want. + * + * We have two policies for vector allocation: + * 1. if num_alloc_vfs is from 1 to 16, then we consider this as small + * number of NFV VFs used for NFV appliances, since this is a special + * case, we try to assign maximum vectors per VF (65) as much as + * possible, based on determine_resources algorithm. + * 2. if num_alloc_vfs is from 17 to 256, then its large number of + * regular VFs which are not used for any special purpose. Hence try to + * grab default interrupt vectors (5 as supported by AVF driver). + */ + if (pf->num_alloc_vfs <= 16) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_MAX_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else if (pf->num_alloc_vfs <= ICE_MAX_VF_COUNT) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_DFLT_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else { + dev_err(&pf->pdev->dev, + "Number of VFs %d exceeds max VF count %d\n", + pf->num_alloc_vfs, ICE_MAX_VF_COUNT); + return -EIO; + } + + if (!num_msix) + return -EIO; + + /* Grab from the common pool + * start by requesting Default queues (4 as supported by AVF driver), + * Note that, the main difference between queues and vectors is, latter + * can only be reserved at init time but queues can be requested by VF + * at runtime through Virtchnl, that is the reason we start by reserving + * few queues. + */ + num_txq = ice_determine_res(pf, pf->q_left_tx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + num_rxq = ice_determine_res(pf, pf->q_left_rx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + if (!num_txq || !num_rxq) + return -EIO; + + /* since AVF driver works with only queue pairs which means, it expects + * to have equal number of Rx and Tx queues, so take the minimum of + * available Tx or Rx queues + */ + pf->num_vf_qps = min_t(int, num_txq, num_rxq); + pf->num_vf_msix = num_msix; + + return 0; +} + +/** + * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset + * @vf: pointer to the VF structure + * + * Cleanup a VF after the hardware reset is finished. Expects the caller to + * have verified whether the reset is finished properly, and ensure the + * minimum amount of wait time has passed. Reallocate VF resources back to make + * VF state active + */ +static void ice_cleanup_and_realloc_vf(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + u32 reg; + + hw = &pf->hw; + + /* PF software completes the flow by notifying VF that reset flow is + * completed. This is done by enabling hardware by clearing the reset + * bit in the VPGEN_VFRTRIG reg and setting VFR_STATE in the VFGEN_RSTAT + * register to VFR completed (done at the end of this function) + * By doing this we allow HW to access VF memory at any point. If we + * did it any sooner, HW could access memory while it was being freed + * in ice_free_vf_res(), causing an IOMMU fault. + * + * On the other hand, this needs to be done ASAP, because the VF driver + * is waiting for this to happen and may report a timeout. It's + * harmless, but it gets logged into Guest OS kernel log, so best avoid + * it. + */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg &= ~VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + + /* reallocate VF resources to finish resetting the VSI state */ + if (!ice_alloc_vf_res(vf)) { + ice_ena_vf_mappings(vf); + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + vf->num_vlan = 0; + } + + /* Tell the VF driver the reset is done. This needs to be done only + * after VF has been fully initialized, because the VF driver may + * request resources immediately after setting this flag. + */ + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); +} + +/** + * ice_reset_all_vfs - reset all allocated VFs in one go + * @pf: pointer to the PF structure + * @is_vflr: true if VFLR was issued, false if not + * + * First, tell the hardware to reset each VF, then do all the waiting in one + * chunk, and finally finish restoring each VF after the wait. This is useful + * during PF routines which need to reset all VFs, as otherwise it must perform + * these resets in a serialized fashion. + * + * Returns true if any VFs were reset, and false otherwise. + */ +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) +{ + struct ice_hw *hw = &pf->hw; + int v, i; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!pf->num_alloc_vfs) + return false; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + /* Begin reset on all VFs at once */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_trigger_vf_reset(&pf->vf[v], is_vflr); + + /* Call Disable LAN Tx queue AQ call with VFR bit set and 0 + * queues to inform Firmware about VF reset. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_dis_vsi_txq(pf->vsi[0]->port_info, 0, NULL, NULL, + ICE_VF_RESET, v, NULL); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in + * sequence to make sure that it has completed. We'll keep track of + * the VFs using a simple iterator that increments once that VF has + * finished resetting. + */ + for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + usleep_range(10000, 20000); + + /* Check each VF in sequence */ + while (v < pf->num_alloc_vfs) { + struct ice_vf *vf = &pf->vf[v]; + u32 reg; + + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & VPGEN_VFRSTAT_VFRD_M)) + break; + + /* If the current VF has finished resetting, move on + * to the next VF in sequence. + */ + v++; + } + } + + /* Display a warning if at least one VF didn't manage to reset in + * time, but continue on with the operation. + */ + if (v < pf->num_alloc_vfs) + dev_warn(&pf->pdev->dev, "VF