diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
58 files changed, 11069 insertions, 2183 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 817977e3039d..0679907980f7 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -43,9 +43,9 @@ ice-$(CONFIG_PCI_IOV) += \ ice_vf_mbx.o \ ice_vf_vsi_vlan_ops.o \ ice_vf_lib.o -ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o +ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice_dpll.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o -ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o +ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o ice-$(CONFIG_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4ba3d99439a0..351e0d36df44 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -76,6 +76,7 @@ #include "ice_vsi_vlan_ops.h" #include "ice_gnss.h" #include "ice_irq.h" +#include "ice_dpll.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -195,11 +196,16 @@ #define ice_pf_to_dev(pf) (&((pf)->pdev->dev)) +#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned) + enum ice_feature { ICE_F_DSCP, - ICE_F_PTP_EXTTS, + ICE_F_PHY_RCLK, ICE_F_SMA_CTRL, + ICE_F_CGU, ICE_F_GNSS, + ICE_F_ROCE_LAG, + ICE_F_SRIOV_LAG, ICE_F_MAX }; @@ -370,6 +376,7 @@ struct ice_vsi { u16 rx_buf_len; struct ice_aqc_vsi_props info; /* VSI properties */ + struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ /* VSI stats */ struct rtnl_link_stats64 net_stats; @@ -505,6 +512,7 @@ enum ice_pf_flags { ICE_FLAG_UNPLUG_AUX_DEV, ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ + ICE_FLAG_DPLL, /* SyncE/PTP dplls initialized */ ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -517,6 +525,7 @@ enum ice_misc_thread_tasks { struct ice_switchdev_info { struct ice_vsi *control_vsi; struct ice_vsi *uplink_vsi; + struct ice_esw_br_offloads *br_offloads; bool is_running; }; @@ -545,6 +554,8 @@ struct ice_pf { * MSIX vectors allowed on this PF. */ u16 sriov_base_vector; + unsigned long *sriov_irq_bm; /* bitmap to track irq usage */ + u16 sriov_irq_size; /* size of the irq_bm bitmap */ u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -567,6 +578,7 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ struct mutex adev_mutex; /* lock to protect aux device access */ + struct mutex lag_mutex; /* protect ice_lag struct in PF */ u32 msg_enable; struct ice_ptp ptp; struct gnss_serial *gnss_serial; @@ -626,6 +638,7 @@ struct ice_pf { struct ice_lag *lag; /* Link Aggregation information */ struct ice_switchdev_info switchdev; + struct ice_esw_br_port *br_port; #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 @@ -634,8 +647,11 @@ struct ice_pf { #define ICE_VF_AGG_NODE_ID_START 65 #define ICE_MAX_VF_AGG_NODES 32 struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; + struct ice_dplls dplls; }; +extern struct workqueue_struct *ice_lag_wq; + struct ice_netdev_priv { struct ice_vsi *vsi; struct ice_repr *repr; @@ -660,6 +676,18 @@ static inline bool ice_vector_ch_enabled(struct ice_q_vector *qv) } /** + * ice_ptp_pf_handles_tx_interrupt - Check if PF handles Tx interrupt + * @pf: Board private structure + * + * Return true if this PF should respond to the Tx timestamp interrupt + * indication in the miscellaneous OICR interrupt handler. + */ +static inline bool ice_ptp_pf_handles_tx_interrupt(struct ice_pf *pf) +{ + return pf->ptp.tx_interrupt_mode != ICE_PTP_TX_INTERRUPT_NONE; +} + +/** * ice_irq_dynamic_ena - Enable default interrupt generation settings * @hw: pointer to HW struct * @vsi: pointer to VSI struct, can be NULL @@ -853,7 +881,7 @@ static inline bool ice_is_adq_active(struct ice_pf *pf) return false; } -bool netif_is_ice(struct net_device *dev); +bool netif_is_ice(const struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); int ice_vsi_open_ctrl(struct ice_vsi *vsi); @@ -909,14 +937,32 @@ void ice_fdir_release_flows(struct ice_hw *hw); void ice_fdir_replay_flows(struct ice_hw *hw); void ice_fdir_replay_fltrs(struct ice_pf *pf); int ice_fdir_create_dflt_rules(struct ice_pf *pf); -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event); + +enum ice_aq_task_state { + ICE_AQ_TASK_NOT_PREPARED, + ICE_AQ_TASK_WAITING, + ICE_AQ_TASK_COMPLETE, + ICE_AQ_TASK_CANCELED, +}; + +struct ice_aq_task { + struct hlist_node entry; + struct ice_rq_event_info event; + enum ice_aq_task_state state; + u16 opcode; +}; + +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode); +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout); int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); +void ice_adv_lnk_speed_maps_init(void); /** * ice_set_rdma_cap - enable RDMA support diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 63d3e1dcbba5..d7fdb7ba7268 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -120,6 +120,9 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE 0x0076 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 +#define ICE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 +#define ICE_AQC_BIT_ROCEV2_LAG 0x01 +#define ICE_AQC_BIT_SRIOV_LAG 0x02 u8 major_ver; u8 minor_ver; @@ -232,6 +235,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) __le16 bad_frame_vsi; __le16 swid; +#define ICE_AQC_PORT_SWID_VALID BIT(15) +#define ICE_AQC_PORT_SWID_M 0xFF u8 reserved[10]; }; @@ -241,10 +246,12 @@ struct ice_aqc_set_port_params { * Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) * Get Allocated Resource Descriptors Command (indirect 0x020A) + * Share Resource command (indirect 0x020B) */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 #define ICE_AQC_RES_TYPE_RECIPE 0x05 +#define ICE_AQC_RES_TYPE_SWID 0x07 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -264,6 +271,7 @@ struct ice_aqc_set_port_params { /* Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) + * Share Resource command (indirect 0x020B) */ struct ice_aqc_alloc_free_res_cmd { __le16 num_entries; /* Number of Resource entries */ @@ -818,7 +826,11 @@ struct ice_aqc_txsched_move_grp_info_hdr { __le32 src_parent_teid; __le32 dest_parent_teid; __le16 num_elems; - __le16 reserved; + u8 mode; +#define ICE_AQC_MOVE_ELEM_MODE_SAME_PF 0x0 +#define ICE_AQC_MOVE_ELEM_MODE_GIVE_OWN 0x1 +#define ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN 0x2 + u8 reserved; }; struct ice_aqc_move_elem { @@ -1087,7 +1099,15 @@ struct ice_aqc_get_phy_caps { #define ICE_PHY_TYPE_HIGH_100G_CAUI2 BIT_ULL(2) #define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC BIT_ULL(3) #define ICE_PHY_TYPE_HIGH_100G_AUI2 BIT_ULL(4) -#define ICE_PHY_TYPE_HIGH_MAX_INDEX 4 +#define ICE_PHY_TYPE_HIGH_200G_CR4_PAM4 BIT_ULL(5) +#define ICE_PHY_TYPE_HIGH_200G_SR4 BIT_ULL(6) +#define ICE_PHY_TYPE_HIGH_200G_FR4 BIT_ULL(7) +#define ICE_PHY_TYPE_HIGH_200G_LR4 BIT_ULL(8) +#define ICE_PHY_TYPE_HIGH_200G_DR4 BIT_ULL(9) +#define ICE_PHY_TYPE_HIGH_200G_KR4_PAM4 BIT_ULL(10) +#define ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC BIT_ULL(11) +#define ICE_PHY_TYPE_HIGH_200G_AUI4 BIT_ULL(12) +#define ICE_PHY_TYPE_HIGH_MAX_INDEX 12 struct ice_aqc_get_phy_caps_data { __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ @@ -1307,11 +1327,41 @@ struct ice_aqc_get_link_status_data { #define ICE_AQ_LINK_SPEED_40GB BIT(8) #define ICE_AQ_LINK_SPEED_50GB BIT(9) #define ICE_AQ_LINK_SPEED_100GB BIT(10) +#define ICE_AQ_LINK_SPEED_200GB BIT(11) #define ICE_AQ_LINK_SPEED_UNKNOWN BIT(15) - __le32 reserved3; /* Aligns next field to 8-byte boundary */ - __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ - __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */ -}; + /* Aligns next field to 8-byte boundary */ + __le16 reserved3; + u8 ext_fec_status; + /* RS 272 FEC enabled */ +#define ICE_AQ_LINK_RS_272_FEC_EN BIT(0) + u8 reserved4; + /* Use values from ICE_PHY_TYPE_LOW_* */ + __le64 phy_type_low; + /* Use values from ICE_PHY_TYPE_HIGH_* */ + __le64 phy_type_high; +#define ICE_AQC_LS_DATA_SIZE_V1 \ + offsetofend(struct ice_aqc_get_link_status_data, phy_type_high) + /* Get link status v2 link partner data */ + __le64 lp_phy_type_low; + __le64 lp_phy_type_high; + u8 lp_fec_adv; +#define ICE_AQ_LINK_LP_10G_KR_FEC_CAP BIT(0) +#define ICE_AQ_LINK_LP_25G_KR_FEC_CAP BIT(1) +#define ICE_AQ_LINK_LP_RS_528_FEC_CAP BIT(2) +#define ICE_AQ_LINK_LP_50G_KR_272_FEC_CAP BIT(3) +#define ICE_AQ_LINK_LP_100G_KR_272_FEC_CAP BIT(4) +#define ICE_AQ_LINK_LP_200G_KR_272_FEC_CAP BIT(5) + u8 lp_fec_req; +#define ICE_AQ_LINK_LP_10G_KR_FEC_REQ BIT(0) +#define ICE_AQ_LINK_LP_25G_KR_FEC_REQ BIT(1) +#define ICE_AQ_LINK_LP_RS_528_FEC_REQ BIT(2) +#define ICE_AQ_LINK_LP_KR_272_FEC_REQ BIT(3) + u8 lp_flowcontrol; +#define ICE_AQ_LINK_LP_PAUSE_ADV BIT(0) +#define ICE_AQ_LINK_LP_ASM_DIR_ADV BIT(1) +#define ICE_AQC_LS_DATA_SIZE_V2 \ + offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol) +} __packed; /* Set event mask command (direct 0x0613) */ struct ice_aqc_set_event_mask { @@ -1339,6 +1389,30 @@ struct ice_aqc_set_mac_lb { u8 reserved[15]; }; +/* Set PHY recovered clock output (direct 0x0630) */ +struct ice_aqc_set_phy_rec_clk_out { + u8 phy_output; + u8 port_num; +#define ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT 0xFF + u8 flags; +#define ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN BIT(0) + u8 rsvd; + __le32 freq; + u8 rsvd2[6]; + __le16 node_handle; +}; + +/* Get PHY recovered clock output (direct 0x0631) */ +struct ice_aqc_get_phy_rec_clk_out { + u8 phy_output; + u8 port_num; +#define ICE_AQC_GET_PHY_REC_CLK_OUT_CURR_PORT 0xFF + u8 flags; +#define ICE_AQC_GET_PHY_REC_CLK_OUT_OUT_EN BIT(0) + u8 rsvd[11]; + __le16 node_handle; +}; + struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; @@ -1355,6 +1429,9 @@ struct ice_aqc_link_topo_params { #define ICE_AQC_LINK_TOPO_NODE_TYPE_CAGE 6 #define ICE_AQC_LINK_TOPO_NODE_TYPE_MEZZ 7 #define ICE_AQC_LINK_TOPO_NODE_TYPE_ID_EEPROM 8 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL 9 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_MUX 10 +#define ICE_AQC_LINK_TOPO_NODE_TYPE_GPS 11 #define ICE_AQC_LINK_TOPO_NODE_CTX_S 4 #define ICE_AQC_LINK_TOPO_NODE_CTX_M \ (0xF << ICE_AQC_LINK_TOPO_NODE_CTX_S) @@ -1391,7 +1468,13 @@ struct ice_aqc_link_topo_addr { struct ice_aqc_get_link_topo { struct ice_aqc_link_topo_addr addr; u8 node_part_num; -#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 0x24 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 0x25 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY 0x30 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_C827 0x31 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX 0x47 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS 0x48 u8 rsvd[9]; }; @@ -1781,11 +1864,10 @@ struct ice_aqc_lldp_filter_ctrl { u8 reserved2[12]; }; +#define ICE_AQC_RSS_VSI_VALID BIT(15) + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { -#define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_KEY_VSI_ID_S) __le16 vsi_id; u8 reserved[6]; __le32 addr_high; @@ -1803,35 +1885,33 @@ struct ice_aqc_get_set_rss_keys { u8 extended_hash_key[ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE]; }; -/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ -struct ice_aqc_get_set_rss_lut { -#define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) - __le16 vsi_id; -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) - -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL 2 +enum ice_lut_type { + ICE_LUT_VSI = 0, + ICE_LUT_PF = 1, + ICE_LUT_GLOBAL = 2, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S 2 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) +enum ice_lut_size { + ICE_LUT_VSI_SIZE = 64, + ICE_LUT_GLOBAL_SIZE = 512, + ICE_LUT_PF_SIZE = 2048, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128 128 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512 512 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K 2048 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG 2 +/* enum ice_aqc_lut_flags combines constants used to fill + * &ice_aqc_get_set_rss_lut ::flags, which is an amalgamation of global LUT ID, + * LUT size and LUT type, last of which does not need neither shift nor mask. + */ +enum ice_aqc_lut_flags { + ICE_AQC_LUT_SIZE_SMALL = 0, /* size = 64 or 128 */ + ICE_AQC_LUT_SIZE_512 = BIT(2), + ICE_AQC_LUT_SIZE_2K = BIT(3), -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S 4 -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M \ - (0xF << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) + ICE_AQC_LUT_GLOBAL_IDX = GENMASK(7, 4), +}; +/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ +struct ice_aqc_get_set_rss_lut { + __le16 vsi_id; __le16 flags; __le32 reserved; __le32 addr_high; @@ -1923,6 +2003,42 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Move/Reconfigure Tx queue (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs { + u8 cmd_type; +#define ICE_AQC_Q_CFG_MOVE_NODE 0x1 +#define ICE_AQC_Q_CFG_TC_CHNG 0x2 +#define ICE_AQC_Q_CFG_MOVE_TC_CHNG 0x3 +#define ICE_AQC_Q_CFG_SUBSEQ_CALL BIT(2) +#define ICE_AQC_Q_CFG_FLUSH BIT(3) + u8 num_qs; + u8 port_num_chng; +#define ICE_AQC_Q_CFG_SRC_PRT_M 0x7 +#define ICE_AQC_Q_CFG_DST_PRT_S 3 +#define ICE_AQC_Q_CFG_DST_PRT_M (0x7 << ICE_AQC_Q_CFG_DST_PRT_S) + u8 time_out; +#define ICE_AQC_Q_CFG_TIMEOUT_S 2 +#define ICE_AQC_Q_CFG_TIMEOUT_M (0x1F << ICE_AQC_Q_CFG_TIMEOUT_S) + __le32 blocked_cgds; + __le32 addr_high; + __le32 addr_low; +}; + +/* Per Q struct for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txq_perq { + __le16 q_handle; + u8 tc; + u8 rsvd; + __le32 q_teid; +}; + +/* The buffer for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs_buf { + __le32 src_parent_teid; + __le32 dst_parent_teid; + struct ice_aqc_cfg_txq_perq queue_info[]; +}; + /* Add Tx RDMA Queue Set (indirect 0x0C33) */ struct ice_aqc_add_rdma_qset { u8 num_qset_grps; @@ -2079,6 +2195,193 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +/* Get CGU abilities command response data structure (indirect 0x0C61) */ +struct ice_aqc_get_cgu_abilities { + u8 num_inputs; + u8 num_outputs; + u8 pps_dpll_idx; + u8 eec_dpll_idx; + __le32 max_in_freq; + __le32 max_in_phase_adj; + __le32 max_out_freq; + __le32 max_out_phase_adj; + u8 cgu_part_num; + u8 rsvd[3]; +}; + +/* Set CGU input config (direct 0x0C62) */ +struct ice_aqc_set_cgu_input_config { + u8 input_idx; + u8 flags1; +#define ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_FREQ BIT(6) +#define ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_DELAY BIT(7) + u8 flags2; +#define ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN BIT(5) +#define ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN BIT(6) + u8 rsvd; + __le32 freq; + __le32 phase_delay; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU input config response descriptor structure (direct 0x0C63) */ +struct ice_aqc_get_cgu_input_config { + u8 input_idx; + u8 status; +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_LOS BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_SCM_FAIL BIT(1) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_CFM_FAIL BIT(2) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_GST_FAIL BIT(3) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_PFM_FAIL BIT(4) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_FAIL BIT(6) +#define ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP BIT(7) + u8 type; +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_READ_ONLY BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_GPS BIT(4) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_EXTERNAL BIT(5) +#define ICE_AQC_GET_CGU_IN_CFG_TYPE_PHY BIT(6) + u8 flags1; +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_PHASE_DELAY_SUPP BIT(0) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_1PPS_SUPP BIT(2) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_10MHZ_SUPP BIT(3) +#define ICE_AQC_GET_CGU_IN_CFG_FLG1_ANYFREQ BIT(7) + __le32 freq; + __le32 phase_delay; + u8 flags2; +#define ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN BIT(5) +#define ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN BIT(6) + u8 rsvd[1]; + __le16 node_handle; +}; + +/* Set CGU output config (direct 0x0C64) */ +struct ice_aqc_set_cgu_output_config { + u8 output_idx; + u8 flags; +#define ICE_AQC_SET_CGU_OUT_CFG_OUT_EN BIT(0) +#define ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN BIT(1) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_FREQ BIT(2) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_PHASE BIT(3) +#define ICE_AQC_SET_CGU_OUT_CFG_UPDATE_SRC_SEL BIT(4) + u8 src_sel; +#define ICE_AQC_SET_CGU_OUT_CFG_DPLL_SRC_SEL ICE_M(0x1F, 0) + u8 rsvd; + __le32 freq; + __le32 phase_delay; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU output config (direct 0x0C65) */ +struct ice_aqc_get_cgu_output_config { + u8 output_idx; + u8 flags; +#define ICE_AQC_GET_CGU_OUT_CFG_OUT_EN BIT(0) +#define ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN BIT(1) +#define ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY BIT(2) + u8 src_sel; +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL_SHIFT 0 +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL \ + ICE_M(0x1F, ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL_SHIFT) +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE_SHIFT 5 +#define ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE \ + ICE_M(0x7, ICE_AQC_GET_CGU_OUT_CFG_DPLL_MODE_SHIFT) + u8 rsvd; + __le32 freq; + __le32 src_freq; + u8 rsvd2[2]; + __le16 node_handle; +}; + +/* Get CGU DPLL status (direct 0x0C66) */ +struct ice_aqc_get_cgu_dpll_status { + u8 dpll_num; + u8 ref_state; +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_LOS BIT(0) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_SCM BIT(1) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_CFM BIT(2) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_GST BIT(3) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_PFM BIT(4) +#define ICE_AQC_GET_CGU_DPLL_STATUS_FAST_LOCK_EN BIT(5) +#define ICE_AQC_GET_CGU_DPLL_STATUS_REF_SW_ESYNC BIT(6) + u8 dpll_state; +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_LOCK BIT(0) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO BIT(1) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO_READY BIT(2) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_FLHIT BIT(5) +#define ICE_AQC_GET_CGU_DPLL_STATUS_STATE_PSLHIT BIT(7) + u8 config; +#define ICE_AQC_GET_CGU_DPLL_CONFIG_CLK_REF_SEL ICE_M(0x1F, 0) +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT 5 +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE \ + ICE_M(0x7, ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT) +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_FREERUN 0 +#define ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_AUTOMATIC \ + ICE_M(0x3, ICE_AQC_GET_CGU_DPLL_CONFIG_MODE_SHIFT) + __le32 phase_offset_h; + __le32 phase_offset_l; + u8 eec_mode; +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_1 0xA +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_2 0xB +#define ICE_AQC_GET_CGU_DPLL_STATUS_EEC_MODE_UNKNOWN 0xF + u8 rsvd[1]; + __le16 node_handle; +}; + +/* Set CGU DPLL config (direct 0x0C67) */ +struct ice_aqc_set_cgu_dpll_config { + u8 dpll_num; + u8 ref_state; +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_LOS BIT(0) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_SCM BIT(1) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_CFM BIT(2) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_GST BIT(3) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_PFM BIT(4) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_FLOCK_EN BIT(5) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_REF_SW_ESYNC BIT(6) + u8 rsvd; + u8 config; +#define ICE_AQC_SET_CGU_DPLL_CONFIG_CLK_REF_SEL ICE_M(0x1F, 0) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT 5 +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE \ + ICE_M(0x7, ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT) +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_FREERUN 0 +#define ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_AUTOMATIC \ + ICE_M(0x3, ICE_AQC_SET_CGU_DPLL_CONFIG_MODE_SHIFT) + u8 rsvd2[8]; + u8 eec_mode; + u8 rsvd3[1]; + __le16 node_handle; +}; + +/* Set CGU reference priority (direct 0x0C68) */ +struct ice_aqc_set_cgu_ref_prio { + u8 dpll_num; + u8 ref_idx; + u8 ref_priority; + u8 rsvd[11]; + __le16 node_handle; +}; + +/* Get CGU reference priority (direct 0x0C69) */ +struct ice_aqc_get_cgu_ref_prio { + u8 dpll_num; + u8 ref_idx; + u8 ref_priority; /* Valid only in response */ + u8 rsvd[13]; +}; + +/* Get CGU info (direct 0x0C6A) */ +struct ice_aqc_get_cgu_info { + __le32 cgu_id; + __le32 cgu_cfg_ver; + __le32 cgu_fw_ver; + u8 node_part_num; + u8 dev_rev; + __le16 node_handle; +}; + /* Driver Shared Parameters (direct, 0x0C90) */ struct ice_aqc_driver_shared_params { u8 set_or_get_op; @@ -2093,16 +2396,6 @@ struct ice_aqc_driver_shared_params { __le32 addr_low; }; -enum ice_aqc_driver_params { - /* OS clock index for PTP timer Domain 0 */ - ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0 = 0, - /* OS clock index for PTP timer Domain 1 */ - ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1, - - /* Add new parameters above */ - ICE_AQC_DRIVER_PARAM_MAX = 16, -}; - /* Lan Queue Overflow Event (direct, 0x1001) */ struct ice_aqc_event_lan_overflow { __le32 prtdcb_ruptq; @@ -2148,6 +2441,8 @@ struct ice_aq_desc { struct ice_aqc_get_phy_caps get_phy; struct ice_aqc_set_phy_cfg set_phy; struct ice_aqc_restart_an restart_an; + struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out; + struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out; struct ice_aqc_gpio read_write_gpio; struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; @@ -2181,12 +2476,22 @@ struct ice_aq_desc { struct ice_aqc_neigh_dev_req neigh_dev; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_cfg_txqs cfg_txqs; struct ice_aqc_add_rdma_qset add_rdma_qset; 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_download_pkg download_pkg; + struct ice_aqc_set_cgu_input_config set_cgu_input_config; + struct ice_aqc_get_cgu_input_config get_cgu_input_config; + struct ice_aqc_set_cgu_output_config set_cgu_output_config; + struct ice_aqc_get_cgu_output_config get_cgu_output_config; + struct ice_aqc_get_cgu_dpll_status get_cgu_dpll_status; + struct ice_aqc_set_cgu_dpll_config set_cgu_dpll_config; + struct ice_aqc_set_cgu_ref_prio set_cgu_ref_prio; + struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio; + struct ice_aqc_get_cgu_info get_cgu_info; struct ice_aqc_driver_shared_params drv_shared_params; struct ice_aqc_set_mac_lb set_mac_lb; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; @@ -2263,6 +2568,7 @@ enum ice_adminq_opc { /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_share_res = 0x020B, ice_aqc_opc_set_vlan_mode_parameters = 0x020C, ice_aqc_opc_get_vlan_mode_parameters = 0x020D, @@ -2310,6 +2616,8 @@ enum ice_adminq_opc { ice_aqc_opc_get_link_status = 0x0607, ice_aqc_opc_set_event_mask = 0x0613, ice_aqc_opc_set_mac_lb = 0x0620, + ice_aqc_opc_set_phy_rec_clk_out = 0x0630, + ice_aqc_opc_get_phy_rec_clk_out = 0x0631, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_read_i2c = 0x06E2, ice_aqc_opc_write_i2c = 0x06E3, @@ -2356,6 +2664,7 @@ enum ice_adminq_opc { /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_cfg_txqs = 0x0C32, ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ @@ -2364,6 +2673,18 @@ enum ice_adminq_opc { ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, + /* 1588/SyncE commands/events */ + ice_aqc_opc_get_cgu_abilities = 0x0C61, + ice_aqc_opc_set_cgu_input_config = 0x0C62, + ice_aqc_opc_get_cgu_input_config = 0x0C63, + ice_aqc_opc_set_cgu_output_config = 0x0C64, + ice_aqc_opc_get_cgu_output_config = 0x0C65, + ice_aqc_opc_get_cgu_dpll_status = 0x0C66, + ice_aqc_opc_set_cgu_dpll_config = 0x0C67, + ice_aqc_opc_set_cgu_ref_prio = 0x0C68, + ice_aqc_opc_get_cgu_ref_prio = 0x0C69, + ice_aqc_opc_get_cgu_info = 0x0C6A, + ice_aqc_opc_driver_shared_params = 0x0C90, /* Standalone Commands/Events */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 074bf9403cd1..7fa43827a3f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -408,7 +408,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) */ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { - int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; u32 rxdid = ICE_RXDID_FLEX_NIC; struct ice_rlan_ctx rlan_ctx; @@ -473,17 +472,11 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ rlan_ctx.showiv = 0; - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - if (ring->xsk_pool) - chain_len = 1; /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ rlan_ctx.rxmax = min_t(u32, vsi->max_frame, - chain_len * ring->rx_buf_len); + ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e16d4c83ed5f..9a6c25f98632 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #include "ice_common.h" #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" +#include "ice_ptp_hw.h" #define ICE_PF_RESET_WAIT_COUNT 300 +#define ICE_MAX_NETLIST_SIZE 10 static const char * const ice_link_mode_str_low[] = { [0] = "100BASE_TX", @@ -152,6 +154,12 @@ static int ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E823L_SFP: hw->mac_type = ICE_MAC_GENERIC; break; + case ICE_DEV_ID_E830_BACKPLANE: + case ICE_DEV_ID_E830_QSFP56: + case ICE_DEV_ID_E830_SFP: + case ICE_DEV_ID_E830_SFP_DD: + hw->mac_type = ICE_MAC_E830; + break; default: hw->mac_type = ICE_MAC_UNKNOWN; break; @@ -435,6 +443,80 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type, } /** + * ice_aq_get_netlist_node + * @hw: pointer to the hw struct + * @cmd: get_link_topo AQ structure + * @node_part_number: output node part number if node found + * @node_handle: output node handle parameter if node found + * + * Get netlist node handle. + */ +int +ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + desc.params.get_link_topo = *cmd; + + if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL)) + return -EINTR; + + if (node_handle) + *node_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + if (node_part_number) + *node_part_number = desc.params.get_link_topo.node_part_num; + + return 0; +} + +/** + * ice_find_netlist_node + * @hw: pointer to the hw struct + * @node_type_ctx: type of netlist node to look for + * @node_part_number: node part number to look for + * @node_handle: output parameter if node found - optional + * + * Scan the netlist for a node handle of the given node type and part number. + * + * If node_handle is non-NULL it will be modified on function exit. It is only + * valid if the function returns zero, and should be ignored on any non-zero + * return value. + * + * Returns: 0 if the node is found, -ENOENT if no handle was found, and + * a negative error code on failure to access the AQ. + */ +static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx, + u8 node_part_number, u16 *node_handle) +{ + u8 idx; + + for (idx = 0; idx < ICE_MAX_NETLIST_SIZE; idx++) { + struct ice_aqc_get_link_topo cmd = {}; + u8 rec_node_part_number; + int status; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, + node_type_ctx); + cmd.addr.topo_params.index = idx; + + status = ice_aq_get_netlist_node(hw, &cmd, + &rec_node_part_number, + node_handle); + if (status) + return status; + + if (rec_node_part_number == node_part_number) + return 0; + } + + return -ENOENT; +} + +/** * ice_is_media_cage_present * @pi: port information structure * @@ -570,6 +652,24 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi) } /** + * ice_get_link_status_datalen + * @hw: pointer to the HW struct + * + * Returns datalength for the Get Link Status AQ command, which is bigger for + * newer adapter families handled by ice driver. + */ +static u16 ice_get_link_status_datalen(struct ice_hw *hw) +{ + switch (hw->mac_type) { + case ICE_MAC_E830: + return ICE_AQC_LS_DATA_SIZE_V2; + case ICE_MAC_E810: + default: + return ICE_AQC_LS_DATA_SIZE_V1; + } +} + +/** * ice_aq_get_link_info * @pi: port information structure * @ena_lse: enable/disable LinkStatusEvent reporting @@ -607,8 +707,8 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, resp->cmd_flags = cpu_to_le16(cmd_flags); resp->lport_num = pi->lport; - status = ice_aq_send_cmd(hw, &desc, &link_data, sizeof(link_data), cd); - + status = ice_aq_send_cmd(hw, &desc, &link_data, + ice_get_link_status_datalen(hw), cd); if (status) return status; @@ -683,8 +783,7 @@ static void ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw, struct ice_aqc_set_mac_cfg *cmd) { - u16 fc_thres_val, tx_timer_val; - u32 val; + u32 val, fc_thres_m; /* We read back the transmit timer and FC threshold value of * LFC. Thus, we will use index = @@ -693,19 +792,32 @@ ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw, * Also, because we are operating on transmit timer and FC * threshold of LFC, we don't turn on any bit in tx_tmr_priority */ -#define IDX_OF_LFC PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX - - /* Retrieve the transmit timer */ - val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(IDX_OF_LFC)); - tx_timer_val = val & - PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M; - cmd->tx_tmr_value = cpu_to_le16(tx_timer_val); - - /* Retrieve the FC threshold */ - val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(IDX_OF_LFC)); - fc_thres_val = val & PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M; - - cmd->fc_refresh_threshold = cpu_to_le16(fc_thres_val); +#define E800_IDX_OF_LFC E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX +#define E800_REFRESH_TMR E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR + + if (hw->mac_type == ICE_MAC_E830) { + /* Retrieve the transmit timer */ + val = rd32(hw, E830_PRTMAC_CL01_PS_QNT); + cmd->tx_tmr_value = + le16_encode_bits(val, E830_PRTMAC_CL01_PS_QNT_CL0_M); + + /* Retrieve the fc threshold */ + val = rd32(hw, E830_PRTMAC_CL01_QNT_THR); + fc_thres_m = E830_PRTMAC_CL01_QNT_THR_CL0_M; + } else { + /* Retrieve the transmit timer */ + val = rd32(hw, + E800_PRTMAC_HSEC_CTL_TX_PS_QNT(E800_IDX_OF_LFC)); + cmd->tx_tmr_value = + le16_encode_bits(val, + E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M); + + /* Retrieve the fc threshold */ + val = rd32(hw, + E800_REFRESH_TMR(E800_IDX_OF_LFC)); + fc_thres_m = E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M; + } + cmd->fc_refresh_threshold = le16_encode_bits(val, fc_thres_m); } /** @@ -1999,37 +2111,31 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /** * ice_aq_alloc_free_res - command to allocate/free resources * @hw: pointer to the HW struct - * @num_entries: number of resource entries in buffer * @buf: Indirect buffer to hold data parameters and response * @buf_size: size of buffer for indirect commands * @opc: pass in the command opcode - * @cd: pointer to command details structure or NULL * * Helper function to allocate/free resources using the admin queue commands */ -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd) +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc) { struct ice_aqc_alloc_free_res_cmd *cmd; struct ice_aq_desc desc; cmd = &desc.params.sw_res_ctrl; - if (!buf) - return -EINVAL; - - if (buf_size < flex_array_size(buf, elem, num_entries)) + if (!buf || buf_size < flex_array_size(buf, elem, 1)) return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - cmd->num_entries = cpu_to_le16(num_entries); + cmd->num_entries = cpu_to_le16(1); - return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + return ice_aq_send_cmd(hw, &desc, buf, buf_size, NULL); } /** @@ -2059,8 +2165,7 @@ ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res) if (btm) buf->res_type |= cpu_to_le16(ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) goto ice_alloc_res_exit; @@ -2094,8 +2199,7 @@ int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) buf->res_type = cpu_to_le16(type); memcpy(buf->elem, res, sizeof(*buf->elem) * num); - status = ice_aq_alloc_free_res(hw, num, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "CQ CMD Buffer:\n"); @@ -2241,6 +2345,14 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, "%s: reset_restrict_support = %d\n", prefix, caps->reset_restrict_support); break; + case ICE_AQC_CAPS_FW_LAG_SUPPORT: + caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n", + prefix, caps->roce_lag); + caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", + prefix, caps->sriov_lag); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2388,16 +2500,21 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, static void ice_parse_fdir_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p) { - u32 reg_val, val; + u32 reg_val, gsize, bsize; reg_val = rd32(hw, GLQF_FD_SIZE); - val = (reg_val & GLQF_FD_SIZE_FD_GSIZE_M) >> - GLQF_FD_SIZE_FD_GSIZE_S; - func_p->fd_fltr_guar = - ice_get_num_per_func(hw, val); - val = (reg_val & GLQF_FD_SIZE_FD_BSIZE_M) >> - GLQF_FD_SIZE_FD_BSIZE_S; - func_p->fd_fltr_best_effort = val; + switch (hw->mac_type) { + case ICE_MAC_E830: + gsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_GSIZE_M, reg_val); + bsize = FIELD_GET(E830_GLQF_FD_SIZE_FD_BSIZE_M, reg_val); + break; + case ICE_MAC_E810: + default: + gsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_GSIZE_M, reg_val); + bsize = FIELD_GET(E800_GLQF_FD_SIZE_FD_BSIZE_M, reg_val); + } + func_p->fd_fltr_guar = ice_get_num_per_func(hw, gsize); + func_p->fd_fltr_best_effort = bsize; ice_debug(hw, ICE_DBG_INIT, "func caps: fd_fltr_guar = %d\n", func_p->fd_fltr_guar); @@ -2654,6 +2771,116 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct + */ +bool ice_is_pf_c827(struct ice_hw *hw) +{ + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; + + if (hw->mac_type != ICE_MAC_E810) + return false; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) + return true; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return false; + + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) + return true; + + return false; +} + +/** + * ice_is_phy_rclk_in_netlist + * @hw: pointer to the hw struct + * + * Check if the PHY Recovered Clock device is present in the netlist + */ +bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_C827, NULL) && + ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY, NULL)) + return false; + + return true; +} + +/** + * ice_is_clock_mux_in_netlist + * @hw: pointer to the hw struct + * + * Check if the Clock Multiplexer device is present in the netlist + */ +bool ice_is_clock_mux_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_MUX, + ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX, + NULL)) + return false; + + return true; +} + +/** + * ice_is_cgu_in_netlist - check for CGU presence + * @hw: pointer to the hw struct + * + * Check if the Clock Generation Unit (CGU) device is present in the netlist. + * Save the CGU part number in the hw structure for later use. + * Return: + * * true - cgu is present + * * false - cgu is not present + */ +bool ice_is_cgu_in_netlist(struct ice_hw *hw) +{ + if (!ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032, + NULL)) { + hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032; + return true; + } else if (!ice_find_netlist_node(hw, + ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL, + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384, + NULL)) { + hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384; + return true; + } + + return false; +} + +/** + * ice_is_gps_in_netlist + * @hw: pointer to the hw struct + * + * Check if the GPS generic device is present in the netlist + */ +bool ice_is_gps_in_netlist(struct ice_hw *hw) +{ + if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_GPS, + ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS, NULL)) + return false; + + return true; +} + +/** * ice_aq_list_caps - query function/device capabilities * @hw: pointer to the HW struct * @buf: a buffer to hold the capabilities @@ -3869,6 +4096,34 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, return status; } +static enum ice_lut_size ice_lut_type_to_size(enum ice_lut_type type) +{ + switch (type) { + case ICE_LUT_VSI: + return ICE_LUT_VSI_SIZE; + case ICE_LUT_GLOBAL: + return ICE_LUT_GLOBAL_SIZE; + case ICE_LUT_PF: + return ICE_LUT_PF_SIZE; + } + WARN_ONCE(1, "incorrect type passed"); + return ICE_LUT_VSI_SIZE; +} + +static enum ice_aqc_lut_flags ice_lut_size_to_flag(enum ice_lut_size size) +{ + switch (size) { + case ICE_LUT_VSI_SIZE: + return ICE_AQC_LUT_SIZE_SMALL; + case ICE_LUT_GLOBAL_SIZE: + return ICE_AQC_LUT_SIZE_512; + case ICE_LUT_PF_SIZE: + return ICE_AQC_LUT_SIZE_2K; + } + WARN_ONCE(1, "incorrect size passed"); + return 0; +} + /** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure @@ -3878,95 +4133,44 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, * Internal function to get (0x0B05) or set (0x0B03) RSS look up table */ static int -__ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set) -{ - u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle; - struct ice_aqc_get_set_rss_lut *cmd_resp; +__ice_aq_get_set_rss_lut(struct ice_hw *hw, + struct ice_aq_get_set_rss_lut_params *params, bool set) +{ + u16 opcode, vsi_id, vsi_handle = params->vsi_handle, glob_lut_idx = 0; + enum ice_lut_type lut_type = params->lut_type; + struct ice_aqc_get_set_rss_lut *desc_params; + enum ice_aqc_lut_flags flags; + enum ice_lut_size lut_size; struct ice_aq_desc desc; - int status; - u8 *lut; - - if (!params) - return -EINVAL; + u8 *lut = params->lut; - vsi_handle = params->vsi_handle; - lut = params->lut; - if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + if (!lut || !ice_is_vsi_valid(hw, vsi_handle)) return -EINVAL; - lut_size = params->lut_size; - lut_type = params->lut_type; - glob_lut_idx = params->global_lut_id; - vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - - cmd_resp = &desc.params.get_set_rss_lut; + lut_size = ice_lut_type_to_size(lut_type); + if (lut_size > params->lut_size) + return -EINVAL; + else if (set && lut_size != params->lut_size) + return -EINVAL; - if (set) { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_lut); + opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut; + ice_fill_dflt_direct_cmd_desc(&desc, opcode); + if (set) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - } else { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_lut); - } - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_LUT_VSI_ID_S) & - ICE_AQC_GSET_RSS_LUT_VSI_ID_M) | - ICE_AQC_GSET_RSS_LUT_VSI_VALID); - - switch (lut_type) { - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL: - flags |= ((lut_type << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M); - break; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } + desc_params = &desc.params.get_set_rss_lut; + vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL) { - flags |= ((glob_lut_idx << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) & - ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M); + if (lut_type == ICE_LUT_GLOBAL) + glob_lut_idx = FIELD_PREP(ICE_AQC_LUT_GLOBAL_IDX, + params->global_lut_id); - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else { - goto ice_aq_get_set_rss_lut_send; - } + flags = lut_type | glob_lut_idx | ice_lut_size_to_flag(lut_size); + desc_params->flags = cpu_to_le16(flags); - /* LUT size is only valid for Global and PF table types */ - switch (lut_size) { - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128: - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512: - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K: - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - } - fallthrough; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } - -ice_aq_get_set_rss_lut_send: - cmd_resp->flags = cpu_to_le16(flags); - status = ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); - -ice_aq_get_set_rss_lut_exit: - return status; + return ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); } /** @@ -4008,12 +4212,10 @@ static int __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, struct ice_aqc_get_set_rss_keys *key, bool set) { - struct ice_aqc_get_set_rss_key *cmd_resp; + struct ice_aqc_get_set_rss_key *desc_params; u16 key_size = sizeof(*key); struct ice_aq_desc desc; - cmd_resp = &desc.params.get_set_rss_key; - if (set) { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); @@ -4021,10 +4223,8 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key); } - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_KEY_VSI_ID_S) & - ICE_AQC_GSET_RSS_KEY_VSI_ID_M) | - ICE_AQC_GSET_RSS_KEY_VSI_VALID); + desc_params = &desc.params.get_set_rss_key; + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); return ice_aq_send_cmd(hw, &desc, key, key_size, NULL); } @@ -4222,6 +4422,53 @@ do_aq: } /** + * ice_aq_cfg_lan_txq + * @hw: pointer to the hardware structure + * @buf: buffer for command + * @buf_size: size of buffer in bytes + * @num_qs: number of queues being configured + * @oldport: origination lport + * @newport: destination lport + * @cd: pointer to command details structure or NULL + * + * Move/Configure LAN Tx queue (0x0C32) + * + * There is a better AQ command to use for moving nodes, so only coding + * this one for configuring the node. + */ +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd) +{ + struct ice_aqc_cfg_txqs *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.cfg_txqs; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (!buf) + return -EINVAL; + + cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG; + cmd->num_qs = num_qs; + cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M); + cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) & + ICE_AQC_Q_CFG_DST_PRT_M; + cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) & + ICE_AQC_Q_CFG_TIMEOUT_M; + cmd->blocked_cgds = 0; + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + ice_debug(hw, ICE_DBG_SCHED, "Failed to reconfigure nodes %d\n", + hw->adminq.sq_last_status); + return status; +} + +/** * ice_aq_add_rdma_qsets * @hw: pointer to the hardware structure * @num_qset_grps: Number of RDMA Qset groups @@ -4644,11 +4891,11 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { - struct ice_aqc_dis_txq_item *qg_list; + DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + u16 i, buf_size = __struct_size(qg_list); struct ice_q_ctx *q_ctx; int status = -ENOENT; struct ice_hw *hw; - u16 i, buf_size; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return -EIO; @@ -4666,11 +4913,6 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, return -EIO; } - buf_size = struct_size(qg_list, q_id, 1); - qg_list = kzalloc(buf_size, GFP_KERNEL); - if (!qg_list) - return -ENOMEM; - mutex_lock(&pi->sched_lock); for (i = 0; i < num_queues; i++) { @@ -4700,9 +4942,9 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, break; ice_free_sched_node(pi, node); q_ctx->q_handle = ICE_INVAL_Q_HANDLE; + q_ctx->q_teid = ICE_INVAL_TEID; } mutex_unlock(&pi->sched_lock); - kfree(qg_list); return status; } @@ -4871,10 +5113,10 @@ int ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, u16 *q_id) { - struct ice_aqc_dis_txq_item *qg_list; + DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + u16 qg_size = __struct_size(qg_list); struct ice_hw *hw; int status = 0; - u16 qg_size; int i; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) @@ -4882,11 +5124,6 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, hw = pi->hw; - qg_size = struct_size(qg_list, q_id, 1); - qg_list = kzalloc(qg_size, GFP_KERNEL); - if (!qg_list) - return -ENOMEM; - mutex_lock(&pi->sched_lock); for (i = 0; i < count; i++) { @@ -4911,7 +5148,395 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, } mutex_unlock(&pi->sched_lock); - kfree(qg_list); + return status; +} + +/** + * ice_aq_get_cgu_abilities - get cgu abilities + * @hw: pointer to the HW struct + * @abilities: CGU abilities + * + * Get CGU abilities (0x0C61) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_abilities(struct ice_hw *hw, + struct ice_aqc_get_cgu_abilities *abilities) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_abilities); + return ice_aq_send_cmd(hw, &desc, abilities, sizeof(*abilities), NULL); +} + +/** + * ice_aq_set_input_pin_cfg - set input pin config + * @hw: pointer to the HW struct + * @input_idx: Input index + * @flags1: Input flags + * @flags2: Input flags + * @freq: Frequency in Hz + * @phase_delay: Delay in ps + * + * Set CGU input config (0x0C62) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2, + u32 freq, s32 phase_delay) +{ + struct ice_aqc_set_cgu_input_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_input_config); + cmd = &desc.params.set_cgu_input_config; + cmd->input_idx = input_idx; + cmd->flags1 = flags1; + cmd->flags2 = flags2; + cmd->freq = cpu_to_le32(freq); + cmd->phase_delay = cpu_to_le32(phase_delay); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_input_pin_cfg - get input pin config + * @hw: pointer to the HW struct + * @input_idx: Input index + * @status: Pin status + * @type: Pin type + * @flags1: Input flags + * @flags2: Input flags + * @freq: Frequency in Hz + * @phase_delay: Delay in ps + * + * Get CGU input config (0x0C63) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type, + u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay) +{ + struct ice_aqc_get_cgu_input_config *cmd; + struct ice_aq_desc desc; + int ret; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_config); + cmd = &desc.params.get_cgu_input_config; + cmd->input_idx = input_idx; + + ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!ret) { + if (status) + *status = cmd->status; + if (type) + *type = cmd->type; + if (flags1) + *flags1 = cmd->flags1; + if (flags2) + *flags2 = cmd->flags2; + if (freq) + *freq = le32_to_cpu(cmd->freq); + if (phase_delay) + *phase_delay = le32_to_cpu(cmd->phase_delay); + } + + return ret; +} + +/** + * ice_aq_set_output_pin_cfg - set output pin config + * @hw: pointer to the HW struct + * @output_idx: Output index + * @flags: Output flags + * @src_sel: Index of DPLL block + * @freq: Output frequency + * @phase_delay: Output phase compensation + * + * Set CGU output config (0x0C64) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags, + u8 src_sel, u32 freq, s32 phase_delay) +{ + struct ice_aqc_set_cgu_output_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_output_config); + cmd = &desc.params.set_cgu_output_config; + cmd->output_idx = output_idx; + cmd->flags = flags; + cmd->src_sel = src_sel; + cmd->freq = cpu_to_le32(freq); + cmd->phase_delay = cpu_to_le32(phase_delay); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_output_pin_cfg - get output pin config + * @hw: pointer to the HW struct + * @output_idx: Output index + * @flags: Output flags + * @src_sel: Internal DPLL source + * @freq: Output frequency + * @src_freq: Source frequency + * + * Get CGU output config (0x0C65) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags, + u8 *src_sel, u32 *freq, u32 *src_freq) +{ + struct ice_aqc_get_cgu_output_config *cmd; + struct ice_aq_desc desc; + int ret; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_output_config); + cmd = &desc.params.get_cgu_output_config; + cmd->output_idx = output_idx; + + ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!ret) { + if (flags) + *flags = cmd->flags; + if (src_sel) + *src_sel = cmd->src_sel; + if (freq) + *freq = le32_to_cpu(cmd->freq); + if (src_freq) + *src_freq = le32_to_cpu(cmd->src_freq); + } + + return ret; +} + +/** + * ice_aq_get_cgu_dpll_status - get dpll status + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_state: Reference clock state + * @config: current DPLL config + * @dpll_state: current DPLL state + * @phase_offset: Phase offset in ns + * @eec_mode: EEC_mode + * + * Get CGU DPLL status (0x0C66) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, + u8 *dpll_state, u8 *config, s64 *phase_offset, + u8 *eec_mode) +{ + struct ice_aqc_get_cgu_dpll_status *cmd; + const s64 nsec_per_psec = 1000LL; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_dpll_status); + cmd = &desc.params.get_cgu_dpll_status; + cmd->dpll_num = dpll_num; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *ref_state = cmd->ref_state; + *dpll_state = cmd->dpll_state; + *config = cmd->config; + *phase_offset = le32_to_cpu(cmd->phase_offset_h); + *phase_offset <<= 32; + *phase_offset += le32_to_cpu(cmd->phase_offset_l); + *phase_offset = div64_s64(sign_extend64(*phase_offset, 47), + nsec_per_psec); + *eec_mode = cmd->eec_mode; + } + + return status; +} + +/** + * ice_aq_set_cgu_dpll_config - set dpll config + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_state: Reference clock state + * @config: DPLL config + * @eec_mode: EEC mode + * + * Set CGU DPLL config (0x0C67) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state, + u8 config, u8 eec_mode) +{ + struct ice_aqc_set_cgu_dpll_config *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_dpll_config); + cmd = &desc.params.set_cgu_dpll_config; + cmd->dpll_num = dpll_num; + cmd->ref_state = ref_state; + cmd->config = config; + cmd->eec_mode = eec_mode; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_set_cgu_ref_prio - set input reference priority + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_idx: Reference pin index + * @ref_priority: Reference input priority + * + * Set CGU reference priority (0x0C68) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 ref_priority) +{ + struct ice_aqc_set_cgu_ref_prio *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_ref_prio); + cmd = &desc.params.set_cgu_ref_prio; + cmd->dpll_num = dpll_num; + cmd->ref_idx = ref_idx; + cmd->ref_priority = ref_priority; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_get_cgu_ref_prio - get input reference priority + * @hw: pointer to the HW struct + * @dpll_num: DPLL index + * @ref_idx: Reference pin index + * @ref_prio: Reference input priority + * + * Get CGU reference priority (0x0C69) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 *ref_prio) +{ + struct ice_aqc_get_cgu_ref_prio *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_ref_prio); + cmd = &desc.params.get_cgu_ref_prio; + cmd->dpll_num = dpll_num; + cmd->ref_idx = ref_idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) + *ref_prio = cmd->ref_priority; + + return status; +} + +/** + * ice_aq_get_cgu_info - get cgu info + * @hw: pointer to the HW struct + * @cgu_id: CGU ID + * @cgu_cfg_ver: CGU config version + * @cgu_fw_ver: CGU firmware version + * + * Get CGU info (0x0C6A) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver, + u32 *cgu_fw_ver) +{ + struct ice_aqc_get_cgu_info *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_info); + cmd = &desc.params.get_cgu_info; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *cgu_id = le32_to_cpu(cmd->cgu_id); + *cgu_cfg_ver = le32_to_cpu(cmd->cgu_cfg_ver); + *cgu_fw_ver = le32_to_cpu(cmd->cgu_fw_ver); + } + + return status; +} + +/** + * ice_aq_set_phy_rec_clk_out - set RCLK phy out + * @hw: pointer to the HW struct + * @phy_output: PHY reference clock output pin + * @enable: GPIO state to be applied + * @freq: PHY output frequency + * + * Set phy recovered clock as reference (0x0630) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable, + u32 *freq) +{ + struct ice_aqc_set_phy_rec_clk_out *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_rec_clk_out); + cmd = &desc.params.set_phy_rec_clk_out; + cmd->phy_output = phy_output; + cmd->port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT; + cmd->flags = enable & ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN; + cmd->freq = cpu_to_le32(*freq); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) + *freq = le32_to_cpu(cmd->freq); + + return status; +} + +/** + * ice_aq_get_phy_rec_clk_out - get phy recovered signal info + * @hw: pointer to the HW struct + * @phy_output: PHY reference clock output pin + * @port_num: Port number + * @flags: PHY flags + * @node_handle: PHY output frequency + * + * Get PHY recovered clock output info (0x0631) + * Return: 0 on success or negative value on failure. + */ +int +ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, + u8 *flags, u16 *node_handle) +{ + struct ice_aqc_get_phy_rec_clk_out *cmd; + struct ice_aq_desc desc; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_rec_clk_out); + cmd = &desc.params.get_phy_rec_clk_out; + cmd->phy_output = *phy_output; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!status) { + *phy_output = cmd->phy_output; + if (port_num) + *port_num = cmd->port_num; + if (flags) + *flags = cmd->flags; + if (node_handle) + *node_handle = le16_to_cpu(cmd->node_handle); + } + return status; } @@ -5185,81 +5810,6 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, } /** - * ice_aq_set_driver_param - Set driver parameter to share via firmware - * @hw: pointer to the HW struct - * @idx: parameter index to set - * @value: the value to set the parameter to - * @cd: pointer to command details structure or NULL - * - * Set the value of one of the software defined parameters. All PFs connected - * to this device can read the value using ice_aq_get_driver_param. - * - * Note that firmware provides no synchronization or locking, and will not - * save the parameter value during a device reset. It is expected that - * a single PF will write the parameter value, while all other PFs will only - * read it. - */ -int -ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 value, struct ice_sq_cd *cd) -{ - struct ice_aqc_driver_shared_params *cmd; - struct ice_aq_desc desc; - - if (idx >= ICE_AQC_DRIVER_PARAM_MAX) - return -EIO; - - cmd = &desc.params.drv_shared_params; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); - - cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_SET; - cmd->param_indx = idx; - cmd->param_val = cpu_to_le32(value); - - return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); -} - -/** - * ice_aq_get_driver_param - Get driver parameter shared via firmware - * @hw: pointer to the HW struct - * @idx: parameter index to set - * @value: storage to return the shared parameter - * @cd: pointer to command details structure or NULL - * - * Get the value of one of the software defined parameters. - * - * Note that firmware provides no synchronization or locking. It is expected - * that only a single PF will write a given parameter. - */ -int -ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 *value, struct ice_sq_cd *cd) -{ - struct ice_aqc_driver_shared_params *cmd; - struct ice_aq_desc desc; - int status; - - if (idx >= ICE_AQC_DRIVER_PARAM_MAX) - return -EIO; - - cmd = &desc.params.drv_shared_params; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); - - cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_GET; - cmd->param_indx = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); - if (status) - return status; - - *value = le32_to_cpu(cmd->param_val); - - return 0; -} - -/** * ice_aq_set_gpio * @hw: pointer to the hw struct * @gpio_ctrl_handle: GPIO controller node handle @@ -5560,6 +6110,7 @@ static const u32 ice_aq_to_link_speed[] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ + SPEED_200000, }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 81961a7d6598..31fdcac33986 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -38,10 +38,9 @@ int ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res); int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res); -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd); +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc); bool ice_is_sbq_supported(struct ice_hw *hw); struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw); int @@ -93,6 +92,14 @@ int 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); +bool ice_is_pf_c827(struct ice_hw *hw); +bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw); +bool ice_is_clock_mux_in_netlist(struct ice_hw *hw); +bool ice_is_cgu_in_netlist(struct ice_hw *hw); +bool ice_is_gps_in_netlist(struct ice_hw *hw); +int +ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle); int ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd); @@ -186,12 +193,54 @@ int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd); int 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); struct ice_q_ctx * ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle); int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in); +int +ice_aq_get_cgu_abilities(struct ice_hw *hw, + struct ice_aqc_get_cgu_abilities *abilities); +int +ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2, + u32 freq, s32 phase_delay); +int +ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type, + u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay); +int +ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags, + u8 src_sel, u32 freq, s32 phase_delay); +int +ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags, + u8 *src_sel, u32 *freq, u32 *src_freq); +int +ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, + u8 *dpll_state, u8 *config, s64 *phase_offset, + u8 *eec_mode); +int +ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state, + u8 config, u8 eec_mode); +int +ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 ref_priority); +int +ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx, + u8 *ref_prio); +int +ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver, + u32 *cgu_fw_ver); + +int +ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable, + u32 *freq); +int +ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num, + u8 *flags, u16 *node_handle); void ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); @@ -204,12 +253,6 @@ int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); int -ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 value, struct ice_sq_cd *cd); -int -ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, - u32 *value, struct ice_sq_cd *cd); -int ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, struct ice_sq_cd *cd); int diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 3eb01731e496..e1fbc6de452d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -70,6 +70,11 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); @@ -170,6 +175,11 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + qos_cfg = &pf->hw.port_info->qos_cfg; /* DSCP configuration is not DCBx negotiated */ @@ -261,6 +271,11 @@ static int ice_dcbnl_setpfc(struct net_device *netdev, struct ieee_pfc *pfc) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; @@ -323,6 +338,11 @@ static void ice_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio, u8 set) if (prio >= ICE_MAX_USER_PRIORITY) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->pfc.pfccap = pf->hw.func_caps.common_cap.maxtc; @@ -379,6 +399,11 @@ static u8 ice_dcbnl_setstate(struct net_device *netdev, u8 state) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + /* Nothing to do */ if (!!state == test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return ICE_DCB_NO_HW_CHG; @@ -451,6 +476,11 @@ ice_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, if (tc >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; /* prio_type, bwg_id and bw_pct per UP are not supported */ @@ -505,6 +535,11 @@ ice_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, u8 bw_pct) if (pgid >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->etscfg.tcbwtable[pgid] = bw_pct; @@ -725,6 +760,11 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + max_tc = pf->hw.func_caps.common_cap.maxtc; if (app->priority >= max_tc) { netdev_err(netdev, "TC %d out of range, max TC %d\n", @@ -836,6 +876,11 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -937,6 +982,11 @@ static u8 ice_dcbnl_cee_set_all(struct net_device *netdev) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index d71ed210f9c4..8b7504a9df31 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -30,7 +30,7 @@ static const struct ice_tunnel_type_scan tnls[] = { * Verifies various attributes of the package file, including length, format * version, and the requirement of at least one segment. */ -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) { u32 seg_count; u32 i; @@ -118,7 +118,7 @@ static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) * * This helper function validates a buffer's header. */ -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) { struct ice_buf_hdr *hdr; u16 section_count; @@ -1153,23 +1153,168 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) } /** - * ice_dwnld_cfg_bufs + * ice_aq_download_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer to transfer + * @buf_size: the size of the package buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Download Package (0x0C40) + */ +static int +ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + int status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == -EIO) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * ice_get_pkg_seg_by_idx + * @pkg_hdr: pointer to the package header to be searched + * @idx: index of segment + */ +static struct ice_generic_seg_hdr * +ice_get_pkg_seg_by_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx) +{ + if (idx < le32_to_cpu(pkg_hdr->seg_count)) + return (struct ice_generic_seg_hdr *) + ((u8 *)pkg_hdr + + le32_to_cpu(pkg_hdr->seg_offset[idx])); + + return NULL; +} + +/** + * ice_is_signing_seg_at_idx - determine if segment is a signing segment + * @pkg_hdr: pointer to package header + * @idx: segment index + */ +static bool ice_is_signing_seg_at_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx) +{ + struct ice_generic_seg_hdr *seg; + + seg = ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) + return false; + + return le32_to_cpu(seg->seg_type) == SEGMENT_TYPE_SIGNING; +} + +/** + * ice_is_signing_seg_type_at_idx + * @pkg_hdr: pointer to package header + * @idx: segment index + * @seg_id: segment id that is expected + * @sign_type: signing type + * + * Determine if a segment is a signing segment of the correct type + */ +static bool +ice_is_signing_seg_type_at_idx(struct ice_pkg_hdr *pkg_hdr, u32 idx, + u32 seg_id, u32 sign_type) +{ + struct ice_sign_seg *seg; + + if (!ice_is_signing_seg_at_idx(pkg_hdr, idx)) + return false; + + seg = (struct ice_sign_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + + if (seg && le32_to_cpu(seg->seg_id) == seg_id && + le32_to_cpu(seg->sign_type) == sign_type) + return true; + + return false; +} + +/** + * ice_is_buffer_metadata - determine if package buffer is a metadata buffer + * @buf: pointer to buffer header + */ +static bool ice_is_buffer_metadata(struct ice_buf_hdr *buf) +{ + if (le32_to_cpu(buf->section_entry[0].type) & ICE_METADATA_BUF) + return true; + + return false; +} + +/** + * ice_is_last_download_buffer + * @buf: pointer to current buffer header + * @idx: index of the buffer in the current sequence + * @count: the buffer count in the current sequence + * + * Note: this routine should only be called if the buffer is not the last buffer + */ +static bool +ice_is_last_download_buffer(struct ice_buf_hdr *buf, u32 idx, u32 count) +{ + struct ice_buf *next_buf; + + if ((idx + 1) == count) + return true; + + /* A set metadata flag in the next buffer will signal that the current + * buffer will be the last buffer downloaded + */ + next_buf = ((struct ice_buf *)buf) + 1; + + return ice_is_buffer_metadata((struct ice_buf_hdr *)next_buf); +} + +/** + * ice_dwnld_cfg_bufs_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers - * @count: the number of buffers in the array + * @start: buffer index of first buffer to download + * @count: the number of buffers to download + * @indicate_last: if true, then set last buffer flag on last buffer download * - * Obtains global config lock and downloads the package configuration buffers - * to the firmware. Metadata buffers are skipped, and the first metadata buffer - * found indicates that the rest of the buffers are all metadata buffers. + * Downloads package configuration buffers to the firmware. Metadata buffers + * are skipped, and the first metadata buffer found indicates that the rest + * of the buffers are all metadata buffers. */ -static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, - struct ice_buf *bufs, u32 count) +static enum ice_ddp_state +ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, + u32 count, bool indicate_last) { enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; struct ice_buf_hdr *bh; enum ice_aq_err err; u32 offset, info, i; - int status; if (!bufs || !count) return ICE_DDP_PKG_ERR; @@ -1178,43 +1323,25 @@ static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, * then there are no buffers to be downloaded, and the operation is * considered a success. */ - bh = (struct ice_buf_hdr *)bufs; + bh = (struct ice_buf_hdr *)(bufs + start); if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) return ICE_DDP_PKG_SUCCESS; - status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); - if (status) { - if (status == -EALREADY) - return ICE_DDP_PKG_ALREADY_LOADED; - return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); - } - for (i = 0; i < count; i++) { - bool last = ((i + 1) == count); - - if (!last) { - /* check next buffer for metadata flag */ - bh = (struct ice_buf_hdr *)(bufs + i + 1); + bool last = false; + int status; - /* A set metadata flag in the next buffer will signal - * that the current buffer will be the last buffer - * downloaded - */ - if (le16_to_cpu(bh->section_count)) - if (le32_to_cpu(bh->section_entry[0].type) & - ICE_METADATA_BUF) - last = true; - } + bh = (struct ice_buf_hdr *)(bufs + start + i); - bh = (struct ice_buf_hdr *)(bufs + i); + if (indicate_last) + last = ice_is_last_download_buffer(bh, i, count); status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, &offset, &info, NULL); /* Save AQ status from download package */ if (status) { - ice_debug(hw, ICE_DBG_PKG, - "Pkg download failed: err %d off %d inf %d\n", + ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n", status, offset, info); err = hw->adminq.sq_last_status; state = ice_map_aq_err_to_ddp_state(err); @@ -1225,50 +1352,231 @@ static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, break; } - if (!status) { - status = ice_set_vlan_mode(hw); - if (status) - ice_debug(hw, ICE_DBG_PKG, - "Failed to set VLAN mode: err %d\n", status); + return state; +} + +/** + * ice_download_pkg_sig_seg - download a signature segment + * @hw: pointer to the hardware structure + * @seg: pointer to signature segment + */ +static enum ice_ddp_state +ice_download_pkg_sig_seg(struct ice_hw *hw, struct ice_sign_seg *seg) +{ + return ice_dwnld_cfg_bufs_no_lock(hw, seg->buf_tbl.buf_array, 0, + le32_to_cpu(seg->buf_tbl.buf_count), + false); +} + +/** + * ice_download_pkg_config_seg - download a config segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @idx: segment index + * @start: starting buffer + * @count: buffer count + * + * Note: idx must reference a ICE segment + */ +static enum ice_ddp_state +ice_download_pkg_config_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + u32 idx, u32 start, u32 count) +{ + struct ice_buf_table *bufs; + struct ice_seg *seg; + u32 buf_count; + + seg = (struct ice_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) + return ICE_DDP_PKG_ERR; + + bufs = ice_find_buf_table(seg); + buf_count = le32_to_cpu(bufs->buf_count); + + if (start >= buf_count || start + count > buf_count) + return ICE_DDP_PKG_ERR; + + return ice_dwnld_cfg_bufs_no_lock(hw, bufs->buf_array, start, count, + true); +} + +/** + * ice_dwnld_sign_and_cfg_segs - download a signing segment and config segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * @idx: segment index (must be a signature segment) + * + * Note: idx must reference a signature segment + */ +static enum ice_ddp_state +ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + u32 idx) +{ + enum ice_ddp_state state; + struct ice_sign_seg *seg; + u32 conf_idx; + u32 start; + u32 count; + + seg = (struct ice_sign_seg *)ice_get_pkg_seg_by_idx(pkg_hdr, idx); + if (!seg) { + state = ICE_DDP_PKG_ERR; + goto exit; } + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); + count = le32_to_cpu(seg->signed_buf_count); + + state = ice_download_pkg_sig_seg(hw, seg); + if (state) + goto exit; + + state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, + count); + +exit: + return state; +} + +/** + * ice_match_signing_seg - determine if a matching signing segment exists + * @pkg_hdr: pointer to package header + * @seg_id: segment id that is expected + * @sign_type: signing type + */ +static bool +ice_match_signing_seg(struct ice_pkg_hdr *pkg_hdr, u32 seg_id, u32 sign_type) +{ + u32 i; + + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + if (ice_is_signing_seg_type_at_idx(pkg_hdr, i, seg_id, + sign_type)) + return true; + } + + return false; +} + +/** + * ice_post_dwnld_pkg_actions - perform post download package actions + * @hw: pointer to the hardware structure + */ +static enum ice_ddp_state +ice_post_dwnld_pkg_actions(struct ice_hw *hw) +{ + int status; + + status = ice_set_vlan_mode(hw); + if (status) { + ice_debug(hw, ICE_DBG_PKG, "Failed to set VLAN mode: err %d\n", + status); + return ICE_DDP_PKG_ERR; + } + + return ICE_DDP_PKG_SUCCESS; +} + +/** + * ice_download_pkg_with_sig_seg + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to package header + * + * Handles the download of a complete package. + */ +static enum ice_ddp_state +ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +{ + enum ice_aq_err aq_err = hw->adminq.sq_last_status; + enum ice_ddp_state state = ICE_DDP_PKG_ERR; + int status; + u32 i; + + ice_debug(hw, ICE_DBG_INIT, "Segment ID %d\n", hw->pkg_seg_id); + ice_debug(hw, ICE_DBG_INIT, "Signature type %d\n", hw->pkg_sign_type); + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + state = ICE_DDP_PKG_ALREADY_LOADED; + else + state = ice_map_aq_err_to_ddp_state(aq_err); + return state; + } + + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + if (!ice_is_signing_seg_type_at_idx(pkg_hdr, i, hw->pkg_seg_id, + hw->pkg_sign_type)) + continue; + + state = ice_dwnld_sign_and_cfg_segs(hw, pkg_hdr, i); + if (state) + break; + } + + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + ice_release_global_cfg_lock(hw); return state; } /** - * ice_aq_get_pkg_info_list + * ice_dwnld_cfg_bufs * @hw: pointer to the hardware structure - * @pkg_info: the buffer which will receive the information list - * @buf_size: the size of the pkg_info information buffer - * @cd: pointer to command details structure or NULL + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array * - * Get Package Info List (0x0C43) + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. */ -static int ice_aq_get_pkg_info_list(struct ice_hw *hw, - struct ice_aqc_get_pkg_info_resp *pkg_info, - u16 buf_size, struct ice_sq_cd *cd) +static enum ice_ddp_state +ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - struct ice_aq_desc desc; + enum ice_ddp_state state; + struct ice_buf_hdr *bh; + int status; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); + if (!bufs || !count) + return ICE_DDP_PKG_ERR; - return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return ICE_DDP_PKG_SUCCESS; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); + } + + state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true); + if (!state) + state = ice_post_dwnld_pkg_actions(hw); + + ice_release_global_cfg_lock(hw); + + return state; } /** - * ice_download_pkg + * ice_download_pkg_without_sig_seg * @hw: pointer to the hardware structure * @ice_seg: pointer to the segment of the package to be downloaded * - * Handles the download of a complete package. + * Handles the download of a complete package without signature segment. */ -static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, - struct ice_seg *ice_seg) +static enum ice_ddp_state +ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg) { struct ice_buf_table *ice_buf_tbl; - int status; ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", ice_seg->hdr.seg_format_ver.major, @@ -1285,79 +1593,52 @@ static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", le32_to_cpu(ice_buf_tbl->buf_count)); - status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, - le32_to_cpu(ice_buf_tbl->buf_count)); - - ice_post_pkg_dwnld_vlan_mode_cfg(hw); - - return status; + return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); } /** - * ice_aq_download_pkg + * ice_download_pkg * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer to transfer - * @buf_size: the size of the package buffer - * @last_buf: last buffer indicator - * @error_offset: returns error offset - * @error_info: returns error information - * @cd: pointer to command details structure or NULL + * @pkg_hdr: pointer to package header + * @ice_seg: pointer to the segment of the package to be downloaded * - * Download Package (0x0C40) + * Handles the download of a complete package. */ -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd) +static enum ice_ddp_state +ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, + struct ice_seg *ice_seg) { - struct ice_aqc_download_pkg *cmd; - struct ice_aq_desc desc; - int status; - - if (error_offset) - *error_offset = 0; - if (error_info) - *error_info = 0; - - cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - if (last_buf) - cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + enum ice_ddp_state state; - status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == -EIO) { - /* Read error from buffer only when the FW returned an error */ - struct ice_aqc_download_pkg_resp *resp; + if (hw->pkg_has_signing_seg) + state = ice_download_pkg_with_sig_seg(hw, pkg_hdr); + else + state = ice_download_pkg_without_sig_seg(hw, ice_seg); - resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } + ice_post_pkg_dwnld_vlan_mode_cfg(hw); - return status; + return state; } /** - * ice_aq_upload_section + * ice_aq_get_pkg_info_list * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer which will receive the section - * @buf_size: the size of the package buffer + * @pkg_info: the buffer which will receive the information list + * @buf_size: the size of the pkg_info information buffer * @cd: pointer to command details structure or NULL * - * Upload Section (0x0C41) + * Get Package Info List (0x0C43) */ -int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, struct ice_sq_cd *cd) +static int ice_aq_get_pkg_info_list(struct ice_hw *hw, + struct ice_aqc_get_pkg_info_resp *pkg_info, + u16 buf_size, struct ice_sq_cd *cd) { struct ice_aq_desc desc; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); - return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); } /** @@ -1408,6 +1689,26 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, } /** + * ice_aq_upload_section + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer which will receive the section + * @buf_size: the size of the package buffer + * @cd: pointer to command details structure or NULL + * + * Upload Section (0x0C41) + */ +int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); +} + +/** * ice_update_pkg_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers @@ -1470,8 +1771,9 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * success it returns a pointer to the segment header, otherwise it will * return NULL. */ -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr) +static struct ice_generic_seg_hdr * +ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr) { u32 i; @@ -1496,6 +1798,73 @@ struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, } /** + * ice_has_signing_seg - determine if package has a signing segment + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to the driver's package hdr + */ +static bool ice_has_signing_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +{ + struct ice_generic_seg_hdr *seg_hdr; + + seg_hdr = (struct ice_generic_seg_hdr *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_SIGNING, pkg_hdr); + + return seg_hdr ? true : false; +} + +/** + * ice_get_pkg_segment_id - get correct package segment id, based on device + * @mac_type: MAC type of the device + */ +static u32 ice_get_pkg_segment_id(enum ice_mac_type mac_type) +{ + u32 seg_id; + + switch (mac_type) { + case ICE_MAC_E830: + seg_id = SEGMENT_TYPE_ICE_E830; + break; + case ICE_MAC_GENERIC: + default: + seg_id = SEGMENT_TYPE_ICE_E810; + break; + } + + return seg_id; +} + +/** + * ice_get_pkg_sign_type - get package segment sign type, based on device + * @mac_type: MAC type of the device + */ +static u32 ice_get_pkg_sign_type(enum ice_mac_type mac_type) +{ + u32 sign_type; + + switch (mac_type) { + case ICE_MAC_E830: + sign_type = SEGMENT_SIGN_TYPE_RSA3K_SBB; + break; + case ICE_MAC_GENERIC: + default: + sign_type = SEGMENT_SIGN_TYPE_RSA2K; + break; + } + + return sign_type; +} + +/** + * ice_get_signing_req - get correct package requirements, based on device + * @hw: pointer to the hardware structure + */ +static void ice_get_signing_req(struct ice_hw *hw) +{ + hw->pkg_seg_id = ice_get_pkg_segment_id(hw->mac_type); + hw->pkg_sign_type = ice_get_pkg_sign_type(hw->mac_type); +} + +/** * ice_init_pkg_info * @hw: pointer to the hardware structure * @pkg_hdr: pointer to the driver's package hdr @@ -1510,7 +1879,14 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, if (!pkg_hdr) return ICE_DDP_PKG_ERR; - seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); + hw->pkg_has_signing_seg = ice_has_signing_seg(hw, pkg_hdr); + ice_get_signing_req(hw); + + ice_debug(hw, ICE_DBG_INIT, "Pkg using segment id: 0x%08X\n", + hw->pkg_seg_id); + + seg_hdr = (struct ice_generic_seg_hdr *) + ice_find_seg_in_pkg(hw, hw->pkg_seg_id, pkg_hdr); if (seg_hdr) { struct ice_meta_sect *meta; struct ice_pkg_enum state; @@ -1558,21 +1934,14 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, */ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) { - enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; - struct ice_aqc_get_pkg_info_resp *pkg_info; - u16 size; + DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, + ICE_PKG_CNT); + u16 size = __struct_size(pkg_info); u32 i; - size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT); - pkg_info = kzalloc(size, GFP_KERNEL); - if (!pkg_info) + if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) return ICE_DDP_PKG_ERR; - if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) { - state = ICE_DDP_PKG_ERR; - goto init_pkg_free_alloc; - } - for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { #define ICE_PKG_FLAG_COUNT 4 char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 }; @@ -1602,10 +1971,7 @@ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) pkg_info->pkg_info[i].name, flags); } -init_pkg_free_alloc: - kfree(pkg_info); - - return state; + return ICE_DDP_PKG_SUCCESS; } /** @@ -1620,9 +1986,10 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, struct ice_seg **seg) { - struct ice_aqc_get_pkg_info_resp *pkg; + DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, + ICE_PKG_CNT); + u16 size = __struct_size(pkg); enum ice_ddp_state state; - u16 size; u32 i; /* Check package version compatibility */ @@ -1633,7 +2000,7 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, } /* find ICE segment in given package */ - *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, + *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, hw->pkg_seg_id, ospkg); if (!*seg) { ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); @@ -1641,15 +2008,8 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, } /* Check if FW is compatible with the OS package */ - size = struct_size(pkg, pkg_info, ICE_PKG_CNT); - pkg = kzalloc(size, GFP_KERNEL); - if (!pkg) - return ICE_DDP_PKG_ERR; - - if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) { - state = ICE_DDP_PKG_LOAD_ERROR; - goto fw_ddp_compat_free_alloc; - } + if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) + return ICE_DDP_PKG_LOAD_ERROR; for (i = 0; i < le32_to_cpu(pkg->count); i++) { /* loop till we find the NVM package */ @@ -1666,8 +2026,7 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, /* done processing NVM package so break */ break; } -fw_ddp_compat_free_alloc: - kfree(pkg); + return state; } @@ -1807,6 +2166,11 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) if (state) return state; + /* must be a matching segment */ + if (hw->pkg_has_signing_seg && + !ice_match_signing_seg(pkg, hw->pkg_seg_id, hw->pkg_sign_type)) + return ICE_DDP_PKG_ERR; + /* before downloading the package, check package version for * compatibility with driver */ @@ -1816,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) /* initialize package hints and then download package */ ice_init_pkg_hints(hw, seg); - state = ice_download_pkg(hw, seg); + state = ice_download_pkg(hw, pkg, seg); if (state == ICE_DDP_PKG_ALREADY_LOADED) { ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index 41acfe26df1c..ff66c2ffb1a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -98,10 +98,21 @@ struct ice_pkg_hdr { __le32 seg_offset[]; }; +/* Package signing algorithm types */ +#define SEGMENT_SIGN_TYPE_INVALID 0x00000000 +#define SEGMENT_SIGN_TYPE_RSA2K 0x00000001 +#define SEGMENT_SIGN_TYPE_RSA3K 0x00000002 +#define SEGMENT_SIGN_TYPE_RSA3K_SBB 0x00000003 /* Secure Boot Block */ +#define SEGMENT_SIGN_TYPE_RSA3K_E825 0x00000005 + /* generic segment */ struct ice_generic_seg_hdr { -#define SEGMENT_TYPE_METADATA 0x00000001 -#define SEGMENT_TYPE_ICE 0x00000010 +#define SEGMENT_TYPE_INVALID 0x00000000 +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_ICE_E810 0x00000010 +#define SEGMENT_TYPE_SIGNING 0x00001001 +#define SEGMENT_TYPE_ICE_RUN_TIME_CFG 0x00000020 +#define SEGMENT_TYPE_ICE_E830 0x00000017 __le32 seg_type; struct ice_pkg_ver seg_format_ver; __le32 seg_size; @@ -163,6 +174,18 @@ struct ice_global_metadata_seg { #define ICE_MIN_S_SZ 1 #define ICE_MAX_S_SZ 4084 +struct ice_sign_seg { + struct ice_generic_seg_hdr hdr; + __le32 seg_id; + __le32 sign_type; + __le32 signed_seg_idx; + __le32 signed_buf_start; + __le32 signed_buf_count; +#define ICE_SIGN_SEG_RESERVED_COUNT 44 + u8 reserved[ICE_SIGN_SEG_RESERVED_COUNT]; + struct ice_buf_table buf_tbl; +}; + /* section information */ struct ice_section_entry { __le32 type; @@ -416,21 +439,13 @@ struct ice_pkg_enum { void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); }; -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd); int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, struct ice_sq_cd *cd); void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size); -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len); - struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw); -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr); - int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); @@ -439,6 +454,4 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf); - #endif diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 6d560d1c74a4..a2d384dbfc76 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #ifndef _ICE_DEVIDS_H_ #define _ICE_DEVIDS_H_ @@ -16,6 +16,14 @@ #define ICE_DEV_ID_E823L_1GBE 0x124F /* Intel(R) Ethernet Connection E823-L for QSFP */ #define ICE_DEV_ID_E823L_QSFP 0x151D +/* Intel(R) Ethernet Controller E830-C for backplane */ +#define ICE_DEV_ID_E830_BACKPLANE 0x12D1 +/* Intel(R) Ethernet Controller E830-C for QSFP */ +#define ICE_DEV_ID_E830_QSFP56 0x12D2 +/* Intel(R) Ethernet Controller E830-C for SFP */ +#define ICE_DEV_ID_E830_SFP 0x12D3 +/* Intel(R) Ethernet Controller E830-C for SFP-DD */ +#define ICE_DEV_ID_E830_SFP_DD 0x12D4 /* Intel(R) Ethernet Controller E810-C for backplane */ #define ICE_DEV_ID_E810C_BACKPLANE 0x1591 /* Intel(R) Ethernet Controller E810-C for QSFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c new file mode 100644 index 000000000000..86b180cb32a0 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -0,0 +1,2117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" +#include "ice_trace.h" +#include <linux/dpll.h> + +#define ICE_CGU_STATE_ACQ_ERR_THRESHOLD 50 +#define ICE_DPLL_PIN_IDX_INVALID 0xff +#define ICE_DPLL_RCLK_NUM_PER_PF 1 + +/** + * enum ice_dpll_pin_type - enumerate ice pin types: + * @ICE_DPLL_PIN_INVALID: invalid pin type + * @ICE_DPLL_PIN_TYPE_INPUT: input pin + * @ICE_DPLL_PIN_TYPE_OUTPUT: output pin + * @ICE_DPLL_PIN_TYPE_RCLK_INPUT: recovery clock input pin + */ +enum ice_dpll_pin_type { + ICE_DPLL_PIN_INVALID, + ICE_DPLL_PIN_TYPE_INPUT, + ICE_DPLL_PIN_TYPE_OUTPUT, + ICE_DPLL_PIN_TYPE_RCLK_INPUT, +}; + +static const char * const pin_type_name[] = { + [ICE_DPLL_PIN_TYPE_INPUT] = "input", + [ICE_DPLL_PIN_TYPE_OUTPUT] = "output", + [ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input", +}; + +/** + * ice_dpll_pin_freq_set - set pin's frequency + * @pf: private board structure + * @pin: pointer to a pin + * @pin_type: type of pin being configured + * @freq: frequency to be set + * @extack: error reporting + * + * Set requested frequency on a pin. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - success + * * negative - error on AQ or wrong pin type given + */ +static int +ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, const u32 freq, + struct netlink_ext_ack *extack) +{ + u8 flags; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + flags = ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_FREQ; + ret = ice_aq_set_input_pin_cfg(&pf->hw, pin->idx, flags, + pin->flags[0], freq, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + flags = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_FREQ; + ret = ice_aq_set_output_pin_cfg(&pf->hw, pin->idx, flags, + 0, freq, 0); + break; + default: + return -EINVAL; + } + if (ret) { + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin freq:%u on pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + freq, pin->idx); + return ret; + } + pin->freq = freq; + + return 0; +} + +/** + * ice_dpll_frequency_set - wrapper for pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * @pin_type: type of pin being configured + * + * Wraps internal set frequency command on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u32 frequency, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_pin_freq_set(pf, p, pin_type, frequency, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_frequency_set - input pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * + * Wraps internal set frequency command on a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_input_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_set(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_frequency_set - output pin callback for set frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: frequency to be set + * @extack: error reporting + * + * Wraps internal set frequency command on a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't set in hw + */ +static int +ice_dpll_output_frequency_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_set(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_frequency_get - wrapper for pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * @pin_type: type of pin being configured + * + * Wraps internal get frequency command of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *frequency = p->freq; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_frequency_get - input pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * + * Wraps internal get frequency command of a input pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_input_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_get(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_frequency_get - output pin callback for get frequency + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: pointer to dpll + * @dpll_priv: private data pointer passed on dpll registration + * @frequency: on success holds pin's frequency + * @extack: error reporting + * + * Wraps internal get frequency command of a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error pin not found or couldn't get from hw + */ +static int +ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack) +{ + return ice_dpll_frequency_get(pin, pin_priv, dpll, dpll_priv, frequency, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_pin_enable - enable a pin on dplls + * @hw: board private hw structure + * @pin: pointer to a pin + * @pin_type: type of pin being enabled + * @extack: error reporting + * + * Enable a pin on both dplls. Store current state in pin->flags. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 flags = 0; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + flags |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0); + break; + default: + return -EINVAL; + } + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to enable %s pin:%u\n", + ret, ice_aq_str(hw->adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + + return ret; +} + +/** + * ice_dpll_pin_disable - disable a pin on dplls + * @hw: board private hw structure + * @pin: pointer to a pin + * @pin_type: type of pin being disabled + * @extack: error reporting + * + * Disable a pin on both dplls. Store current state in pin->flags. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 flags = 0; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0); + break; + default: + return -EINVAL; + } + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to disable %s pin:%u\n", + ret, ice_aq_str(hw->adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + + return ret; +} + +/** + * ice_dpll_pin_state_update - update pin's state + * @pf: private board struct + * @pin: structure with pin attributes to be updated + * @pin_type: type of pin being updated + * @extack: error reporting + * + * Determine pin current state and frequency, then update struct + * holding the pin info. For input pin states are separated for each + * dpll, for rclk pins states are separated for each parent. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - OK + * * negative - error + */ +static int +ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, + enum ice_dpll_pin_type pin_type, + struct netlink_ext_ack *extack) +{ + u8 parent, port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT; + int ret; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL, + NULL, &pin->flags[0], + &pin->freq, NULL); + if (ret) + goto err; + if (ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN & pin->flags[0]) { + if (pin->pin) { + pin->state[pf->dplls.eec.dpll_idx] = + pin->pin == pf->dplls.eec.active_input ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_SELECTABLE; + pin->state[pf->dplls.pps.dpll_idx] = + pin->pin == pf->dplls.pps.active_input ? + DPLL_PIN_STATE_CONNECTED : + DPLL_PIN_STATE_SELECTABLE; + } else { + pin->state[pf->dplls.eec.dpll_idx] = + DPLL_PIN_STATE_SELECTABLE; + pin->state[pf->dplls.pps.dpll_idx] = + DPLL_PIN_STATE_SELECTABLE; + } + } else { + pin->state[pf->dplls.eec.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + pin->state[pf->dplls.pps.dpll_idx] = + DPLL_PIN_STATE_DISCONNECTED; + } + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + ret = ice_aq_get_output_pin_cfg(&pf->hw, pin->idx, + &pin->flags[0], NULL, + &pin->freq, NULL); + if (ret) + goto err; + if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) + pin->state[0] = DPLL_PIN_STATE_CONNECTED; + else + pin->state[0] = DPLL_PIN_STATE_DISCONNECTED; + break; + case ICE_DPLL_PIN_TYPE_RCLK_INPUT: + for (parent = 0; parent < pf->dplls.rclk.num_parents; + parent++) { + u8 p = parent; + + ret = ice_aq_get_phy_rec_clk_out(&pf->hw, &p, + &port_num, + &pin->flags[parent], + NULL); + if (ret) + goto err; + if (ICE_AQC_GET_PHY_REC_CLK_OUT_OUT_EN & + pin->flags[parent]) + pin->state[parent] = DPLL_PIN_STATE_CONNECTED; + else + pin->state[parent] = + DPLL_PIN_STATE_DISCONNECTED; + } + break; + default: + return -EINVAL; + } + + return 0; +err: + if (extack) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to update %s pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + else + dev_err_ratelimited(ice_pf_to_dev(pf), + "err:%d %s failed to update %s pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + pin_type_name[pin_type], pin->idx); + return ret; +} + +/** + * ice_dpll_hw_input_prio_set - set input priority value in hardware + * @pf: board private structure + * @dpll: ice dpll pointer + * @pin: ice pin pointer + * @prio: priority value being set on a dpll + * @extack: error reporting + * + * Internal wrapper for setting the priority in the hardware. + * + * Context: Called under pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, + struct ice_dpll_pin *pin, const u32 prio, + struct netlink_ext_ack *extack) +{ + int ret; + + ret = ice_aq_set_cgu_ref_prio(&pf->hw, dpll->dpll_idx, pin->idx, + (u8)prio); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin prio:%u on pin:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + prio, pin->idx); + else + dpll->input_prio[pin->idx] = prio; + + return ret; +} + +/** + * ice_dpll_lock_status_get - get dpll lock status callback + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @status: on success holds dpll's lock status + * @extack: error reporting + * + * Dpll subsystem callback, provides dpll's lock status. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_lock_status *status, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *status = d->dpll_state; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_mode_supported - check if dpll's working mode is supported + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @mode: mode to be checked for support + * @extack: error reporting + * + * Dpll subsystem callback. Provides information if working mode is supported + * by dpll. + * + * Return: + * * true - mode is supported + * * false - mode is not supported + */ +static bool ice_dpll_mode_supported(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_mode mode, + struct netlink_ext_ack *extack) +{ + if (mode == DPLL_MODE_AUTOMATIC) + return true; + + return false; +} + +/** + * ice_dpll_mode_get - get dpll's working mode + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @mode: on success holds current working mode of dpll + * @extack: error reporting + * + * Dpll subsystem callback. Provides working mode of dpll. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int ice_dpll_mode_get(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_mode *mode, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *mode = d->mode; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_pin_state_set - set pin's state on dpll + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @enable: if pin shalll be enabled + * @extack: error reporting + * @pin_type: type of a pin + * + * Set pin state on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - OK or no change required + * * negative - error + */ +static int +ice_dpll_pin_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + bool enable, struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + if (enable) + ret = ice_dpll_pin_enable(&pf->hw, p, pin_type, extack); + else + ret = ice_dpll_pin_disable(&pf->hw, p, pin_type, extack); + if (!ret) + ret = ice_dpll_pin_state_update(pf, p, pin_type, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_state_set - enable/disable output pin on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: dpll being configured + * @dpll_priv: private data pointer passed on dpll registration + * @state: state of pin to be set + * @extack: error reporting + * + * Dpll subsystem callback. Set given state on output type pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - successfully enabled mode + * * negative - failed to enable mode + */ +static int +ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + bool enable = state == DPLL_PIN_STATE_CONNECTED; + + return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_input_state_set - enable/disable input pin on dpll levice + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: dpll being configured + * @dpll_priv: private data pointer passed on dpll registration + * @state: state of pin to be set + * @extack: error reporting + * + * Dpll subsystem callback. Enables given mode on input type pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - successfully enabled mode + * * negative - failed to enable mode + */ +static int +ice_dpll_input_state_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + bool enable = state == DPLL_PIN_STATE_SELECTABLE; + + return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_pin_state_get - set pin's state on dpll + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * @pin_type: type of questioned pin + * + * Determine pin state set it on a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_pin_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_pin_state_update(pf, p, pin_type, extack); + if (ret) + goto unlock; + if (pin_type == ICE_DPLL_PIN_TYPE_INPUT) + *state = p->state[d->dpll_idx]; + else if (pin_type == ICE_DPLL_PIN_TYPE_OUTPUT) + *state = p->state[0]; + ret = 0; +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_state_get - get output pin state on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * + * Dpll subsystem callback. Check state of a pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_output_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_state_get(pin, pin_priv, dpll, dpll_priv, state, + extack, ICE_DPLL_PIN_TYPE_OUTPUT); +} + +/** + * ice_dpll_input_state_get - get input pin state on dpll device + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds state of the pin + * @extack: error reporting + * + * Dpll subsystem callback. Check state of a input pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failed to get state + */ +static int +ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_state_get(pin, pin_priv, dpll, dpll_priv, state, + extack, ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_input_prio_get - get dpll's input prio + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @prio: on success - returns input priority on dpll + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting priority of a input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_input_prio_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 *prio, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + *prio = d->input_prio[p->idx]; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_prio_set - set dpll input prio + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @prio: input priority to be set on dpll + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting priority of a input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 prio, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack); + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_direction - callback for get input pin direction + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @direction: holds input pin direction + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting direction of a input pin. + * + * Return: + * * 0 - success + */ +static int +ice_dpll_input_direction(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack) +{ + *direction = DPLL_PIN_DIRECTION_INPUT; + + return 0; +} + +/** + * ice_dpll_output_direction - callback for get output pin direction + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @direction: holds output pin direction + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting direction of an output pin. + * + * Return: + * * 0 - success + */ +static int +ice_dpll_output_direction(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack) +{ + *direction = DPLL_PIN_DIRECTION_OUTPUT; + + return 0; +} + +/** + * ice_dpll_pin_phase_adjust_get - callback for get pin phase adjust value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: on success holds pin phase_adjust value + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting phase adjust value of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_pin_phase_adjust_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 *phase_adjust, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_pf *pf = p->pf; + + mutex_lock(&pf->dplls.lock); + *phase_adjust = p->phase_adjust; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_pin_phase_adjust_set - helper for setting a pin phase adjust value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * @type: type of a pin + * + * Helper for dpll subsystem callback. Handler for setting phase adjust value + * of a pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack, + enum ice_dpll_pin_type type) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flag, flags_en = 0; + int ret; + + mutex_lock(&pf->dplls.lock); + switch (type) { + case ICE_DPLL_PIN_TYPE_INPUT: + flag = ICE_AQC_SET_CGU_IN_CFG_FLG1_UPDATE_DELAY; + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, flag, flags_en, + 0, phase_adjust); + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + flag = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_PHASE; + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN) + flag |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) + flag |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flag, 0, 0, + phase_adjust); + break; + default: + ret = -EINVAL; + } + if (!ret) + p->phase_adjust = phase_adjust; + mutex_unlock(&pf->dplls.lock); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + phase_adjust, p->idx, d->dpll_idx); + + return ret; +} + +/** + * ice_dpll_input_phase_adjust_set - callback for set input pin phase adjust + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * + * Dpll subsystem callback. Wraps a handler for setting phase adjust on input + * pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_phase_adjust_set(pin, pin_priv, dpll, dpll_priv, + phase_adjust, extack, + ICE_DPLL_PIN_TYPE_INPUT); +} + +/** + * ice_dpll_output_phase_adjust_set - callback for set output pin phase adjust + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_adjust: phase_adjust to be set + * @extack: error reporting + * + * Dpll subsystem callback. Wraps a handler for setting phase adjust on output + * pin. + * + * Context: Calls a function which acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 phase_adjust, + struct netlink_ext_ack *extack) +{ + return ice_dpll_pin_phase_adjust_set(pin, pin_priv, dpll, dpll_priv, + phase_adjust, extack, + ICE_DPLL_PIN_TYPE_OUTPUT); +} + +#define ICE_DPLL_PHASE_OFFSET_DIVIDER 100 +#define ICE_DPLL_PHASE_OFFSET_FACTOR \ + (DPLL_PHASE_OFFSET_DIVIDER / ICE_DPLL_PHASE_OFFSET_DIVIDER) +/** + * ice_dpll_phase_offset_get - callback for get dpll phase shift value + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @phase_offset: on success holds pin phase_offset value + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting phase shift value between + * dpll's input and output. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *phase_offset, struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + if (d->active_input == pin) + *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + else + *phase_offset = 0; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @parent_pin: pin parent pointer + * @parent_pin_priv: parent private data pointer passed on pin registration + * @state: state to be set on pin + * @extack: error reporting + * + * Dpll subsystem callback, set a state of a rclk pin on a parent pin + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv, *parent = parent_pin_priv; + bool enable = state == DPLL_PIN_STATE_CONNECTED; + struct ice_pf *pf = p->pf; + int ret = -EINVAL; + u32 hw_idx; + + mutex_lock(&pf->dplls.lock); + hw_idx = parent->idx - pf->dplls.base_rclk_idx; + if (hw_idx >= pf->dplls.num_inputs) + goto unlock; + + if ((enable && p->state[hw_idx] == DPLL_PIN_STATE_CONNECTED) || + (!enable && p->state[hw_idx] == DPLL_PIN_STATE_DISCONNECTED)) { + NL_SET_ERR_MSG_FMT(extack, + "pin:%u state:%u on parent:%u already set", + p->idx, state, parent->idx); + goto unlock; + } + ret = ice_aq_set_phy_rec_clk_out(&pf->hw, hw_idx, enable, + &p->freq); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n", + ret, + ice_aq_str(pf->hw.adminq.sq_last_status), + state, p->idx, parent->idx); +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_rclk_state_on_pin_get - get a state of rclk pin + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @parent_pin: pin parent pointer + * @parent_pin_priv: pin parent priv data pointer passed on pin registration + * @state: on success holds pin state on parent pin + * @extack: error reporting + * + * dpll subsystem callback, get a state of a recovered clock pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - failure + */ +static int +ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv, *parent = parent_pin_priv; + struct ice_pf *pf = p->pf; + int ret = -EINVAL; + u32 hw_idx; + + mutex_lock(&pf->dplls.lock); + hw_idx = parent->idx - pf->dplls.base_rclk_idx; + if (hw_idx >= pf->dplls.num_inputs) + goto unlock; + + ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_RCLK_INPUT, + extack); + if (ret) + goto unlock; + + *state = p->state[hw_idx]; + ret = 0; +unlock: + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +static const struct dpll_pin_ops ice_dpll_rclk_ops = { + .state_on_pin_set = ice_dpll_rclk_state_on_pin_set, + .state_on_pin_get = ice_dpll_rclk_state_on_pin_get, + .direction_get = ice_dpll_input_direction, +}; + +static const struct dpll_pin_ops ice_dpll_input_ops = { + .frequency_get = ice_dpll_input_frequency_get, + .frequency_set = ice_dpll_input_frequency_set, + .state_on_dpll_get = ice_dpll_input_state_get, + .state_on_dpll_set = ice_dpll_input_state_set, + .prio_get = ice_dpll_input_prio_get, + .prio_set = ice_dpll_input_prio_set, + .direction_get = ice_dpll_input_direction, + .phase_adjust_get = ice_dpll_pin_phase_adjust_get, + .phase_adjust_set = ice_dpll_input_phase_adjust_set, + .phase_offset_get = ice_dpll_phase_offset_get, +}; + +static const struct dpll_pin_ops ice_dpll_output_ops = { + .frequency_get = ice_dpll_output_frequency_get, + .frequency_set = ice_dpll_output_frequency_set, + .state_on_dpll_get = ice_dpll_output_state_get, + .state_on_dpll_set = ice_dpll_output_state_set, + .direction_get = ice_dpll_output_direction, + .phase_adjust_get = ice_dpll_pin_phase_adjust_get, + .phase_adjust_set = ice_dpll_output_phase_adjust_set, +}; + +static const struct dpll_device_ops ice_dpll_ops = { + .lock_status_get = ice_dpll_lock_status_get, + .mode_supported = ice_dpll_mode_supported, + .mode_get = ice_dpll_mode_get, +}; + +/** + * ice_generate_clock_id - generates unique clock_id for registering dpll. + * @pf: board private structure + * + * Generates unique (per board) clock_id for allocation and search of dpll + * devices in Linux dpll subsystem. + * + * Return: generated clock id for the board + */ +static u64 ice_generate_clock_id(struct ice_pf *pf) +{ + return pci_get_dsn(pf->pdev); +} + +/** + * ice_dpll_notify_changes - notify dpll subsystem about changes + * @d: pointer do dpll + * + * Once change detected appropriate event is submitted to the dpll subsystem. + */ +static void ice_dpll_notify_changes(struct ice_dpll *d) +{ + bool pin_notified = false; + + if (d->prev_dpll_state != d->dpll_state) { + d->prev_dpll_state = d->dpll_state; + dpll_device_change_ntf(d->dpll); + } + if (d->prev_input != d->active_input) { + if (d->prev_input) + dpll_pin_change_ntf(d->prev_input); + d->prev_input = d->active_input; + if (d->active_input) { + dpll_pin_change_ntf(d->active_input); + pin_notified = true; + } + } + if (d->prev_phase_offset != d->phase_offset) { + d->prev_phase_offset = d->phase_offset; + if (!pin_notified && d->active_input) + dpll_pin_change_ntf(d->active_input); + } +} + +/** + * ice_dpll_update_state - update dpll state + * @pf: pf private structure + * @d: pointer to queried dpll device + * @init: if function called on initialization of ice dpll + * + * Poll current state of dpll from hw and update ice_dpll struct. + * + * Context: Called by kworker under pf->dplls.lock + * Return: + * * 0 - success + * * negative - AQ failure + */ +static int +ice_dpll_update_state(struct ice_pf *pf, struct ice_dpll *d, bool init) +{ + struct ice_dpll_pin *p = NULL; + int ret; + + ret = ice_get_cgu_state(&pf->hw, d->dpll_idx, d->prev_dpll_state, + &d->input_idx, &d->ref_state, &d->eec_mode, + &d->phase_offset, &d->dpll_state); + + dev_dbg(ice_pf_to_dev(pf), + "update dpll=%d, prev_src_idx:%u, src_idx:%u, state:%d, prev:%d mode:%d\n", + d->dpll_idx, d->prev_input_idx, d->input_idx, + d->dpll_state, d->prev_dpll_state, d->mode); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "update dpll=%d state failed, ret=%d %s\n", + d->dpll_idx, ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); + return ret; + } + if (init) { + if (d->dpll_state == DPLL_LOCK_STATUS_LOCKED || + d->dpll_state == DPLL_LOCK_STATUS_LOCKED_HO_ACQ) + d->active_input = pf->dplls.inputs[d->input_idx].pin; + p = &pf->dplls.inputs[d->input_idx]; + return ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, NULL); + } + if (d->dpll_state == DPLL_LOCK_STATUS_HOLDOVER || + d->dpll_state == DPLL_LOCK_STATUS_UNLOCKED) { + d->active_input = NULL; + if (d->input_idx != ICE_DPLL_PIN_IDX_INVALID) + p = &pf->dplls.inputs[d->input_idx]; + d->prev_input_idx = ICE_DPLL_PIN_IDX_INVALID; + d->input_idx = ICE_DPLL_PIN_IDX_INVALID; + if (!p) + return 0; + ret = ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, NULL); + } else if (d->input_idx != d->prev_input_idx) { + if (d->prev_input_idx != ICE_DPLL_PIN_IDX_INVALID) { + p = &pf->dplls.inputs[d->prev_input_idx]; + ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, + NULL); + } + if (d->input_idx != ICE_DPLL_PIN_IDX_INVALID) { + p = &pf->dplls.inputs[d->input_idx]; + d->active_input = p->pin; + ice_dpll_pin_state_update(pf, p, + ICE_DPLL_PIN_TYPE_INPUT, + NULL); + } + d->prev_input_idx = d->input_idx; + } + + return ret; +} + +/** + * ice_dpll_periodic_work - DPLLs periodic worker + * @work: pointer to kthread_work structure + * + * DPLLs periodic worker is responsible for polling state of dpll. + * Context: Holds pf->dplls.lock + */ +static void ice_dpll_periodic_work(struct kthread_work *work) +{ + struct ice_dplls *d = container_of(work, struct ice_dplls, work.work); + struct ice_pf *pf = container_of(d, struct ice_pf, dplls); + struct ice_dpll *de = &pf->dplls.eec; + struct ice_dpll *dp = &pf->dplls.pps; + int ret; + + mutex_lock(&pf->dplls.lock); + ret = ice_dpll_update_state(pf, de, false); + if (!ret) + ret = ice_dpll_update_state(pf, dp, false); + if (ret) { + d->cgu_state_acq_err_num++; + /* stop rescheduling this worker */ + if (d->cgu_state_acq_err_num > + ICE_CGU_STATE_ACQ_ERR_THRESHOLD) { + dev_err(ice_pf_to_dev(pf), + "EEC/PPS DPLLs periodic work disabled\n"); + mutex_unlock(&pf->dplls.lock); + return; + } + } + mutex_unlock(&pf->dplls.lock); + ice_dpll_notify_changes(de); + ice_dpll_notify_changes(dp); + + /* Run twice a second or reschedule if update failed */ + kthread_queue_delayed_work(d->kworker, &d->work, + ret ? msecs_to_jiffies(10) : + msecs_to_jiffies(500)); +} + +/** + * ice_dpll_release_pins - release pins resources from dpll subsystem + * @pins: pointer to pins array + * @count: number of pins + * + * Release resources of given pins array in the dpll subsystem. + */ +static void ice_dpll_release_pins(struct ice_dpll_pin *pins, int count) +{ + int i; + + for (i = 0; i < count; i++) + dpll_pin_put(pins[i].pin); +} + +/** + * ice_dpll_get_pins - get pins from dpll subsystem + * @pf: board private structure + * @pins: pointer to pins array + * @start_idx: get starts from this pin idx value + * @count: number of pins + * @clock_id: clock_id of dpll device + * + * Get pins - allocate - in dpll subsystem, store them in pin field of given + * pins array. + * + * Return: + * * 0 - success + * * negative - allocation failure reason + */ +static int +ice_dpll_get_pins(struct ice_pf *pf, struct ice_dpll_pin *pins, + int start_idx, int count, u64 clock_id) +{ + int i, ret; + + for (i = 0; i < count; i++) { + pins[i].pin = dpll_pin_get(clock_id, i + start_idx, THIS_MODULE, + &pins[i].prop); + if (IS_ERR(pins[i].pin)) { + ret = PTR_ERR(pins[i].pin); + goto release_pins; + } + } + + return 0; + +release_pins: + while (--i >= 0) + dpll_pin_put(pins[i].pin); + return ret; +} + +/** + * ice_dpll_unregister_pins - unregister pins from a dpll + * @dpll: dpll device pointer + * @pins: pointer to pins array + * @ops: callback ops registered with the pins + * @count: number of pins + * + * Unregister pins of a given array of pins from given dpll device registered in + * dpll subsystem. + */ +static void +ice_dpll_unregister_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins, + const struct dpll_pin_ops *ops, int count) +{ + int i; + + for (i = 0; i < count; i++) + dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]); +} + +/** + * ice_dpll_register_pins - register pins with a dpll + * @dpll: dpll pointer to register pins with + * @pins: pointer to pins array + * @ops: callback ops registered with the pins + * @count: number of pins + * + * Register pins of a given array with given dpll in dpll subsystem. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_register_pins(struct dpll_device *dpll, struct ice_dpll_pin *pins, + const struct dpll_pin_ops *ops, int count) +{ + int ret, i; + + for (i = 0; i < count; i++) { + ret = dpll_pin_register(dpll, pins[i].pin, ops, &pins[i]); + if (ret) + goto unregister_pins; + } + + return 0; + +unregister_pins: + while (--i >= 0) + dpll_pin_unregister(dpll, pins[i].pin, ops, &pins[i]); + return ret; +} + +/** + * ice_dpll_deinit_direct_pins - deinitialize direct pins + * @cgu: if cgu is present and controlled by this NIC + * @pins: pointer to pins array + * @count: number of pins + * @ops: callback ops registered with the pins + * @first: dpll device pointer + * @second: dpll device pointer + * + * If cgu is owned unregister pins from given dplls. + * Release pins resources to the dpll subsystem. + */ +static void +ice_dpll_deinit_direct_pins(bool cgu, struct ice_dpll_pin *pins, int count, + const struct dpll_pin_ops *ops, + struct dpll_device *first, + struct dpll_device *second) +{ + if (cgu) { + ice_dpll_unregister_pins(first, pins, ops, count); + ice_dpll_unregister_pins(second, pins, ops, count); + } + ice_dpll_release_pins(pins, count); +} + +/** + * ice_dpll_init_direct_pins - initialize direct pins + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * @pins: pointer to pins array + * @start_idx: on which index shall allocation start in dpll subsystem + * @count: number of pins + * @ops: callback ops registered with the pins + * @first: dpll device pointer + * @second: dpll device pointer + * + * Allocate directly connected pins of a given array in dpll subsystem. + * If cgu is owned register allocated pins with given dplls. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_init_direct_pins(struct ice_pf *pf, bool cgu, + struct ice_dpll_pin *pins, int start_idx, int count, + const struct dpll_pin_ops *ops, + struct dpll_device *first, struct dpll_device *second) +{ + int ret; + + ret = ice_dpll_get_pins(pf, pins, start_idx, count, pf->dplls.clock_id); + if (ret) + return ret; + if (cgu) { + ret = ice_dpll_register_pins(first, pins, ops, count); + if (ret) + goto release_pins; + ret = ice_dpll_register_pins(second, pins, ops, count); + if (ret) + goto unregister_first; + } + + return 0; + +unregister_first: + ice_dpll_unregister_pins(first, pins, ops, count); +release_pins: + ice_dpll_release_pins(pins, count); + return ret; +} + +/** + * ice_dpll_deinit_rclk_pin - release rclk pin resources + * @pf: board private structure + * + * Deregister rclk pin from parent pins and release resources in dpll subsystem. + */ +static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) +{ + struct ice_dpll_pin *rclk = &pf->dplls.rclk; + struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct dpll_pin *parent; + int i; + + for (i = 0; i < rclk->num_parents; i++) { + parent = pf->dplls.inputs[rclk->parent_idx[i]].pin; + if (!parent) + continue; + dpll_pin_on_pin_unregister(parent, rclk->pin, + &ice_dpll_rclk_ops, rclk); + } + if (WARN_ON_ONCE(!vsi || !vsi->netdev)) + return; + netdev_dpll_pin_clear(vsi->netdev); + dpll_pin_put(rclk->pin); +} + +/** + * ice_dpll_init_rclk_pins - initialize recovered clock pin + * @pf: board private structure + * @pin: pin to register + * @start_idx: on which index shall allocation start in dpll subsystem + * @ops: callback ops registered with the pins + * + * Allocate resource for recovered clock pin in dpll subsystem. Register the + * pin with the parents it has in the info. Register pin with the pf's main vsi + * netdev. + * + * Return: + * * 0 - success + * * negative - registration failure reason + */ +static int +ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, + int start_idx, const struct dpll_pin_ops *ops) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct dpll_pin *parent; + int ret, i; + + ret = ice_dpll_get_pins(pf, pin, start_idx, ICE_DPLL_RCLK_NUM_PER_PF, + pf->dplls.clock_id); + if (ret) + return ret; + for (i = 0; i < pf->dplls.rclk.num_parents; i++) { + parent = pf->dplls.inputs[pf->dplls.rclk.parent_idx[i]].pin; + if (!parent) { + ret = -ENODEV; + goto unregister_pins; + } + ret = dpll_pin_on_pin_register(parent, pf->dplls.rclk.pin, + ops, &pf->dplls.rclk); + if (ret) + goto unregister_pins; + } + if (WARN_ON((!vsi || !vsi->netdev))) + return -EINVAL; + netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + + return 0; + +unregister_pins: + while (i) { + parent = pf->dplls.inputs[pf->dplls.rclk.parent_idx[--i]].pin; + dpll_pin_on_pin_unregister(parent, pf->dplls.rclk.pin, + &ice_dpll_rclk_ops, &pf->dplls.rclk); + } + ice_dpll_release_pins(pin, ICE_DPLL_RCLK_NUM_PER_PF); + return ret; +} + +/** + * ice_dpll_deinit_pins - deinitialize direct pins + * @pf: board private structure + * @cgu: if cgu is controlled by this pf + * + * If cgu is owned unregister directly connected pins from the dplls. + * Release resources of directly connected pins from the dpll subsystem. + */ +static void ice_dpll_deinit_pins(struct ice_pf *pf, bool cgu) +{ + struct ice_dpll_pin *outputs = pf->dplls.outputs; + struct ice_dpll_pin *inputs = pf->dplls.inputs; + int num_outputs = pf->dplls.num_outputs; + int num_inputs = pf->dplls.num_inputs; + struct ice_dplls *d = &pf->dplls; + struct ice_dpll *de = &d->eec; + struct ice_dpll *dp = &d->pps; + + ice_dpll_deinit_rclk_pin(pf); + if (cgu) { + ice_dpll_unregister_pins(dp->dpll, inputs, &ice_dpll_input_ops, + num_inputs); + ice_dpll_unregister_pins(de->dpll, inputs, &ice_dpll_input_ops, + num_inputs); + } + ice_dpll_release_pins(inputs, num_inputs); + if (cgu) { + ice_dpll_unregister_pins(dp->dpll, outputs, + &ice_dpll_output_ops, num_outputs); + ice_dpll_unregister_pins(de->dpll, outputs, + &ice_dpll_output_ops, num_outputs); + ice_dpll_release_pins(outputs, num_outputs); + } +} + +/** + * ice_dpll_init_pins - init pins and register pins with a dplls + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * + * Initialize directly connected pf's pins within pf's dplls in a Linux dpll + * subsystem. + * + * Return: + * * 0 - success + * * negative - initialization failure reason + */ +static int ice_dpll_init_pins(struct ice_pf *pf, bool cgu) +{ + u32 rclk_idx; + int ret; + + ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.inputs, 0, + pf->dplls.num_inputs, + &ice_dpll_input_ops, + pf->dplls.eec.dpll, pf->dplls.pps.dpll); + if (ret) + return ret; + if (cgu) { + ret = ice_dpll_init_direct_pins(pf, cgu, pf->dplls.outputs, + pf->dplls.num_inputs, + pf->dplls.num_outputs, + &ice_dpll_output_ops, + pf->dplls.eec.dpll, + pf->dplls.pps.dpll); + if (ret) + goto deinit_inputs; + } + rclk_idx = pf->dplls.num_inputs + pf->dplls.num_outputs + pf->hw.pf_id; + ret = ice_dpll_init_rclk_pins(pf, &pf->dplls.rclk, rclk_idx, + &ice_dpll_rclk_ops); + if (ret) + goto deinit_outputs; + + return 0; +deinit_outputs: + ice_dpll_deinit_direct_pins(cgu, pf->dplls.outputs, + pf->dplls.num_outputs, + &ice_dpll_output_ops, pf->dplls.pps.dpll, + pf->dplls.eec.dpll); +deinit_inputs: + ice_dpll_deinit_direct_pins(cgu, pf->dplls.inputs, pf->dplls.num_inputs, + &ice_dpll_input_ops, pf->dplls.pps.dpll, + pf->dplls.eec.dpll); + return ret; +} + +/** + * ice_dpll_deinit_dpll - deinitialize dpll device + * @pf: board private structure + * @d: pointer to ice_dpll + * @cgu: if cgu is present and controlled by this NIC + * + * If cgu is owned unregister the dpll from dpll subsystem. + * Release resources of dpll device from dpll subsystem. + */ +static void +ice_dpll_deinit_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu) +{ + if (cgu) + dpll_device_unregister(d->dpll, &ice_dpll_ops, d); + dpll_device_put(d->dpll); +} + +/** + * ice_dpll_init_dpll - initialize dpll device in dpll subsystem + * @pf: board private structure + * @d: dpll to be initialized + * @cgu: if cgu is present and controlled by this NIC + * @type: type of dpll being initialized + * + * Allocate dpll instance for this board in dpll subsystem, if cgu is controlled + * by this NIC, register dpll with the callback ops. + * + * Return: + * * 0 - success + * * negative - initialization failure reason + */ +static int +ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu, + enum dpll_type type) +{ + u64 clock_id = pf->dplls.clock_id; + int ret; + + d->dpll = dpll_device_get(clock_id, d->dpll_idx, THIS_MODULE); + if (IS_ERR(d->dpll)) { + ret = PTR_ERR(d->dpll); + dev_err(ice_pf_to_dev(pf), + "dpll_device_get failed (%p) err=%d\n", d, ret); + return ret; + } + d->pf = pf; + if (cgu) { + ice_dpll_update_state(pf, d, true); + ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d); + if (ret) { + dpll_device_put(d->dpll); + return ret; + } + } + + return 0; +} + +/** + * ice_dpll_deinit_worker - deinitialize dpll kworker + * @pf: board private structure + * + * Stop dpll's kworker, release it's resources. + */ +static void ice_dpll_deinit_worker(struct ice_pf *pf) +{ + struct ice_dplls *d = &pf->dplls; + + kthread_cancel_delayed_work_sync(&d->work); + kthread_destroy_worker(d->kworker); +} + +/** + * ice_dpll_init_worker - Initialize DPLLs periodic worker + * @pf: board private structure + * + * Create and start DPLLs periodic worker. + * + * Context: Shall be called after pf->dplls.lock is initialized. + * Return: + * * 0 - success + * * negative - create worker failure + */ +static int ice_dpll_init_worker(struct ice_pf *pf) +{ + struct ice_dplls *d = &pf->dplls; + struct kthread_worker *kworker; + + kthread_init_delayed_work(&d->work, ice_dpll_periodic_work); + kworker = kthread_create_worker(0, "ice-dplls-%s", + dev_name(ice_pf_to_dev(pf))); + if (IS_ERR(kworker)) + return PTR_ERR(kworker); + d->kworker = kworker; + d->cgu_state_acq_err_num = 0; + kthread_queue_delayed_work(d->kworker, &d->work, 0); + + return 0; +} + +/** + * ice_dpll_init_info_direct_pins - initializes direct pins info + * @pf: board private structure + * @pin_type: type of pins being initialized + * + * Init information for directly connected pins, cache them in pf's pins + * structures. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int +ice_dpll_init_info_direct_pins(struct ice_pf *pf, + enum ice_dpll_pin_type pin_type) +{ + struct ice_dpll *de = &pf->dplls.eec, *dp = &pf->dplls.pps; + int num_pins, i, ret = -EINVAL; + struct ice_hw *hw = &pf->hw; + struct ice_dpll_pin *pins; + unsigned long caps; + u8 freq_supp_num; + bool input; + + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + pins = pf->dplls.inputs; + num_pins = pf->dplls.num_inputs; + input = true; + break; + case ICE_DPLL_PIN_TYPE_OUTPUT: + pins = pf->dplls.outputs; + num_pins = pf->dplls.num_outputs; + input = false; + break; + default: + return -EINVAL; + } + + for (i = 0; i < num_pins; i++) { + caps = 0; + pins[i].idx = i; + pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input); + pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input); + if (input) { + ret = ice_aq_get_cgu_ref_prio(hw, de->dpll_idx, i, + &de->input_prio[i]); + if (ret) + return ret; + ret = ice_aq_get_cgu_ref_prio(hw, dp->dpll_idx, i, + &dp->input_prio[i]); + if (ret) + return ret; + caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | + DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); + pins[i].prop.phase_range.min = + pf->dplls.input_phase_adj_max; + pins[i].prop.phase_range.max = + -pf->dplls.input_phase_adj_max; + } else { + pins[i].prop.phase_range.min = + pf->dplls.output_phase_adj_max; + pins[i].prop.phase_range.max = + -pf->dplls.output_phase_adj_max; + ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); + if (ret) + return ret; + } + pins[i].prop.capabilities = caps; + ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); + if (ret) + return ret; + pins[i].prop.freq_supported = + ice_cgu_get_pin_freq_supp(hw, i, input, &freq_supp_num); + pins[i].prop.freq_supported_num = freq_supp_num; + pins[i].pf = pf; + } + + return ret; +} + +/** + * ice_dpll_init_info_rclk_pin - initializes rclk pin information + * @pf: board private structure + * + * Init information for rclk pin, cache them in pf->dplls.rclk. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info_rclk_pin(struct ice_pf *pf) +{ + struct ice_dpll_pin *pin = &pf->dplls.rclk; + + pin->prop.type = DPLL_PIN_TYPE_SYNCE_ETH_PORT; + pin->prop.capabilities |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + pin->pf = pf; + + return ice_dpll_pin_state_update(pf, pin, + ICE_DPLL_PIN_TYPE_RCLK_INPUT, NULL); +} + +/** + * ice_dpll_init_pins_info - init pins info wrapper + * @pf: board private structure + * @pin_type: type of pins being initialized + * + * Wraps functions for pin initialization. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int +ice_dpll_init_pins_info(struct ice_pf *pf, enum ice_dpll_pin_type pin_type) +{ + switch (pin_type) { + case ICE_DPLL_PIN_TYPE_INPUT: + case ICE_DPLL_PIN_TYPE_OUTPUT: + return ice_dpll_init_info_direct_pins(pf, pin_type); + case ICE_DPLL_PIN_TYPE_RCLK_INPUT: + return ice_dpll_init_info_rclk_pin(pf); + default: + return -EINVAL; + } +} + +/** + * ice_dpll_deinit_info - release memory allocated for pins info + * @pf: board private structure + * + * Release memory allocated for pins by ice_dpll_init_info function. + */ +static void ice_dpll_deinit_info(struct ice_pf *pf) +{ + kfree(pf->dplls.inputs); + kfree(pf->dplls.outputs); + kfree(pf->dplls.eec.input_prio); + kfree(pf->dplls.pps.input_prio); +} + +/** + * ice_dpll_init_info - prepare pf's dpll information structure + * @pf: board private structure + * @cgu: if cgu is present and controlled by this NIC + * + * Acquire (from HW) and set basic dpll information (on pf->dplls struct). + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) +{ + struct ice_aqc_get_cgu_abilities abilities; + struct ice_dpll *de = &pf->dplls.eec; + struct ice_dpll *dp = &pf->dplls.pps; + struct ice_dplls *d = &pf->dplls; + struct ice_hw *hw = &pf->hw; + int ret, alloc_size, i; + + d->clock_id = ice_generate_clock_id(pf); + ret = ice_aq_get_cgu_abilities(hw, &abilities); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "err:%d %s failed to read cgu abilities\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + return ret; + } + + de->dpll_idx = abilities.eec_dpll_idx; + dp->dpll_idx = abilities.pps_dpll_idx; + d->num_inputs = abilities.num_inputs; + d->num_outputs = abilities.num_outputs; + d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj); + d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj); + + alloc_size = sizeof(*d->inputs) * d->num_inputs; + d->inputs = kzalloc(alloc_size, GFP_KERNEL); + if (!d->inputs) + return -ENOMEM; + + alloc_size = sizeof(*de->input_prio) * d->num_inputs; + de->input_prio = kzalloc(alloc_size, GFP_KERNEL); + if (!de->input_prio) + return -ENOMEM; + + dp->input_prio = kzalloc(alloc_size, GFP_KERNEL); + if (!dp->input_prio) + return -ENOMEM; + + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_INPUT); + if (ret) + goto deinit_info; + + if (cgu) { + alloc_size = sizeof(*d->outputs) * d->num_outputs; + d->outputs = kzalloc(alloc_size, GFP_KERNEL); + if (!d->outputs) { + ret = -ENOMEM; + goto deinit_info; + } + + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_OUTPUT); + if (ret) + goto deinit_info; + } + + ret = ice_get_cgu_rclk_pin_info(&pf->hw, &d->base_rclk_idx, + &pf->dplls.rclk.num_parents); + if (ret) + return ret; + for (i = 0; i < pf->dplls.rclk.num_parents; i++) + pf->dplls.rclk.parent_idx[i] = d->base_rclk_idx + i; + ret = ice_dpll_init_pins_info(pf, ICE_DPLL_PIN_TYPE_RCLK_INPUT); + if (ret) + return ret; + de->mode = DPLL_MODE_AUTOMATIC; + dp->mode = DPLL_MODE_AUTOMATIC; + + dev_dbg(ice_pf_to_dev(pf), + "%s - success, inputs:%u, outputs:%u rclk-parents:%u\n", + __func__, d->num_inputs, d->num_outputs, d->rclk.num_parents); + + return 0; + +deinit_info: + dev_err(ice_pf_to_dev(pf), + "%s - fail: d->inputs:%p, de->input_prio:%p, dp->input_prio:%p, d->outputs:%p\n", + __func__, d->inputs, de->input_prio, + dp->input_prio, d->outputs); + ice_dpll_deinit_info(pf); + return ret; +} + +/** + * ice_dpll_deinit - Disable the driver/HW support for dpll subsystem + * the dpll device. + * @pf: board private structure + * + * Handles the cleanup work required after dpll initialization, freeing + * resources and unregistering the dpll, pin and all resources used for + * handling them. + * + * Context: Destroys pf->dplls.lock mutex. Call only if ICE_FLAG_DPLL was set. + */ +void ice_dpll_deinit(struct ice_pf *pf) +{ + bool cgu = ice_is_feature_supported(pf, ICE_F_CGU); + + clear_bit(ICE_FLAG_DPLL, pf->flags); + if (cgu) + ice_dpll_deinit_worker(pf); + + ice_dpll_deinit_pins(pf, cgu); + ice_dpll_deinit_dpll(pf, &pf->dplls.pps, cgu); + ice_dpll_deinit_dpll(pf, &pf->dplls.eec, cgu); + ice_dpll_deinit_info(pf); + mutex_destroy(&pf->dplls.lock); +} + +/** + * ice_dpll_init - initialize support for dpll subsystem + * @pf: board private structure + * + * Set up the device dplls, register them and pins connected within Linux dpll + * subsystem. Allow userspace to obtain state of DPLL and handling of DPLL + * configuration requests. + * + * Context: Initializes pf->dplls.lock mutex. + */ +void ice_dpll_init(struct ice_pf *pf) +{ + bool cgu = ice_is_feature_supported(pf, ICE_F_CGU); + struct ice_dplls *d = &pf->dplls; + int err = 0; + + err = ice_dpll_init_info(pf, cgu); + if (err) + goto err_exit; + err = ice_dpll_init_dpll(pf, &pf->dplls.eec, cgu, DPLL_TYPE_EEC); + if (err) + goto deinit_info; + err = ice_dpll_init_dpll(pf, &pf->dplls.pps, cgu, DPLL_TYPE_PPS); + if (err) + goto deinit_eec; + err = ice_dpll_init_pins(pf, cgu); + if (err) + goto deinit_pps; + mutex_init(&d->lock); + if (cgu) { + err = ice_dpll_init_worker(pf); + if (err) + goto deinit_pins; + } + set_bit(ICE_FLAG_DPLL, pf->flags); + + return; + +deinit_pins: + ice_dpll_deinit_pins(pf, cgu); +deinit_pps: + ice_dpll_deinit_dpll(pf, &pf->dplls.pps, cgu); +deinit_eec: + ice_dpll_deinit_dpll(pf, &pf->dplls.eec, cgu); +deinit_info: + ice_dpll_deinit_info(pf); +err_exit: + mutex_destroy(&d->lock); + dev_warn(ice_pf_to_dev(pf), "DPLLs init failure err:%d\n", err); +} diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h new file mode 100644 index 000000000000..93172e93995b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2022, Intel Corporation. */ + +#ifndef _ICE_DPLL_H_ +#define _ICE_DPLL_H_ + +#include "ice.h" + +#define ICE_DPLL_RCLK_NUM_MAX 4 + +/** ice_dpll_pin - store info about pins + * @pin: dpll pin structure + * @pf: pointer to pf, which has registered the dpll_pin + * @idx: ice pin private idx + * @num_parents: hols number of parent pins + * @parent_idx: hold indexes of parent pins + * @flags: pin flags returned from HW + * @state: state of a pin + * @prop: pin properties + * @freq: current frequency of a pin + * @phase_adjust: current phase adjust value + */ +struct ice_dpll_pin { + struct dpll_pin *pin; + struct ice_pf *pf; + u8 idx; + u8 num_parents; + u8 parent_idx[ICE_DPLL_RCLK_NUM_MAX]; + u8 flags[ICE_DPLL_RCLK_NUM_MAX]; + u8 state[ICE_DPLL_RCLK_NUM_MAX]; + struct dpll_pin_properties prop; + u32 freq; + s32 phase_adjust; +}; + +/** ice_dpll - store info required for DPLL control + * @dpll: pointer to dpll dev + * @pf: pointer to pf, which has registered the dpll_device + * @dpll_idx: index of dpll on the NIC + * @input_idx: currently selected input index + * @prev_input_idx: previously selected input index + * @ref_state: state of dpll reference signals + * @eec_mode: eec_mode dpll is configured for + * @phase_offset: phase offset of active pin vs dpll signal + * @prev_phase_offset: previous phase offset of active pin vs dpll signal + * @input_prio: priorities of each input + * @dpll_state: current dpll sync state + * @prev_dpll_state: last dpll sync state + * @active_input: pointer to active input pin + * @prev_input: pointer to previous active input pin + */ +struct ice_dpll { + struct dpll_device *dpll; + struct ice_pf *pf; + u8 dpll_idx; + u8 input_idx; + u8 prev_input_idx; + u8 ref_state; + u8 eec_mode; + s64 phase_offset; + s64 prev_phase_offset; + u8 *input_prio; + enum dpll_lock_status dpll_state; + enum dpll_lock_status prev_dpll_state; + enum dpll_mode mode; + struct dpll_pin *active_input; + struct dpll_pin *prev_input; +}; + +/** ice_dplls - store info required for CCU (clock controlling unit) + * @kworker: periodic worker + * @work: periodic work + * @lock: locks access to configuration of a dpll + * @eec: pointer to EEC dpll dev + * @pps: pointer to PPS dpll dev + * @inputs: input pins pointer + * @outputs: output pins pointer + * @rclk: recovered pins pointer + * @num_inputs: number of input pins available on dpll + * @num_outputs: number of output pins available on dpll + * @cgu_state_acq_err_num: number of errors returned during periodic work + * @base_rclk_idx: idx of first pin used for clock revocery pins + * @clock_id: clock_id of dplls + * @input_phase_adj_max: max phase adjust value for an input pins + * @output_phase_adj_max: max phase adjust value for an output pins + */ +struct ice_dplls { + struct kthread_worker *kworker; + struct kthread_delayed_work work; + struct mutex lock; + struct ice_dpll eec; + struct ice_dpll pps; + struct ice_dpll_pin *inputs; + struct ice_dpll_pin *outputs; + struct ice_dpll_pin rclk; + u8 num_inputs; + u8 num_outputs; + int cgu_state_acq_err_num; + u8 base_rclk_idx; + u64 clock_id; + s32 input_phase_adj_max; + s32 output_phase_adj_max; +}; + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void ice_dpll_init(struct ice_pf *pf); +void ice_dpll_deinit(struct ice_pf *pf); +#else +static inline void ice_dpll_init(struct ice_pf *pf) { } +static inline void ice_dpll_deinit(struct ice_pf *pf) { } +#endif + +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 8f232c41a89e..a655d499abfa 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_eswitch.h" +#include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" #include "ice_devlink.h" @@ -83,10 +84,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) struct ice_vsi_vlan_ops *vlan_ops; bool rule_added = false; - vlan_ops = ice_get_compat_vsi_vlan_ops(ctrl_vsi); - if (vlan_ops->dis_stripping(ctrl_vsi)) - return -ENODEV; - ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); netif_addr_lock_bh(uplink_netdev); @@ -103,17 +100,28 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) rule_added = true; } + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + if (vlan_ops->dis_rx_filtering(uplink_vsi)) + goto err_dis_rx; + if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_uplink; if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_control; + if (ice_vsi_update_local_lb(uplink_vsi, true)) + goto err_override_local_lb; + return 0; +err_override_local_lb: + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: + vlan_ops->ena_rx_filtering(uplink_vsi); +err_dis_rx: if (rule_added) ice_clear_dflt_vsi(uplink_vsi); err_def_rx: @@ -306,6 +314,9 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; + if (repr->br_port) + repr->br_port->vsi = vsi; + ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); @@ -331,6 +342,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; + if (!vsi || !ice_is_switchdev_running(vsi->back)) + return NETDEV_TX_BUSY; + if (ice_is_reset_in_progress(vsi->back->state) || test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; @@ -378,9 +392,14 @@ static void ice_eswitch_release_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + + ice_vsi_update_local_lb(uplink_vsi, false); ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); + vlan_ops->ena_rx_filtering(uplink_vsi); ice_clear_dflt_vsi(uplink_vsi); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, @@ -455,16 +474,24 @@ static void ice_eswitch_napi_disable(struct ice_pf *pf) */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi; + struct ice_vsi *ctrl_vsi, *uplink_vsi; + + uplink_vsi = ice_get_main_vsi(pf); + if (!uplink_vsi) + return -ENODEV; + + if (netif_is_any_bridge_port(uplink_vsi->netdev)) { + dev_err(ice_pf_to_dev(pf), + "Uplink port cannot be a bridge port\n"); + return -EINVAL; + } pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); if (!pf->switchdev.control_vsi) return -ENODEV; ctrl_vsi = pf->switchdev.control_vsi; - pf->switchdev.uplink_vsi = ice_get_main_vsi(pf); - if (!pf->switchdev.uplink_vsi) - goto err_vsi; + pf->switchdev.