reset check timeout\n"); + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_free_vf_res(&pf->vf[v]); + + if (ice_check_avail_res(pf)) { + dev_err(&pf->pdev->dev, + "Cannot allocate VF resources, try with fewer number of VFs\n"); + return false; + } + + /* Finish the reset on each VF */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_cleanup_and_realloc_vf(&pf->vf[v]); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_reset_vf - Reset a particular VF + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Returns true if the VF is reset, false otherwise. + */ +static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw = &pf->hw; + bool rsd = false; + u32 reg; + int i; + + /* If the VFs have been disabled, this means something else is + * resetting the VF, so we shouldn't continue. + */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + ice_trigger_vf_reset(vf, is_vflr); + + if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET, + vf->vf_id); + ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]); + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + } else { + /* Call Disable LAN Tx queue AQ call even when queues are not + * enabled. This is needed for successful completiom of VFR + */ + ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0, + NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL); + } + + /* poll VPGEN_VFRSTAT reg to make sure + * that reset is complete + */ + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. + */ + usleep_range(10000, 20000); + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (reg & VPGEN_VFRSTAT_VFRD_M) { + rsd = true; + break; + } + } + + /* Display a warning if VF didn't manage to reset in time, but need to + * continue on with the operation. + */ + if (!rsd) + dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + vf->vf_id); + + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + ice_free_vf_res(vf); + + ice_cleanup_and_realloc_vf(vf); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_vc_notify_link_state - Inform all VFs on a PF of link status + * @pf: pointer to the PF structure + */ +void ice_vc_notify_link_state(struct ice_pf *pf) +{ + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++) + ice_vc_notify_vf_link_state(&pf->vf[i]); +} + +/** + * ice_vc_notify_reset - Send pending reset message to all VFs + * @pf: pointer to the PF structure + * + * indicate a pending reset to all VFs on a given PF + */ +void ice_vc_notify_reset(struct ice_pf *pf) +{ + struct virtchnl_pf_event pfe; + + if (!pf->num_alloc_vfs) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, ICE_SUCCESS, + (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); +} + +/** + * ice_vc_notify_vf_reset - Notify VF of a reset event + * @vf: pointer to the VF structure + */ +static void ice_vc_notify_vf_reset(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return; + + /* verify if the VF is in either init or active before proceeding */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, + (u8 *)&pfe, sizeof(pfe), NULL); +} + +/** + * ice_alloc_vfs - Allocate and set up VFs resources + * @pf: pointer to the PF structure + * @num_alloc_vfs: number of VFs to allocate + */ +static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vfs; + int i, ret; + + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ + wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx), + ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); + + ice_flush(hw); + + ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); + if (ret) { + pf->num_alloc_vfs = 0; + goto err_unroll_intr; + } + /* allocate memory */ + vfs = devm_kcalloc(&pf->pdev->dev, num_alloc_vfs, sizeof(*vfs), + GFP_KERNEL); + if (!vfs) { + ret = -ENOMEM; + goto err_unroll_sriov; + } + pf->vf = vfs; + + /* apply default profile */ + for (i = 0; i < num_alloc_vfs; i++) { + vfs[i].pf = pf; + vfs[i].vf_sw_id = pf->first_sw; + vfs[i].vf_id = i; + + /* assign default capabilities */ + set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); + vfs[i].spoofchk = true; + + /* Set this state so that PF driver does VF vector assignment */ + set_bit(ICE_VF_STATE_CFG_INTR, vfs[i].vf_states); + } + pf->num_alloc_vfs = num_alloc_vfs; + + /* VF resources get allocated during reset */ + if (!ice_reset_all_vfs(pf, false)) + goto err_unroll_sriov; + + goto err_unroll_intr; + +err_unroll_sriov: + pci_disable_sriov(pf->pdev); +err_unroll_intr: + /* rearm interrupts here */ + ice_irq_dynamic_ena(hw, NULL, NULL); + return ret; +} + +/** + * ice_pf_state_is_nominal - checks the pf for nominal state + * @pf: pointer to pf to check + * + * Check the PF's state for a collection of bits that would indicate + * the PF is in a state that would inhibit normal operation for + * driver functionality. + * + * Returns true if PF is in a nominal state. + * Returns false otherwise + */ +static bool ice_pf_state_is_nominal(struct ice_pf *pf) +{ + DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; + + if (!pf) + return false; + + bitmap_set(check_bits, 0, __ICE_STATE_NOMINAL_CHECK_BITS); + if (bitmap_intersects(pf->state, check_bits, __ICE_STATE_NBITS)) + return false; + + return true; +} + +/** + * ice_pci_sriov_ena - Enable or change number of VFs + * @pf: pointer to the PF structure + * @num_vfs: number of VFs to allocate + */ +static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs) +{ + int pre_existing_vfs = pci_num_vf(pf->pdev); + struct device *dev = &pf->pdev->dev; + int err; + + if (!ice_pf_state_is_nominal(pf)) { + dev_err(dev, "Cannot enable