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) goto err_vsi; @@ -480,10 +507,15 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) if (ice_vsi_open(ctrl_vsi)) goto err_setup_reprs; + if (ice_eswitch_br_offloads_init(pf)) + goto err_br_offloads; + ice_eswitch_napi_enable(pf); return 0; +err_br_offloads: + ice_vsi_close(ctrl_vsi); err_setup_reprs: ice_repr_rem_from_all_vfs(pf); err_repr_add: @@ -502,8 +534,8 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; ice_eswitch_napi_disable(pf); + ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_rem_adv_rule_for_vsi(&pf->hw, ctrl_vsi->idx); ice_eswitch_release_reprs(pf, ctrl_vsi); ice_vsi_release(ctrl_vsi); ice_repr_rem_from_all_vfs(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c new file mode 100644 index 000000000000..6ae0269bdf73 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -0,0 +1,1346 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_eswitch_br.h" +#include "ice_repr.h" +#include "ice_switch.h" +#include "ice_vlan.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_trace.h" + +#define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000) + +static const struct rhashtable_params ice_fdb_ht_params = { + .key_offset = offsetof(struct ice_esw_br_fdb_entry, data), + .key_len = sizeof(struct ice_esw_br_fdb_data), + .head_offset = offsetof(struct ice_esw_br_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev) +{ + /* Accept only PF netdev, PRs and LAG */ + return ice_is_port_repr_netdev(dev) || netif_is_ice(dev) || + netif_is_lag_master(dev); +} + +static struct net_device * +ice_eswitch_br_get_uplink_from_lag(struct net_device *lag_dev) +{ + struct net_device *lower; + struct list_head *iter; + + netdev_for_each_lower_dev(lag_dev, lower, iter) { + if (netif_is_ice(lower)) + return lower; + } + + return NULL; +} + +static struct ice_esw_br_port * +ice_eswitch_br_netdev_to_port(struct net_device *dev) +{ + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + return repr->br_port; + } else if (netif_is_ice(dev) || netif_is_lag_master(dev)) { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return NULL; + + pf = ice_netdev_to_pf(ice_dev); + + return pf->br_port; + } + + return NULL; +} + +static void +ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info, + u8 pf_id, u16 vf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = vf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_RX; + rule_info->sw_act.src = pf_id; + rule_info->priority = 2; +} + +static void +ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info, + u16 pf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = pf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_TX; + rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + rule_info->flags_info.act_valid = true; + rule_info->priority = 2; +} + +static int +ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule) +{ + int err; + + if (!rule) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(hw, rule); + kfree(rule); + + return err; +} + +static u16 +ice_eswitch_br_get_lkups_cnt(u16 vid) +{ + return ice_eswitch_br_is_vid_valid(vid) ? 2 : 1; +} + +static void +ice_eswitch_br_add_vlan_lkup(struct ice_adv_lkup_elem *list, u16 vid) +{ + if (ice_eswitch_br_is_vid_valid(vid)) { + list[1].type = ICE_VLAN_OFOS; + list[1].h_u.vlan_hdr.vlan = cpu_to_be16(vid & VLAN_VID_MASK); + list[1].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + } +} + +static struct ice_rule_query_data * +ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + u16 lkups_cnt; + int err; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return ERR_PTR(-ENOMEM); + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) { + err = -ENOMEM; + goto err_list_alloc; + } + + switch (port_type) { + case ICE_ESWITCH_BR_UPLINK_PORT: + ice_eswitch_br_egress_rule_setup(&rule_info, vsi_idx); + break; + case ICE_ESWITCH_BR_VF_REPR_PORT: + ice_eswitch_br_ingress_rule_setup(&rule_info, hw->pf_id, + vsi_idx); + break; + default: + err = -EINVAL; + goto err_add_rule; + } + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.need_pass_l2 = true; + + rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); + + return ERR_PTR(err); +} + +static struct ice_rule_query_data * +ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + int err = -ENOMEM; + u16 lkups_cnt; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + goto err_exit; + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + goto err_list_alloc; + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.allow_pass_l2 = true; + rule_info.sw_act.vsi_handle = vsi_idx; + rule_info.sw_act.fltr_act = ICE_NOP; + rule_info.priority = 2; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); +err_exit: + return ERR_PTR(err); +} + +static struct ice_esw_br_flow * +ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx, + int port_type, const unsigned char *mac, u16 vid) +{ + struct ice_rule_query_data *fwd_rule, *guard_rule; + struct ice_esw_br_flow *flow; + int err; + + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac, + vid); + err = PTR_ERR_OR_ZERO(fwd_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_fwd_rule; + } + + guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac, vid); + err = PTR_ERR_OR_ZERO(guard_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_guard_rule; + } + + flow->fwd_rule = fwd_rule; + flow->guard_rule = guard_rule; + + return flow; + +err_guard_rule: + ice_eswitch_br_rule_delete(hw, fwd_rule); +err_fwd_rule: + kfree(flow); + + return ERR_PTR(err); +} + +static struct ice_esw_br_fdb_entry * +ice_eswitch_br_fdb_find(struct ice_esw_br *bridge, const unsigned char *mac, + u16 vid) +{ + struct ice_esw_br_fdb_data data = { + .vid = vid, + }; + + ether_addr_copy(data.addr, mac); + return rhashtable_lookup_fast(&bridge->fdb_ht, &data, + ice_fdb_ht_params); +} + +static void +ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->fwd_rule); + if (err) + dev_err(dev, "Failed to delete FDB forward rule, err: %d\n", + err); + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->guard_rule); + if (err) + dev_err(dev, "Failed to delete FDB guard rule, err: %d\n", + err); + + kfree(flow); +} + +static struct ice_esw_br_vlan * +ice_esw_br_port_vlan_lookup(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) { + dev_info(dev, "Bridge port lookup failed (vsi=%u)\n", vsi_idx); + return ERR_PTR(-EINVAL); + } + + vlan = xa_load(&port->vlans, vid); + if (!vlan) { + dev_info(dev, "Bridge port vlan metadata lookup failed (vsi=%u)\n", + vsi_idx); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static void +ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *fdb_entry) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + + rhashtable_remove_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + list_del(&fdb_entry->list); + + ice_eswitch_br_flow_delete(pf, fdb_entry->flow); + + kfree(fdb_entry); +} + +static void +ice_eswitch_br_fdb_offload_notify(struct net_device *dev, + const unsigned char *mac, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info fdb_info = { + .addr = mac, + .vid = vid, + .offloaded = true, + }; + + call_switchdev_notifiers(val, dev, &fdb_info.info, NULL); +} + +static void +ice_eswitch_br_fdb_entry_notify_and_cleanup(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *entry) +{ + if (!(entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER)) + ice_eswitch_br_fdb_offload_notify(entry->dev, entry->data.addr, + entry->data.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + ice_eswitch_br_fdb_entry_delete(bridge, entry); +} + +static void +ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge, + const unsigned char *mac, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct ice_esw_br_fdb_entry *fdb_entry; + struct device *dev = ice_pf_to_dev(pf); + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (!fdb_entry) { + dev_err(dev, "FDB entry with mac: %pM and vid: %u not found\n", + mac, vid); + return; + } + + trace_ice_eswitch_br_fdb_entry_find_and_delete(fdb_entry); + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); +} + +static void +ice_eswitch_br_fdb_entry_create(struct net_device *netdev, + struct ice_esw_br_port *br_port, + bool added_by_user, + const unsigned char *mac, u16 vid) +{ + struct ice_esw_br *bridge = br_port->bridge; + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_fdb_entry *fdb_entry; + struct ice_esw_br_flow *flow; + struct ice_esw_br_vlan *vlan; + struct ice_hw *hw = &pf->hw; + unsigned long event; + int err; + + /* untagged filtering is not yet supported */ + if (!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING) && vid) + return; + + if ((bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) { + vlan = ice_esw_br_port_vlan_lookup(bridge, br_port->vsi_idx, + vid); + if (IS_ERR(vlan)) { + dev_err(dev, "Failed to find vlan lookup, err: %ld\n", + PTR_ERR(vlan)); + return; + } + } + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (fdb_entry) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); + + fdb_entry = kzalloc(sizeof(*fdb_entry), GFP_KERNEL); + if (!fdb_entry) { + err = -ENOMEM; + goto err_exit; + } + + flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx, + br_port->type, mac, vid); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_add_flow; + } + + ether_addr_copy(fdb_entry->data.addr, mac); + fdb_entry->data.vid = vid; + fdb_entry->br_port = br_port; + fdb_entry->flow = flow; + fdb_entry->dev = netdev; + fdb_entry->last_use = jiffies; + event = SWITCHDEV_FDB_ADD_TO_BRIDGE; + + if (added_by_user) { + fdb_entry->flags |= ICE_ESWITCH_BR_FDB_ADDED_BY_USER; + event = SWITCHDEV_FDB_OFFLOADED; + } + + err = rhashtable_insert_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + if (err) + goto err_fdb_insert; + + list_add(&fdb_entry->list, &bridge->fdb_list); + trace_ice_eswitch_br_fdb_entry_create(fdb_entry); + + ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event); + + return; + +err_fdb_insert: + ice_eswitch_br_flow_delete(pf, flow); +err_add_flow: + kfree(fdb_entry); +err_exit: + dev_err(dev, "Failed to create fdb entry, err: %d\n", err); +} + +static void +ice_eswitch_br_fdb_work_dealloc(struct ice_esw_br_fdb_work *fdb_work) +{ + kfree(fdb_work->fdb_info.addr); + kfree(fdb_work); +} + +static void +ice_eswitch_br_fdb_event_work(struct work_struct *work) +{ + struct ice_esw_br_fdb_work *fdb_work = ice_work_to_fdb_work(work); + bool added_by_user = fdb_work->fdb_info.added_by_user; + const unsigned char *mac = fdb_work->fdb_info.addr; + u16 vid = fdb_work->fdb_info.vid; + struct ice_esw_br_port *br_port; + + rtnl_lock(); + + br_port = ice_eswitch_br_netdev_to_port(fdb_work->dev); + if (!br_port) + goto err_exit; + + switch (fdb_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + ice_eswitch_br_fdb_entry_create(fdb_work->dev, br_port, + added_by_user, mac, vid); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + ice_eswitch_br_fdb_entry_find_and_delete(br_port->bridge, + mac, vid); + break; + default: + goto err_exit; + } + +err_exit: + rtnl_unlock(); + dev_put(fdb_work->dev); + ice_eswitch_br_fdb_work_dealloc(fdb_work); +} + +static struct ice_esw_br_fdb_work * +ice_eswitch_br_fdb_work_alloc(struct switchdev_notifier_fdb_info *fdb_info, + struct net_device *dev, + unsigned long event) +{ + struct ice_esw_br_fdb_work *work; + unsigned char *mac; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&work->work, ice_eswitch_br_fdb_event_work); + memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info)); + + mac = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!mac) { + kfree(work); + return ERR_PTR(-ENOMEM); + } + + ether_addr_copy(mac, fdb_info->addr); + work->fdb_info.addr = mac; + work->event = event; + work->dev = dev; + + return work; +} + +static int +ice_eswitch_br_switchdev_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_fdb_info *fdb_info; + struct switchdev_notifier_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct ice_esw_br_fdb_work *work; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, switchdev_nb); + extack = switchdev_notifier_info_to_extack(ptr); + + upper = netdev_master_upper_dev_get_rcu(dev); + if (!upper) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(upper)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_is_dev_valid(dev)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_netdev_to_port(dev)) + return NOTIFY_DONE; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = container_of(info, typeof(*fdb_info), info); + + work = ice_eswitch_br_fdb_work_alloc(fdb_info, dev, event); + if (IS_ERR(work)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init switchdev fdb work"); + return notifier_from_errno(PTR_ERR(work)); + } + dev_hold(dev); + + queue_work(br_offloads->wq, &work->work); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); +} + +static void +ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable) +{ + if (enable == !!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) + return; + + ice_eswitch_br_fdb_flush(bridge); + if (enable) + bridge->flags |= ICE_ESWITCH_BR_VLAN_FILTERING; + else + bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING; +} + +static void +ice_eswitch_br_clear_pvid(struct ice_esw_br_port *port) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, port->pvid, 0); + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + + vlan_ops->del_vlan(port->vsi, &port_vlan); + vlan_ops->clear_port_vlan(port->vsi); + + ice_vf_vsi_disable_port_vlan(port->vsi); + + port->pvid = 0; +} + +static void +ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_esw_br *bridge = port->bridge; + + trace_ice_eswitch_br_vlan_cleanup(vlan); + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (vlan->vid == fdb_entry->data.vid) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + xa_erase(&port->vlans, vlan->vid); + if (port->pvid == vlan->vid) + ice_eswitch_br_clear_pvid(port); + kfree(vlan); +} + +static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port) +{ + struct ice_esw_br_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_set_pvid(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, vlan->vid, 0); + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + if (port->pvid == vlan->vid || vlan->vid == 1) + return 0; + + /* Setting port vlan on uplink isn't supported by hw */ + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + return -EOPNOTSUPP; + + if (port->pvid) { + dev_info(dev, + "Port VLAN (vsi=%u, vid=%u) already exists on the port, remove it before adding new one\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + ice_vf_vsi_enable_port_vlan(port->vsi); + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + err = vlan_ops->set_port_vlan(port->vsi, &port_vlan); + if (err) + return err; + + err = vlan_ops->add_vlan(port->vsi, &port_vlan); + if (err) + return err; + + ice_eswitch_br_port_vlans_flush(port); + port->pvid = vlan->vid; + + return 0; +} + +static struct ice_esw_br_vlan * +ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port) +{ + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_esw_br_vlan *vlan; + int err; + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + if ((flags & BRIDGE_VLAN_INFO_PVID) && + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + err = ice_eswitch_br_set_pvid(port, vlan); + if (err) + goto err_set_pvid; + } else if ((flags & BRIDGE_VLAN_INFO_PVID) || + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + dev_info(dev, "VLAN push and pop are supported only simultaneously\n"); + err = -EOPNOTSUPP; + goto err_set_pvid; + } + + err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL); + if (err) + goto err_insert; + + trace_ice_eswitch_br_vlan_create(vlan); + + return vlan; + +err_insert: + if (port->pvid) + ice_eswitch_br_clear_pvid(port); +err_set_pvid: + kfree(vlan); + return ERR_PTR(err); +} + +static int +ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid, + u16 flags, struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return -EINVAL; + + if (port->pvid) { + dev_info(ice_pf_to_dev(port->vsi->back), + "Port VLAN (vsi=%u, vid=%d) exists on the port, remove it to add trunk VLANs\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + vlan = xa_load(&port->vlans, vid); + if (vlan) { + if (vlan->flags == flags) + return 0; + + ice_eswitch_br_vlan_cleanup(port, vlan); + } + + vlan = ice_eswitch_br_vlan_create(vid, flags, port); + if (IS_ERR(vlan)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to create VLAN entry, vid: %u, vsi: %u", + vid, vsi_idx); + return PTR_ERR(vlan); + } + + return 0; +} + +static void +ice_eswitch_br_port_vlan_del(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return; + + vlan = xa_load(&port->vlans, vid); + if (!vlan) + return; + + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_port_obj_add(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + int err; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = ice_eswitch_br_port_vlan_add(br_port->bridge, + br_port->vsi_idx, vlan->vid, + vlan->flags, extack); + return err; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_del(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + ice_eswitch_br_port_vlan_del(br_port->bridge, br_port->vsi_idx, + vlan->vid); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + + if (!br_port) + return -EINVAL; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ice_eswitch_br_vlan_filtering_set(br_port->bridge, + attr->u.vlan_filtering); + return 0; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + br_port->bridge->ageing_time = + clock_t_to_jiffies(attr->u.ageing_time); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_event_blocking(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_add); + break; + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_del); + break; + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_attr_set); + break; + default: + err = 0; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, + struct ice_esw_br_port *br_port) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_vsi *vsi = br_port->vsi; + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (br_port == fdb_entry->br_port) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) + vsi->back->br_port = NULL; + else if (vsi->vf && vsi->vf->repr) + vsi->vf->repr->br_port = NULL; + + xa_erase(&bridge->ports, br_port->vsi_idx); + ice_eswitch_br_port_vlans_flush(br_port); + kfree(br_port); +} + +static struct ice_esw_br_port * +ice_eswitch_br_port_init(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *br_port; + + br_port = kzalloc(sizeof(*br_port), GFP_KERNEL); + if (!br_port) + return ERR_PTR(-ENOMEM); + + xa_init(&br_port->vlans); + + br_port->bridge = bridge; + + return br_port; +} + +static int +ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, + struct ice_repr *repr) +{ + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = repr->src_vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + repr->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static int +ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf) +{ + struct ice_vsi *vsi = pf->switchdev.uplink_vsi; + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_UPLINK_PORT; + pf->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static void +ice_eswitch_br_ports_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *port; + unsigned long i; + + xa_for_each(&bridge->ports, i, port) + ice_eswitch_br_port_deinit(bridge, port); +} + +static void +ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + if (!bridge) + return; + + /* Cleanup all the ports that were added asynchronously + * through NETDEV_CHANGEUPPER event. + */ + ice_eswitch_br_ports_flush(bridge); + WARN_ON(!xa_empty(&bridge->ports)); + xa_destroy(&bridge->ports); + rhashtable_destroy(&bridge->fdb_ht); + + br_offloads->bridge = NULL; + kfree(bridge); +} + +static struct ice_esw_br * +ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex) +{ + struct ice_esw_br *bridge; + int err; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&bridge->fdb_ht, &ice_fdb_ht_params); + if (err) { + kfree(bridge); + return ERR_PTR(err); + } + + INIT_LIST_HEAD(&bridge->fdb_list); + bridge->br_offloads = br_offloads; + bridge->ifindex = ifindex; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); + xa_init(&bridge->ports); + br_offloads->bridge = bridge; + + return bridge; +} + +static struct ice_esw_br * +ice_eswitch_br_get(struct ice_esw_br_offloads *br_offloads, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + + if (bridge) { + if (bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Only one bridge is supported per eswitch"); + return ERR_PTR(-EOPNOTSUPP); + } + return bridge; + } + + /* Create the bridge if it doesn't exist yet */ + bridge = ice_eswitch_br_init(br_offloads, ifindex); + if (IS_ERR(bridge)) + NL_SET_ERR_MSG_MOD(extack, "Failed to init the bridge"); + + return bridge; +} + +static void +ice_eswitch_br_verify_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + /* Remove the bridge if it exists and there are no ports left */ + if (!bridge || !xa_empty(&bridge->ports)) + return; + + ice_eswitch_br_deinit(br_offloads, bridge); +} + +static int +ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(dev); + struct ice_esw_br *bridge; + + if (!br_port) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is not attached to any bridge"); + return -EINVAL; + } + + if (br_port->bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is attached to another bridge"); + return -EINVAL; + } + + bridge = br_port->bridge; + + trace_ice_eswitch_br_port_unlink(br_port); + ice_eswitch_br_port_deinit(br_port->bridge, br_port); + ice_eswitch_br_verify_deinit(br_offloads, bridge); + + return 0; +} + +static int +ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge; + int err; + + if (ice_eswitch_br_netdev_to_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Port is already attached to the bridge"); + return -EINVAL; + } + + bridge = ice_eswitch_br_get(br_offloads, ifindex, extack); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); + + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + err = ice_eswitch_br_vf_repr_port_init(bridge, repr); + trace_ice_eswitch_br_port_link(repr->br_port); + } else { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return 0; + + pf = ice_netdev_to_pf(ice_dev); + + err = ice_eswitch_br_uplink_port_init(bridge, pf); + trace_ice_eswitch_br_port_link(pf->br_port); + } + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port"); + goto err_port_init; + } + + return 0; + +err_port_init: + ice_eswitch_br_verify_deinit(br_offloads, bridge); + return err; +} + +static int +ice_eswitch_br_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, netdev_nb); + + if (!ice_eswitch_br_is_dev_valid(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (info->linking) + return ice_eswitch_br_port_link(br_offloads, dev, + upper->ifindex, extack); + else + return ice_eswitch_br_port_unlink(br_offloads, dev, + upper->ifindex, extack); +} + +static int +ice_eswitch_br_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + err = ice_eswitch_br_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads; + + ASSERT_RTNL(); + + if (!br_offloads) + return; + + ice_eswitch_br_deinit(br_offloads, br_offloads->bridge); + + pf->switchdev.br_offloads = NULL; + kfree(br_offloads); +} + +static struct ice_esw_br_offloads * +ice_eswitch_br_offloads_alloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + ASSERT_RTNL(); + + if (pf->switchdev.br_offloads) + return ERR_PTR(-EEXIST); + + br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + pf->switchdev.br_offloads = br_offloads; + br_offloads->pf = pf; + + return br_offloads; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = pf->switchdev.br_offloads; + if (!br_offloads) + return; + + cancel_delayed_work_sync(&br_offloads->update_work); + unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + unregister_switchdev_notifier(&br_offloads->switchdev_nb); + destroy_workqueue(br_offloads->wq); + /* Although notifier block is unregistered just before, + * so we don't get any new events, some events might be + * already in progress. Hold the rtnl lock and wait for + * them to finished. + */ + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); +} + +static void ice_eswitch_br_update(struct ice_esw_br_offloads *br_offloads) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + struct ice_esw_br_fdb_entry *entry, *tmp; + + if (!bridge) + return; + + rtnl_lock(); + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + if (entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER) + continue; + + if (time_is_after_eq_jiffies(entry->last_use + + bridge->ageing_time)) + continue; + + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); + } + rtnl_unlock(); +} + +static void ice_eswitch_br_update_work(struct work_struct *work) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = ice_work_to_br_offloads(work); + + ice_eswitch_br_update(br_offloads); + + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); +} + +int +ice_eswitch_br_offloads_init(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + struct device *dev = ice_pf_to_dev(pf); + int err; + + rtnl_lock(); + br_offloads = ice_eswitch_br_offloads_alloc(pf); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + dev_err(dev, "Failed to init eswitch bridge\n"); + return PTR_ERR(br_offloads); + } + + br_offloads->wq = alloc_ordered_workqueue("ice_bridge_wq", 0); + if (!br_offloads->wq) { + err = -ENOMEM; + dev_err(dev, "Failed to allocate bridge workqueue\n"); + goto err_alloc_wq; + } + + br_offloads->switchdev_nb.notifier_call = + ice_eswitch_br_switchdev_event; + err = register_switchdev_notifier(&br_offloads->switchdev_nb); + if (err) { + dev_err(dev, + "Failed to register switchdev notifier\n"); + goto err_reg_switchdev_nb; + } + + br_offloads->switchdev_blk.notifier_call = + ice_eswitch_br_event_blocking; + err = register_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + if (err) { + dev_err(dev, + "Failed to register bridge blocking switchdev notifier\n"); + goto err_reg_switchdev_blk; + } + + br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + dev_err(dev, + "Failed to register bridge port event notifier\n"); + goto err_reg_netdev_nb; + } + + INIT_DELAYED_WORK(&br_offloads->update_work, + ice_eswitch_br_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); + + return 0; + +err_reg_netdev_nb: + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); +err_reg_switchdev_blk: + unregister_switchdev_notifier(&br_offloads->switchdev_nb); +err_reg_switchdev_nb: + destroy_workqueue(br_offloads->wq); +err_alloc_wq: + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); + + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h new file mode 100644 index 000000000000..85a8fadb2928 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_ESWITCH_BR_H_ +#define _ICE_ESWITCH_BR_H_ + +#include <linux/rhashtable.h> +#include <linux/workqueue.h> + +struct ice_esw_br_fdb_data { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +struct ice_esw_br_flow { + struct ice_rule_query_data *fwd_rule; + struct ice_rule_query_data *guard_rule; +}; + +enum { + ICE_ESWITCH_BR_FDB_ADDED_BY_USER = BIT(0), +}; + +struct ice_esw_br_fdb_entry { + struct ice_esw_br_fdb_data data; + struct rhash_head ht_node; + struct list_head list; + + int flags; + + struct net_device *dev; + struct ice_esw_br_port *br_port; + struct ice_esw_br_flow *flow; + + unsigned long last_use; +}; + +enum ice_esw_br_port_type { + ICE_ESWITCH_BR_UPLINK_PORT = 0, + ICE_ESWITCH_BR_VF_REPR_PORT = 1, +}; + +struct ice_esw_br_port { + struct ice_esw_br *bridge; + struct ice_vsi *vsi; + enum ice_esw_br_port_type type; + u16 vsi_idx; + u16 pvid; + struct xarray vlans; +}; + +enum { + ICE_ESWITCH_BR_VLAN_FILTERING = BIT(0), +}; + +struct ice_esw_br { + struct ice_esw_br_offloads *br_offloads; + struct xarray ports; + + struct rhashtable fdb_ht; + struct list_head fdb_list; + + int ifindex; + u32 flags; + unsigned long ageing_time; +}; + +struct ice_esw_br_offloads { + struct ice_pf *pf; + struct ice_esw_br *bridge; + struct notifier_block netdev_nb; + struct notifier_block switchdev_blk; + struct notifier_block switchdev_nb; + + struct workqueue_struct *wq; + struct delayed_work update_work; +}; + +struct ice_esw_br_fdb_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +struct ice_esw_br_vlan { + u16 vid; + u16 flags; +}; + +#define ice_nb_to_br_offloads(nb, nb_name) \ + container_of(nb, \ + struct ice_esw_br_offloads, \ + nb_name) + +#define ice_work_to_br_offloads(w) \ + container_of(w, \ + struct ice_esw_br_offloads, \ + update_work.work) + +#define ice_work_to_fdb_work(w) \ + container_of(w, \ + struct ice_esw_br_fdb_work, \ + work) + +static inline bool ice_eswitch_br_is_vid_valid(u16 vid) +{ + /* In trunk VLAN mode, for untagged traffic the bridge sends requests + * to offload VLAN 1 with pvid and untagged flags set. Since these + * flags are not supported, add a MAC filter instead. + */ + return vid > 1; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf); +int +ice_eswitch_br_offloads_init(struct ice_pf *pf); + +#endif /* _ICE_ESWITCH_BR_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index ad4d4702129f..bde9bc74f928 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -345,6 +345,88 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) +static const u32 ice_adv_lnk_speed_100[] __initconst = { + ETHTOOL_LINK_MODE_100baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_1000[] __initconst = { + ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_2500[] __initconst = { + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_5000[] __initconst = { + ETHTOOL_LINK_MODE_5000baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_10000[] __initconst = { + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_25000[] __initconst = { + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_40000[] __initconst = { + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_50000[] __initconst = { + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_100000[] __initconst = { + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_200000[] __initconst = { + ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, +}; + +static struct ethtool_forced_speed_map ice_adv_lnk_speed_maps[] __ro_after_init = { + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 1000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 2500), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 5000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 10000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 25000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 40000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 50000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 200000), +}; + +void __init ice_adv_lnk_speed_maps_init(void) +{ + ethtool_forced_speed_maps_init(ice_adv_lnk_speed_maps, + ARRAY_SIZE(ice_adv_lnk_speed_maps)); +} + static void __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, struct ice_vsi *vsi) @@ -1060,7 +1142,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, switch (stringset) { case ETH_SS_STATS: for (i = 0; i < ICE_VSI_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_vsi_stats[i].stat_string); if (ice_is_port_repr_netdev(netdev)) @@ -1080,7 +1162,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, return; for (i = 0; i < ICE_PF_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_pf_stats[i].stat_string); for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { @@ -1097,7 +1179,8 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, break; case ETH_SS_PRIV_FLAGS: for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) - ethtool_sprintf(&p, ice_gstrings_priv_flags[i].name); + ethtool_sprintf(&p, "%s", + ice_gstrings_priv_flags[i].name); break; default: break; @@ -1638,6 +1721,15 @@ ice_get_ethtool_stats(struct net_device *netdev, ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC | \ ICE_PHY_TYPE_HIGH_100G_AUI2) +#define ICE_PHY_TYPE_HIGH_MASK_200G (ICE_PHY_TYPE_HIGH_200G_CR4_PAM4 | \ + ICE_PHY_TYPE_HIGH_200G_SR4 | \ + ICE_PHY_TYPE_HIGH_200G_FR4 | \ + ICE_PHY_TYPE_HIGH_200G_LR4 | \ + ICE_PHY_TYPE_HIGH_200G_DR4 | \ + ICE_PHY_TYPE_HIGH_200G_KR4_PAM4 | \ + ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC | \ + ICE_PHY_TYPE_HIGH_200G_AUI4) + /** * ice_mask_min_supported_speeds * @hw: pointer to the HW structure @@ -1652,8 +1744,9 @@ ice_mask_min_supported_speeds(struct ice_hw *hw, u64 phy_types_high, u64 *phy_types_low) { /* if QSFP connection with 100G speed, minimum supported speed is 25G */ - if (*phy_types_low & ICE_PHY_TYPE_LOW_MASK_100G || - phy_types_high & ICE_PHY_TYPE_HIGH_MASK_100G) + if ((*phy_types_low & ICE_PHY_TYPE_LOW_MASK_100G) || + (phy_types_high & ICE_PHY_TYPE_HIGH_MASK_100G) || + (phy_types_high & ICE_PHY_TYPE_HIGH_MASK_200G)) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_25G; else if (!ice_is_100m_speed_supported(hw)) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_1G; @@ -1757,14 +1850,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev, linkmode_zero(ks->link_modes.supported); linkmode_zero(ks->link_modes.advertising); - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) { if (phy_types_low & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, req_speeds, advert_phy_type_lo, i); } - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) { if (phy_types_high & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, req_speeds, advert_phy_type_hi, @@ -1796,6 +1889,9 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, ice_phy_type_to_ethtool(netdev, ks); switch (link_info->link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + ks->base.speed = SPEED_200000; + break; case ICE_AQ_LINK_SPEED_100GB: ks->base.speed = SPEED_100000; break; @@ -2008,79 +2104,69 @@ done: } /** + * ice_speed_to_aq_link - Get AQ link speed by Ethtool forced speed + * @speed: ethtool forced speed + */ +static u16 ice_speed_to_aq_link(int speed) +{ + int aq_speed; + + switch (speed) { + case SPEED_10: + aq_speed = ICE_AQ_LINK_SPEED_10MB; + break; + case SPEED_100: + aq_speed = ICE_AQ_LINK_SPEED_100MB; + break; + case SPEED_1000: + aq_speed = ICE_AQ_LINK_SPEED_1000MB; + break; + case SPEED_2500: + aq_speed = ICE_AQ_LINK_SPEED_2500MB; + break; + case SPEED_5000: + aq_speed = ICE_AQ_LINK_SPEED_5GB; + break; + case SPEED_10000: + aq_speed = ICE_AQ_LINK_SPEED_10GB; + break; + case SPEED_20000: + aq_speed = ICE_AQ_LINK_SPEED_20GB; + break; + case SPEED_25000: + aq_speed = ICE_AQ_LINK_SPEED_25GB; + break; + case SPEED_40000: + aq_speed = ICE_AQ_LINK_SPEED_40GB; + break; + case SPEED_50000: + aq_speed = ICE_AQ_LINK_SPEED_50GB; + break; + case SPEED_100000: + aq_speed = ICE_AQ_LINK_SPEED_100GB; + break; + default: + aq_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + return aq_speed; +} + +/** * 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) { + const struct ethtool_forced_speed_map *map; 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) || - 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) || - 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) || - 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; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseKR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseSR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_50GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseLR4_ER4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_100GB; + for (u32 i = 0; i < ARRAY_SIZE(ice_adv_lnk_speed_maps); i++) { + map = ice_adv_lnk_speed_maps + i; + if (linkmode_intersects(ks->link_modes.advertising, map->caps)) + adv_link_speed |= ice_speed_to_aq_link(map->speed); + } return adv_link_speed; } @@ -3285,7 +3371,7 @@ ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; - info->phc_index = ice_get_ptp_clock_index(pf); + info->phc_index = ice_ptp_clock_index(pf); info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index b403ee79cd5e..b88e3da06f13 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -100,6 +100,14 @@ phy_type_high_lkup[] = { [2] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), [3] = ICE_PHY_TYPE(100GB, 100000baseSR2_Full), [4] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), + [5] = ICE_PHY_TYPE(200GB, 200000baseCR4_Full), + [6] = ICE_PHY_TYPE(200GB, 200000baseSR4_Full), + [7] = ICE_PHY_TYPE(200GB, 200000baseLR4_ER4_FR4_Full), + [8] = ICE_PHY_TYPE(200GB, 200000baseLR4_ER4_FR4_Full), + [9] = ICE_PHY_TYPE(200GB, 200000baseDR4_Full), + [10] = ICE_PHY_TYPE(200GB, 200000baseKR4_Full), + [11] = ICE_PHY_TYPE(200GB, 200000baseSR4_Full), + [12] = ICE_PHY_TYPE(200GB, 200000baseCR4_Full), }; #endif /* !_ICE_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 8c6e13f87b7d..d151e5bacfec 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2018-2020, Intel Corporation. */ +/* Copyright (C) 2018-2023, Intel Corporation. */ /* flow director ethtool support for ice */ @@ -540,16 +540,24 @@ static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi) /* total guaranteed filters assigned to this VSI */ num_guar = vsi->num_gfltr; - /* minus the guaranteed filters programed by this VSI */ - num_guar -= (rd32(hw, VSIQF_FD_CNT(vsi_num)) & - VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S; - /* total global best effort filters */ num_be = hw->func_caps.fd_fltr_best_effort; - /* minus the global best effort filters programmed */ - num_be -= (rd32(hw, GLQF_FD_CNT) & GLQF_FD_CNT_FD_BCNT_M) >> - GLQF_FD_CNT_FD_BCNT_S; + /* Subtract the number of programmed filters from the global values */ + switch (hw->mac_type) { + case ICE_MAC_E830: + num_guar -= FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, + rd32(hw, VSIQF_FD_CNT(vsi_num))); + num_be -= FIELD_GET(E830_GLQF_FD_CNT_FD_BCNT_M, + rd32(hw, GLQF_FD_CNT)); + break; + case ICE_MAC_E810: + default: + num_guar -= FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, + rd32(hw, VSIQF_FD_CNT(vsi_num))); + num_be -= FIELD_GET(E800_GLQF_FD_CNT_FD_BCNT_M, + rd32(hw, GLQF_FD_CNT)); + } return num_guar + num_be; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 85cca572c22a..fb8b925aaf8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1318,7 +1318,6 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, list_del(&entry->l_entry); - devm_kfree(ice_hw_to_dev(hw), entry->entry); devm_kfree(ice_hw_to_dev(hw), entry); return 0; @@ -1645,10 +1644,8 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, *entry_h = ICE_FLOW_ENTRY_HNDL(e); out: - if (status && e) { - devm_kfree(ice_hw_to_dev(hw), e->entry); + if (status) devm_kfree(ice_hw_to_dev(hw), e); - } return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index b465d27d9b80..96923ef0a5a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -350,11 +350,8 @@ struct ice_flow_entry { u64 id; struct ice_flow_prof *prof; - /* Flow entry's content */ - void *entry; enum ice_flow_priority priority; u16 vsi_handle; - u16 entry_sz; }; #define ICE_FLOW_ENTRY_HNDL(e) ((u64)(uintptr_t)e) diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 3dc5662d62a6..319a2d6fe26c 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -293,16 +293,17 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; u32 completion_offset; int err; - memset(&event, 0, sizeof(event)); - dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n", block_size, module, offset); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write); + err = ice_aq_update_nvm(hw, module, offset, block_size, block, last_cmd, 0, NULL); if (err) { @@ -319,7 +320,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, * is conservative and is intended to prevent failure to update when * firmware is slow to respond. */ - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, 15 * HZ); if (err) { dev_err(dev, "Timed out while trying to flash module 0x%02x with block of size %u at offset %u, err %d\n", module, block_size, offset, err); @@ -327,11 +328,12 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); - completion_offset = le16_to_cpu(event.desc.params.nvm.offset_low); - completion_offset |= event.desc.params.nvm.offset_high << 16; + completion_offset = le16_to_cpu(desc->params.nvm.offset_low); + completion_offset |= desc->params.nvm.offset_high << 16; if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n", @@ -363,8 +365,8 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, */ if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) { if (hw->dev_caps.common_cap.pcie_reset_avoidance) { - *reset_level = (event.desc.params.nvm.cmd_flags & - ICE_AQC_NVM_RESET_LVL_M); + *reset_level = desc->params.nvm.cmd_flags & + ICE_AQC_NVM_RESET_LVL_M; dev_dbg(dev, "Firmware reported required reset level as %u\n", *reset_level); } else { @@ -479,19 +481,20 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; struct devlink *devlink; int err; dev_dbg(dev, "Beginning erase of flash component '%s', module 0x%02x\n", component, module); - memset(&event, 0, sizeof(event)); - devlink = priv_to_devlink(pf); devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_erase); + err = ice_aq_erase_nvm(hw, module, NULL); if (err) { dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n", @@ -502,7 +505,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, ICE_FW_ERASE_TIMEOUT * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n", component, module, err); @@ -510,8 +513,9 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in erase completion for %s: got 0x%x, expected 0x%x\n", @@ -560,13 +564,13 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, u8 *emp_reset_available, struct netlink_ext_ack *extack) { struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; u16 completion_retval; u8 response_flags; int err; - memset(&event, 0, sizeof(event)); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write_activate); err = ice_nvm_write_activate(hw, activate_flags, &response_flags); if (err) { @@ -592,8 +596,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, } } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, - &event); + err = ice_aq_wait_for_event(pf, &task, 30 * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", err); @@ -601,7 +604,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, return err; } - completion_retval = le16_to_cpu(event.desc.retval); + completion_retval = le16_to_cpu(task.event.desc.retval); if (completion_retval) { dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n", ice_aq_str((enum ice_aq_err)completion_retval)); diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 75c9de675f20..c8ea1af51ad3 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -389,6 +389,9 @@ bool ice_gnss_is_gps_present(struct ice_hw *hw) if (!hw->func_caps.ts_func_info.src_tmr_owned) return false; + if (!ice_is_gps_in_netlist(hw)) + return false; + #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) if (ice_is_e810t(hw)) { int err; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index a92dc9a16035..86936b758ade 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ /* Machine-generated file */ @@ -231,6 +231,7 @@ #define PFINT_SB_CTL 0x0016B600 #define PFINT_SB_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_SB_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_TSYN_MSK 0x0016C980 #define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) #define QINT_RQCTL_MSIX_INDX_S 0 #define QINT_RQCTL_MSIX_INDX_M ICE_M(0x7FF, 0) @@ -284,11 +285,11 @@ #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 PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i) (0x001E36E0 + ((_i) * 32)) -#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8 -#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M ICE_M(0xFFFF, 0) -#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3800 + ((_i) * 32)) -#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M ICE_M(0xFFFF, 0) +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT(_i) (0x001E36E0 + ((_i) * 32)) +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_MAX 8 +#define E800_PRTMAC_HSEC_CTL_TX_PS_QNT_M GENMASK(15, 0) +#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR(_i) (0x001E3800 + ((_i) * 32)) +#define E800_PRTMAC_HSEC_CTL_TX_PS_RFSH_TMR_M GENMASK(15, 0) #define GL_MDCK_TX_TDPU 0x00049348 #define GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M BIT(1) #define GL_MDET_RX 0x00294C00 @@ -311,7 +312,11 @@ #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_BY_MAC(hw) \ + ((hw)->mac_type == ICE_MAC_E830 ? E830_GL_MDET_TX_TCLAN : \ + E800_GL_MDET_TX_TCLAN) +#define E800_GL_MDET_TX_TCLAN 0x000FC068 +#define E830_GL_MDET_TX_TCLAN 0x000FCCC0 #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 @@ -325,7 +330,11 @@ #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_BY_MAC(hw) \ + ((hw)->mac_type == ICE_MAC_E830 ? E830_PF_MDET_TX_TCLAN : \ + E800_PF_MDET_TX_TCLAN) +#define E800_PF_MDET_TX_TCLAN 0x000FC000 +#define E830_PF_MDET_TX_TCLAN 0x000FCC00 #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) @@ -335,6 +344,10 @@ #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 E800_GL_MNG_FWSM_FW_MODES_M GENMASK(2, 0) +#define E830_GL_MNG_FWSM_FW_MODES_M GENMASK(1, 0) +#define GL_MNG_FWSM 0x000B6134 +#define GL_MNG_FWSM_FW_LOADING_M BIT(30) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 @@ -361,13 +374,18 @@ #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) #define GLQF_FD_CNT 0x00460018 +#define E800_GLQF_FD_CNT_FD_GCNT_M GENMASK(14, 0) +#define E830_GLQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) #define GLQF_FD_CNT_FD_BCNT_S 16 -#define GLQF_FD_CNT_FD_BCNT_M ICE_M(0x7FFF, 16) +#define E800_GLQF_FD_CNT_FD_BCNT_M GENMASK(30, 16) +#define E830_GLQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define GLQF_FD_SIZE 0x00460010 #define GLQF_FD_SIZE_FD_GSIZE_S 0 -#define GLQF_FD_SIZE_FD_GSIZE_M ICE_M(0x7FFF, 0) +#define E800_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(14, 0) +#define E830_GLQF_FD_SIZE_FD_GSIZE_M GENMASK(15, 0) #define GLQF_FD_SIZE_FD_BSIZE_S 16 -#define GLQF_FD_SIZE_FD_BSIZE_M ICE_M(0x7FFF, 16) +#define E800_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(30, 16) +#define E830_GLQF_FD_SIZE_FD_BSIZE_M GENMASK(31, 16) #define GLQF_FDINSET(_i, _j) (0x00412000 + ((_i) * 4 + (_j) * 512)) #define GLQF_FDMASK(_i) (0x00410800 + ((_i) * 4)) #define GLQF_FDMASK_MAX_INDEX 31 @@ -386,6 +404,10 @@ #define GLQF_HMASK_SEL(_i) (0x00410000 + ((_i) * 4)) #define GLQF_HMASK_SEL_MAX_INDEX 127 #define GLQF_HMASK_SEL_MASK_SEL_S 0 +#define E800_PFQF_FD_CNT_FD_GCNT_M GENMASK(14, 0) +#define E830_PFQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) +#define E800_PFQF_FD_CNT_FD_BCNT_M GENMASK(30, 16) +#define E830_PFQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define PFQF_FD_ENA 0x0043A000 #define PFQF_FD_ENA_FD_ENA_M BIT(0) #define PFQF_FD_SIZE 0x00460100 @@ -476,6 +498,7 @@ #define GLTSYN_SYNC_DLAY 0x00088818 #define GLTSYN_TGT_H_0(_i) (0x00088930 + ((_i) * 4)) #define GLTSYN_TGT_L_0(_i) (0x00088928 + ((_i) * 4)) +#define GLTSYN_TIME_0(_i) (0x000888C8 + ((_i) * 4)) #define GLTSYN_TIME_H(_i) (0x000888D8 + ((_i) * 4)) #define GLTSYN_TIME_L(_i) (0x000888D0 + ((_i) * 4)) #define PFHH_SEM 0x000A4200 /* Reset Source: PFR */ @@ -484,12 +507,13 @@ #define PFTSYN_SEM_BUSY_M BIT(0) #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 -#define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) +#define E800_VSIQF_FD_CNT_FD_GCNT_M GENMASK(13, 0) +#define E830_VSIQF_FD_CNT_FD_GCNT_M GENMASK(15, 0) #define VSIQF_FD_CNT_FD_BCNT_S 16 -#define VSIQF_FD_CNT_FD_BCNT_M ICE_M(0x3FFF, 16) +#define E800_VSIQF_FD_CNT_FD_BCNT_M GENMASK(29, 16) +#define E830_VSIQF_FD_CNT_FD_BCNT_M GENMASK(31, 16) #define VSIQF_FD_SIZE(_VSI) (0x00462000 + ((_VSI) * 4)) #define VSIQF_HKEY_MAX_INDEX 12 -#define VSIQF_HLUT_MAX_INDEX 15 #define PFPM_APM 0x000B8080 #define PFPM_APM_APME_M BIT(0) #define PFPM_WUFC 0x0009DC00 @@ -499,6 +523,10 @@ #define PFPM_WUS_MAG_M BIT(1) #define PFPM_WUS_MNG_M BIT(3) #define PFPM_WUS_FW_RST_WK_M BIT(31) +#define E830_PRTMAC_CL01_PS_QNT 0x001E32A0 +#define E830_PRTMAC_CL01_PS_QNT_CL0_M GENMASK(15, 0) +#define E830_PRTMAC_CL01_QNT_THR 0x001E3320 +#define E830_PRTMAC_CL01_QNT_THR_CL0_M GENMASK(15, 0) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 5a7753bda324..b47cd43ae871 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -4,8 +4,27 @@ /* Link Aggregation code */ #include "ice.h" +#include "ice_lib.h" #include "ice_lag.h" +#define ICE_LAG_RES_SHARED BIT(14) +#define ICE_LAG_RES_VALID BIT(15) + +#define LACP_TRAIN_PKT_LEN 16 +static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, + 0x88, 0x09, 0, 0 }; + +#define ICE_RECIPE_LEN 64 +static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30 }; +static const u8 ice_lport_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x16, 0, 0, 0, 0xff, 0xff, 0x07, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30 }; + /** * ice_lag_set_primary - set PF LAG state as Primary * @lag: LAG info struct @@ -47,16 +66,257 @@ static void ice_lag_set_backup(struct ice_lag *lag) } /** + * netif_is_same_ice - determine if netdev is on the same ice NIC as local PF + * @pf: local PF struct + * @netdev: netdev we are evaluating + */ +static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *test_pf; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return false; + + np = netdev_priv(netdev); + if (!np) + return false; + + vsi = np->vsi; + if (!vsi) + return false; + + test_pf = vsi->back; + if (!test_pf) + return false; + + if (pf->pdev->bus != test_pf->pdev->bus || + pf->pdev->slot != test_pf->pdev->slot) + return false; + + return true; +} + +/** + * ice_netdev_to_lag - return pointer to associated lag struct from netdev + * @netdev: pointer to net_device struct to query + */ +static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return NULL; + + np = netdev_priv(netdev); + if (!np) + return NULL; + + vsi = np->vsi; + if (!vsi) + return NULL; + + return vsi->back->lag; +} + +/** + * ice_lag_find_hw_by_lport - return an hw struct from bond members lport + * @lag: lag struct + * @lport: lport value to search for + */ +static struct ice_hw * +ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) +{ + struct ice_lag_netdev_list *entry; + struct net_device *tmp_netdev; + struct ice_netdev_priv *np; + struct ice_hw *hw; + + list_for_each_entry(entry, lag->netdev_head, node) { + tmp_netdev = entry->netdev; + if (!tmp_netdev || !netif_is_ice(tmp_netdev)) + continue; + + np = netdev_priv(tmp_netdev); + if (!np || !np->vsi) + continue; + + hw = &np->vsi->back->hw; + if (hw->port_info->lport == lport) + return hw; + } + + return NULL; +} + +/** + * ice_lag_find_primary - returns pointer to primary interfaces lag struct + * @lag: local interfaces lag struct + */ +static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) +{ + struct ice_lag *primary_lag = NULL; + struct list_head *tmp; + + list_for_each(tmp, lag->netdev_head) { + struct ice_lag_netdev_list *entry; + struct ice_lag *tmp_lag; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + tmp_lag = ice_netdev_to_lag(entry->netdev); + if (tmp_lag && tmp_lag->primary) { + primary_lag = tmp_lag; + break; + } + } + + return primary_lag; +} + +/** + * ice_lag_cfg_fltr - Add/Remove rule for LAG + * @lag: lag struct for local interface + * @act: rule action + * @recipe_id: recipe id for the new rule + * @rule_idx: pointer to rule index + * @add: boolean on whether we are adding filters + */ +static int +ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, + bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule; + u16 s_rule_sz, vsi_num; + struct ice_hw *hw; + u8 *eth_hdr; + u32 opc; + int err; + + hw = &lag->pf->hw; + vsi_num = ice_get_hw_vsi_num(hw, 0); + + s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule); + s_rule = kzalloc(s_rule_sz, GFP_KERNEL); + if (!s_rule) { + dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG\n"); + return -ENOMEM; + } + + if (add) { + eth_hdr = s_rule->hdr_data; + ice_fill_eth_hdr(eth_hdr); + + act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(recipe_id); + s_rule->src = cpu_to_le16(hw->port_info->lport); + s_rule->act = cpu_to_le32(act); + s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + s_rule->index = cpu_to_le16(*rule_idx); + opc = ice_aqc_opc_remove_sw_rules; + } + + err = ice_aq_sw_rules(&lag->pf->hw, s_rule, s_rule_sz, 1, opc, NULL); + if (err) + goto dflt_fltr_free; + + if (add) + *rule_idx = le16_to_cpu(s_rule->index); + else + *rule_idx = 0; + +dflt_fltr_free: + kfree(s_rule); + return err; +} + +/** + * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + + return ice_lag_cfg_fltr(lag, act, lag->pf_recipe, + &lag->pf_rule_id, add); +} + +/** + * ice_lag_cfg_drop_fltr - Add/Remove lport drop rule + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | + ICE_SINGLE_ACT_DROP; + + return ice_lag_cfg_fltr(lag, act, lag->lport_recipe, + &lag->lport_rule_idx, add); +} + +/** + * ice_lag_cfg_pf_fltrs - set filters up for new active port + * @lag: local interfaces lag struct + * @ptr: opaque data containing notifier event + */ +static void +ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; + struct device *dev; + + event_netdev = netdev_notifier_info_to_dev(ptr); + /* not for this netdev */ + if (event_netdev != lag->netdev) + return; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + dev = ice_pf_to_dev(lag->pf); + + /* interface not active - remove old default VSI rule */ + if (bonding_info->slave.state && lag->pf_rule_id) { + if (ice_lag_cfg_dflt_fltr(lag, false)) + dev_err(dev, "Error removing old default VSI filter\n"); + if (ice_lag_cfg_drop_fltr(lag, true)) + dev_err(dev, "Error adding new drop filter\n"); + return; + } + + /* interface becoming active - add new default VSI rule */ + if (!bonding_info->slave.state && !lag->pf_rule_id) { + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(dev, "Error adding new default VSI filter\n"); + if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false)) + dev_err(dev, "Error removing old drop filter\n"); + } +} + +/** * ice_display_lag_info - print LAG info * @lag: LAG info struct */ static void ice_display_lag_info(struct ice_lag *lag) { - const char *name, *peer, *upper, *role, *bonded, *primary; + const char *name, *upper, *role, *bonded, *primary; struct device *dev = &lag->pf->pdev->dev; name = lag->netdev ? netdev_name(lag->netdev) : "unset"; - peer = lag->peer_netdev ? netdev_name(lag->peer_netdev) : "unset"; upper = lag->upper_netdev ? netdev_name(lag->upper_netdev) : "unset"; primary = lag->primary ? "TRUE" : "FALSE"; bonded = lag->bonded ? "BONDED" : "UNBONDED"; @@ -78,8 +338,445 @@ static void ice_display_lag_info(struct ice_lag *lag) role = "ERROR"; } - dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name, - bonded, peer, upper, role, primary); + dev_dbg(dev, "%s %s, upper:%s, role:%s, primary:%s\n", name, bonded, + upper, role, primary); +} + +/** + * ice_lag_qbuf_recfg - generate a buffer of queues for a reconfigure command + * @hw: HW struct that contains the queue contexts + * @qbuf: pointer to buffer to populate + * @vsi_num: index of the VSI in PF space + * @numq: number of queues to search for + * @tc: traffic class that contains the queues + * + * function returns the number of valid queues in buffer + */ +static u16 +ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf, + u16 vsi_num, u16 numq, u8 tc) +{ + struct ice_q_ctx *q_ctx; + u16 qid, count = 0; + struct ice_pf *pf; + int i; + + pf = hw->back; + for (i = 0; i < numq; i++) { + q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i); + if (!q_ctx) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d NO Q CONTEXT\n", + __func__, i); + continue; + } + if (q_ctx->q_teid == ICE_INVAL_TEID) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL TEID\n", + __func__, i); + continue; + } + if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL Q HANDLE\n", + __func__, i); + continue; + } + + qid = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle]; + qbuf->queue_info[count].q_handle = cpu_to_le16(qid); + qbuf->queue_info[count].tc = tc; + qbuf->queue_info[count].q_teid = cpu_to_le32(q_ctx->q_teid); + count++; + } + + return count; +} + +/** + * ice_lag_get_sched_parent - locate or create a sched node parent + * @hw: HW struct for getting parent in + * @tc: traffic class on parent/node + */ +static struct ice_sched_node * +ice_lag_get_sched_parent(struct ice_hw *hw, u8 tc) +{ + struct ice_sched_node *tc_node, *aggnode, *parent = NULL; + u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; + struct ice_port_info *pi = hw->port_info; + struct device *dev; + u8 aggl, vsil; + int n; + + dev = ice_hw_to_dev(hw); + + tc_node = ice_sched_get_tc_node(pi, tc); + if (!tc_node) { + dev_warn(dev, "Failure to find TC node for LAG move\n"); + return parent; + } + + aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID); + if (!aggnode) { + dev_warn(dev, "Failure to find aggregate node for LAG move\n"); + return parent; + } + + aggl = ice_sched_get_agg_layer(hw); + vsil = ice_sched_get_vsi_layer(hw); + + for (n = aggl + 1; n < vsil; n++) + num_nodes[n] = 1; + + for (n = 0; n < aggnode->num_children; n++) { + parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n], + num_nodes); + if (parent) + return parent; + } + + /* if free parent not found - add one */ + parent = aggnode; + for (n = aggl + 1; n < vsil; n++) { + u16 num_nodes_added; + u32 first_teid; + int err; + + err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n, + num_nodes[n], &first_teid, + &num_nodes_added); + if (err || num_nodes[n] != num_nodes_added) + return NULL; + + if (num_nodes_added) + parent = ice_sched_find_node_by_teid(tc_node, + first_teid); + else + parent = parent->children[0]; + if (!parent) { + dev_warn(dev, "Failure to add new parent for LAG move\n"); + return parent; + } + } + + return parent; +} + +/** + * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC + * @lag: lag info struct + * @oldport: lport of previous nodes location + * @newport: lport of destination nodes location + * @vsi_num: array index of VSI in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num, u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + struct ice_hw *new_hw = NULL; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + u32 tmp_teid; + + ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG failover\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + /* locate HW struct for destination port */ + new_hw = ice_lag_find_hw_by_lport(lag, newport); + if (!new_hw) { + dev_warn(dev, "Unable to locate HW struct for LAG node destination\n"); + return; + } + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + /* if no teid assigned or numq == 0, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend VSI subtree for Traffic Class "tc" on + * this VF's VSI + */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfigure all VF's queues on this Traffic Class + * to new port + */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_traffic; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG failover\n"); + goto qbuf_none; + } + + if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport, + newport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto qbuf_err; + } + +qbuf_none: + kfree(qbuf); + + /* find new parent in destination port's tree for VF VSI node on this + * Traffic Class + */ + n_prt = ice_lag_get_sched_parent(new_hw, tc); + if (!n_prt) + goto resume_traffic; + + /* Move Vf's VSI node for this TC to newport's scheduler tree */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for failover\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_traffic; + +qbuf_err: + kfree(qbuf); + +resume_traffic: + /* restart traffic for VSI node */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false)) + dev_dbg(dev, "Problem restarting traffic for LAG node move\n"); +} + +/** + * ice_lag_build_netdev_list - populate the lag struct's netdev list + * @lag: local lag struct + * @ndlist: pointer to netdev list to populate + */ +static void ice_lag_build_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist->node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_ATOMIC); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist->node); + } + rcu_read_unlock(); + lag->netdev_head = &ndlist->node; +} + +/** + * ice_lag_destroy_netdev_list - free lag struct's netdev list + * @lag: pointer to local lag struct + * @ndlist: pointer to lag struct netdev list + */ +static void ice_lag_destroy_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *entry, *n; + + rcu_read_lock(); + list_for_each_entry_safe(entry, n, &ndlist->node, node) { + list_del(&entry->node); + kfree(entry); + } + rcu_read_unlock(); + lag->netdev_head = NULL; +} + +/** + * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF + * @lag: primary interface LAG struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + * @vsi_num: SW index of VF's VSI + */ +static void +ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num) +{ + u8 tc; + + ice_for_each_traffic_class(tc) + ice_lag_move_vf_node_tc(lag, oldport, newport, vsi_num, tc); +} + +/** + * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required + * @vf: the VF to move Tx nodes for + * + * Called just after configuring new VF queues. Check whether the VF Tx + * scheduling nodes need to be updated to fail over to the active port. If so, + * move them now. + */ +void ice_lag_move_new_vf_nodes(struct ice_vf *vf) +{ + struct ice_lag_netdev_list ndlist; + u8 pri_port, act_port; + struct ice_lag *lag; + struct ice_vsi *vsi; + struct ice_pf *pf; + + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + if (WARN_ON(vsi->type != ICE_VSI_VF)) + return; + + pf = vf->pf; + lag = pf->lag; + + mutex_lock(&pf->lag_mutex); + if (!lag->bonded) + goto new_vf_unlock; + + pri_port = pf->hw.port_info->lport; + act_port = lag->active_port; + + if (lag->upper_netdev) + ice_lag_build_netdev_list(lag, &ndlist); + + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) && + lag->bonded && lag->primary && pri_port != act_port && + !list_empty(lag->netdev_head)) + ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx); + + ice_lag_destroy_netdev_list(lag, &ndlist); + +new_vf_unlock: + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port + * @lag: lag info struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + */ +static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) +{ + struct ice_pf *pf; + int i; + + if (!lag->primary) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_lag_move_single_vf_nodes(lag, oldport, newport, i); +} + +/** + * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context + * @lag: local lag struct + * @src_prt: lport value for source port + * @dst_prt: lport value for destination port + * + * This function is used to move nodes during an out-of-netdev-event situation, + * primarily when the driver needs to reconfigure or recreate resources. + * + * Must be called while holding the lag_mutex to avoid lag events from + * processing while out-of-sync moves are happening. Also, paired moves, + * such as used in a reset flow, should both be called under the same mutex + * lock to avoid changes between start of reset and end of reset. + */ +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt) +{ + struct ice_lag_netdev_list ndlist; + + ice_lag_build_netdev_list(lag, &ndlist); + ice_lag_move_vf_nodes(lag, src_prt, dst_prt); + ice_lag_destroy_netdev_list(lag, &ndlist); +} + +#define ICE_LAG_SRIOV_CP_RECIPE 10 +#define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 + +/** + * ice_lag_cfg_cp_fltr - configure filter for control packets + * @lag: local interface's lag struct + * @add: add or remove rule + */ +static void +ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule = NULL; + struct ice_vsi *vsi; + u16 buf_len, opc; + + vsi = lag->pf->vsi[0]; + + buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, + ICE_LAG_SRIOV_TRAIN_PKT_LEN); + s_rule = kzalloc(buf_len, GFP_KERNEL); + if (!s_rule) { + netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n"); + return; + } + + if (add) { + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE); + s_rule->src = cpu_to_le16(vsi->port_info->lport); + s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI | + ICE_SINGLE_ACT_LAN_ENABLE | + ICE_SINGLE_ACT_VALID_BIT | + ((vsi->vsi_num << + ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M)); + s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN); + memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + opc = ice_aqc_opc_remove_sw_rules; + s_rule->index = cpu_to_le16(lag->cp_rule_idx); + } + if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) { + netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n", + add ? "ADDING" : "REMOVING"); + goto cp_free; + } + + if (add) + lag->cp_rule_idx = le16_to_cpu(s_rule->index); + else + lag->cp_rule_idx = 0; + +cp_free: + kfree(s_rule); } /** @@ -124,117 +821,422 @@ lag_out: } /** + * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface + * @lag: primary interface lag struct + * @src_hw: HW struct current node location + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, + u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + /* if !teid or !numq, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_reclaim; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG reclaim\n"); + goto reclaim_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, + src_hw->port_info->lport, hw->port_info->lport, + NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto reclaim_qerr; + } + +reclaim_none: + kfree(qbuf); + + /* find parent in primary tree */ + n_prt = ice_lag_get_sched_parent(hw, tc); + if (!n_prt) + goto resume_reclaim; + + /* Move node to new parent */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_reclaim; + +reclaim_qerr: + kfree(qbuf); + +resume_reclaim: + /* restart traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n"); +} + +/** + * ice_lag_reclaim_vf_nodes - When interface leaving bond primary reclaims nodes + * @lag: primary interface lag struct + * @src_hw: HW struct for current node location + */ +static void +ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !src_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); +} + +/** * ice_lag_link - handle LAG link event * @lag: LAG info struct - * @info: info from the netdev notifier */ -static void -ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) +static void ice_lag_link(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; struct ice_pf *pf = lag->pf; - int peers = 0; if (lag->bonded) dev_warn(ice_pf_to_dev(pf), "%s Already part of a bond\n", netdev_name(lag->netdev)); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) - peers++; - rcu_read_unlock(); - - if (lag->upper_netdev != upper) { - dev_hold(upper); - lag->upper_netdev = upper; - } - - ice_clear_rdma_cap(pf); - lag->bonded = true; lag->role = ICE_LAG_UNSET; - - /* if this is the first element in an LAG mark as primary */ - lag->primary = !!(peers == 1); + netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n"); } /** * ice_lag_unlink - handle unlink event * @lag: LAG info struct - * @info: info from netdev notification */ -static void -ice_lag_unlink(struct ice_lag *lag, - struct netdev_notifier_changeupper_info *info) +static void ice_lag_unlink(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; + u8 pri_port, act_port, loc_port; struct ice_pf *pf = lag->pf; - bool found = false; if (!lag->bonded) { netdev_dbg(lag->netdev, "bonding unlink event on non-LAG netdev\n"); return; } - /* determine if we are in the new LAG config or not */ - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) { - if (netdev_tmp == lag->netdev) { - found = true; - break; + if (lag->primary) { + act_port = lag->active_port; + pri_port = lag->pf->hw.port_info->lport; + if (act_port != pri_port && act_port != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes(lag, act_port, pri_port); + lag->primary = false; + lag->active_port = ICE_LAG_INVALID_PORT; + } else { + struct ice_lag *primary_lag; + + primary_lag = ice_lag_find_primary(lag); + if (primary_lag) { + act_port = primary_lag->active_port; + pri_port = primary_lag->pf->hw.port_info->lport; + loc_port = pf->hw.port_info->lport; + if (act_port == loc_port && + act_port != ICE_LAG_INVALID_PORT) { + ice_lag_reclaim_vf_nodes(primary_lag, + &lag->pf->hw); + primary_lag->active_port = ICE_LAG_INVALID_PORT; + } } } - rcu_read_unlock(); - if (found) + lag->bonded = false; + lag->role = ICE_LAG_NONE; + lag->upper_netdev = NULL; +} + +/** + * ice_lag_link_unlink - helper function to call lag_link/unlink + * @lag: lag info struct + * @ptr: opaque pointer data + */ +static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + + if (netdev != lag->netdev) return; - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; + if (info->linking) + ice_lag_link(lag); + else + ice_lag_unlink(lag); +} + +/** + * ice_lag_set_swid - set the SWID on secondary interface + * @primary_swid: primary interface's SWID + * @local_lag: local interfaces LAG struct + * @link: Is this a linking activity + * + * If link is false, then primary_swid should be expected to not be valid + * This function should never be called in interrupt context. + */ +static void +ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag, + bool link) +{ + struct ice_aqc_alloc_free_res_elem *buf; + struct ice_aqc_set_port_params *cmd; + struct ice_aq_desc desc; + u16 buf_len, swid; + int status, i; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) { + dev_err(ice_pf_to_dev(local_lag->pf), "-ENOMEM error setting SWID\n"); + return; } - lag->peer_netdev = NULL; - ice_set_rdma_cap(pf); - lag->bonded = false; - lag->role = ICE_LAG_NONE; + buf->num_elems = cpu_to_le16(1); + buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID); + /* if unlinnking need to free the shared resource */ + if (!link && local_lag->bond_swid) { + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, + buf_len, ice_aqc_opc_free_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n"); + local_lag->bond_swid = 0; + } + + if (link) { + buf->res_type |= cpu_to_le16(ICE_LAG_RES_SHARED | + ICE_LAG_RES_VALID); + /* store the primary's SWID in case it leaves bond first */ + local_lag->bond_swid = primary_swid; + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + } else { + buf->elem[0].e.sw_resp = + cpu_to_le16(local_lag->pf->hw.port_info->sw_id); + } + + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, buf_len, + ice_aqc_opc_alloc_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n", + local_lag->bond_swid); + + kfree(buf); + + /* Configure port param SWID to correct value */ + if (link) + swid = primary_swid; + else + swid = local_lag->pf->hw.port_info->sw_id; + + cmd = &desc.params.set_port_params; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + + cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid); + /* If this is happening in reset context, it is possible that the + * primary interface has not finished setting its SWID to SHARED + * yet. Allow retries to account for this timing issue between + * interfaces. + */ + for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) { + status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, + NULL); + if (!status) + break; + + usleep_range(1000, 2000); + } + + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n", + status); } /** - * ice_lag_unregister - handle netdev unregister events - * @lag: LAG info struct - * @netdev: netdev reporting the event + * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID + * @lag: primary interface's lag struct + * @link: is this a linking activity + * + * Implement setting primary SWID as shared using 0x020B */ -static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +static void ice_lag_primary_swid(struct ice_lag *lag, bool link) { - struct ice_pf *pf = lag->pf; + struct ice_hw *hw; + u16 swid; - /* check to see if this event is for this netdev - * check that we are in an aggregate - */ - if (netdev != lag->netdev || !lag->bonded) + hw = &lag->pf->hw; + swid = hw->port_info->sw_id; + + if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid)) + dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n"); +} + +/** + * ice_lag_add_prune_list - Adds event_pf's VSI to primary's prune list + * @lag: lag info struct + * @event_pf: PF struct for VSI we are adding to primary's prune list + */ +static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + event_vsi_num = event_pf->vsi[0]->vsi_num; + prim_vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + prim_vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n"); return; + } - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; - ice_set_rdma_cap(pf); + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n"); + return; } - /* perform some cleanup in case we come back */ - lag->bonded = false; - lag->role = ICE_LAG_NONE; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_SET); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(event_vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, s_rule, rule_buf_sz, 1, + ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error adding VSI prune list\n"); + kfree(s_rule); +} + +/** + * ice_lag_del_prune_list - Remove secondary's vsi from primary's prune list + * @lag: primary interface's ice_lag struct + * @event_pf: PF struct for unlinking interface + */ +static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + vsi_num = event_pf->vsi[0]->vsi_num; + vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n"); + return; + } + + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n"); + return; + } + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error clearing VSI prune list\n"); + + kfree(s_rule); +} + +/** + * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * @pf: PF struct + */ +static void ice_lag_init_feature_support_flag(struct ice_pf *pf) +{ + struct ice_hw_common_caps *caps; + + caps = &pf->hw.dev_caps.common_cap; + if (caps->roce_lag) + ice_set_feature_support(pf, ICE_F_ROCE_LAG); + else + ice_clear_feature_support(pf, ICE_F_ROCE_LAG); + + if (caps->sriov_lag) + ice_set_feature_support(pf, ICE_F_SRIOV_LAG); + else + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); } /** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data - * - * ptr is to be cast into netdev_notifier_changeupper_info */ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) { struct netdev_notifier_changeupper_info *info; + struct ice_lag *primary_lag; struct net_device *netdev; info = ptr; @@ -244,44 +1246,437 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) if (netdev != lag->netdev) return; - if (!info->upper_dev) { - netdev_dbg(netdev, "changeupper rcvd, but no upper defined\n"); + primary_lag = ice_lag_find_primary(lag); + if (info->linking) { + lag->upper_netdev = info->upper_dev; + /* If there is not already a primary interface in the LAG, + * then mark this one as primary. + */ + if (!primary_lag) { + lag->primary = true; + /* Configure primary's SWID to be shared */ + ice_lag_primary_swid(lag, true); + primary_lag = lag; + } else { + u16 swid; + + swid = primary_lag->pf->hw.port_info->sw_id; + ice_lag_set_swid(swid, lag, true); + ice_lag_add_prune_list(primary_lag, lag->pf); + ice_lag_cfg_drop_fltr(lag, true); + } + /* add filter for primary control packets */ + ice_lag_cfg_cp_fltr(lag, true); + } else { + if (!primary_lag && lag->primary) + primary_lag = lag; + + if (!lag->primary) { + ice_lag_set_swid(0, lag, false); + } else { + if (primary_lag && lag->primary) { + ice_lag_primary_swid(lag, false); + ice_lag_del_prune_list(primary_lag, lag->pf); + } + } + /* remove filter for control packets */ + ice_lag_cfg_cp_fltr(lag, false); + } +} + +/** + * ice_lag_monitor_link - monitor interfaces entering/leaving the aggregate + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function only operates after a primary has been set. + */ +static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_hw *prim_hw, *active_hw; + struct net_device *event_netdev; + struct ice_pf *pf; + u8 prim_port; + + if (!lag->primary) return; + + event_netdev = netdev_notifier_info_to_dev(ptr); + if (!netif_is_same_ice(lag->pf, event_netdev)) + return; + + pf = lag->pf; + prim_hw = &pf->hw; + prim_port = prim_hw->port_info->lport; + + info = (struct netdev_notifier_changeupper_info *)ptr; + if (info->upper_dev != lag->upper_netdev) + return; + + if (!info->linking) { + /* Since there are only two interfaces allowed in SRIOV+LAG, if + * one port is leaving, then nodes need to be on primary + * interface. + */ + if (prim_port != lag->active_port && + lag->active_port != ICE_LAG_INVALID_PORT) { + active_hw = ice_lag_find_hw_by_lport(lag, + lag->active_port); + ice_lag_reclaim_vf_nodes(lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } } +} + +/** + * ice_lag_monitor_active - main PF keep track of which port is active + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function is for the primary PF to monitor changes in which port is + * active and handle changes for SRIOV VF functionality + */ +static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct ice_netdev_priv *event_np; + struct ice_pf *pf, *event_pf; + u8 prim_port, event_port; + + if (!lag->primary) + return; - netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK"); + pf = lag->pf; + if (!pf) + return; - if (!netif_is_lag_master(info->upper_dev)) { - netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n"); + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev) return; + + event_np = netdev_priv(event_netdev); + event_pf = event_np->vsi->back; + event_port = event_pf->hw.port_info->lport; + prim_port = pf->hw.port_info->lport; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + + if (!bonding_info->slave.state) { + /* if no port is currently active, then nodes and filters exist + * on primary port, check if we need to move them + */ + if (lag->active_port == ICE_LAG_INVALID_PORT) { + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, prim_port, + event_port); + lag->active_port = event_port; + return; + } + + /* active port is already set and is current event port */ + if (lag->active_port == event_port) + return; + /* new active port */ + ice_lag_move_vf_nodes(lag, lag->active_port, event_port); + lag->active_port = event_port; + } else { + /* port not set as currently active (e.g. new active port + * has already claimed the nodes and filters + */ + if (lag->active_port != event_port) + return; + /* This is the case when neither port is active (both link down) + * Link down on the bond - set active port to invalid and move + * nodes and filters back to primary if not already there + */ + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, event_port, prim_port); + lag->active_port = ICE_LAG_INVALID_PORT; } +} - if (info->linking) - ice_lag_link(lag, info); - else - ice_lag_unlink(lag, info); +/** + * ice_lag_chk_comp - evaluate bonded interface for feature support + * @lag: lag info struct + * @ptr: opaque data for netdev event info + */ +static bool +ice_lag_chk_comp(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct list_head *tmp; + struct device *dev; + int count = 0; - ice_display_lag_info(lag); + if (!lag->primary) + return true; + + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (event_upper != lag->upper_netdev) + return true; + + dev = ice_pf_to_dev(lag->pf); + + /* only supporting switchdev mode for SRIOV VF LAG. + * primary interface has to be in switchdev mode + */ + if (!ice_is_switchdev_running(lag->pf)) { + dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n"); + return false; + } + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + lag->bond_mode = bonding_info->master.bond_mode; + if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) { + dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n"); + return false; + } + + list_for_each(tmp, lag->netdev_head) { + struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg; + struct ice_lag_netdev_list *entry; + struct ice_netdev_priv *peer_np; + struct net_device *peer_netdev; + struct ice_vsi *vsi, *peer_vsi; + struct ice_pf *peer_pf; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + peer_netdev = entry->netdev; + if (!netif_is_ice(peer_netdev)) { + dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + count++; + if (count > 2) { + dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n"); + return false; + } + + peer_np = netdev_priv(peer_netdev); + vsi = ice_get_main_vsi(lag->pf); + peer_vsi = peer_np->vsi; + if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus || + lag->pf->pdev->slot != peer_vsi->back->pdev->slot) { + dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg; + if (memcmp(dcb_cfg, peer_dcb_cfg, + sizeof(struct ice_dcbx_cfg))) { + dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + peer_pf = peer_vsi->back; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) { + dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + } + + return true; } /** - * ice_lag_changelower_event - handle LAG changelower event + * ice_lag_unregister - handle netdev unregister events * @lag: LAG info struct - * @ptr: opaque data pointer + * @event_netdev: netdev struct for target of notifier event + */ +static void +ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *event_pf; + struct ice_lag *p_lag; + + p_lag = ice_lag_find_primary(lag); + np = netdev_priv(event_netdev); + event_pf = np->vsi->back; + + if (p_lag) { + if (p_lag->active_port != p_lag->pf->hw.port_info->lport && + p_lag->active_port != ICE_LAG_INVALID_PORT) { + struct ice_hw *active_hw; + + active_hw = ice_lag_find_hw_by_lport(lag, + p_lag->active_port); + if (active_hw) + ice_lag_reclaim_vf_nodes(p_lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } + } + + /* primary processing for primary */ + if (lag->primary && lag->netdev == event_netdev) + ice_lag_primary_swid(lag, false); + + /* primary processing for secondary */ + if (lag->primary && lag->netdev != event_netdev) + ice_lag_del_prune_list(lag, event_pf); + + /* secondary processing for secondary */ + if (!lag->primary && lag->netdev == event_netdev) + ice_lag_set_swid(0, lag, false); +} + +/** + * ice_lag_monitor_rdma - set and clear rdma functionality + * @lag: pointer to lag struct + * @ptr: opaque data for netdev event info + */ +static void +ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct net_device *netdev; + + info = ptr; + netdev = netdev_notifier_info_to_dev(ptr); + + if (netdev != lag->netdev) + return; + + if (info->linking) + ice_clear_rdma_cap(lag->pf); + else + ice_set_rdma_cap(lag->pf); +} + +/** + * ice_lag_chk_disabled_bond - monitor interfaces entering/leaving disabled bond + * @lag: lag info struct + * @ptr: opaque data containing event * - * ptr to be cast to netdev_notifier_changelowerstate_info + * as interfaces enter a bond - determine if the bond is currently + * SRIOV LAG compliant and flag if not. As interfaces leave the + * bond, reset their compliant status. */ -static void ice_lag_changelower_event(struct ice_lag *lag, void *ptr) +static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_lag *prim_lag; if (netdev != lag->netdev) return; - netdev_dbg(netdev, "bonding info\n"); + if (info->linking) { + prim_lag = ice_lag_find_primary(lag); + if (prim_lag && + !ice_is_feature_supported(prim_lag->pf, ICE_F_SRIOV_LAG)) { + ice_clear_feature_support(lag->pf, ICE_F_SRIOV_LAG); + netdev_info(netdev, "Interface added to non-compliant SRIOV LAG aggregate\n"); + } + } else { + ice_lag_init_feature_support_flag(lag->pf); + } +} + +/** + * ice_lag_disable_sriov_bond - set members of bond as not supporting SRIOV LAG + * @lag: primary interfaces lag struct + */ +static void ice_lag_disable_sriov_bond(struct ice_lag *lag) +{ + struct ice_netdev_priv *np; + struct ice_pf *pf; + + np = netdev_priv(lag->netdev); + pf = np->vsi->back; + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); +} + +/** + * ice_lag_process_event - process a task assigned to the lag_wq + * @work: pointer to work_struct + */ +static void ice_lag_process_event(struct work_struct *work) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_lag_work *lag_work; + struct net_device *netdev; + struct list_head *tmp, *n; + struct ice_pf *pf; + + lag_work = container_of(work, struct ice_lag_work, lag_task); + pf = lag_work->lag->pf; + + mutex_lock(&pf->lag_mutex); + lag_work->lag->netdev_head = &lag_work->netdev_list.node; + + switch (lag_work->event) { + case NETDEV_CHANGEUPPER: + info = &lag_work->info.changeupper_info; + ice_lag_chk_disabled_bond(lag_work->lag, info); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + ice_lag_monitor_link(lag_work->lag, info); + ice_lag_changeupper_event(lag_work->lag, info); + ice_lag_link_unlink(lag_work->lag, info); + } + ice_lag_monitor_rdma(lag_work->lag, info); + break; + case NETDEV_BONDING_INFO: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + if (!ice_lag_chk_comp(lag_work->lag, + &lag_work->info.bonding_info)) { + netdev = lag_work->info.bonding_info.info.dev; + ice_lag_disable_sriov_bond(lag_work->lag); + ice_lag_unregister(lag_work->lag, netdev); + goto lag_cleanup; + } + ice_lag_monitor_active(lag_work->lag, + &lag_work->info.bonding_info); + ice_lag_cfg_pf_fltrs(lag_work->lag, + &lag_work->info.bonding_info); + } + ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info); + break; + case NETDEV_UNREGISTER: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + netdev = lag_work->info.bonding_info.info.dev; + if ((netdev == lag_work->lag->netdev || + lag_work->lag->primary) && lag_work->lag->bonded) + ice_lag_unregister(lag_work->lag, netdev); + } + break; + default: + break; + } + +lag_cleanup: + /* cleanup resources allocated for this work item */ + list_for_each_safe(tmp, n, &lag_work->netdev_list.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + lag_work->lag->netdev_head = NULL; + + mutex_unlock(&pf->lag_mutex); - if (!netif_is_lag_port(netdev)) - netdev_dbg(netdev, "CHANGELOWER rcvd, but netdev not in LAG. Bail\n"); + kfree(lag_work); } /** @@ -295,34 +1690,79 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_netdev; + struct ice_lag_work *lag_work; struct ice_lag *lag; - lag = container_of(notif_blk, struct ice_lag, notif_block); + if (!netif_is_ice(netdev)) + return NOTIFY_DONE; + + if (event != NETDEV_CHANGEUPPER && event != NETDEV_BONDING_INFO && + event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (!(netdev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + lag = container_of(notif_blk, struct ice_lag, notif_block); if (!lag->netdev) return NOTIFY_DONE; - /* Check that the netdev is in the working namespace */ if (!net_eq(dev_net(netdev), &init_net)) return NOTIFY_DONE; + /* This memory will be freed at the end of ice_lag_process_event */ + lag_work = kzalloc(sizeof(*lag_work), GFP_KERNEL); + if (!lag_work) + return -ENOMEM; + + lag_work->event_netdev = netdev; + lag_work->lag = lag; + lag_work->event = event; + if (event == NETDEV_CHANGEUPPER) { + struct netdev_notifier_changeupper_info *info; + + info = ptr; + upper_netdev = info->upper_dev; + } else { + upper_netdev = netdev_master_upper_dev_get(netdev); + } + + INIT_LIST_HEAD(&lag_work->netdev_list.node); + if (upper_netdev) { + struct ice_lag_netdev_list *nd_list; + struct net_device *tmp_nd; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) { + nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC); + if (!nd_list) + break; + + nd_list->netdev = tmp_nd; + list_add(&nd_list->node, &lag_work->netdev_list.node); + } + rcu_read_unlock(); + } + switch (event) { case NETDEV_CHANGEUPPER: - ice_lag_changeupper_event(lag, ptr); - break; - case NETDEV_CHANGELOWERSTATE: - ice_lag_changelower_event(lag, ptr); + lag_work->info.changeupper_info = + *((struct netdev_notifier_changeupper_info *)ptr); break; case NETDEV_BONDING_INFO: - ice_lag_info_event(lag, ptr); - break; - case NETDEV_UNREGISTER: - ice_lag_unregister(lag, netdev); + lag_work->info.bonding_info = + *((struct netdev_notifier_bonding_info *)ptr); break; default: + lag_work->info.notifier_info = + *((struct netdev_notifier_info *)ptr); break; } + INIT_WORK(&lag_work->lag_task, ice_lag_process_event); + queue_work(ice_lag_wq, &lag_work->lag_task); + return NOTIFY_DONE; } @@ -366,6 +1806,166 @@ static void ice_unregister_lag_handler(struct ice_lag *lag) } /** + * ice_create_lag_recipe + * @hw: pointer to HW struct + * @rid: pointer to u16 to pass back recipe index + * @base_recipe: recipe to base the new recipe on + * @prio: priority for new recipe + * + * function returns 0 on error + */ +static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid, + const u8 *base_recipe, u8 prio) +{ + struct ice_aqc_recipe_data_elem *new_rcp; + int err; + + err = ice_alloc_recipe(hw, rid); + if (err) + return err; + + new_rcp = kzalloc(ICE_RECIPE_LEN * ICE_MAX_NUM_RECIPES, GFP_KERNEL); + if (!new_rcp) + return -ENOMEM; + + memcpy(new_rcp, base_recipe, ICE_RECIPE_LEN); + new_rcp->content.act_ctrl_fwd_priority = prio; + new_rcp->content.rid = *rid | ICE_AQ_RECIPE_ID_IS_ROOT; + new_rcp->recipe_indx = *rid; + bitmap_zero((unsigned long *)new_rcp->recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(*rid, (unsigned long *)new_rcp->recipe_bitmap); + + err = ice_aq_add_recipe(hw, new_rcp, 1, NULL); + if (err) + *rid = 0; + + kfree(new_rcp); + return err; +} + +/** + * ice_lag_move_vf_nodes_tc_sync - move a VF's nodes for a tc during reset + * @lag: primary interfaces lag struct + * @dest_hw: HW struct for destination's interface + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, + u16 vsi_num, u8 tc) +{ + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + struct device *dev = ice_pf_to_dev(lag->pf); + u16 numq, valq, num_moved, qbuf_size; + u16 buf_size = __struct_size(buf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n"); + return; + } + + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + if (!tmp_teid || !numq) + return; + + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic during reset rebuild\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n"); + goto resume_sync; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n"); + goto sync_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport, + dest_hw->port_info->lport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n"); + goto sync_qerr; + } + +sync_none: + kfree(qbuf); + + /* find parent in destination tree */ + n_prt = ice_lag_get_sched_parent(dest_hw, tc); + if (!n_prt) + goto resume_sync; + + /* Move node to new parent */ + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved)) + dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + goto resume_sync; + +sync_qerr: + kfree(qbuf); + +resume_sync: + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n"); +} + +/** + * ice_lag_move_vf_nodes_sync - move vf nodes to active interface + * @lag: primary interfaces lag struct + * @dest_hw: lport value for currently active port + * + * This function is used in a reset context, outside of event handling, + * to move the VF nodes to the secondary interface when that interface + * is the active interface during a reset rebuild + */ +static void +ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !dest_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, + tc); +} + +/** * ice_init_lag - initialize support for LAG * @pf: PF struct * @@ -377,7 +1977,12 @@ int ice_init_lag(struct ice_pf *pf) struct device *dev = ice_pf_to_dev(pf); struct ice_lag *lag; struct ice_vsi *vsi; - int err; + u64 recipe_bits = 0; + int n, err; + + ice_lag_init_feature_support_flag(pf); + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + return 0; pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -394,8 +1999,8 @@ int ice_init_lag(struct ice_pf *pf) lag->pf = pf; lag->netdev = vsi->netdev; lag->role = ICE_LAG_NONE; + lag->active_port = ICE_LAG_INVALID_PORT; lag->bonded = false; - lag->peer_netdev = NULL; lag->upper_netdev = NULL; lag->notif_block.notifier_call = NULL; @@ -405,11 +2010,39 @@ int ice_init_lag(struct ice_pf *pf) goto lag_error; } + err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, + ice_dflt_vsi_rcp, 1); + if (err) + goto lag_error; + + err = ice_create_lag_recipe(&pf->hw, &lag->lport_recipe, + ice_lport_rcp, 3); + if (err) + goto free_rcp_res; + + /* associate recipes to profiles */ + for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { + err = ice_aq_get_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + if (err) + continue; + + if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) { + recipe_bits |= BIT(lag->pf_recipe) | + BIT(lag->lport_recipe); + ice_aq_map_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + } + } + ice_display_lag_info(lag); dev_dbg(dev, "INIT LAG complete\n"); return 0; +free_rcp_res: + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); lag_error: kfree(lag); pf->lag = NULL; @@ -435,11 +2068,107 @@ void ice_deinit_lag(struct ice_pf *pf) if (lag->pf) ice_unregister_lag_handler(lag); - dev_put(lag->upper_netdev); + flush_workqueue(ice_lag_wq); - dev_put(lag->peer_netdev); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->lport_recipe); kfree(lag); pf->lag = NULL; } + +/** + * ice_lag_rebuild - rebuild lag resources after reset + * @pf: pointer to local pf struct + * + * PF resets are promoted to CORER resets when interface in an aggregate. This + * means that we need to rebuild the PF resources for the interface. Since + * this will happen outside the normal event processing, need to acquire the lag + * lock. + * + * This function will also evaluate the VF resources if this is the primary + * interface. + */ +void ice_lag_rebuild(struct ice_pf *pf) +{ + struct ice_lag_netdev_list ndlist; + struct ice_lag *lag, *prim_lag; + u8 act_port, loc_port; + + if (!pf->lag || !pf->lag->bonded) + return; + + mutex_lock(&pf->lag_mutex); + + lag = pf->lag; + if (lag->primary) { + prim_lag = lag; + } else { + ice_lag_build_netdev_list(lag, &ndlist); + prim_lag = ice_lag_find_primary(lag); + } + + if (!prim_lag) { + dev_dbg(ice_pf_to_dev(pf), "No primary interface in aggregate, can't rebuild\n"); + goto lag_rebuild_out; + } + + act_port = prim_lag->active_port; + loc_port = lag->pf->hw.port_info->lport; + + /* configure SWID for this port */ + if (lag->primary) { + ice_lag_primary_swid(lag, true); + } else { + ice_lag_set_swid(prim_lag->pf->hw.port_info->sw_id, lag, true); + ice_lag_add_prune_list(prim_lag, pf); + if (act_port == loc_port) + ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw); + } + + ice_lag_cfg_cp_fltr(lag, true); + + if (lag->pf_rule_id) + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n"); + + ice_clear_rdma_cap(pf); +lag_rebuild_out: + ice_lag_destroy_netdev_list(lag, &ndlist); + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_is_switchdev_running + * @pf: pointer to PF structure + * + * Check if switchdev is running on any of the interfaces connected to lag. + */ +bool ice_lag_is_switchdev_running(struct ice_pf *pf) +{ + struct ice_lag *lag = pf->lag; + struct net_device *tmp_nd; + + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || !lag) + return false; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + struct ice_netdev_priv *priv = netdev_priv(tmp_nd); + + if (!netif_is_ice(tmp_nd) || !priv || !priv->vsi || + !priv->vsi->back) + continue; + + if (ice_is_switchdev_running(priv->vsi->back)) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 2c373676c42f..ede833dfa658 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -14,20 +14,56 @@ enum ice_lag_role { ICE_LAG_UNSET }; +#define ICE_LAG_INVALID_PORT 0xFF + +#define ICE_LAG_RESET_RETRIES 5 + struct ice_pf; +struct ice_vf; + +struct ice_lag_netdev_list { + struct list_head node; + struct net_device *netdev; +}; /* LAG info struct */ struct ice_lag { struct ice_pf *pf; /* backlink to PF struct */ struct net_device *netdev; /* this PF's netdev */ - struct net_device *peer_netdev; struct net_device *upper_netdev; /* upper bonding netdev */ + struct list_head *netdev_head; struct notifier_block notif_block; + s32 bond_mode; + u16 bond_swid; /* swid for primary interface */ + u8 active_port; /* lport value for the current active port */ u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ + u16 pf_recipe; + u16 lport_recipe; + u16 pf_rule_id; + u16 cp_rule_idx; + u16 lport_rule_idx; u8 role; }; +/* LAG workqueue struct */ +struct ice_lag_work { + struct work_struct lag_task; + struct ice_lag_netdev_list netdev_list; + struct ice_lag *lag; + unsigned long event; + struct net_device *event_netdev; + union { + struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_bonding_info bonding_info; + struct netdev_notifier_info notifier_info; + } info; +}; + +void ice_lag_move_new_vf_nodes(struct ice_vf *vf); int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); +void ice_lag_rebuild(struct ice_pf *pf); +bool ice_lag_is_switchdev_running(struct ice_pf *pf); +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0054d7e64ec3..1bad6e17f9be 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -229,7 +229,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the * original vector count */ - vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF; + vsi->num_q_vectors = vf->num_msix - ICE_NONQ_VECS_VF; break; case ICE_VSI_CTRL: vsi->alloc_txq = 1; @@ -907,6 +907,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) { struct ice_hw_common_caps *cap; struct ice_pf *pf = vsi->back; + u16 max_rss_size; if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->rss_size = 1; @@ -914,32 +915,31 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) } cap = &pf->hw.func_caps.common_cap; + max_rss_size = BIT(cap->rss_table_entry_width); switch (vsi->type) { case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ vsi->rss_table_size = (u16)cap->rss_table_size; if (vsi->type == ICE_VSI_CHNL) - vsi->rss_size = min_t(u16, vsi->num_rxq, - BIT(cap->rss_table_entry_width)); + vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size); else vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + max_rss_size); + vsi->rss_lut_type = ICE_LUT_PF; break; case ICE_VSI_SWITCHDEV_CTRL: - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; - vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; + vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size); + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_VF: /* VF VSI will get 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_table_size = ICE_LUT_VSI_SIZE; vsi->rss_size = ICE_MAX_RSS_QS_PER_VF; - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_LB: break; @@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) 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); + (hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M); } static void @@ -1228,6 +1227,17 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) } /** + * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not + * @vsi: VSI to check whether or not VLAN pruning is enabled. + * + * returns true if Rx VLAN pruning is enabled and false otherwise. + */ +static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +{ + return vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; +} + +/** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured * @vsi_flags: VSI configuration flags @@ -1685,6 +1695,27 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) } /** + * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length + * @vsi: VSI + */ +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +{ + if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; +#if (PAGE_SIZE < 8192) + } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + vsi->rx_buf_len = ICE_RXBUF_3072; + } +} + +/** * ice_pf_state_is_nominal - checks the PF for nominal state * @pf: pointer to PF to check * @@ -1759,27 +1790,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; - vsi->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_3072; - } -} - -/** * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register * @hw: HW pointer * @pf_q: index of the Rx queue in the PF's queue space @@ -1821,21 +1831,14 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) { - struct ice_aqc_add_tx_qgrp *qg_buf; - int err; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) return -EINVAL; - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - qg_buf->num_txqs = 1; - err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); - kfree(qg_buf); - return err; + return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); } /** @@ -1877,24 +1880,18 @@ setup_rings: static int ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { - struct ice_aqc_add_tx_qgrp *qg_buf; - u16 q_idx = 0; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); int err = 0; - - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; + u16 q_idx; qg_buf->num_txqs = 1; for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) - goto err_cfg_txqs; + break; } -err_cfg_txqs: - kfree(qg_buf); return err; } @@ -2185,20 +2182,6 @@ bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) return false; } -/** - * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not - * @vsi: VSI to check whether or not VLAN pruning is enabled. - * - * returns true if Rx VLAN pruning is enabled and false otherwise. - */ -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) -{ - if (!vsi) - return false; - - return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); -} - static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { @@ -2388,6 +2371,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) } else { max_txqs[i] = vsi->alloc_txq; } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); @@ -2637,10 +2623,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; - if (vsi->agg_node) { - vsi->agg_node->valid = false; - vsi->agg_node->agg_id = 0; - } } /** @@ -2944,21 +2926,6 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) } /** - * ice_napi_del - Remove NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be removed - */ -void ice_napi_del(struct ice_vsi *vsi) -{ - int v_idx; - - if (!vsi->netdev) - return; - - ice_for_each_q_vector(vsi, v_idx) - netif_napi_del(&vsi->q_vectors[v_idx]->napi); -} - -/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -3593,6 +3560,12 @@ int ice_set_dflt_vsi(struct ice_vsi *vsi) dev = ice_pf_to_dev(vsi->back); + if (ice_lag_is_switchdev_running(vsi->back)) { + dev_dbg(dev, "VSI %d passed is a part of LAG containing interfaces in switchdev mode, nothing to do\n", + vsi->vsi_num); + return 0; + } + /* the VSI passed in is already the default VSI */ if (ice_is_vsi_dflt_vsi(vsi)) { dev_dbg(dev, "VSI %d passed in is already the default forwarding VSI, nothing to do\n", @@ -3970,7 +3943,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) * @pf: pointer to the struct ice_pf instance * @f: feature enum to set */ -static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) { if (f < 0 || f >= ICE_F_MAX) return; @@ -4003,13 +3976,21 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_BACKPLANE: case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810_XXV_BACKPLANE: + case ICE_DEV_ID_E810_XXV_QSFP: + case ICE_DEV_ID_E810_XXV_SFP: ice_set_feature_support(pf, ICE_F_DSCP); - ice_set_feature_support(pf, ICE_F_PTP_EXTTS); - if (ice_is_e810t(&pf->hw)) { + if (ice_is_phy_rclk_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_PHY_RCLK); + /* If we don't own the timer - don't enable other caps */ + if (!ice_pf_src_tmr_owned(pf)) + break; + if (ice_is_cgu_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_CGU); + if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) - ice_set_feature_support(pf, ICE_F_GNSS); - } + if (ice_gnss_is_gps_present(&pf->hw)) + ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; @@ -4076,3 +4057,28 @@ void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) { ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; } + +/** + * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit + * @vsi: pointer to VSI structure + * @set: set or unset the bit + */ +int +ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set) +{ + struct ice_vsi_ctx ctx = { + .info = vsi->info, + }; + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + if (set) + ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + else + ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e985766e6bb5..f24f5d1e6f9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -76,8 +76,6 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); - void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -93,8 +91,6 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); -void ice_napi_del(struct ice_vsi *vsi); - int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); @@ -130,7 +126,6 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); void ice_write_itr(struct ice_ring_container *rc, u16 itr); void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); @@ -157,11 +152,13 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); +int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set); int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b40dfe6ae321..fb9c93f37e84 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ /* Intel(R) Ethernet Connection E800 Series Linux Driver */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <generated/utsrelease.h> +#include <linux/crash_dump.h> #include "ice.h" #include "ice_base.h" #include "ice_lib.h" @@ -64,6 +65,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw) } static struct workqueue_struct *ice_wq; +struct workqueue_struct *ice_lag_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -80,7 +82,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); -bool netif_is_ice(struct net_device *dev) +bool netif_is_ice(const struct net_device *dev) { return dev && (dev->netdev_ops == &ice_netdev_ops); } @@ -635,6 +637,11 @@ 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); + if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) { + dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + ice_prepare_for_reset(pf, reset_type); /* trigger the reset */ @@ -718,8 +725,13 @@ static void ice_reset_subtask(struct ice_pf *pf) } /* No pending resets to finish processing. Check for new resets */ - if (test_bit(ICE_PFR_REQ, pf->state)) + if (test_bit(ICE_PFR_REQ, pf->state)) { reset_type = ICE_RESET_PFR; + if (pf->lag && pf->lag->bonded) { + dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + } if (test_bit(ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; if (test_bit(ICE_GLOBR_REQ, pf->state)) @@ -1239,64 +1251,63 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) return status; } -enum ice_aq_task_state { - ICE_AQ_TASK_WAITING = 0, - ICE_AQ_TASK_COMPLETE, - ICE_AQ_TASK_CANCELED, -}; - -struct ice_aq_task { - struct hlist_node entry; +/** + * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware + * @pf: pointer to the PF private structure + * @task: intermediate helper storage and identifier for waiting + * @opcode: the opcode to wait for + * + * Prepares to wait for a specific AdminQ completion event on the ARQ for + * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event(). + * + * Calls are separated to allow caller registering for event before sending + * the command, which mitigates a race between registering and FW responding. + * + * To obtain only the descriptor contents, pass an task->event with null + * msg_buf. If the complete data buffer is desired, allocate the + * task->event.msg_buf with enough space ahead of time. + */ +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode) +{ + INIT_HLIST_NODE(&task->entry); + task->opcode = opcode; + task->state = ICE_AQ_TASK_WAITING; - u16 opcode; - struct ice_rq_event_info *event; - enum ice_aq_task_state state; -}; + spin_lock_bh(&pf->aq_wait_lock); + hlist_add_head(&task->entry, &pf->aq_wait_list); + spin_unlock_bh(&pf->aq_wait_lock); +} /** * ice_aq_wait_for_event - Wait for an AdminQ event from firmware * @pf: pointer to the PF private structure - * @opcode: the opcode to wait for + * @task: ptr prepared by ice_aq_prep_for_event() * @timeout: how long to wait, in jiffies - * @event: storage for the event info * * Waits for a specific AdminQ completion event on the ARQ for a given PF. The * current thread will be put to sleep until the specified event occurs or * until the given timeout is reached. * - * To obtain only the descriptor contents, pass an event without an allocated - * msg_buf. If the complete data buffer is desired, allocate the - * event->msg_buf with enough space ahead of time. - * * Returns: zero on success, or a negative error code on failure. */ -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event) +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout) { + enum ice_aq_task_state *state = &task->state; struct device *dev = ice_pf_to_dev(pf); - struct ice_aq_task *task; - unsigned long start; + unsigned long start = jiffies; long ret; int err; - task = kzalloc(sizeof(*task), GFP_KERNEL); - if (!task) - return -ENOMEM; - - INIT_HLIST_NODE(&task->entry); - task->opcode = opcode; - task->event = event; - task->state = ICE_AQ_TASK_WAITING; - - spin_lock_bh(&pf->aq_wait_lock); - hlist_add_head(&task->entry, &pf->aq_wait_list); - spin_unlock_bh(&pf->aq_wait_lock); - - start = jiffies; - - ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state, + ret = wait_event_interruptible_timeout(pf->aq_wait_queue, + *state != ICE_AQ_TASK_WAITING, timeout); - switch (task->state) { + switch (*state) { + case ICE_AQ_TASK_NOT_PREPARED: + WARN(1, "call to %s without ice_aq_prep_for_event()", __func__); + err = -EINVAL; + break; case ICE_AQ_TASK_WAITING: err = ret < 0 ? ret : -ETIMEDOUT; break; @@ -1307,7 +1318,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, err = ret < 0 ? ret : 0; break; default: - WARN(1, "Unexpected AdminQ wait task state %u", task->state); + WARN(1, "Unexpected AdminQ wait task state %u", *state); err = -EINVAL; break; } @@ -1315,12 +1326,11 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n", jiffies_to_msecs(jiffies - start), jiffies_to_msecs(timeout), - opcode); + task->opcode); spin_lock_bh(&pf->aq_wait_lock); hlist_del(&task->entry); spin_unlock_bh(&pf->aq_wait_lock); - kfree(task); return err; } @@ -1346,23 +1356,26 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, struct ice_rq_event_info *event) { + struct ice_rq_event_info *task_ev; struct ice_aq_task *task; bool found = false; spin_lock_bh(&pf->aq_wait_lock); hlist_for_each_entry(task, &pf->aq_wait_list, entry) { - if (task->state || task->opcode != opcode) + if (task->state != ICE_AQ_TASK_WAITING) + continue; + if (task->opcode != opcode) continue; - memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); - task->event->msg_len = event->msg_len; + task_ev = &task->event; + memcpy(&task_ev->desc, &event->desc, sizeof(event->desc)); + task_ev->msg_len = event->msg_len; /* Only copy the data buffer if a destination was set */ - if (task->event->msg_buf && - task->event->buf_len > event->buf_len) { - memcpy(task->event->msg_buf, event->msg_buf, + if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) { + memcpy(task_ev->msg_buf, event->msg_buf, event->buf_len); - task->event->buf_len = event->buf_len; + task_ev->buf_len = event->buf_len; } task->state = ICE_AQ_TASK_COMPLETE; @@ -1746,7 +1759,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) wr32(hw, GL_MDET_TX_PQM, 0xffffffff); } - reg = rd32(hw, GL_MDET_TX_TCLAN); + reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw)); 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; @@ -1760,7 +1773,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (netif_msg_tx_err(pf)) dev_info(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); + wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX); } reg = rd32(hw, GL_MDET_RX); @@ -1788,9 +1801,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n"); } - reg = rd32(hw, PF_MDET_TX_TCLAN); + reg = rd32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & PF_MDET_TX_TCLAN_VALID_M) { - wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + wr32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw), 0xffff); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n"); } @@ -3137,7 +3150,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & PFINT_OICR_TSYN_TX_M) { ena_mask &= ~PFINT_OICR_TSYN_TX_M; - if (!hw->reset_ongoing) + if (!hw->reset_ongoing && ice_ptp_pf_handles_tx_interrupt(pf)) set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); } @@ -3147,7 +3160,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) ena_mask &= ~PFINT_OICR_TSYN_EVNT_M; - if (hw->func_caps.ts_func_info.src_tmr_owned) { + if (ice_pf_src_tmr_owned(pf)) { /* Save EVENTs from GLTSYN register */ pf->ptp.ext_ts_irq |= gltsyn_stat & (GLTSYN_STAT_EVENT0_M | @@ -3392,6 +3405,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD; } /** @@ -3794,6 +3808,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); @@ -3856,7 +3871,8 @@ static void ice_set_pf_caps(struct ice_pf *pf) } clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); - if (func_caps->common_cap.ieee_1588) + if (func_caps->common_cap.ieee_1588 && + !(pf->hw.mac_type == ICE_MAC_E830)) set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); pf->max_pf_txqs = func_caps->common_cap.num_txq; @@ -3874,6 +3890,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); mutex_init(&pf->adev_mutex); + mutex_init(&pf->lag_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -4506,6 +4523,31 @@ static void ice_deinit_eth(struct ice_pf *pf) ice_decfg_netdev(vsi); } +/** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + static int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); @@ -4518,6 +4560,18 @@ static int ice_init_dev(struct ice_pf *pf) return err; } + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + err = ice_wait_for_fw(hw, 30000); + if (err) { + dev_err(dev, "ice_wait_for_fw timed out"); + return err; + } + } + ice_init_feature_support(pf); ice_request_fw(pf); @@ -4613,6 +4667,10 @@ static void ice_init_features(struct ice_pf *pf) if (ice_is_feature_supported(pf, ICE_F_GNSS)) ice_gnss_init(pf); + if (ice_is_feature_supported(pf, ICE_F_CGU) || + ice_is_feature_supported(pf, ICE_F_PHY_RCLK)) + ice_dpll_init(pf); + /* Note: Flow director init failure is non-fatal to load */ if (ice_init_fdir(pf)) dev_err(dev, "could not initialize flow director\n"); @@ -4631,6 +4689,9 @@ static void ice_init_features(struct ice_pf *pf) static void ice_deinit_features(struct ice_pf *pf) { + if (ice_is_safe_mode(pf)) + return; + ice_deinit_lag(pf); if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) ice_cfg_lldp_mib_change(&pf->hw, false); @@ -4639,6 +4700,8 @@ static void ice_deinit_features(struct ice_pf *pf) ice_gnss_exit(pf); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_release(pf); + if (test_bit(ICE_FLAG_DPLL, pf->flags)) + ice_dpll_deinit(pf); } static void ice_init_wakeup(struct ice_pf *pf) @@ -4962,6 +5025,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return -EINVAL; } + /* when under a kdump kernel initiate a reset before enabling the + * device in order to clear out any pending DMA transactions. These + * transactions can cause some systems to machine check when doing + * the pcim_enable_device() below. + */ + if (is_kdump_kernel()) { + pci_save_state(pdev); + pci_clear_master(pdev); + err = pcie_flr(pdev); + if (err) + return err; + pci_restore_state(pdev); + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ @@ -5465,7 +5542,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } - ice_restore_all_vfs_msi_state(pdev); + ice_restore_all_vfs_msi_state(pf); ice_do_reset(pf, ICE_RESET_PFR); ice_service_task_restart(pf); @@ -5508,34 +5585,38 @@ static void ice_pci_err_reset_done(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_E810C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP_DD) }, /* required last entry */ - { 0, } + {} }; MODULE_DEVICE_TABLE(pci, ice_pci_tbl); @@ -5559,6 +5640,8 @@ static struct pci_driver ice_driver = { #endif /* CONFIG_PM */ .shutdown = ice_shutdown, .sriov_configure = ice_sriov_configure, + .sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix, + .sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count, .err_handler = &ice_pci_err_handler }; @@ -5570,23 +5653,37 @@ static struct pci_driver ice_driver = { */ static int __init ice_module_init(void) { - int status; + int status = -ENOMEM; pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); + ice_adv_lnk_speed_maps_init(); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); - return -ENOMEM; + return status; + } + + ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0); + if (!ice_lag_wq) { + pr_err("Failed to create LAG workqueue\n"); + goto err_dest_wq; } status = pci_register_driver(&ice_driver); if (status) { pr_err("failed to register PCI driver, err %d\n", status); - destroy_workqueue(ice_wq); + goto err_dest_lag_wq; } + return 0; + +err_dest_lag_wq: + destroy_workqueue(ice_lag_wq); +err_dest_wq: + destroy_workqueue(ice_wq); return status; } module_init(ice_module_init); @@ -5601,6 +5698,7 @@ static void __exit ice_module_exit(void) { pci_unregister_driver(&ice_driver); destroy_workqueue(ice_wq); + destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); } module_exit(ice_module_exit); @@ -5703,7 +5801,7 @@ static void ice_set_rx_mode(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - if (!vsi) + if (!vsi || ice_is_switchdev_running(vsi->back)) return; /* Set the flags to synchronize filters @@ -6255,7 +6353,7 @@ static void ice_tx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); @@ -6275,7 +6373,7 @@ static void ice_rx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); @@ -7303,10 +7401,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } - /* configure PTP timestamping after VSI rebuild */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_cfg_timestamp(pf, false); - err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL); if (err) { dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err); @@ -7356,6 +7450,11 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_RESET_FAILED, pf->state); ice_plug_aux_dev(pf); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + ice_lag_rebuild(pf); + + /* Restore timestamp mode settings after VSI rebuild */ + ice_ptp_restore_timestamp_mode(pf); return; err_vsi_rebuild: diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 6a9364761165..f6f27361c3cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -287,6 +287,7 @@ struct ice_nvgre_hdr { * M = EVLAN (0x8100) - Outer L2 header has EVLAN (ethernet type 0x8100) * N = EVLAN (0x9100) - Outer L2 header has EVLAN (ethernet type 0x9100) */ +#define ICE_PKT_FROM_NETWORK BIT(3) #define ICE_PKT_VLAN_STAG BIT(12) #define ICE_PKT_VLAN_ITAG BIT(13) #define ICE_PKT_VLAN_EVLAN (BIT(14) | BIT(15)) @@ -392,10 +393,10 @@ enum ice_hw_metadata_offset { }; enum ice_pkt_flags { - ICE_PKT_FLAGS_VLAN = 0, - ICE_PKT_FLAGS_TUNNEL = 1, - ICE_PKT_FLAGS_TCP = 2, - ICE_PKT_FLAGS_ERROR = 3, + ICE_PKT_FLAGS_MDID20 = 0, + ICE_PKT_FLAGS_MDID21 = 1, + ICE_PKT_FLAGS_MDID22 = 2, + ICE_PKT_FLAGS_MDID23 = 3, }; struct ice_hw_metadata { diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 81d96a40d5a7..71f405f8a6fe 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -39,8 +39,8 @@ ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) /* initialize with defaults */ for (i = 0; i < NUM_PTP_PINS_E810T; i++) { - snprintf(ptp_pins[i].name, sizeof(ptp_pins[i].name), - "%s", ice_pin_desc_e810t[i].name); + strscpy(ptp_pins[i].name, ice_pin_desc_e810t[i].name, + sizeof(ptp_pins[i].name)); ptp_pins[i].index = ice_pin_desc_e810t[i].index; ptp_pins[i].func = ice_pin_desc_e810t[i].func; ptp_pins[i].chan = ice_pin_desc_e810t[i].chan; @@ -256,36 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, } /** - * ice_set_tx_tstamp - Enable or disable Tx timestamping - * @pf: The PF pointer to search in - * @on: bool value for whether timestamps are enabled or disabled + * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device + * @pf: Board private structure + * + * Program the device to respond appropriately to the Tx timestamp interrupt + * cause. */ -static void ice_set_tx_tstamp(struct ice_pf *pf, bool on) +static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf) { - struct ice_vsi *vsi; + struct ice_hw *hw = &pf->hw; + bool enable; u32 val; - u16 i; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return; - /* Set the timestamp enable flag for all the Tx rings */ - ice_for_each_txq(vsi, i) { - if (!vsi->tx_rings[i]) - continue; - vsi->tx_rings[i]->ptp_tx = on; + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_ALL: + /* React to interrupts across all quads. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); + enable = true; + break; + case ICE_PTP_TX_INTERRUPT_NONE: + /* Do not react to interrupts on any quad. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); + enable = false; + break; + case ICE_PTP_TX_INTERRUPT_SELF: + default: + enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON; + break; } /* Configure the Tx timestamp interrupt */ - val = rd32(&pf->hw, PFINT_OICR_ENA); - if (on) + val = rd32(hw, PFINT_OICR_ENA); + if (enable) val |= PFINT_OICR_TSYN_TX_M; else val &= ~PFINT_OICR_TSYN_TX_M; - wr32(&pf->hw, PFINT_OICR_ENA, val); - - pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + wr32(hw, PFINT_OICR_ENA, val); } /** @@ -299,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) u16 i; vsi = ice_get_main_vsi(pf); - if (!vsi) + if (!vsi || !vsi->rx_rings) return; /* Set the timestamp flag for all the Rx rings */ @@ -308,148 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) continue; vsi->rx_rings[i]->ptp_rx = on; } - - pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL : - HWTSTAMP_FILTER_NONE; } /** - * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit + * ice_ptp_disable_timestamp_mode - Disable current timestamp mode * @pf: Board private structure - * @ena: bool value to enable or disable time stamp - * - * This function will configure timestamping during PTP initialization - * and deinitialization - */ -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) -{ - ice_set_tx_tstamp(pf, ena); - ice_set_rx_tstamp(pf, ena); -} - -/** - * ice_get_ptp_clock_index - Get the PTP clock index - * @pf: the PF pointer - * - * Determine the clock index of the PTP clock associated with this device. If - * this is the PF controlling the clock, just use the local access to the - * clock device pointer. - * - * Otherwise, read from the driver shared parameters to determine the clock - * index value. - * - * Returns: the index of the PTP clock associated with this device, or -1 if - * there is no associated clock. - */ -int ice_get_ptp_clock_index(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; - struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - u32 value; - int err; - - /* Use the ptp_clock structure if we're the main PF */ - if (pf->ptp.clock) - return ptp_clock_index(pf->ptp.clock); - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; - - err = ice_aq_get_driver_param(hw, param_idx, &value, NULL); - if (err) { - dev_err(dev, "Failed to read PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - return -1; - } - - /* The PTP clock index is an integer, and will be between 0 and - * INT_MAX. The highest bit of the driver shared parameter is used to - * indicate whether or not the currently stored clock index is valid. - */ - if (!(value & PTP_SHARED_CLK_IDX_VALID)) - return -1; - - return value & ~PTP_SHARED_CLK_IDX_VALID; -} - -/** - * ice_set_ptp_clock_index - Set the PTP clock index - * @pf: the PF pointer - * - * Set the PTP clock index for this device into the shared driver parameters, - * so that other PFs associated with this device can read it. * - * If the PF is unable to store the clock index, it will log an error, but - * will continue operating PTP. + * Called during preparation for reset to temporarily disable timestamping on + * the device. Called during remove to disable timestamping while cleaning up + * driver resources. */ -static void ice_set_ptp_clock_index(struct ice_pf *pf) +static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - u32 value; - int err; - - if (!pf->ptp.clock) - return; - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + u32 val; - value = (u32)ptp_clock_index(pf->ptp.clock); - if (value > INT_MAX) { - dev_err(dev, "PTP Clock index is too large to store\n"); - return; - } - value |= PTP_SHARED_CLK_IDX_VALID; + val = rd32(hw, PFINT_OICR_ENA); + val &= ~PFINT_OICR_TSYN_TX_M; + wr32(hw, PFINT_OICR_ENA, val); - err = ice_aq_set_driver_param(hw, param_idx, value, NULL); - if (err) { - dev_err(dev, "Failed to set PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - } + ice_set_rx_tstamp(pf, false); } /** - * ice_clear_ptp_clock_index - Clear the PTP clock index - * @pf: the PF pointer + * ice_ptp_restore_timestamp_mode - Restore timestamp configuration + * @pf: Board private structure * - * Clear the PTP clock index for this device. Must be called when - * unregistering the PTP clock, in order to ensure other PFs stop reporting - * a clock object that no longer exists. + * Called at the end of rebuild to restore timestamp configuration after + * a device reset. */ -static void ice_clear_ptp_clock_index(struct ice_pf *pf) +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - enum ice_aqc_driver_params param_idx; struct ice_hw *hw = &pf->hw; - u8 tmr_idx; - int err; + bool enable_rx; - /* Do not clear the index if we don't own the timer */ - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return; + ice_ptp_cfg_tx_interrupt(pf); - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - if (!tmr_idx) - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; - else - param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + ice_set_rx_tstamp(pf, enable_rx); - err = ice_aq_set_driver_param(hw, param_idx, 0, NULL); - if (err) { - dev_dbg(dev, "Failed to clear PTP clock index parameter, err %d aq_err %s\n", - err, ice_aq_str(hw->adminq.sq_last_status)); - } + /* Trigger an immediate software interrupt to ensure that timestamps + * which occurred during reset are handled now. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); } /** @@ -674,9 +582,6 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) int err; u8 idx; - if (!tx->init) - return; - ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); hw = &pf->hw; @@ -775,6 +680,39 @@ skip_ts_read: } /** + * ice_ptp_tx_tstamp_owner - Process Tx timestamps for all ports on the device + * @pf: Board private structure + */ +static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + unsigned int i; + + mutex_lock(&pf->ptp.ports_owner.lock); + list_for_each_entry(port, &pf->ptp.ports_owner.ports, list_member) { + struct ice_ptp_tx *tx = &port->tx; + + if (!tx || !tx->init) + continue; + + ice_ptp_process_tx_tstamp(tx); + } + mutex_unlock(&pf->ptp.ports_owner.lock); + + for (i = 0; i < ICE_MAX_QUAD; i++) { + u64 tstamp_ready; + int err; + + /* Read the Tx ready status first */ + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (err || tstamp_ready) + return ICE_TX_TSTAMP_WORK_PENDING; + } + + return ICE_TX_TSTAMP_WORK_DONE; +} + +/** * ice_ptp_tx_tstamp - Process Tx timestamps for this function. * @tx: Tx tracking structure to initialize * @@ -1366,6 +1304,7 @@ out_unlock: void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) { struct ice_ptp_port *ptp_port; + struct ice_hw *hw = &pf->hw; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; @@ -1380,11 +1319,16 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; - /* E810 devices do not need to reconfigure the PHY */ - if (ice_is_e810(&pf->hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: + /* Do not reconfigure E810 PHY */ return; - - ice_ptp_port_phy_restart(ptp_port); + case ICE_PHY_E822: + ice_ptp_port_phy_restart(ptp_port); + return; + default: + dev_warn(ice_pf_to_dev(pf), "%s: Unknown PHY type\n", __func__); + } } /** @@ -1441,6 +1385,24 @@ static void ice_ptp_reset_phy_timestamping(struct ice_pf *pf) } /** + * ice_ptp_restart_all_phy - Restart all PHYs to recalibrate timestamping + * @pf: Board private structure + */ +static void ice_ptp_restart_all_phy(struct ice_pf *pf) +{ + struct list_head *entry; + + list_for_each(entry, &pf->ptp.ports_owner.ports) { + struct ice_ptp_port *port = list_entry(entry, + struct ice_ptp_port, + list_member); + + if (port->link_up) + ice_ptp_port_phy_restart(port); + } +} + +/** * ice_ptp_adjfine - Adjust clock increment rate * @info: the driver's PTP info structure * @scaled_ppm: Parts per million with 16-bit fractional field @@ -1877,9 +1839,9 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* Reenable periodic outputs */ ice_ptp_enable_all_clkout(pf); - /* Recalibrate and re-enable timestamp block */ - if (pf->ptp.port.link_up) - ice_ptp_port_phy_restart(&pf->ptp.port); + /* Recalibrate and re-enable timestamp blocks for E822/E823 */ + if (hw->phy_model == ICE_PHY_E822) + ice_ptp_restart_all_phy(pf); exit: if (err) { dev_err(ice_pf_to_dev(pf), "PTP failed to set time %d\n", err); @@ -1976,21 +1938,32 @@ ice_ptp_get_syncdevicetime(ktime_t *device, u32 hh_lock, hh_art_ctl; int i; - /* Get the HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); +#define MAX_HH_HW_LOCK_TRIES 5 +#define MAX_HH_CTL_LOCK_TRIES 100 + + for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) { + /* Get the HW lock */ + hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); + if (hh_lock & PFHH_SEM_BUSY_M) { + usleep_range(10000, 15000); + continue; + } + break; + } if (hh_lock & PFHH_SEM_BUSY_M) { dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n"); - return -EFAULT; + return -EBUSY; } + /* Program cmd to master timer */ + ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); + /* Start the ART and device clock sync sequence */ hh_art_ctl = rd32(hw, GLHH_ART_CTL); hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M; wr32(hw, GLHH_ART_CTL, hh_art_ctl); -#define MAX_HH_LOCK_TRIES 100 - - for (i = 0; i < MAX_HH_LOCK_TRIES; i++) { + for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) { /* Wait for sync to complete */ hh_art_ctl = rd32(hw, GLHH_ART_CTL); if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) { @@ -2014,19 +1987,23 @@ ice_ptp_get_syncdevicetime(ktime_t *device, break; } } + + /* Clear the master timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Release HW lock */ hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); hh_lock = hh_lock & ~PFHH_SEM_BUSY_M; wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock); - if (i == MAX_HH_LOCK_TRIES) + if (i == MAX_HH_CTL_LOCK_TRIES) return -ETIMEDOUT; return 0; } /** - * ice_ptp_getcrosststamp_e822 - Capture a device cross timestamp + * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp * @info: the driver's PTP info structure * @cts: The memory to fill the cross timestamp info * @@ -2034,14 +2011,14 @@ ice_ptp_get_syncdevicetime(ktime_t *device, * clock. Fill the cross timestamp information and report it back to the * caller. * - * This is only valid for E822 devices which have support for generating the - * cross timestamp via PCIe PTM. + * This is only valid for E822 and E823 devices which have support for + * generating the cross timestamp via PCIe PTM. * * In order to correctly correlate the ART timestamp back to the TSC time, the * CPU must have X86_FEATURE_TSC_KNOWN_FREQ. */ static int -ice_ptp_getcrosststamp_e822(struct ptp_clock_info *info, +ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info, struct system_device_crosststamp *cts) { struct ice_pf *pf = ptp_info_to_pf(info); @@ -2081,10 +2058,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { switch (config->tx_type) { case HWTSTAMP_TX_OFF: - ice_set_tx_tstamp(pf, false); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF; break; case HWTSTAMP_TX_ON: - ice_set_tx_tstamp(pf, true); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON; break; default: return -ERANGE; @@ -2092,7 +2069,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - ice_set_rx_tstamp(pf, false); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: @@ -2108,12 +2085,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_ALL: - ice_set_rx_tstamp(pf, true); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } + /* Immediately update the device timestamping mode */ + ice_ptp_restore_timestamp_mode(pf); + return 0; } @@ -2246,18 +2226,20 @@ ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) static void ice_ptp_setup_pins_e810(struct ice_pf *pf, struct ptp_clock_info *info) { - info->n_per_out = N_PER_OUT_E810; - - if (ice_is_feature_supported(pf, ICE_F_PTP_EXTTS)) - info->n_ext_ts = N_EXT_TS_E810; - if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { info->n_ext_ts = N_EXT_TS_E810; + info->n_per_out = N_PER_OUT_E810T; info->n_pins = NUM_PTP_PINS_E810T; info->verify = ice_verify_pin_e810t; /* Complete setup of the SMA pins */ ice_ptp_setup_sma_pins_e810t(pf, info); + } else if (ice_is_e810t(&pf->hw)) { + info->n_ext_ts = N_EXT_TS_NO_SMA_E810T; + info->n_per_out = N_PER_OUT_NO_SMA_E810T; + } else { + info->n_per_out = N_PER_OUT_E810; + info->n_ext_ts = N_EXT_TS_E810; } } @@ -2275,22 +2257,22 @@ ice_ptp_setup_pins_e823(struct ice_pf *pf, struct ptp_clock_info *info) } /** - * ice_ptp_set_funcs_e822 - Set specialized functions for E822 support + * ice_ptp_set_funcs_e82x - Set specialized functions for E82x support * @pf: Board private structure * @info: PTP info to fill * - * Assign functions to the PTP capabiltiies structure for E822 devices. + * Assign functions to the PTP capabiltiies structure for E82x devices. * Functions which operate across all device families should be set directly - * in ice_ptp_set_caps. Only add functions here which are distinct for E822 + * in ice_ptp_set_caps. Only add functions here which are distinct for E82x * devices. */ static void -ice_ptp_set_funcs_e822(struct ice_pf *pf, struct ptp_clock_info *info) +ice_ptp_set_funcs_e82x(struct ice_pf *pf, struct ptp_clock_info *info) { #ifdef CONFIG_ICE_HWTS if (boot_cpu_has(X86_FEATURE_ART) && boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) - info->getcrosststamp = ice_ptp_getcrosststamp_e822; + info->getcrosststamp = ice_ptp_getcrosststamp_e82x; #endif /* CONFIG_ICE_HWTS */ } @@ -2324,6 +2306,8 @@ ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) static void ice_ptp_set_funcs_e823(struct ice_pf *pf, struct ptp_clock_info *info) { + ice_ptp_set_funcs_e82x(pf, info); + info->enable = ice_ptp_gpio_enable_e823; ice_ptp_setup_pins_e823(pf, info); } @@ -2351,7 +2335,7 @@ static void ice_ptp_set_caps(struct ice_pf *pf) else if (ice_is_e823(&pf->hw)) ice_ptp_set_funcs_e823(pf, info); else - ice_ptp_set_funcs_e822(pf, info); + ice_ptp_set_funcs_e82x(pf, info); } /** @@ -2366,7 +2350,6 @@ static void ice_ptp_set_caps(struct ice_pf *pf) static long ice_ptp_create_clock(struct ice_pf *pf) { struct ptp_clock_info *info; - struct ptp_clock *clock; struct device *dev; /* No need to create a clock device if we already have one */ @@ -2379,11 +2362,11 @@ static long ice_ptp_create_clock(struct ice_pf *pf) dev = ice_pf_to_dev(pf); /* Attempt to register the clock before enabling the hardware. */ - clock = ptp_clock_register(info, dev); - if (IS_ERR(clock)) - return PTR_ERR(clock); - - pf->ptp.clock = clock; + pf->ptp.clock = ptp_clock_register(info, dev); + if (IS_ERR(pf->ptp.clock)) { + dev_err(ice_pf_to_dev(pf), "Failed to register PTP clock device"); + return PTR_ERR(pf->ptp.clock); + } return 0; } @@ -2440,7 +2423,21 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) */ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) { - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_NONE: + /* This device has the clock owner handle timestamps for it */ + return ICE_TX_TSTAMP_WORK_DONE; + case ICE_PTP_TX_INTERRUPT_SELF: + /* This device handles its own timestamps */ + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + case ICE_PTP_TX_INTERRUPT_ALL: + /* This device handles timestamps for all ports */ + return ice_ptp_tx_tstamp_owner(pf); + default: + WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", + pf->ptp.tx_interrupt_mode); + return ICE_TX_TSTAMP_WORK_DONE; + } } static void ice_ptp_periodic_work(struct kthread_work *work) @@ -2474,7 +2471,7 @@ void ice_ptp_reset(struct ice_pf *pf) if (test_bit(ICE_PFR_REQ, pf->state)) goto pfr; - if (!hw->func_caps.ts_func_info.src_tmr_owned) + if (!ice_pf_src_tmr_owned(pf)) goto reset_ts; err = ice_ptp_init_phc(hw); @@ -2550,6 +2547,209 @@ err: } /** + * ice_ptp_aux_dev_to_aux_pf - Get auxiliary PF handle for the auxiliary device + * @aux_dev: auxiliary device to get the auxiliary PF for + */ +static struct ice_pf * +ice_ptp_aux_dev_to_aux_pf(struct auxiliary_device *aux_dev) +{ + struct ice_ptp_port *aux_port; + struct ice_ptp *aux_ptp; + + aux_port = container_of(aux_dev, struct ice_ptp_port, aux_dev); + aux_ptp = container_of(aux_port, struct ice_ptp, port); + + return container_of(aux_ptp, struct ice_pf, ptp); +} + +/** + * ice_ptp_aux_dev_to_owner_pf - Get PF handle for the auxiliary device + * @aux_dev: auxiliary device to get the PF for + */ +static struct ice_pf * +ice_ptp_aux_dev_to_owner_pf(struct auxiliary_device *aux_dev) +{ + struct ice_ptp_port_owner *ports_owner; + struct auxiliary_driver *aux_drv; + struct ice_ptp *owner_ptp; + + if (!aux_dev->dev.driver) + return NULL; + + aux_drv = to_auxiliary_drv(aux_dev->dev.driver); + ports_owner = container_of(aux_drv, struct ice_ptp_port_owner, + aux_driver); + owner_ptp = container_of(ports_owner, struct ice_ptp, ports_owner); + return container_of(owner_ptp, struct ice_pf, ptp); +} + +/** + * ice_ptp_auxbus_probe - Probe auxiliary devices + * @aux_dev: PF's auxiliary device + * @id: Auxiliary device ID + */ +static int ice_ptp_auxbus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id) +{ + struct ice_pf *owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + struct ice_pf *aux_pf = ice_ptp_aux_dev_to_aux_pf(aux_dev); + + if (WARN_ON(!owner_pf)) + return -ENODEV; + + INIT_LIST_HEAD(&aux_pf->ptp.port.list_member); + mutex_lock(&owner_pf->ptp.ports_owner.lock); + list_add(&aux_pf->ptp.port.list_member, + &owner_pf->ptp.ports_owner.ports); + mutex_unlock(&owner_pf->ptp.ports_owner.lock); + + return 0; +} + +/** + * ice_ptp_auxbus_remove - Remove auxiliary devices from the bus + * @aux_dev: PF's auxiliary device + */ +static void ice_ptp_auxbus_remove(struct auxiliary_device *aux_dev) +{ + struct ice_pf *owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + struct ice_pf *aux_pf = ice_ptp_aux_dev_to_aux_pf(aux_dev); + + mutex_lock(&owner_pf->ptp.ports_owner.lock); + list_del(&aux_pf->ptp.port.list_member); + mutex_unlock(&owner_pf->ptp.ports_owner.lock); +} + +/** + * ice_ptp_auxbus_shutdown + * @aux_dev: PF's auxiliary device + */ +static void ice_ptp_auxbus_shutdown(struct auxiliary_device *aux_dev) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ +} + +/** + * ice_ptp_auxbus_suspend + * @aux_dev: PF's auxiliary device + * @state: power management state indicator + */ +static int +ice_ptp_auxbus_suspend(struct auxiliary_device *aux_dev, pm_message_t state) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ + return 0; +} + +/** + * ice_ptp_auxbus_resume + * @aux_dev: PF's auxiliary device + */ +static int ice_ptp_auxbus_resume(struct auxiliary_device *aux_dev) +{ + /* Doing nothing here, but handle to auxbus driver must be satisfied */ + return 0; +} + +/** + * ice_ptp_auxbus_create_id_table - Create auxiliary device ID table + * @pf: Board private structure + * @name: auxiliary bus driver name + */ +static struct auxiliary_device_id * +ice_ptp_auxbus_create_id_table(struct ice_pf *pf, const char *name) +{ + struct auxiliary_device_id *ids; + + /* Second id left empty to terminate the array */ + ids = devm_kcalloc(ice_pf_to_dev(pf), 2, + sizeof(struct auxiliary_device_id), GFP_KERNEL); + if (!ids) + return NULL; + + snprintf(ids[0].name, sizeof(ids[0].name), "ice.