SR-IOV, device not ready\n"); + return -EBUSY; + } + + if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) { + dev_err(dev, "This device is not capable of SR-IOV\n"); + return -ENODEV; + } + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + ice_free_vfs(pf); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + return num_vfs; + + if (num_vfs > pf->num_vfs_supported) { + dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n", + num_vfs, pf->num_vfs_supported); + return -ENOTSUPP; + } + + dev_info(dev, "Allocating %d VFs\n", num_vfs); + err = ice_alloc_vfs(pf, num_vfs); + if (err) { + dev_err(dev, "Failed to enable SR-IOV: %d\n", err); + return err; + } + + set_bit(ICE_FLAG_SRIOV_ENA, pf->flags); + return num_vfs; +} + +/** + * ice_sriov_configure - Enable or change number of VFs via sysfs + * @pdev: pointer to a pci_dev structure + * @num_vfs: number of VFs to allocate + * + * This function is called when the user updates the number of VFs in sysfs. + */ +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + if (num_vfs) + return ice_pci_sriov_ena(pf, num_vfs); + + if (!pci_vfs_assigned(pdev)) { + ice_free_vfs(pf); + } else { + dev_err(&pf->pdev->dev, + "can't free VFs because some are assigned to VMs.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * ice_process_vflr_event - Free VF resources via IRQ calls + * @pf: pointer to the PF structure + * + * called from the VLFR IRQ handler to + * free up VF resources and state variables + */ +void ice_process_vflr_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int vf_id; + u32 reg; + + if (!test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + !pf->num_alloc_vfs) + return; + + /* Re-enable the VFLR interrupt cause here, before looking for which + * VF got reset. Otherwise, if another VF gets a reset while the + * first one is being processed, that interrupt will be lost, and + * that VF will be stuck in reset forever. + */ + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_VFLR_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); + + clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) { + struct ice_vf *vf = &pf->vf[vf_id]; + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + /* read GLGEN_VFLRSTAT register to find out the flr VFs */ + reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); + if (reg & BIT(bit_idx)) + /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + ice_reset_vf(vf, true); + } +} + +/** + * ice_vc_dis_vf - Disable a given VF via SW reset + * @vf: pointer to the VF info + * + * Disable the VF through a SW reset + */ +static void ice_vc_dis_vf(struct ice_vf *vf) +{ + ice_vc_notify_vf_reset(vf); + ice_reset_vf(vf, false); +} + +/** + * ice_vc_send_msg_to_vf - Send message to VF + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + */ +static int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + enum ice_status aq_ret; + struct ice_pf *pf; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return -EINVAL; + + pf = vf->pf; + + /* single place to detect unsuccessful return values */ + if (v_retval) { + vf->num_inval_msgs++; + dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", + vf->vf_id, v_opcode, v_retval); + if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { + dev_err(&pf->pdev->dev, + "Number of invalid messages exceeded for VF %d\n", + vf->vf_id); + dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + return -EIO; + } + } else { + vf->num_valid_msgs++; + /* reset the invalid counter, if a valid message is received. */ + vf->num_inval_msgs = 0; + } + + aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, + msg, msglen, NULL); + if (aq_ret) { + dev_info(&pf->pdev->dev, + "Unable to send the message to VF %d aq_err %d\n", + vf->vf_id, pf->hw.mailboxq.sq_last_status); + return -EIO; + } + + return 0; +} + +/** + * ice_vc_get_ver_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request the API version used by the PF + */ +static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_version_info info = { + VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR + }; + + vf->vf_ver = *(struct virtchnl_version_info *)msg; + /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */ + if (VF_IS_V10(&vf->vf_ver)) + info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, ICE_SUCCESS, + (u8 *)&info, + sizeof(struct virtchnl_version_info)); +} + +/** + * ice_vc_get_vf_res_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request its resources + */ +static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_resource *vfres = NULL; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_vf_resource); + + vfres = devm_kzalloc(&pf->pdev->dev, len, GFP_KERNEL); + if (!vfres) { + aq_ret = ICE_ERR_NO_MEMORY; + len = 0; + goto err; + } + if (VF_IS_V11(&vf->vf_ver)) + vf->driver_caps = *(u32 *)msg; + else + vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | + VIRTCHNL_VF_OFFLOAD_RSS_REG | + VIRTCHNL_VF_OFFLOAD_VLAN; + + vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi->info.pvid) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; + } else { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; + else + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; + } + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + + vfres->num_vsis = 1; + /* Tx and Rx queue are equal for VF */ + vfres->num_queue_pairs = vsi->num_txq; + vfres->max_vectors = pf->num_vf_msix; + vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; + vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + + vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; + vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; + ether_addr_copy(vfres->vsi_res[0].default_mac_addr, + vf->dflt_lan_addr.addr); + + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, aq_ret, + (u8 *)vfres, len); + + devm_kfree(&pf->pdev->dev, vfres); + return ret; +} + +/** + * ice_vc_reset_vf_msg + * @vf: pointer to the VF info + * + * called from the VF to reset itself, + * unlike other virtchnl messages, PF driver + * doesn't send the response back to the VF + */ +static void ice_vc_reset_vf_msg(struct ice_vf *vf) +{ + if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ice_reset_vf(vf, false); +} + +/** + * ice_find_vsi_from_id + * @pf: the pf structure to search for the VSI + * @id: id of the VSI it is searching for + * + * searches for the VSI with the given id + */ +static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id) +{ + int i; + + for (i = 0; i < pf->num_alloc_vsi; i++) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == id) + return pf->vsi[i]; + + return NULL; +} + +/** + * ice_vc_isvalid_vsi_id + * @vf: pointer to the VF info + * @vsi_id: VF relative VSI id + * + * check for the valid VSI id + */ +static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_find_vsi_from_id(pf, vsi_id); + + return (vsi && (vsi->vf_id == vf->vf_id)); +} + +/** + * ice_vc_isvalid_q_id + * @vf: pointer to the VF info + * @vsi_id: VSI id + * @qid: VSI relative queue id + * + * check for the valid queue id + */ +static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +{ + struct ice_vsi *vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + /* allocated Tx and Rx queues should be always equal for VF VSI */ + return (vsi && (qid < vsi->alloc_txq)); +} + +/** + * ice_vc_config_rss_key + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS key + */ +static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrk->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, vrk->key, NULL, 0); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, aq_ret, + NULL, 0); +} + +/** + * ice_vc_config_rss_lut + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS LUT + */ +static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, aq_ret, + NULL, 0); +} + +/** + * ice_vc_get_stats_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to get VSI stats + */ +static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_eth_stats stats; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + memset(&stats, 0, sizeof(struct ice_eth_stats)); + ice_update_eth_stats(vsi); + + stats = vsi->eth_stats; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, aq_ret, + (u8 *)&stats, sizeof(stats)); +} + +/** + * ice_vc_ena_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to enable all or specific queue(s) + */ +static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* Enable only Rx rings, Tx rings were enabled by the FW when the + * Tx queue group list was configured and the context bits were + * programmed using ice_vsi_cfg_txqs + */ + if (ice_vsi_start_rx_rings(vsi)) + aq_ret = ICE_ERR_PARAM; + + /* Set flag to indicate that queues are enabled */ + if (!aq_ret) + set_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_dis_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to disable all or specific + * queue(s) + */ +static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && + !test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop tx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + if (ice_vsi_stop_rx_rings(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop rx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + /* Clear enabled queues flag */ + if (!aq_ret) + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_irq_map_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the IRQ to queue map + */ +static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_irq_map_info *irqmap_info = + (struct virtchnl_irq_map_info *)msg; + u16 vsi_id, vsi_q_id, vector_id; + struct virtchnl_vector_map *map; + struct ice_vsi *vsi = NULL; + struct ice_pf *pf = vf->pf; + enum ice_status aq_ret = 0; + unsigned long qmap; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < irqmap_info->num_vectors; i++) { + map = &irqmap_info->vecmap[i]; + + vector_id = map->vector_id; + vsi_id = map->vsi_id; + /* validate msg params */ + if (!(vector_id < pf->hw.func_caps.common_cap + .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* lookout for the invalid queue index */ + qmap = map->rxq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_rx++; + q_vector->rx.itr_idx = map->rxitr_idx; + vsi->rx_rings[vsi_q_id]->q_vector = q_vector; + } + + qmap = map->txq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_tx++; + q_vector->tx.itr_idx = map->txitr_idx; + vsi->tx_rings[vsi_q_id]->q_vector = q_vector; + } + } + + if (vsi) + ice_vsi_cfg_msix(vsi); +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the Rx/Tx queues + */ +static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vsi_queue_config_info *qci = + (struct virtchnl_vsi_queue_config_info *)msg; + struct virtchnl_queue_pair_info *qpi; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, qci->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < qci->num_queue_pairs; i++) { + qpi = &qci->qpair[i]; + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != qpi->txq.queue_id || + !