%s", name); + + return ids; +} + +/** + * ice_ptp_register_auxbus_driver - Register PTP auxiliary bus driver + * @pf: Board private structure + */ +static int ice_ptp_register_auxbus_driver(struct ice_pf *pf) +{ + struct auxiliary_driver *aux_driver; + struct ice_ptp *ptp; + struct device *dev; + char *name; + int err; + + ptp = &pf->ptp; + dev = ice_pf_to_dev(pf); + aux_driver = &ptp->ports_owner.aux_driver; + INIT_LIST_HEAD(&ptp->ports_owner.ports); + mutex_init(&ptp->ports_owner.lock); + name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", + pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), + ice_get_ptp_src_clock_index(&pf->hw)); + + aux_driver->name = name; + aux_driver->shutdown = ice_ptp_auxbus_shutdown; + aux_driver->suspend = ice_ptp_auxbus_suspend; + aux_driver->remove = ice_ptp_auxbus_remove; + aux_driver->resume = ice_ptp_auxbus_resume; + aux_driver->probe = ice_ptp_auxbus_probe; + aux_driver->id_table = ice_ptp_auxbus_create_id_table(pf, name); + if (!aux_driver->id_table) + return -ENOMEM; + + err = auxiliary_driver_register(aux_driver); + if (err) { + devm_kfree(dev, aux_driver->id_table); + dev_err(dev, "Failed registering aux_driver, name <%s>\n", + name); + } + + return err; +} + +/** + * ice_ptp_unregister_auxbus_driver - Unregister PTP auxiliary bus driver + * @pf: Board private structure + */ +static void ice_ptp_unregister_auxbus_driver(struct ice_pf *pf) +{ + struct auxiliary_driver *aux_driver = &pf->ptp.ports_owner.aux_driver; + + auxiliary_driver_unregister(aux_driver); + devm_kfree(ice_pf_to_dev(pf), aux_driver->id_table); + + mutex_destroy(&pf->ptp.ports_owner.lock); +} + +/** + * ice_ptp_clock_index - Get the PTP clock index for this device + * @pf: Board private structure + * + * Returns: the PTP clock index associated with this PF, or -1 if no PTP clock + * is associated. + */ +int ice_ptp_clock_index(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev; + struct ice_pf *owner_pf; + struct ptp_clock *clock; + + aux_dev = &pf->ptp.port.aux_dev; + owner_pf = ice_ptp_aux_dev_to_owner_pf(aux_dev); + if (!owner_pf) + return -1; + clock = owner_pf->ptp.clock; + + return clock ? ptp_clock_index(clock) : -1; +} + +/** * ice_ptp_prepare_for_reset - Prepare PTP for reset * @pf: Board private structure */ @@ -2561,7 +2761,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf) clear_bit(ICE_FLAG_PTP, pf->flags); /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); kthread_cancel_delayed_work_sync(&ptp->work); @@ -2639,11 +2839,15 @@ static int ice_ptp_init_owner(struct ice_pf *pf) if (err) goto err_clk; - /* Store the PTP clock index for other PFs */ - ice_set_ptp_clock_index(pf); + err = ice_ptp_register_auxbus_driver(pf); + if (err) { + dev_err(ice_pf_to_dev(pf), "Failed to register PTP auxbus driver"); + goto err_aux; + } return 0; - +err_aux: + ptp_clock_unregister(pf->ptp.clock); err_clk: pf->ptp.clock = NULL; err_exit: @@ -2685,14 +2889,117 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) */ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) { + struct ice_hw *hw = &pf->hw; + mutex_init(&ptp_port->ps_lock); - if (ice_is_e810(&pf->hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_ptp_init_tx_e810(pf, &ptp_port->tx); + case ICE_PHY_E822: + kthread_init_delayed_work(&ptp_port->ov_work, + ice_ptp_wait_for_offsets); + + return ice_ptp_init_tx_e822(pf, &ptp_port->tx, + ptp_port->port_num); + default: + return -ENODEV; + } +} - kthread_init_delayed_work(&ptp_port->ov_work, - ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e822(pf, &ptp_port->tx, ptp_port->port_num); +/** + * ice_ptp_release_auxbus_device + * @dev: device that utilizes the auxbus + */ +static void ice_ptp_release_auxbus_device(struct device *dev) +{ + /* Doing nothing here, but handle to auxbux device must be satisfied */ +} + +/** + * ice_ptp_create_auxbus_device - Create PTP auxiliary bus device + * @pf: Board private structure + */ +static int ice_ptp_create_auxbus_device(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev; + struct ice_ptp *ptp; + struct device *dev; + char *name; + int err; + u32 id; + + ptp = &pf->ptp; + id = ptp->port.port_num; + dev = ice_pf_to_dev(pf); + + aux_dev = &ptp->port.aux_dev; + + name = devm_kasprintf(dev, GFP_KERNEL, "ptp_aux_dev_%u_%u_clk%u", + pf->pdev->bus->number, PCI_SLOT(pf->pdev->devfn), + ice_get_ptp_src_clock_index(&pf->hw)); + + aux_dev->name = name; + aux_dev->id = id; + aux_dev->dev.release = ice_ptp_release_auxbus_device; + aux_dev->dev.parent = dev; + + err = auxiliary_device_init(aux_dev); + if (err) + goto aux_err; + + err = auxiliary_device_add(aux_dev); + if (err) { + auxiliary_device_uninit(aux_dev); + goto aux_err; + } + + return 0; +aux_err: + dev_err(dev, "Failed to create PTP auxiliary bus device <%s>\n", name); + devm_kfree(dev, name); + return err; +} + +/** + * ice_ptp_remove_auxbus_device - Remove PTP auxiliary bus device + * @pf: Board private structure + */ +static void ice_ptp_remove_auxbus_device(struct ice_pf *pf) +{ + struct auxiliary_device *aux_dev = &pf->ptp.port.aux_dev; + + auxiliary_device_delete(aux_dev); + auxiliary_device_uninit(aux_dev); + + memset(aux_dev, 0, sizeof(*aux_dev)); +} + +/** + * ice_ptp_init_tx_interrupt_mode - Initialize device Tx interrupt mode + * @pf: Board private structure + * + * Initialize the Tx timestamp interrupt mode for this device. For most device + * types, each PF processes the interrupt and manages its own timestamps. For + * E822-based devices, only the clock owner processes the timestamps. Other + * PFs disable the interrupt and do not process their own timestamps. + */ +static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) +{ + switch (pf->hw.phy_model) { + case ICE_PHY_E822: + /* E822 based PHY has the clock owner process the interrupt + * for all ports. + */ + if (ice_pf_src_tmr_owned(pf)) + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_ALL; + else + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_NONE; + break; + default: + /* other PHY types handle their own Tx interrupt */ + pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_SELF; + } } /** @@ -2713,10 +3020,14 @@ void ice_ptp_init(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; int err; + ice_ptp_init_phy_model(hw); + + ice_ptp_init_tx_interrupt_mode(pf); + /* If this function owns the clock hardware, it must allocate and * configure the PTP clock device to represent it. */ - if (hw->func_caps.ts_func_info.src_tmr_owned) { + if (ice_pf_src_tmr_owned(pf)) { err = ice_ptp_init_owner(pf); if (err) goto err; @@ -2730,11 +3041,18 @@ void ice_ptp_init(struct ice_pf *pf) /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); + /* Configure initial Tx interrupt settings */ + ice_ptp_cfg_tx_interrupt(pf); + set_bit(ICE_FLAG_PTP, pf->flags); err = ice_ptp_init_work(pf, ptp); if (err) goto err; + err = ice_ptp_create_auxbus_device(pf); + if (err) + goto err; + dev_info(ice_pf_to_dev(pf), "PTP init successful\n"); return; @@ -2761,7 +3079,9 @@ void ice_ptp_release(struct ice_pf *pf) return; /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); + + ice_ptp_remove_auxbus_device(pf); ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); @@ -2782,9 +3102,10 @@ void ice_ptp_release(struct ice_pf *pf) /* Disable periodic outputs */ ice_ptp_disable_all_clkout(pf); - ice_clear_ptp_clock_index(pf); ptp_clock_unregister(pf->ptp.clock); pf->ptp.clock = NULL; + ice_ptp_unregister_auxbus_driver(pf); + dev_info(ice_pf_to_dev(pf), "Removed PTP clock\n"); } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 995a57019ba7..06a330867fc9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -157,7 +157,9 @@ struct ice_ptp_tx { * ready for PTP functionality. It is used to track the port initialization * and determine when the port's PHY offset is valid. * + * @list_member: list member structure of auxiliary device * @tx: Tx timestamp tracking for this port + * @aux_dev: auxiliary device associated with this port * @ov_work: delayed work task for tracking when PHY offset is valid * @ps_lock: mutex used to protect the overall PTP PHY start procedure * @link_up: indicates whether the link is up @@ -165,7 +167,9 @@ struct ice_ptp_tx { * @port_num: the port number this structure represents */ struct ice_ptp_port { + struct list_head list_member; struct ice_ptp_tx tx; + struct auxiliary_device aux_dev; struct kthread_delayed_work ov_work; struct mutex ps_lock; /* protects overall PTP PHY start procedure */ bool link_up; @@ -173,11 +177,35 @@ struct ice_ptp_port { u8 port_num; }; +enum ice_ptp_tx_interrupt { + ICE_PTP_TX_INTERRUPT_NONE = 0, + ICE_PTP_TX_INTERRUPT_SELF, + ICE_PTP_TX_INTERRUPT_ALL, +}; + +/** + * struct ice_ptp_port_owner - data used to handle the PTP clock owner info + * + * This structure contains data necessary for the PTP clock owner to correctly + * handle the timestamping feature for all attached ports. + * + * @aux_driver: the structure carring the auxiliary driver information + * @ports: list of porst handled by this port owner + * @lock: protect access to ports list + */ +struct ice_ptp_port_owner { + struct auxiliary_driver aux_driver; + struct list_head ports; + struct mutex lock; +}; + #define GLTSYN_TGT_H_IDX_MAX 4 /** * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK + * @tx_interrupt_mode: the TX interrupt mode for the PTP clock * @port: data for the PHY port initialization procedure + * @ports_owner: data for the auxiliary driver owner * @work: delayed work function for periodic tasks * @cached_phc_time: a cached copy of the PHC time for timestamp extension * @cached_phc_jiffies: jiffies when cached_phc_time was last updated @@ -197,7 +225,9 @@ struct ice_ptp_port { * @late_cached_phc_updates: number of times cached PHC update is late */ struct ice_ptp { + enum ice_ptp_tx_interrupt tx_interrupt_mode; struct ice_ptp_port port; + struct ice_ptp_port_owner ports_owner; struct kthread_delayed_work work; u64 cached_phc_time; unsigned long cached_phc_jiffies; @@ -258,11 +288,11 @@ struct ice_ptp { #define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +int ice_ptp_clock_index(struct ice_pf *pf); struct ice_pf; int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr); int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr); -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena); -int ice_get_ptp_clock_index(struct ice_pf *pf); +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf); void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); @@ -287,12 +317,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) return -EOPNOTSUPP; } -static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { } -static inline int ice_get_ptp_clock_index(struct ice_pf *pf) -{ - return -1; -} - +static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { } static inline void ice_ptp_extts_event(struct ice_pf *pf) { } static inline s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) @@ -314,5 +339,10 @@ static inline void ice_ptp_release(struct ice_pf *pf) { } static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) { } + +static inline int ice_ptp_clock_index(struct ice_pf *pf) +{ + return -1; +} #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ #endif /* _ICE_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index a38614d21ea8..a00b55e14aac 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -7,6 +7,132 @@ #include "ice_ptp_consts.h" #include "ice_cgu_regs.h" +static struct dpll_pin_frequency ice_cgu_pin_freq_common[] = { + DPLL_PIN_FREQUENCY_1PPS, + DPLL_PIN_FREQUENCY_10MHZ, +}; + +static struct dpll_pin_frequency ice_cgu_pin_freq_1_hz[] = { + DPLL_PIN_FREQUENCY_1PPS, +}; + +static struct dpll_pin_frequency ice_cgu_pin_freq_10_mhz[] = { + DPLL_PIN_FREQUENCY_10MHZ, +}; + +static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_inputs[] = { + { "CVL-SDP22", ZL_REF0P, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "CVL-SDP20", ZL_REF0N, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "C827_0-RCLKA", ZL_REF1P, DPLL_PIN_TYPE_MUX, 0, }, + { "C827_0-RCLKB", ZL_REF1N, DPLL_PIN_TYPE_MUX, 0, }, + { "SMA1", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "SMA2/U.FL2", ZL_REF3N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0, }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = { + { "CVL-SDP22", ZL_REF0P, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "CVL-SDP20", ZL_REF0N, DPLL_PIN_TYPE_INT_OSCILLATOR, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "C827_0-RCLKA", ZL_REF1P, DPLL_PIN_TYPE_MUX, }, + { "C827_0-RCLKB", ZL_REF1N, DPLL_PIN_TYPE_MUX, }, + { "C827_1-RCLKA", ZL_REF2P, DPLL_PIN_TYPE_MUX, }, + { "C827_1-RCLKB", ZL_REF2N, DPLL_PIN_TYPE_MUX, }, + { "SMA1", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "SMA2/U.FL2", ZL_REF3N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_outputs[] = { + { "REF-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "REF-SMA2/U.FL2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, }, + { "MAC-CLK", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, }, + { "CVL-SDP21", ZL_OUT4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "CVL-SDP23", ZL_OUT5, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, +}; + +static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_outputs[] = { + { "REF-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "REF-SMA2/U.FL2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "PHY2-CLK", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "MAC-CLK", ZL_OUT4, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "CVL-SDP21", ZL_OUT5, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "CVL-SDP23", ZL_OUT6, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, +}; + +static const struct ice_cgu_pin_desc ice_e823_si_cgu_inputs[] = { + { "NONE", SI_REF0P, 0, 0 }, + { "NONE", SI_REF0N, 0, 0 }, + { "SYNCE0_DP", SI_REF1P, DPLL_PIN_TYPE_MUX, 0 }, + { "SYNCE0_DN", SI_REF1N, DPLL_PIN_TYPE_MUX, 0 }, + { "EXT_CLK_SYNC", SI_REF2P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", SI_REF2N, 0, 0 }, + { "EXT_PPS_OUT", SI_REF3, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "INT_PPS_OUT", SI_REF4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, +}; + +static const struct ice_cgu_pin_desc ice_e823_si_cgu_outputs[] = { + { "1588-TIME_SYNC", SI_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "PHY-CLK", SI_OUT1, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "10MHZ-SMA2", SI_OUT2, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_10_mhz), ice_cgu_pin_freq_10_mhz }, + { "PPS-SMA1", SI_OUT3, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, +}; + +static const struct ice_cgu_pin_desc ice_e823_zl_cgu_inputs[] = { + { "NONE", ZL_REF0P, 0, 0 }, + { "INT_PPS_OUT", ZL_REF0N, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "SYNCE0_DP", ZL_REF1P, DPLL_PIN_TYPE_MUX, 0 }, + { "SYNCE0_DN", ZL_REF1N, DPLL_PIN_TYPE_MUX, 0 }, + { "NONE", ZL_REF2P, 0, 0 }, + { "NONE", ZL_REF2N, 0, 0 }, + { "EXT_CLK_SYNC", ZL_REF3P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", ZL_REF3N, 0, 0 }, + { "EXT_PPS_OUT", ZL_REF4P, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0 }, +}; + +static const struct ice_cgu_pin_desc ice_e823_zl_cgu_outputs[] = { + { "PPS-SMA1", ZL_OUT0, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, + { "10MHZ-SMA2", ZL_OUT1, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_10_mhz), ice_cgu_pin_freq_10_mhz }, + { "PHY-CLK", ZL_OUT2, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "1588-TIME_REF", ZL_OUT3, DPLL_PIN_TYPE_SYNCE_ETH_PORT, 0 }, + { "CPK-TIME_SYNC", ZL_OUT4, DPLL_PIN_TYPE_EXT, + ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, + { "NONE", ZL_OUT5, 0, 0 }, +}; + /* Low level functions for interacting with and managing the device clock used * for the Precision Time Protocol. * @@ -107,7 +233,7 @@ static u64 ice_ptp_read_src_incval(struct ice_hw *hw) * * Prepare the source timer for an upcoming timer sync command. */ -static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val; u8 tmr_idx; @@ -116,21 +242,23 @@ static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) cmd_val = tmr_idx << SEL_CPK_SRC; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val |= GLTSYN_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val |= GLTSYN_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val |= GLTSYN_CMD_ADJ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val |= GLTSYN_CMD_READ_TIME; break; + case ICE_PTP_NOP: + break; } wr32(hw, GLTSYN_CMD, cmd_val); @@ -166,9 +294,9 @@ ice_fill_phy_msg_e822(struct ice_sbq_msg_input *msg, u8 port, u16 offset) { int phy_port, phy, quadtype; - phy_port = port % ICE_PORTS_PER_PHY; - phy = port / ICE_PORTS_PER_PHY; - quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_NUM_QUAD_TYPE; + phy_port = port % ICE_PORTS_PER_PHY_E822; + phy = port / ICE_PORTS_PER_PHY_E822; + quadtype = (port / ICE_PORTS_PER_QUAD) % ICE_QUADS_PER_PHY_E822; if (quadtype == 0) { msg->msg_addr_low = P_Q0_L(P_0_BASE + offset, phy_port); @@ -293,7 +421,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) * * Read a PHY register for the given port over the device sideband queue. */ -int +static int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) { struct ice_sbq_msg_input msg = {0}; @@ -370,7 +498,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) * * Write a PHY register for the given port over the device sideband queue. */ -int +static int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) { struct ice_sbq_msg_input msg = {0}; @@ -493,20 +621,25 @@ ice_write_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 val) * Fill a message buffer for accessing a register in a quad shared between * multiple PHYs. */ -static void +static int ice_fill_quad_msg_e822(struct ice_sbq_msg_input *msg, u8 quad, u16 offset) { u32 addr; + if (quad >= ICE_MAX_QUAD) + return -EINVAL; + msg->dest_dev = rmn_0; - if ((quad % ICE_NUM_QUAD_TYPE) == 0) + if ((quad % ICE_QUADS_PER_PHY_E822) == 0) addr = Q_0_BASE + offset; else addr = Q_1_BASE + offset; msg->msg_addr_low = lower_16_bits(addr); msg->msg_addr_high = upper_16_bits(addr); + + return 0; } /** @@ -525,10 +658,10 @@ ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val) struct ice_sbq_msg_input msg = {0}; int err; - if (quad >= ICE_MAX_QUAD) - return -EINVAL; + err = ice_fill_quad_msg_e822(&msg, quad, offset); + if (err) + return err; - ice_fill_quad_msg_e822(&msg, quad, offset); msg.opcode = ice_sbq_msg_rd; err = ice_sbq_rw_reg(hw, &msg); @@ -559,10 +692,10 @@ ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val) struct ice_sbq_msg_input msg = {0}; int err; - if (quad >= ICE_MAX_QUAD) - return -EINVAL; + err = ice_fill_quad_msg_e822(&msg, quad, offset); + if (err) + return err; - ice_fill_quad_msg_e822(&msg, quad, offset); msg.opcode = ice_sbq_msg_wr; msg.data = val; @@ -626,29 +759,32 @@ ice_read_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * @quad: the quad to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the PHY quad block that is - * shared between the internal PHYs on the E822 devices. + * Read the timestamp out of the quad to clear its timestamp status bit from + * the PHY quad block that is shared between the internal PHYs of the E822 + * devices. + * + * Note that unlike E810, software cannot directly write to the quad memory + * bank registers. E822 relies on the ice_get_phy_tx_tstamp_ready() function + * to determine which timestamps are valid. Reading a timestamp auto-clears + * the valid bit. + * + * To directly clear the contents of the timestamp block entirely, discarding + * all timestamp data at once, software should instead use + * ice_ptp_reset_ts_memory_quad_e822(). + * + * This function should only be called on an idx whose bit is set according to + * ice_get_phy_tx_tstamp_ready(). */ static int ice_clear_phy_tstamp_e822(struct ice_hw *hw, u8 quad, u8 idx) { - u16 lo_addr, hi_addr; + u64 unused_tstamp; int err; - lo_addr = (u16)TS_L(Q_REG_TX_MEMORY_BANK_START, idx); - hi_addr = (u16)TS_H(Q_REG_TX_MEMORY_BANK_START, idx); - - err = ice_write_quad_reg_e822(hw, quad, lo_addr, 0); + err = ice_read_phy_tstamp_e822(hw, quad, idx, &unused_tstamp); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, err %d\n", - err); - return err; - } - - err = ice_write_quad_reg_e822(hw, quad, hi_addr, 0); - if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for quad %u, idx %u, err %d\n", + quad, idx, err); return err; } @@ -1023,7 +1159,7 @@ static int ice_ptp_init_phc_e822(struct ice_hw *hw) * @time: Time to initialize the PHY port clocks to * * Program the PHY port registers with a new initial time value. The port - * clock will be initialized once the driver issues an INIT_TIME sync + * clock will be initialized once the driver issues an ICE_PTP_INIT_TIME sync * command. The time value is the upper 32 bits of the PHY timer, usually in * units of nominal nanoseconds. */ @@ -1072,14 +1208,14 @@ exit_err: * * Program the port for an atomic adjustment by writing the Tx and Rx timer * registers. The atomic adjustment won't be completed until the driver issues - * an ADJ_TIME command. + * an ICE_PTP_ADJ_TIME command. * * Note that time is not in units of nanoseconds. It is in clock time * including the lower sub-nanosecond portion of the port timer. * * Negative adjustments are supported using 2s complement arithmetic. */ -int +static int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time) { u32 l_time, u_time; @@ -1125,7 +1261,7 @@ exit_err: * * Prepare the PHY ports for an atomic time adjustment by programming the PHY * Tx and Rx port registers. The actual adjustment is completed by issuing an - * ADJ_TIME or ADJ_TIME_AT_TIME sync command. + * ICE_PTP_ADJ_TIME or ICE_PTP_ADJ_TIME_AT_TIME sync command. */ static int ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) @@ -1160,7 +1296,7 @@ ice_ptp_prep_phy_adj_e822(struct ice_hw *hw, s32 adj) * * Prepare each of the PHY ports for a new increment value by programming the * port's TIMETUS registers. The new increment value will be updated after - * issuing an INIT_INCVAL command. + * issuing an ICE_PTP_INIT_INCVAL command. */ static int ice_ptp_prep_phy_incval_e822(struct ice_hw *hw, u64 incval) @@ -1226,18 +1362,18 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) } /** - * ice_ptp_one_port_cmd - Prepare a single PHY port for a timer command + * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command * @hw: pointer to HW struct * @port: Port to which cmd has to be sent * @cmd: Command to be sent to the port * * Prepare the requested port for an upcoming timer sync command. * - * Note there is no equivalent of this operation on E810, as that device - * always handles all external PHYs internally. + * Do not use this function directly. If you want to configure exactly one + * port, use ice_ptp_one_port_cmd() instead. */ static int -ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) +ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val, val; u8 tmr_idx; @@ -1246,21 +1382,23 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) tmr_idx = ice_get_ptp_src_clock_index(hw); cmd_val = tmr_idx << SEL_PHY_SRC; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val |= PHY_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val |= PHY_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val |= PHY_CMD_ADJ_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val |= PHY_CMD_READ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME; break; + case ICE_PTP_NOP: + break; } /* Tx case */ @@ -1307,6 +1445,39 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) } /** + * ice_ptp_one_port_cmd - Prepare one port for a timer command + * @hw: pointer to the HW struct + * @configured_port: the port to configure with configured_cmd + * @configured_cmd: timer command to prepare on the configured_port + * + * Prepare the configured_port for the configured_cmd, and prepare all other + * ports for ICE_PTP_NOP. This causes the configured_port to execute the + * desired command while all other ports perform no operation. + */ +static int +ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd) +{ + u8 port; + + for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + enum ice_ptp_tmr_cmd cmd; + int err; + + if (port == configured_port) + cmd = configured_cmd; + else + cmd = ICE_PTP_NOP; + + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + if (err) + return err; + } + + return 0; +} + +/** * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command * @hw: pointer to the HW struct * @cmd: timer command to prepare @@ -1322,7 +1493,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_one_port_cmd(hw, port, cmd); + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); if (err) return err; } @@ -2159,8 +2330,8 @@ int ice_phy_cfg_rx_offset_e822(struct ice_hw *hw, u8 port) * @phy_time: on return, the 64bit PHY timer value * @phc_time: on return, the lower 64bits of PHC time * - * Issue a READ_TIME timer command to simultaneously capture the PHY and PHC - * timer values. + * Issue a ICE_PTP_READ_TIME timer command to simultaneously capture the PHY + * and PHC timer values. */ static int ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, @@ -2173,15 +2344,15 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, tmr_idx = ice_get_ptp_src_clock_index(hw); - /* Prepare the PHC timer for a READ_TIME capture command */ - ice_ptp_src_cmd(hw, READ_TIME); + /* Prepare the PHC timer for a ICE_PTP_READ_TIME capture command */ + ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); - /* Prepare the PHY timer for a READ_TIME capture command */ - err = ice_ptp_one_port_cmd(hw, port, READ_TIME); + /* Prepare the PHY timer for a ICE_PTP_READ_TIME capture command */ + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_READ_TIME); if (err) return err; - /* Issue the sync to start the READ_TIME capture */ + /* Issue the sync to start the ICE_PTP_READ_TIME capture */ ice_ptp_exec_tmr_cmd(hw); /* Read the captured PHC time from the shadow time registers */ @@ -2215,10 +2386,11 @@ ice_read_phy_and_phc_time_e822(struct ice_hw *hw, u8 port, u64 *phy_time, * @port: the PHY port to synchronize * * Perform an adjustment to ensure that the PHY and PHC timers are in sync. - * This is done by issuing a READ_TIME command which triggers a simultaneous - * read of the PHY timer and PHC timer. Then we use the difference to - * calculate an appropriate 2s complement addition to add to the PHY timer in - * order to ensure it reads the same value as the primary PHC timer. + * This is done by issuing a ICE_PTP_READ_TIME command which triggers a + * simultaneous read of the PHY timer and PHC timer. Then we use the + * difference to calculate an appropriate 2s complement addition to add + * to the PHY timer in order to ensure it reads the same value as the + * primary PHC timer. */ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) { @@ -2248,10 +2420,13 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) goto err_unlock; - err = ice_ptp_one_port_cmd(hw, port, ADJ_TIME); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_ADJ_TIME); if (err) goto err_unlock; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Issue the sync to activate the time adjustment */ ice_ptp_exec_tmr_cmd(hw); @@ -2368,10 +2543,13 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) return err; - err = ice_ptp_one_port_cmd(hw, port, INIT_INCVAL); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) return err; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + ice_ptp_exec_tmr_cmd(hw); err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); @@ -2393,7 +2571,7 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) return err; - err = ice_ptp_one_port_cmd(hw, port, INIT_INCVAL); + err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) return err; @@ -2642,28 +2820,39 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) * @lport: the lport to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the timestamp block of the - * external PHY on the E810 device. + * Read the timestamp and then forcibly overwrite its value to clear the valid + * bit from the timestamp block of the external PHY on the E810 device. + * + * This function should only be called on an idx whose bit is set according to + * ice_get_phy_tx_tstamp_ready(). */ static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx) { u32 lo_addr, hi_addr; + u64 unused_tstamp; int err; + err = ice_read_phy_tstamp_e810(hw, lport, idx, &unused_tstamp); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read the timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); + return err; + } + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); err = ice_write_phy_reg_e810(hw, lo_addr, 0); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); return err; } err = ice_write_phy_reg_e810(hw, hi_addr, 0); if (err) { - ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, err %d\n", - err); + ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register for lport %u, idx %u, err %d\n", + lport, idx, err); return err; } @@ -2714,7 +2903,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw) * * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the * initial clock time. The time will not actually be programmed until the - * driver issues an INIT_TIME command. + * driver issues an ICE_PTP_INIT_TIME command. * * The time value is the upper 32 bits of the PHY timer, usually in units of * nominal nanoseconds. @@ -2749,7 +2938,7 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) * * Prepare the PHY port for an atomic adjustment by programming the PHY * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual adjustment - * is completed by issuing an ADJ_TIME sync command. + * is completed by issuing an ICE_PTP_ADJ_TIME sync command. * * The adjustment value only contains the portion used for the upper 32bits of * the PHY timer, usually in units of nominal nanoseconds. Negative @@ -2789,7 +2978,7 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) * * Prepare the PHY port for a new increment value by programming the PHY * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual change is - * completed by issuing an INIT_INCVAL command. + * completed by issuing an ICE_PTP_INIT_INCVAL command. */ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) { @@ -2832,21 +3021,23 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) int err; switch (cmd) { - case INIT_TIME: + case ICE_PTP_INIT_TIME: cmd_val = GLTSYN_CMD_INIT_TIME; break; - case INIT_INCVAL: + case ICE_PTP_INIT_INCVAL: cmd_val = GLTSYN_CMD_INIT_INCVAL; break; - case ADJ_TIME: + case ICE_PTP_ADJ_TIME: cmd_val = GLTSYN_CMD_ADJ_TIME; break; - case READ_TIME: + case ICE_PTP_READ_TIME: cmd_val = GLTSYN_CMD_READ_TIME; break; - case ADJ_TIME_AT_TIME: + case ICE_PTP_ADJ_TIME_AT_TIME: cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; break; + case ICE_PTP_NOP: + return 0; } /* Read, modify, write */ @@ -2869,6 +3060,185 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) return 0; } +/** + * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + * + * E810 devices do not use a Tx memory status register. Instead simply + * indicate that all timestamps are currently ready. + */ +static int +ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) +{ + *tstamp_ready = 0xFFFFFFFFFFFFFFFF; + return 0; +} + +/* E810T SMA functions + * + * The following functions operate specifically on E810T hardware and are used + * to access the extended GPIOs available. + */ + +/** + * ice_get_pca9575_handle + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value + */ +static int +ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int status; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + + /* If handle was not detected read it from the netlist */ + cmd = &desc.params.get_link_topo; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + + /* Set node type to GPIO controller */ + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -EOPNOTSUPP; + + cmd->addr.topo_params.index = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (status) + return -EOPNOTSUPP; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -EOPNOTSUPP; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: pointer to data to be read from the GPIO controller + * + * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the + * PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + *data = 0; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + &pin, NULL); + if (status) + break; + *data |= (u8)(!pin) << i; + } + + return status; +} + +/** + * ice_write_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: data to be written to the GPIO controller + * + * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 + * of the PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + pin = !(data & (1 << i)); + status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + pin, NULL); + if (status) + break; + } + + return status; +} + +/** + * ice_read_pca9575_reg_e810t + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Read the register from the GPIO controller + */ +int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + /* Device agnostic functions * * The following functions implement shared behavior common to both E822 and @@ -2926,6 +3296,21 @@ void ice_ptp_unlock(struct ice_hw *hw) } /** + * ice_ptp_init_phy_model - Initialize hw->phy_model based on device type + * @hw: pointer to the HW structure + * + * Determine the PHY model for the device, and initialize hw->phy_model + * for use by other functions. + */ +void ice_ptp_init_phy_model(struct ice_hw *hw) +{ + if (ice_is_e810(hw)) + hw->phy_model = ICE_PHY_E810; + else + hw->phy_model = ICE_PHY_E822; +} + +/** * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command * @hw: pointer to HW struct * @cmd: the command to issue @@ -2943,10 +3328,17 @@ static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) ice_ptp_src_cmd(hw, cmd); /* Next, prepare the ports */ - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_port_cmd_e810(hw, cmd); - else + break; + case ICE_PHY_E822: err = ice_ptp_port_cmd_e822(hw, cmd); + break; + default: + err = -EOPNOTSUPP; + } + if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, err %d\n", cmd, err); @@ -2988,14 +3380,21 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_time_e822(hw, time & 0xFFFFFFFF); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, INIT_TIME); + return ice_ptp_tmr_cmd(hw, ICE_PTP_INIT_TIME); } /** @@ -3008,8 +3407,8 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) * * 1) Write the increment value to the source timer shadow registers * 2) Write the increment value to the PHY timer shadow registers - * 3) Issue an INIT_INCVAL timer command to synchronously switch both the - * source and port timers to the new increment value at the next clock + * 3) Issue an ICE_PTP_INIT_INCVAL timer command to synchronously switch both + * the source and port timers to the new increment value at the next clock * cycle. */ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) @@ -3023,14 +3422,21 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_incval_e822(hw, incval); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, INIT_INCVAL); + return ice_ptp_tmr_cmd(hw, ICE_PTP_INIT_INCVAL); } /** @@ -3064,8 +3470,8 @@ int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval) * * 1) Write the adjustment to the source timer shadow registers * 2) Write the adjustment to the PHY timer shadow registers - * 3) Issue an ADJ_TIME timer command to synchronously apply the adjustment to - * both the source and port timers at the next clock cycle. + * 3) Issue an ICE_PTP_ADJ_TIME timer command to synchronously apply the + * adjustment to both the source and port timers at the next clock cycle. */ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) { @@ -3075,21 +3481,28 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Write the desired clock adjustment into the GLTSYN_SHADJ register. - * For an ADJ_TIME command, this set of registers represents the value - * to add to the clock time. It supports subtraction by interpreting - * the value as a 2's complement integer. + * For an ICE_PTP_ADJ_TIME command, this set of registers represents + * the value to add to the clock time. It supports subtraction by + * interpreting the value as a 2's complement integer. */ wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); - else + break; + case ICE_PHY_E822: err = ice_ptp_prep_phy_adj_e822(hw, adj); + break; + default: + err = -EOPNOTSUPP; + } + if (err) return err; - return ice_ptp_tmr_cmd(hw, ADJ_TIME); + return ice_ptp_tmr_cmd(hw, ICE_PTP_ADJ_TIME); } /** @@ -3105,10 +3518,14 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) */ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) { - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - else + case ICE_PHY_E822: return ice_read_phy_tstamp_e822(hw, block, idx, tstamp); + default: + return -EOPNOTSUPP; + } } /** @@ -3117,267 +3534,484 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) * @block: the block to read from * @idx: the timestamp index to reset * - * Clear a timestamp, resetting its valid bit, from the timestamp block. For - * E822 devices, the block is the quad to clear from. For E810 devices, the - * block is the logical port to clear from. + * Clear a timestamp from the timestamp block, discarding its value without + * returning it. This resets the memory status bit for the timestamp index + * allowing it to be reused for another timestamp in the future. + * + * For E822 devices, the block number is the PHY quad to clear from. For E810 + * devices, the block number is the logical port to clear from. + * + * This function must only be called on a timestamp index whose valid bit is + * set according to ice_get_phy_tx_tstamp_ready(). */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - if (ice_is_e810(hw)) + switch (hw->phy_model) { + case ICE_PHY_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - else + case ICE_PHY_E822: return ice_clear_phy_tstamp_e822(hw, block, idx); + default: + return -EOPNOTSUPP; + } } /** - * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register - * @hw: pointer to the HW struct - * @port: the PHY port to read - * @tstamp_ready: contents of the Tx memory status register - * - * E810 devices do not use a Tx memory status register. Instead simply - * indicate that all timestamps are currently ready. - */ -static int -ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) -{ - *tstamp_ready = 0xFFFFFFFFFFFFFFFF; - return 0; -} - -/* E810T SMA functions - * - * The following functions operate specifically on E810T hardware and are used - * to access the extended GPIOs available. - */ - -/** - * ice_get_pca9575_handle + * ice_get_pf_c827_idx - find and return the C827 index for the current pf * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value + * @idx: index of the found C827 PHY + * Return: + * * 0 - success + * * negative - failure */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) { - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; + struct ice_aqc_get_link_topo cmd; + u8 node_part_number; + u16 node_handle; int status; - u8 idx; + u8 ctx; - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; + if (hw->mac_type != ICE_MAC_E810) + return -ENODEV; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) { + *idx = C827_0; return 0; } - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + memset(&cmd, 0, sizeof(cmd)); - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + ctx = ICE_AQC_LINK_TOPO_NODE_TYPE_PHY << ICE_AQC_LINK_TOPO_NODE_TYPE_S; + ctx |= ICE_AQC_LINK_TOPO_NODE_CTX_PORT << ICE_AQC_LINK_TOPO_NODE_CTX_S; + cmd.addr.topo_params.node_type_ctx = ctx; -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return -ENOENT; - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; + if (node_handle == E810C_QSFP_C827_0_HANDLE) + *idx = C827_0; + else if (node_handle == E810C_QSFP_C827_1_HANDLE) + *idx = C827_1; else - return -EOPNOTSUPP; + return -EIO; - cmd->addr.topo_params.index = idx; + return 0; +} - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; +/** + * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks + * @hw: pointer to the HW struct + */ +void ice_ptp_reset_ts_memory(struct ice_hw *hw) +{ + switch (hw->phy_model) { + case ICE_PHY_E822: + ice_ptp_reset_ts_memory_e822(hw); + break; + case ICE_PHY_E810: + default: + return; + } +} - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; +/** + * ice_ptp_init_phc - Initialize PTP hardware clock + * @hw: pointer to the HW struct + * + * Perform the steps required to initialize the PTP hardware clock. + */ +int ice_ptp_init_phc(struct ice_hw *hw) +{ + u8 src_idx = hw->func_caps.ts_func_info.tmr_index_owned; - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; + /* Enable source clocks */ + wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M); - return 0; + /* Clear event err indications for auxiliary pins */ + (void)rd32(hw, GLTSYN_STAT(src_idx)); + + switch (hw->phy_model) { + case ICE_PHY_E810: + return ice_ptp_init_phc_e810(hw); + case ICE_PHY_E822: + return ice_ptp_init_phc_e822(hw); + default: + return -EOPNOTSUPP; + } } /** - * ice_read_sma_ctrl_e810t + * ice_get_phy_tx_tstamp_ready - Read PHY Tx memory status indication + * @hw: pointer to the HW struct + * @block: the timestamp block to check + * @tstamp_ready: storage for the PHY Tx memory status information + * + * Check the PHY for Tx timestamp memory status. This reports a 64 bit value + * which indicates which timestamps in the block may be captured. A set bit + * means the timestamp can be read. An unset bit means the timestamp is not + * ready and software should avoid reading the register. + */ +int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) +{ + switch (hw->phy_model) { + case ICE_PHY_E810: + return ice_get_phy_tx_tstamp_ready_e810(hw, block, + tstamp_ready); + case ICE_PHY_E822: + return ice_get_phy_tx_tstamp_ready_e822(hw, block, + tstamp_ready); + break; + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_cgu_get_pin_desc_e823 - get pin description array * @hw: pointer to the hw struct - * @data: pointer to data to be read from the GPIO controller + * @input: if request is done against input or output pin + * @size: number of inputs/outputs * - * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the - * PCA9575 expander, so only bits 3-7 in data are valid. + * Return: pointer to pin description array associated to given hw. */ -int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +static const struct ice_cgu_pin_desc * +ice_cgu_get_pin_desc_e823(struct ice_hw *hw, bool input, int *size) { - int status; - u16 handle; - u8 i; + static const struct ice_cgu_pin_desc *t; - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032) { + if (input) { + t = ice_e823_zl_cgu_inputs; + *size = ARRAY_SIZE(ice_e823_zl_cgu_inputs); + } else { + t = ice_e823_zl_cgu_outputs; + *size = ARRAY_SIZE(ice_e823_zl_cgu_outputs); + } + } else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384) { + if (input) { + t = ice_e823_si_cgu_inputs; + *size = ARRAY_SIZE(ice_e823_si_cgu_inputs); + } else { + t = ice_e823_si_cgu_outputs; + *size = ARRAY_SIZE(ice_e823_si_cgu_outputs); + } + } else { + t = NULL; + *size = 0; + } - *data = 0; + return t; +} - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; +/** + * ice_cgu_get_pin_desc - get pin description array + * @hw: pointer to the hw struct + * @input: if request is done against input or output pins + * @size: size of array returned by function + * + * Return: pointer to pin description array associated to given hw. + */ +static const struct ice_cgu_pin_desc * +ice_cgu_get_pin_desc(struct ice_hw *hw, bool input, int *size) +{ + const struct ice_cgu_pin_desc *t = NULL; - status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - &pin, NULL); - if (status) - break; - *data |= (u8)(!pin) << i; + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (input) { + t = ice_e810t_sfp_cgu_inputs; + *size = ARRAY_SIZE(ice_e810t_sfp_cgu_inputs); + } else { + t = ice_e810t_sfp_cgu_outputs; + *size = ARRAY_SIZE(ice_e810t_sfp_cgu_outputs); + } + break; + case ICE_DEV_ID_E810C_QSFP: + if (input) { + t = ice_e810t_qsfp_cgu_inputs; + *size = ARRAY_SIZE(ice_e810t_qsfp_cgu_inputs); + } else { + t = ice_e810t_qsfp_cgu_outputs; + *size = ARRAY_SIZE(ice_e810t_qsfp_cgu_outputs); + } + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + t = ice_cgu_get_pin_desc_e823(hw, input, size); + break; + default: + break; } - return status; + return t; } /** - * ice_write_sma_ctrl_e810t + * ice_cgu_get_pin_type - get pin's type * @hw: pointer to the hw struct - * @data: data to be written to the GPIO controller + * @pin: pin index + * @input: if request is done against input or output pin * - * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 - * of the PCA9575 expander, so only bits 3-7 in data are valid. + * Return: type of a pin. */ -int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input) { - int status; - u16 handle; - u8 i; + const struct ice_cgu_pin_desc *t; + int t_size; - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; + t = ice_cgu_get_pin_desc(hw, input, &t_size); - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; + if (!t) + return 0; - pin = !