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + /* copy Tx queue info from VF into VSI */ + vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[i]->count = qpi->txq.ring_len; + /* copy Rx queue info from VF into vsi */ + vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; + vsi->rx_rings[i]->count = qpi->rxq.ring_len; + if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->rx_buf_len = qpi->rxq.databuffer_size; + if (qpi->rxq.max_pkt_size >= (16 * 1024) || + qpi->rxq.max_pkt_size < 64) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->max_frame = qpi->rxq.max_pkt_size; + } + + /* VF can request to configure less than allocated queues + * or default allocated queues. So update the VSI with new number + */ + vsi->num_txq = qci->num_queue_pairs; + vsi->num_rxq = qci->num_queue_pairs; + + if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi)) + aq_ret = 0; + else + aq_ret = ICE_ERR_PARAM; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_is_vf_trusted + * @vf: pointer to the VF info + */ +static bool ice_is_vf_trusted(struct ice_vf *vf) +{ + return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); +} + +/** + * ice_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool ice_can_vf_change_mac(struct ice_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !ice_is_vf_trusted(vf)) + return false; + + return true; +} + +/** + * ice_vc_handle_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @set: true if mac filters are being set, false otherwise + * + * add guest mac address filter + */ +static int +ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) +{ + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_pf *pf = vf->pf; + enum virtchnl_ops vc_op; + enum ice_status ret; + LIST_HEAD(mac_list); + struct ice_vsi *vsi; + int mac_count = 0; + int i; + + if (set) + vc_op = VIRTCHNL_OP_ADD_ETH_ADDR; + else + vc_op = VIRTCHNL_OP_DEL_ETH_ADDR; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (set && !ice_is_vf_trusted(vf) && + (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { + dev_err(&pf->pdev->dev, + "Can't add more MAC addresses, because VF is not trusted, switch the VF to trusted mode in order to add more functionalities\n"); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + + for (i = 0; i < al->num_elements; i++) { + u8 *maddr = al->list[i].addr; + + if (ether_addr_equal(maddr, vf->dflt_lan_addr.addr) || + is_broadcast_ether_addr(maddr)) { + if (set) { + /* VF is trying to add filters that the PF + * already added. Just continue. + */ + dev_info(&pf->pdev->dev, + "mac %pM already set for VF %d\n", + maddr, vf->vf_id); + continue; + } else { + /* VF can't remove dflt_lan_addr/bcast mac */ + dev_err(&pf->pdev->dev, + "can't remove mac %pM for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + } + + /* check for the invalid cases and bail if necessary */ + if (is_zero_ether_addr(maddr)) { + dev_err(&pf->pdev->dev, + "invalid mac %pM provided for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (is_unicast_ether_addr(maddr) && + !ice_can_vf_change_mac(vf)) { + dev_err(&pf->pdev->dev, + "can't change unicast mac for untrusted VF %d\n", + vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + /* get here if maddr is multicast or if VF can change mac */ + if (ice_add_mac_to_list(vsi, &mac_list, al->list[i].addr)) { + ret = ICE_ERR_NO_MEMORY; + goto handle_mac_exit; + } + mac_count++; + } + + /* program the updated filter list */ + if (set) + ret = ice_add_mac(&pf->hw, &mac_list); + else + ret = ice_remove_mac(&pf->hw, &mac_list); + + if (ret) { + dev_err(&pf->pdev->dev, + "can't update mac filters for VF %d, error %d\n", + vf->vf_id, ret); + } else { + if (set) + vf->num_mac += mac_count; + else + vf->num_mac -= mac_count; + } + +handle_mac_exit: + ice_free_fltr_list(&pf->pdev->dev, &mac_list); + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, vc_op, ret, NULL, 0); +} + +/** + * ice_vc_add_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * add guest MAC address filter + */ +static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, true); +} + +/** + * ice_vc_del_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove guest MAC address filter + */ +static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, false); +} + +/** + * ice_vc_request_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * VFs get a default number of queues but can use this message to request a + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queue pairs via virtchnl message response to VF. + */ +static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + int req_queues = vfres->num_queue_pairs; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + int tx_rx_queue_left; + int cur_queues; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + cur_queues = pf->num_vf_qps; + tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); + if (req_queues <= 0) { + dev_err(&pf->pdev->dev, + "VF %d tried to request %d queues. Ignoring.\n", + vf->vf_id, req_queues); + } else if (req_queues > ICE_MAX_QS_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d tried to request more than %d queues.\n", + vf->vf_id, ICE_MAX_QS_PER_VF); + vfres->num_queue_pairs = ICE_MAX_QS_PER_VF; + } else if (req_queues - cur_queues > tx_rx_queue_left) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but only %d left.\n", + vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); + vfres->num_queue_pairs = tx_rx_queue_left + cur_queues; + } else { + /* request is successful, then reset VF */ + vf->num_req_qs = req_queues; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, + "VF %d granted request of %d queues.\n", + vf->vf_id, req_queues); + return 0; + } + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, + aq_ret, (u8 *)vfres, sizeof(*vfres)); +} + +/** + * ice_set_vf_port_vlan + * @netdev: network interface device structure + * @vf_id: VF identifier + * @vlan_id: VLAN id being set + * @qos: priority setting + * @vlan_proto: VLAN protocol + * + * program VF Port VLAN id and/or qos + */ +int +ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) +{ + u16 vlanprio = vlan_id | (qos << ICE_VLAN_PRIORITY_S); + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct ice_vsi *vsi; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + if (vlan_id > ICE_MAX_VLANID || qos > 7) { + dev_err(&pf->pdev->dev, "Invalid VF Parameters\n"); + return -EINVAL; + } + + if (vlan_proto != htons(ETH_P_8021Q)) { + dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n"); + return -EPROTONOSUPPORT; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (le16_to_cpu(vsi->info.pvid) == vlanprio) { + /* duplicate request, so just return success */ + dev_info(&pf->pdev->dev, + "Duplicate pvid %d request\n", vlanprio); + return ret; + } + + /* If pvid, then remove all filters on the old VLAN */ + if (vsi->info.pvid) + ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) & + VLAN_VID_MASK)); + + if (vlan_id || qos) { + ret = ice_vsi_set_pvid(vsi, vlanprio); + if (ret) + goto error_set_pvid; + } else { + ice_vsi_kill_pvid(vsi); + } + + if (vlan_id) { + dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n", + vlan_id, qos, vf_id); + + /* add new VLAN filter for each MAC */ + ret = ice_vsi_add_vlan(vsi, vlan_id); + if (ret) + goto error_set_pvid; + } + + /* The Port VLAN needs to be saved across resets the same as the + * default LAN MAC address. + */ + vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + +error_set_pvid: + return ret; +} + +/** + * ice_vc_process_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @add_v: Add VLAN if true, otherwise delete VLAN + * + * Process virtchnl op to add or remove programmed guest VLAN id + */ +static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) +{ + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v && !ice_is_vf_trusted(vf) && + vf->num_vlan >= ICE_MAX_VLAN_PER_VF) { + dev_info(&pf->pdev->dev, + "VF is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n"); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < vfl->num_elements; i++) { + if (vfl->vlan_id[i] > ICE_MAX_VLANID) { + aq_ret = ICE_ERR_PARAM; + dev_err(&pf->pdev->dev, + "invalid VF VLAN id %d\n", vfl->vlan_id[i]); + goto error_param; + } + } + + vsi = ice_find_vsi_from_id(vf->pf, vfl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vsi->info.pvid) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_manage_vlan_stripping(vsi, add_v)) { + dev_err(&pf->pdev->dev, + "%sable VLAN stripping failed for VSI %i\n", + add_v ? "en" : "dis", vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v) { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + if (!ice_vsi_add_vlan(vsi, vid)) { + vf->num_vlan++; + set_bit(vid, vsi->active_vlans); + + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) + if (ice_cfg_vlan_pruning(vsi, true)) + aq_ret = ICE_ERR_PARAM; + } else { + aq_ret = ICE_ERR_PARAM; + } + } + } else { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + /* Make sure ice_vsi_kill_vlan is successful before + * updating VLAN information + */ + if (!ice_vsi_kill_vlan(vsi, vid)) { + vf->num_vlan--; + clear_bit(vid, vsi->active_vlans); + + /* Disable VLAN pruning when removing VLAN 0 */ + if (unlikely(!vid)) + ice_cfg_vlan_pruning(vsi, false); + } + } + } + +error_param: + /* send the response to the VF */ + if (add_v) + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, aq_ret, + NULL, 0); + else + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, aq_ret, + NULL, 0); +} + +/** + * ice_vc_add_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Add and program guest VLAN id + */ +static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, true); +} + +/** + * ice_vc_remove_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove programmed guest VLAN id + */ +static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, false); +} + +/** + * ice_vc_ena_vlan_stripping + * @vf: pointer to the VF info + * + * Enable VLAN header stripping for a given VF + */ +static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, true)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping + * @vf: pointer to the VF info + * + * Disable VLAN header stripping for a given VF + */ +static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, false)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_process_vf_msg - Process request from VF + * @pf: pointer to the PF structure + * @event: pointer to the AQ event + * + * called from the common asq/arq handler to + * process request from VF + */ +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 v_opcode = le32_to_cpu(event->desc.cookie_high); + s16 vf_id = le16_to_cpu(event->desc.retval); + u16 msglen = event->msg_len; + u8 *msg = event->msg_buf; + struct ice_vf *vf = NULL; + int err = 0; + + if (vf_id >= pf->num_alloc_vfs) { + err = -EINVAL; + goto error_handler; + } + + vf = &pf->vf[vf_id]; + + /* Check if VF is disabled. */ + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { + err = -EPERM; + goto error_handler; + } + + /* Perform basic checks on the msg */ + err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); + if (err) { + if (err == VIRTCHNL_ERR_PARAM) + err = -EPERM; + else + err = -EINVAL; + goto error_handler; + } + + /* Perform additional checks specific to RSS and Virtchnl */ + if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) { + struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) + err = -EINVAL; + } else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) { + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) + err = -EINVAL; + } + +error_handler: + if (err) { + ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_PARAM, NULL, 0); + dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", + vf_id, v_opcode, msglen, err); + return; + } + + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + err = ice_vc_get_ver_msg(vf, msg); + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + err = ice_vc_get_vf_res_msg(vf, msg); + break; + case VIRTCHNL_OP_RESET_VF: + ice_vc_reset_vf_msg(vf); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + err = ice_vc_add_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_ETH_ADDR: + err = ice_vc_del_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + err = ice_vc_cfg_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + err = ice_vc_ena_qs_msg(vf, msg); + ice_vc_notify_vf_link_state(vf); + break; + case VIRTCHNL_OP_DISABLE_QUEUES: + err = ice_vc_dis_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_REQUEST_QUEUES: + err = ice_vc_request_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + err = ice_vc_cfg_irq_map_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + err = ice_vc_config_rss_key(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + err = ice_vc_config_rss_lut(vf, msg); + break; + case VIRTCHNL_OP_GET_STATS: + err = ice_vc_get_stats_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_VLAN: + err = ice_vc_add_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN: + err = ice_vc_remove_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + err = ice_vc_ena_vlan_stripping(vf); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + err = ice_vc_dis_vlan_stripping(vf); + break; + case VIRTCHNL_OP_UNKNOWN: + default: + dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", + v_opcode, vf_id); + err = ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_NOT_IMPL, + NULL, 0); + break; + } + if (err) { + /* Helper function cares less about error return values here + * as it is busy with pending work. + */ + dev_info(&pf->pdev->dev, + "PF failed to honor VF %d, opcode %d\n, error %d\n", + vf_id, v_opcode, err); + } +} + +/** + * ice_get_vf_cfg + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ivi: VF configuration structure + * + * return VF configuration + */ +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + ivi->vf = vf_id; + ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr); + + /* VF configuration for VLAN and applicable QoS */ + ivi->vlan = le16_to_cpu(vsi->info.pvid) & ICE_VLAN_M; + ivi->qos = (le16_to_cpu(vsi->info.pvid) & ICE_PRIORITY_M) >> + ICE_VLAN_PRIORITY_S; + + ivi->trusted = vf->trusted; + ivi->spoofchk = vf->spoofchk; + if (!vf->link_forced) + ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + else + ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; + ivi->max_tx_rate = vf->tx_rate; + ivi->min_tx_rate = 0; + return 0; +} + +/** + * ice_set_vf_spoofchk + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ena: flag to enable or disable feature + * + * Enable or disable VF spoof checking + */ +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_ctx ctx = { 0 }; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int status; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (ena == vf->spoofchk) { + dev_dbg(&pf->pdev->dev, "VF spoofchk already %s\n", + ena ? "ON" : "OFF"); + return 0; + } + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (ena) { + ctx.info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + ctx.info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M; + } + + status = ice_update_vsi(&pf->hw, vsi->idx, &ctx, NULL); + if (status) { + dev_dbg(&pf->pdev->dev, + "Error %d, failed to update VSI* parameters\n", status); + return -EIO; + } + + vf->spoofchk = ena; + vsi->info.sec_flags = ctx.info.sec_flags; + vsi->info.sw_flags2 = ctx.info.sw_flags2; + + return status; +} + +/** + * ice_set_vf_mac + * @netdev: network interface device structure + * @vf_id: VF identifier + * @mac: mac address + * + * program VF mac address + */ +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { + netdev_err(netdev, "%pM not a valid unicast address\n", mac); + return -EINVAL; + } + + /* copy mac into dflt_lan_addr and trigger a VF reset. The reset + * flow will use the updated dflt_lan_addr and add a MAC filter + * using ice_add_mac. Also set pf_set_mac to indicate that the PF has + * set the MAC address for this VF. + */ + ether_addr_copy(vf->dflt_lan_addr.addr, mac); + vf->pf_set_mac = true; + netdev_info(netdev, + "mac on VF %d set to %pM\n. VF driver will be reinitialized\n", + vf_id, mac); + + ice_vc_dis_vf(vf); + return ret; +} + +/** + * ice_set_vf_trust + * @netdev: network interface device structure + * @vf_id: VF identifier + * @trusted: Boolean value to enable/disable trusted VF + * + * Enable or disable a given VF as trusted + */ +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + /* Check if already trusted */ + if (trusted == vf->trusted) + return 0; + + vf->trusted = trusted; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", + vf_id, trusted ? "" : "un"); + + return 0; +} + +/** + * ice_set_vf_link_state + * @netdev: network interface device structure + * @vf_id: VF identifier + * @link_state: required link state + * + * Set VF's link state, irrespective of physical link state status + */ +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_vf *vf; + struct ice_hw *hw; + + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + hw = &pf->hw; + ls = &pf->hw.port_info->phy.link_info; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "vf %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + switch (link_state) { + case IFLA_VF_LINK_STATE_AUTO: + vf->link_forced = false; + vf->link_up = ls->link_info & ICE_AQ_LINK_UP; + break; + case IFLA_VF_LINK_STATE_ENABLE: + vf->link_forced = true; + vf->link_up = true; + break; + case IFLA_VF_LINK_STATE_DISABLE: + vf->link_forced = true; + vf->link_up = false; + break; + default: + return -EINVAL; + } + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up); + + /* Notify the VF of its new link state */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h new file mode 100644 index 000000000000..10131e0180f9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -0,0 +1,173 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_PF_H_ +#define _ICE_VIRTCHNL_PF_H_ +#include "ice.h" + +#define ICE_MAX_VLANID 4095 +#define ICE_VLAN_PRIORITY_S 12 +#define ICE_VLAN_M 0xFFF +#define ICE_PRIORITY_M 0x7000 + +/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ +#define ICE_MAX_VLAN_PER_VF 8 +#define ICE_MAX_MACADDR_PER_VF 12 + +/* Malicious Driver Detection */ +#define ICE_DFLT_NUM_MDD_EVENTS_ALLOWED 3 +#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 + +/* Static VF transaction/status register def */ +#define VF_DEVICE_STATUS 0xAA +#define VF_TRANS_PENDING_M 0x20 + +/* Specific VF states */ +enum ice_vf_states { + ICE_VF_STATE_INIT = 0, + ICE_VF_STATE_ACTIVE, + ICE_VF_STATE_ENA, + ICE_VF_STATE_DIS, + ICE_VF_STATE_MC_PROMISC, + ICE_VF_STATE_UC_PROMISC, + /* state to indicate if PF needs to do vector assignment for VF. + * This needs to be set during first time VF initialization or later + * when VF asks for more Vectors through virtchnl OP. + */ + ICE_VF_STATE_CFG_INTR, + ICE_VF_STATES_NBITS +}; + +/* VF capabilities */ +enum ice_virtchnl_cap { + ICE_VIRTCHNL_VF_CAP_L2 = 0, + ICE_VIRTCHNL_VF_CAP_PRIVILEGE, +}; + +/* VF information structure */ +struct ice_vf { + struct ice_pf *pf; + + s16 vf_id; /* VF id in the PF space */ + u32 driver_caps; /* reported by VF driver */ + int first_vector_idx; /* first vector index of this VF */ + struct ice_sw *vf_sw_id; /* switch id the VF VSIs connect to */ + struct virtchnl_version_info vf_ver; + struct virtchnl_ether_addr dflt_lan_addr; + u16 port_vlan_id; + u8 pf_set_mac; /* VF MAC address set by VMM admin */ + u8 trusted; + u16 lan_vsi_idx; /* index into PF struct */ + u16 lan_vsi_num; /* ID as used by firmware */ + u64 num_mdd_events; /* number of mdd events detected */ + u64 num_inval_msgs; /* number of continuous invalid msgs */ + u64 num_valid_msgs; /* number of valid msgs detected */ + unsigned long vf_caps; /* vf's adv. capabilities */ + DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ + unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ + u8 link_forced; + u8 link_up; /* only valid if VF link is forced */ + u8 spoofchk; + u16 num_mac; + u16 num_vlan; + u8 num_req_qs; /* num of queue pairs requested by VF */ +}; + +#ifdef CONFIG_PCI_IOV +void ice_process_vflr_event(struct ice_pf *pf); +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi); + +void ice_free_vfs(struct ice_pf *pf); +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_vc_notify_link_state(struct ice_pf *pf); +void ice_vc_notify_reset(struct ice_pf *pf); +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); + +int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto); + +int ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); + +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); + +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); + +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); +#else /* CONFIG_PCI_IOV */ +#define ice_process_vflr_event(pf) do {} while (0) +#define ice_free_vfs(pf) do {} while (0) +#define ice_vc_process_vf_msg(pf, event) do {} while (0) +#define ice_vc_notify_link_state(pf) do {} while (0) +#define ice_vc_notify_reset(pf) do {} while (0) + +static inline bool +ice_reset_all_vfs(struct ice_pf __always_unused *pf, + bool __always_unused is_vflr) +{ + return true; +} + +static inline int +ice_sriov_configure(struct pci_dev __always_unused *pdev, + int __always_unused num_vfs) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_mac(struct net_device __always_unused *netdev, + int __always_unused vf_id, u8 __always_unused *mac) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_get_vf_cfg(struct net_device __always_unused *netdev, + int __always_unused vf_id, + struct ifla_vf_info __always_unused *ivi) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_trust(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused trusted) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_port_vlan(struct net_device __always_unused *netdev, + int __always_unused vf_id, u16 __always_unused vid, + u8 __always_unused qos, __be16 __always_unused v_proto) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_spoofchk(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused ena) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_link_state(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused link_state) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_bw(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused min_tx_rate, + int __always_unused max_tx_rate) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_VIRTCHNL_PF_H_ */ |