(data & (1 << i)); - status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - pin, NULL); - if (status) - break; - } + if (pin >= t_size) + return 0; - return status; + return t[pin].type; } /** - * ice_read_pca9575_reg_e810t + * ice_cgu_get_pin_freq_supp - get pin's supported frequency * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller + * @pin: pin index + * @input: if request is done against input or output pin + * @num: output number of supported frequencies * - * Read the register from the GPIO controller + * Get frequency supported number and array of supported frequencies. + * + * Return: array of supported frequencies for given pin. */ -int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +struct dpll_pin_frequency * +ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num) { - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; + const struct ice_cgu_pin_desc *t; + int t_size; - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; + *num = 0; + t = ice_cgu_get_pin_desc(hw, input, &t_size); + if (!t) + return NULL; + if (pin >= t_size) + return NULL; + *num = t[pin].freq_supp_num; - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); + return t[pin].freq_supp; } /** - * ice_is_pca9575_present + * ice_cgu_get_pin_name - get pin's name * @hw: pointer to the hw struct + * @pin: pin index + * @input: if request is done against input or output pin * - * Check if the SW IO expander is present in the netlist + * Return: + * * null terminated char array with name + * * NULL in case of failure */ -bool ice_is_pca9575_present(struct ice_hw *hw) +const char *ice_cgu_get_pin_name(struct ice_hw *hw, u8 pin, bool input) { - u16 handle = 0; - int status; + const struct ice_cgu_pin_desc *t; + int t_size; - if (!ice_is_e810t(hw)) - return false; + t = ice_cgu_get_pin_desc(hw, input, &t_size); - status = ice_get_pca9575_handle(hw, &handle); + if (!t) + return NULL; - return !status && handle; + if (pin >= t_size) + return NULL; + + return t[pin].name; } /** - * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks - * @hw: pointer to the HW struct - */ -void ice_ptp_reset_ts_memory(struct ice_hw *hw) -{ - if (ice_is_e810(hw)) - return; + * ice_get_cgu_state - get the state of the DPLL + * @hw: pointer to the hw struct + * @dpll_idx: Index of internal DPLL unit + * @last_dpll_state: last known state of DPLL + * @pin: pointer to a buffer for returning currently active pin + * @ref_state: reference clock state + * @eec_mode: eec mode of the DPLL + * @phase_offset: pointer to a buffer for returning phase offset + * @dpll_state: state of the DPLL (output) + * + * This function will read the state of the DPLL(dpll_idx). Non-null + * 'pin', 'ref_state', 'eec_mode' and 'phase_offset' parameters are used to + * retrieve currently active pin, state, mode and phase_offset respectively. + * + * Return: state of the DPLL + */ +int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, + enum dpll_lock_status last_dpll_state, u8 *pin, + u8 *ref_state, u8 *eec_mode, s64 *phase_offset, + enum dpll_lock_status *dpll_state) +{ + u8 hw_ref_state, hw_dpll_state, hw_eec_mode, hw_config; + s64 hw_phase_offset; + int status; + + status = ice_aq_get_cgu_dpll_status(hw, dpll_idx, &hw_ref_state, + &hw_dpll_state, &hw_config, + &hw_phase_offset, &hw_eec_mode); + if (status) + return status; + + if (pin) + /* current ref pin in dpll_state_refsel_status_X register */ + *pin = hw_config & ICE_AQC_GET_CGU_DPLL_CONFIG_CLK_REF_SEL; + if (phase_offset) + *phase_offset = hw_phase_offset; + if (ref_state) + *ref_state = hw_ref_state; + if (eec_mode) + *eec_mode = hw_eec_mode; + if (!dpll_state) + return 0; - ice_ptp_reset_ts_memory_e822(hw); + /* According to ZL DPLL documentation, once state reach LOCKED_HO_ACQ + * it would never return to FREERUN. This aligns to ITU-T G.781 + * Recommendation. We cannot report HOLDOVER as HO memory is cleared + * while switching to another reference. + * Only for situations where previous state was either: "LOCKED without + * HO_ACQ" or "HOLDOVER" we actually back to FREERUN. + */ + if (hw_dpll_state & ICE_AQC_GET_CGU_DPLL_STATUS_STATE_LOCK) { + if (hw_dpll_state & ICE_AQC_GET_CGU_DPLL_STATUS_STATE_HO_READY) + *dpll_state = DPLL_LOCK_STATUS_LOCKED_HO_ACQ; + else + *dpll_state = DPLL_LOCK_STATUS_LOCKED; + } else if (last_dpll_state == DPLL_LOCK_STATUS_LOCKED_HO_ACQ || + last_dpll_state == DPLL_LOCK_STATUS_HOLDOVER) { + *dpll_state = DPLL_LOCK_STATUS_HOLDOVER; + } else { + *dpll_state = DPLL_LOCK_STATUS_UNLOCKED; + } + + return 0; } /** - * ice_ptp_init_phc - Initialize PTP hardware clock - * @hw: pointer to the HW struct + * ice_get_cgu_rclk_pin_info - get info on available recovered clock pins + * @hw: pointer to the hw struct + * @base_idx: returns index of first recovered clock pin on device + * @pin_num: returns number of recovered clock pins available on device * - * Perform the steps required to initialize the PTP hardware clock. + * Based on hw provide caller info about recovery clock pins available on the + * board. + * + * Return: + * * 0 - success, information is valid + * * negative - failure, information is not valid */ -int ice_ptp_init_phc(struct ice_hw *hw) +int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num) { - u8 src_idx = hw->func_caps.ts_func_info.tmr_index_owned; + u8 phy_idx; + int ret; - /* Enable source clocks */ - wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M); + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810C_QSFP: - /* Clear event err indications for auxiliary pins */ - (void)rd32(hw, GLTSYN_STAT(src_idx)); + ret = ice_get_pf_c827_idx(hw, &phy_idx); + if (ret) + return ret; + *base_idx = E810T_CGU_INPUT_C827(phy_idx, ICE_RCLKA_PIN); + *pin_num = ICE_E810_RCLK_PINS_NUM; + ret = 0; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + *pin_num = ICE_E822_RCLK_PINS_NUM; + ret = 0; + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032) + *base_idx = ZL_REF1P; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384) + *base_idx = SI_REF1P; + else + ret = -ENODEV; - if (ice_is_e810(hw)) - return ice_ptp_init_phc_e810(hw); - else - return ice_ptp_init_phc_e822(hw); + break; + default: + ret = -ENODEV; + break; + } + + return ret; } /** - * ice_get_phy_tx_tstamp_ready - Read PHY Tx memory status indication - * @hw: pointer to the HW struct - * @block: the timestamp block to check - * @tstamp_ready: storage for the PHY Tx memory status information + * ice_cgu_get_output_pin_state_caps - get output pin state capabilities + * @hw: pointer to the hw struct + * @pin_id: id of a pin + * @caps: capabilities to modify * - * Check the PHY for Tx timestamp memory status. This reports a 64 bit value - * which indicates which timestamps in the block may be captured. A set bit - * means the timestamp can be read. An unset bit means the timestamp is not - * ready and software should avoid reading the register. + * Return: + * * 0 - success, state capabilities were modified + * * negative - failure, capabilities were not modified */ -int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps) { - if (ice_is_e810(hw)) - return ice_get_phy_tx_tstamp_ready_e810(hw, block, - tstamp_ready); + bool can_change = true; + + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3) + can_change = false; + break; + case ICE_DEV_ID_E810C_QSFP: + if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4) + can_change = false; + break; + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_QSFP: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_SGMII: + if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 && + pin_id == ZL_OUT2) + can_change = false; + else if (hw->cgu_part_number == + ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 && + pin_id == SI_OUT1) + can_change = false; + break; + default: + return -EINVAL; + } + if (can_change) + *caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; else - return ice_get_phy_tx_tstamp_ready_e822(hw, block, - tstamp_ready); + *caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 3b68cb91bd81..cf76701566c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -3,13 +3,15 @@ #ifndef _ICE_PTP_HW_H_ #define _ICE_PTP_HW_H_ +#include <linux/dpll.h> enum ice_ptp_tmr_cmd { - INIT_TIME, - INIT_INCVAL, - ADJ_TIME, - ADJ_TIME_AT_TIME, - READ_TIME + ICE_PTP_INIT_TIME, + ICE_PTP_INIT_INCVAL, + ICE_PTP_ADJ_TIME, + ICE_PTP_ADJ_TIME_AT_TIME, + ICE_PTP_READ_TIME, + ICE_PTP_NOP, }; enum ice_ptp_serdes { @@ -109,9 +111,83 @@ struct ice_cgu_pll_params_e822 { u32 post_pll_div; }; +#define E810C_QSFP_C827_0_HANDLE 2 +#define E810C_QSFP_C827_1_HANDLE 3 +enum ice_e810_c827_idx { + C827_0, + C827_1 +}; + +enum ice_phy_rclk_pins { + ICE_RCLKA_PIN = 0, /* SCL pin */ + ICE_RCLKB_PIN, /* SDA pin */ +}; + +#define ICE_E810_RCLK_PINS_NUM (ICE_RCLKB_PIN + 1) +#define ICE_E822_RCLK_PINS_NUM (ICE_RCLKA_PIN + 1) +#define E810T_CGU_INPUT_C827(_phy, _pin) ((_phy) * ICE_E810_RCLK_PINS_NUM + \ + (_pin) + ZL_REF1P) + +enum ice_zl_cgu_in_pins { + ZL_REF0P = 0, + ZL_REF0N, + ZL_REF1P, + ZL_REF1N, + ZL_REF2P, + ZL_REF2N, + ZL_REF3P, + ZL_REF3N, + ZL_REF4P, + ZL_REF4N, + NUM_ZL_CGU_INPUT_PINS +}; + +enum ice_zl_cgu_out_pins { + ZL_OUT0 = 0, + ZL_OUT1, + ZL_OUT2, + ZL_OUT3, + ZL_OUT4, + ZL_OUT5, + ZL_OUT6, + NUM_ZL_CGU_OUTPUT_PINS +}; + +enum ice_si_cgu_in_pins { + SI_REF0P = 0, + SI_REF0N, + SI_REF1P, + SI_REF1N, + SI_REF2P, + SI_REF2N, + SI_REF3, + SI_REF4, + NUM_SI_CGU_INPUT_PINS +}; + +enum ice_si_cgu_out_pins { + SI_OUT0 = 0, + SI_OUT1, + SI_OUT2, + SI_OUT3, + SI_OUT4, + NUM_SI_CGU_OUTPUT_PINS +}; + +struct ice_cgu_pin_desc { + char *name; + u8 index; + enum dpll_pin_type type; + u32 freq_supp_num; + struct dpll_pin_frequency *freq_supp; +}; + extern const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; +#define E810C_QSFP_C827_0_HANDLE 2 +#define E810C_QSFP_C827_1_HANDLE 3 + /* Table of constants related to possible TIME_REF sources */ extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ]; @@ -127,6 +203,7 @@ extern const struct ice_vernier_info_e822 e822_vernier[NUM_ICE_PTP_LNK_SPD]; u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); bool ice_ptp_lock(struct ice_hw *hw); void ice_ptp_unlock(struct ice_hw *hw); +void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd); int ice_ptp_init_time(struct ice_hw *hw, u64 time); int ice_ptp_write_incval(struct ice_hw *hw, u64 incval); int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval); @@ -138,11 +215,8 @@ int ice_ptp_init_phc(struct ice_hw *hw); int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); /* E822 family functions */ -int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val); -int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val); int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val); -int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time); void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad); /** @@ -197,6 +271,19 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data); bool ice_is_pca9575_present(struct ice_hw *hw); +enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); +struct dpll_pin_frequency * +ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num); +const char *ice_cgu_get_pin_name(struct ice_hw *hw, u8 pin, bool input); +int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx, + enum dpll_lock_status last_dpll_state, u8 *pin, + u8 *ref_state, u8 *eec_mode, s64 *phase_offset, + enum dpll_lock_status *dpll_state); +int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num); + +void ice_ptp_init_phy_model(struct ice_hw *hw); +int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id, + unsigned long *caps); #define PFTSYN_SEM_BYTES 4 diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index e30e12321abd..c686ac0935eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -254,7 +254,7 @@ static const struct net_device_ops ice_repr_netdev_ops = { * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev * @netdev: pointer to netdev */ -bool ice_is_port_repr_netdev(struct net_device *netdev) +bool ice_is_port_repr_netdev(const struct net_device *netdev) { return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); } diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 9c2a6f496b3b..e1ee2d2c1d2d 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -12,6 +12,7 @@ struct ice_repr { struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; + struct ice_esw_br_port *br_port; #ifdef CONFIG_ICE_SWITCHDEV /* info about slow path rule */ struct ice_rule_query_data sp_rule; @@ -27,5 +28,5 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr); void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); -bool ice_is_port_repr_netdev(struct net_device *netdev); +bool ice_is_port_repr_netdev(const struct net_device *netdev); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index b664d60fd037..2f4a621254e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -229,29 +229,22 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req, * ice_sched_remove_elems - remove nodes from HW * @hw: pointer to the HW struct * @parent: pointer to the parent node - * @num_nodes: number of nodes - * @node_teids: array of node teids to be deleted + * @node_teid: node teid to be deleted * * This function remove nodes from HW */ static int ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, - u16 num_nodes, u32 *node_teids) + u32 node_teid) { - struct ice_aqc_delete_elem *buf; - u16 i, num_groups_removed = 0; - u16 buf_size; + DEFINE_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); + u16 buf_size = __struct_size(buf); + u16 num_groups_removed = 0; int status; - buf_size = struct_size(buf, teid, num_nodes); - buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - 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]); + buf->hdr.num_elems = cpu_to_le16(1); + buf->teid[0] = cpu_to_le32(node_teid); status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size, &num_groups_removed, NULL); @@ -259,7 +252,6 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, ice_debug(hw, ICE_DBG_SCHED, "remove node failed FW error %d\n", hw->adminq.sq_last_status); - devm_kfree(ice_hw_to_dev(hw), buf); return status; } @@ -326,7 +318,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF) { u32 teid = le32_to_cpu(node->info.node_teid); - ice_sched_remove_elems(hw, node->parent, 1, &teid); + ice_sched_remove_elems(hw, node->parent, teid); } parent = node->parent; /* root has no parent */ @@ -437,24 +429,20 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, } /** - * ice_aq_move_sched_elems - move scheduler elements + * ice_aq_move_sched_elems - move scheduler element (just 1 group) * @hw: pointer to the HW struct - * @grps_req: number of groups to move * @buf: pointer to buffer * @buf_size: buffer size in bytes * @grps_movd: returns total number of groups moved - * @cd: pointer to command details structure or NULL * * Move scheduling elements (0x0408) */ -static int -ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, - struct ice_aqc_move_elem *buf, u16 buf_size, - u16 *grps_movd, struct ice_sq_cd *cd) +int +ice_aq_move_sched_elems(struct ice_hw *hw, struct ice_aqc_move_elem *buf, + u16 buf_size, u16 *grps_movd) { return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_move_sched_elems, - grps_req, (void *)buf, buf_size, - grps_movd, cd); + 1, buf, buf_size, grps_movd, NULL); } /** @@ -526,7 +514,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, * * This function suspends or resumes HW nodes */ -static int +int ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, bool suspend) { @@ -569,18 +557,24 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) { struct ice_vsi_ctx *vsi_ctx; struct ice_q_ctx *q_ctx; + u16 idx; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) return -EINVAL; /* allocate LAN queue contexts */ if (!vsi_ctx->lan_q_ctx[tc]) { - vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), - new_numqs, - sizeof(*q_ctx), - GFP_KERNEL); - if (!vsi_ctx->lan_q_ctx[tc]) + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) return -ENOMEM; + + for (idx = 0; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; return 0; } @@ -592,9 +586,16 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) return -ENOMEM; + memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]); + + for (idx = prev_num; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; } @@ -1044,7 +1045,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, * * This function add nodes to a given layer. */ -static int +int ice_sched_add_nodes_to_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -1119,7 +1120,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw) * * This function returns the current VSI layer number */ -static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) +u8 ice_sched_get_vsi_layer(struct ice_hw *hw) { /* Num Layers VSI layer * 9 6 @@ -1142,7 +1143,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * * This function returns the current aggregator layer number */ -static u8 ice_sched_get_agg_layer(struct ice_hw *hw) +u8 ice_sched_get_agg_layer(struct ice_hw *hw) { /* Num Layers aggregator layer * 9 4 @@ -1180,7 +1181,7 @@ static void ice_rm_dflt_leaf_node(struct ice_port_info *pi) int status; /* remove the default leaf node */ - status = ice_sched_remove_elems(pi->hw, node->parent, 1, &teid); + status = ice_sched_remove_elems(pi->hw, node->parent, teid); if (!status) ice_free_sched_node(pi, node); } @@ -1577,7 +1578,7 @@ ice_sched_get_vsi_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, * This function retrieves an aggregator node for a given aggregator ID from * a given TC branch */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, u32 agg_id) { @@ -2139,7 +2140,7 @@ ice_get_agg_info(struct ice_hw *hw, u32 agg_id) * This function walks through the aggregator subtree to find a free parent * node */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, u16 *num_nodes) { @@ -2219,12 +2220,12 @@ int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { - struct ice_aqc_move_elem *buf; + DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + u16 buf_len = __struct_size(buf); struct ice_sched_node *node; u16 i, grps_movd = 0; struct ice_hw *hw; int status = 0; - u16 buf_len; hw = pi->hw; @@ -2236,35 +2237,27 @@ ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, hw->max_children[parent->tx_sched_layer]) return -ENOSPC; - buf_len = struct_size(buf, teid, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - for (i = 0; i < num_items; i++) { node = ice_sched_find_node_by_teid(pi->root, list[i]); if (!node) { status = -EINVAL; - goto move_err_exit; + break; } buf->hdr.src_parent_teid = node->info.parent_teid; buf->hdr.dest_parent_teid = parent->info.node_teid; buf->teid[0] = node->info.node_teid; buf->hdr.num_elems = cpu_to_le16(1); - status = ice_aq_move_sched_elems(hw, 1, buf, buf_len, - &grps_movd, NULL); + status = ice_aq_move_sched_elems(hw, buf, buf_len, &grps_movd); if (status && grps_movd != 1) { status = -EIO; - goto move_err_exit; + break; } /* update the SW DB */ ice_sched_update_parent(parent, node); } -move_err_exit: - kfree(buf); return status; } @@ -3958,7 +3951,7 @@ ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id, * This function sets BW limit of VSI or Aggregator scheduling node * based on TC information from passed in argument BW. */ -int +static int ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, enum ice_agg_type agg_type, u8 tc, enum ice_rl_type rl_type, u32 bw) diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 9c100747445a..1aef05ea5a57 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -141,13 +141,28 @@ ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, int ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type); -int -ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, - enum ice_agg_type agg_type, u8 tc, - enum ice_rl_type rl_type, u32 bw); int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); +int +ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, + bool suspend); +struct ice_sched_node * +ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, + u32 agg_id); +u8 ice_sched_get_agg_layer(struct ice_hw *hw); +u8 ice_sched_get_vsi_layer(struct ice_hw *hw); +struct ice_sched_node * +ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, + u16 *num_nodes); +int +ice_sched_add_nodes_to_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); +int ice_aq_move_sched_elems(struct ice_hw *hw, struct ice_aqc_move_elem *buf, + u16 buf_size, u16 *grps_movd); int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 31314e7540f8..e1494f24f661 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -64,7 +64,7 @@ static void ice_free_vf_res(struct ice_vf *vf) vf->num_mac = 0; } - last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1; + last_vector_idx = vf->first_vector_idx + vf->num_msix - 1; /* clear VF MDD event information */ memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); @@ -102,7 +102,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); first = vf->first_vector_idx; - last = first + pf->vfs.num_msix_per - 1; + last = first + vf->num_msix - 1; for (v = first; v <= last; v++) { u32 reg; @@ -138,6 +138,8 @@ static int ice_sriov_free_msix_res(struct ice_pf *pf) if (!pf) return -EINVAL; + bitmap_free(pf->sriov_irq_bm); + pf->sriov_irq_size = 0; pf->sriov_base_vector = 0; return 0; @@ -244,22 +246,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) return vsi; } -/** - * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space - * @pf: pointer to PF structure - * @vf: pointer to VF that the first MSIX vector index is being calculated for - * - * This returns the first MSIX vector index in PF space that is used by this VF. - * This index is used when accessing PF relative registers such as - * GLINT_VECT2FUNC and GLINT_DYN_CTL. - * This will always be the OICR index in the AVF driver so any functionality - * using vf->first_vector_idx for queue configuration will have to increment by - * 1 to avoid meddling with the OICR index. - */ -static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) -{ - return pf->sriov_base_vector + vf->vf_id * pf->vfs.num_msix_per; -} /** * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware @@ -280,12 +266,12 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) hw = &pf->hw; pf_based_first_msix = vf->first_vector_idx; - pf_based_last_msix = (pf_based_first_msix + pf->vfs.num_msix_per) - 1; + pf_based_last_msix = (pf_based_first_msix + vf->num_msix) - 1; device_based_first_msix = pf_based_first_msix + pf->hw.func_caps.common_cap.msix_vector_first_id; device_based_last_msix = - (device_based_first_msix + pf->vfs.num_msix_per) - 1; + (device_based_first_msix + vf->num_msix) - 1; device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & @@ -388,16 +374,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) */ int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) { - struct ice_pf *pf; - if (!vf || !q_vector) return -EINVAL; - pf = vf->pf; - /* always add one to account for the OICR being the first MSIX */ - return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id + - q_vector->v_idx + 1; + return vf->first_vector_idx + q_vector->v_idx + 1; } /** @@ -527,6 +508,52 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) } /** + * ice_sriov_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get + * + * This returns the first MSI-X vector index in PF space that is used by this + * VF. This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality + * using vf->first_vector_idx for queue configuration_id: id of VF which will + * use this irqs + * + * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are + * allocated from the end of global irq index. First bit in sriov_irq_bm means + * last irq index etc. It simplifies extension of SRIOV vectors. + * They will be always located from sriov_base_vector to the last irq + * index. While increasing/decreasing sriov_base_vector can be moved. + */ +static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed) +{ + int res = bitmap_find_next_zero_area(pf->sriov_irq_bm, + pf->sriov_irq_size, 0, needed, 0); + /* conversion from number in bitmap to global irq index */ + int index = pf->sriov_irq_size - res - needed; + + if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector) + return -ENOENT; + + bitmap_set(pf->sriov_irq_bm, res, needed); + return index; +} + +/** + * ice_sriov_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @vf: pointer to VF structure + */ +static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf) +{ + /* Move back from first vector index to first index in bitmap */ + int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix; + + bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix); + vf->first_vector_idx = 0; +} + +/** * ice_init_vf_vsi_res - initialize/setup VF VSI resources * @vf: VF to initialize/setup the VSI for * @@ -539,7 +566,9 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -ENOMEM; vsi = ice_vf_vsi_setup(vf); if (!vsi) @@ -789,14 +818,19 @@ static const struct ice_vf_ops ice_sriov_vf_ops = { */ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) { + struct pci_dev *pdev = pf->pdev; struct ice_vfs *vfs = &pf->vfs; + struct pci_dev *vfdev = NULL; struct ice_vf *vf; - u16 vf_id; - int err; + u16 vf_pdev_id; + int err, pos; lockdep_assert_held(&vfs->table_lock); - for (vf_id = 0; vf_id < num_vfs; vf_id++) { + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_pdev_id); + + for (u16 vf_id = 0; vf_id < num_vfs; vf_id++) { vf = kzalloc(sizeof(*vf), GFP_KERNEL); if (!vf) { err = -ENOMEM; @@ -812,11 +846,28 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) ice_initialize_vf_entry(vf); + do { + vfdev = pci_get_device(pdev->vendor, vf_pdev_id, vfdev); + } while (vfdev && vfdev->physfn != pdev); + vf->vfdev = vfdev; vf->vf_sw_id = pf->first_sw; + pci_dev_get(vfdev); + + /* set default number of MSI-X */ + vf->num_msix = pf->vfs.num_msix_per; + vf->num_vf_qs = pf->vfs.num_qps_per; + ice_vc_set_default_allowlist(vf); + hash_add_rcu(vfs->table, &vf->entry, vf_id); } + /* Decrement of refcount done by pci_get_device() inside the loop does + * not touch the last iteration's vfdev, so it has to be done manually + * to balance pci_dev_get() added within the loop. + */ + pci_dev_put(vfdev); + return 0; err_free_entries: @@ -831,10 +882,16 @@ err_free_entries: */ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) { + int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int ret; + pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL); + if (!pf->sriov_irq_bm) + return -ENOMEM; + pf->sriov_irq_size = total_vectors; + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); @@ -893,6 +950,7 @@ err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); clear_bit(ICE_OICR_INTR_DIS, pf->state); + bitmap_free(pf->sriov_irq_bm); return ret; } @@ -957,6 +1015,175 @@ static int ice_check_sriov_allowed(struct ice_pf *pf) } /** + * ice_sriov_get_vf_total_msix - return number of MSI-X used by VFs + * @pdev: pointer to pci_dev struct + * + * The function is called via sysfs ops + */ +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf); +} + +static int ice_sriov_move_base_vector(struct ice_pf *pf, int move) +{ + if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf)) + return -ENOMEM; + + pf->sriov_base_vector -= move; + return 0; +} + +static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) +{ + u16 vf_ids[ICE_MAX_SRIOV_VFS]; + struct ice_vf *tmp_vf; + int to_remap = 0, bkt; + + /* For better irqs usage try to remap irqs of VFs + * that aren't running yet + */ + ice_for_each_vf(pf, bkt, tmp_vf) { + /* skip VF which is changing the number of MSI-X */ + if (restricted_id == tmp_vf->vf_id || + test_bit(ICE_VF_STATE_ACTIVE, tmp_vf->vf_states)) + continue; + + ice_dis_vf_mappings(tmp_vf); + ice_sriov_free_irqs(pf, tmp_vf); + + vf_ids[to_remap] = tmp_vf->vf_id; + to_remap += 1; + } + + for (int i = 0; i < to_remap; i++) { + tmp_vf = ice_get_vf_by_id(pf, vf_ids[i]); + if (!tmp_vf) + continue; + + tmp_vf->first_vector_idx = + ice_sriov_get_irqs(pf, tmp_vf->num_msix); + /* there is no need to rebuild VSI as we are only changing the + * vector indexes not amount of MSI-X or queues + */ + ice_ena_vf_mappings(tmp_vf); + ice_put_vf(tmp_vf); + } +} + +/** + * ice_sriov_set_msix_vec_count + * @vf_dev: pointer to pci_dev struct of VF device + * @msix_vec_count: new value for MSI-X amount on this VF + * + * Set requested MSI-X, queues and registers for @vf_dev. + * + * First do some sanity checks like if there are any VFs, if the new value + * is correct etc. Then disable old mapping (MSI-X and queues registers), change + * MSI-X and queues, rebuild VSI and enable new mapping. + * + * If it is possible (driver not binded to VF) try to remap also other VFs to + * linearize irqs register usage. + */ +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + struct pci_dev *pdev = pci_physfn(vf_dev); + struct ice_pf *pf = pci_get_drvdata(pdev); + u16 prev_msix, prev_queues, queues; + bool needs_rebuild = false; + struct ice_vf *vf; + int id; + + if (!ice_get_num_vfs(pf)) + return -ENOENT; + + if (!msix_vec_count) + return 0; + + queues = msix_vec_count; + /* add 1 MSI-X for OICR */ + msix_vec_count += 1; + + if (queues > min(ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf))) + return -EINVAL; + + if (msix_vec_count < ICE_MIN_INTR_PER_VF) + return -EINVAL; + + /* Transition of PCI VF function number to function_id */ + for (id = 0; id < pci_num_vf(pdev); id++) { + if (vf_dev->devfn == pci_iov_virtfn_devfn(pdev, id)) + break; + } + + if (id == pci_num_vf(pdev)) + return -ENOENT; + + vf = ice_get_vf_by_id(pf, id); + + if (!vf) + return -ENOENT; + + prev_msix = vf->num_msix; + prev_queues = vf->num_vf_qs; + + if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) { + ice_put_vf(vf); + return -ENOSPC; + } + + ice_dis_vf_mappings(vf); + ice_sriov_free_irqs(pf, vf); + + /* Remap all VFs beside the one is now configured */ + ice_sriov_remap_vectors(pf, vf->vf_id); + + vf->num_msix = msix_vec_count; + vf->num_vf_qs = queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + goto unroll; + + ice_vf_vsi_release(vf); + if (vf->vf_ops->create_vsi(vf)) { + /* Try to rebuild with previous values */ + needs_rebuild = true; + goto unroll; + } + + dev_info(ice_pf_to_dev(pf), + "Changing VF %d resources to %d vectors and %d queues\n", + vf->vf_id, vf->num_msix, vf->num_vf_qs); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return 0; + +unroll: + dev_info(ice_pf_to_dev(pf), + "Can't set %d vectors on VF %d, falling back to %d\n", + vf->num_msix, vf->vf_id, prev_msix); + + vf->num_msix = prev_msix; + vf->num_vf_qs = prev_queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -EINVAL; + + if (needs_rebuild) + vf->vf_ops->create_vsi(vf); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return -EINVAL; +} + +/** * 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 or 0 to free VFs @@ -1709,31 +1936,16 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) /** * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR - * @pdev: pointer to a pci_dev structure + * @pf: pointer to the PF structure * * Called when recovering from a PF FLR to restore interrupt capability to * the VFs. */ -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) +void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { - u16 vf_id; - int pos; - - if (!pci_num_vf(pdev)) - return; + struct ice_vf *vf; + u32 bkt; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); - if (pos) { - struct pci_dev *vfdev; - - pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, - &vf_id); - vfdev = pci_get_device(pdev->vendor, vf_id, NULL); - while (vfdev) { - if (vfdev->is_virtfn && vfdev->physfn == pdev) - pci_restore_msi_state(vfdev); - vfdev = pci_get_device(pdev->vendor, vf_id, - vfdev); - } - } + ice_for_each_vf(pf, bkt, vf) + pci_restore_msi_state(vf->vfdev); } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 346cb2666f3a..8488df38b586 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -33,7 +33,7 @@ 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_restore_all_vfs_msi_state(struct pci_dev *pdev); +void ice_restore_all_vfs_msi_state(struct ice_pf *pf); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -60,6 +60,8 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); bool ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev); +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count); #else /* CONFIG_PCI_IOV */ static inline void ice_process_vflr_event(struct ice_pf *pf) { } static inline void ice_free_vfs(struct ice_pf *pf) { } @@ -67,7 +69,7 @@ static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } -static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } +static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { } static inline int ice_sriov_configure(struct pci_dev __always_unused *pdev, @@ -142,5 +144,16 @@ ice_get_vf_stats(struct net_device __always_unused *netdev, { return -EOPNOTSUPP; } + +static inline u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + return 0; +} + +static inline int +ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6db4ca7978cb..ee19f3aa3d19 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -20,12 +20,11 @@ * byte 0 = 0x2: to identify it as locally administered DA MAC * byte 6 = 0x2: to identify it as locally administered SA MAC * byte 12 = 0x81 & byte 13 = 0x00: - * In case of VLAN filter first two bytes defines ether type (0x8100) - * and remaining two bytes are placeholder for programming a given VLAN ID - * In case of Ether type filter it is treated as header without VLAN tag - * and byte 12 and 13 is used to program a given Ether type instead + * In case of VLAN filter first two bytes defines ether type (0x8100) + * and remaining two bytes are placeholder for programming a given VLAN ID + * In case of Ether type filter it is treated as header without VLAN tag + * and byte 12 and 13 is used to program a given Ether type instead */ -#define DUMMY_ETH_HDR_LEN 16 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; @@ -1369,14 +1368,6 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(tcp, 0), }; -#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) -#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) -#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) -#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) - /* this is a recipe to profile association bitmap */ static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], ICE_MAX_NUM_PROFILES); @@ -1821,15 +1812,11 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type, enum ice_adminq_opc opc) { - struct ice_aqc_alloc_free_res_elem *sw_buf; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); struct ice_aqc_res_elem *vsi_ele; - u16 buf_len; int status; - buf_len = struct_size(sw_buf, elem, 1); - sw_buf = devm_kzalloc(ice_hw_to_dev(hw), buf_len, GFP_KERNEL); - if (!sw_buf) - return -ENOMEM; sw_buf->num_elems = cpu_to_le16(1); if (lkup_type == ICE_SW_LKUP_MAC || @@ -1841,28 +1828,30 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_DFLT) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { - sw_buf->res_type = - cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); + if (opc == ice_aqc_opc_alloc_res) + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); } else { - status = -EINVAL; - goto ice_aq_alloc_free_vsi_list_exit; + return -EINVAL; } if (opc == ice_aqc_opc_free_res) sw_buf->elem[0].e.sw_resp = cpu_to_le16(*vsi_list_id); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, opc, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, opc); if (status) - goto ice_aq_alloc_free_vsi_list_exit; + return status; if (opc == ice_aqc_opc_alloc_res) { vsi_ele = &sw_buf->elem[0]; *vsi_list_id = le16_to_cpu(vsi_ele->e.sw_resp); } -ice_aq_alloc_free_vsi_list_exit: - devm_kfree(ice_hw_to_dev(hw), sw_buf); - return status; + return 0; } /** @@ -1910,7 +1899,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, * * Add(0x0290) */ -static int +int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd) @@ -1947,7 +1936,7 @@ ice_aq_add_recipe(struct ice_hw *hw, * The caller must supply enough space in s_recipe_list to hold all possible * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. */ -static int +int ice_aq_get_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) @@ -2040,7 +2029,7 @@ error_out: * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ -static int +int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2066,7 +2055,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ -static int +int ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2090,26 +2079,20 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ -static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { - struct ice_aqc_alloc_free_res_elem *sw_buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + u16 buf_len = __struct_size(sw_buf); int status; - buf_len = struct_size(sw_buf, elem, 1); - sw_buf = kzalloc(buf_len, GFP_KERNEL); - if (!sw_buf) - return -ENOMEM; - sw_buf->num_elems = cpu_to_le16(1); sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << ICE_AQC_RES_TYPE_S) | ICE_AQC_RES_TYPE_FLAG_SHARED); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, + ice_aqc_opc_alloc_res); if (!status) *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); - kfree(sw_buf); return status; } @@ -2272,6 +2255,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Propagate some data to the recipe database */ recps[idx].is_root = !!is_root; recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + recps[idx].need_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { recps[idx].chain_idx = root_bufs.content.result_indx & @@ -2460,6 +2447,15 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) } /** + * ice_fill_eth_hdr - helper to copy dummy_eth_hdr into supplied buffer + * @eth_hdr: pointer to buffer to populate + */ +void ice_fill_eth_hdr(u8 *eth_hdr) +{ + memcpy(eth_hdr, dummy_eth_header, DUMMY_ETH_HDR_LEN); +} + +/** * ice_fill_sw_rule - Helper function to fill switch rule structure * @hw: pointer to the hardware structure * @f_info: entry containing packet forwarding information @@ -3118,7 +3114,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) * 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 * +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) { @@ -3129,7 +3125,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, list_head = &sw->recp_list[recp_id].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { - if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { + if (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; @@ -3400,54 +3396,6 @@ exit: } /** - * ice_mac_fltr_exist - does this MAC filter exist for given VSI - * @hw: pointer to the hardware structure - * @mac: MAC address to be checked (for MAC filter) - * @vsi_handle: check MAC filter for this VSI - */ -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle) -{ - struct ice_fltr_mgmt_list_entry *entry; - struct list_head *rule_head; - struct ice_switch_info *sw; - struct mutex *rule_lock; /* Lock to protect filter rule list */ - u16 hw_vsi_id; - - if (!ice_is_vsi_valid(hw, vsi_handle)) - return false; - - hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - sw = hw->switch_info; - rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; - if (!rule_head) - return false; - - rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; - mutex_lock(rule_lock); - list_for_each_entry(entry, rule_head, list_entry) { - struct ice_fltr_info *f_info = &entry->fltr_info; - u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - - if (is_zero_ether_addr(mac_addr)) - continue; - - if (f_info->flag != ICE_FLTR_TX || - f_info->src_id != ICE_SRC_ID_VSI || - f_info->lkup_type != ICE_SW_LKUP_MAC || - f_info->fltr_act != ICE_FWD_TO_VSI || - hw_vsi_id != f_info->fwd_id.hw_vsi_id) - continue; - - if (ether_addr_equal(mac, mac_addr)) { - mutex_unlock(rule_lock); - return true; - } - } - mutex_unlock(rule_lock); - return false; -} - -/** * ice_vlan_fltr_exist - does this VLAN filter exist for given VSI * @hw: pointer to the hardware structure * @vlan_id: VLAN ID @@ -4473,29 +4421,19 @@ int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id) { - struct ice_aqc_alloc_free_res_elem *buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); int status; - /* Allocate resource */ - buf_len = struct_size(buf, elem, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & ICE_AQC_RES_TYPE_M) | alloc_shared); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) - goto exit; + return status; *counter_id = le16_to_cpu(buf->elem[0].e.sw_resp); - -exit: - kfree(buf); return status; } @@ -4511,27 +4449,19 @@ int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id) { - struct ice_aqc_alloc_free_res_elem *buf; - u16 buf_len; + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); int status; - /* Free resource */ - buf_len = struct_size(buf, elem, 1); - buf = kzalloc(buf_len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & ICE_AQC_RES_TYPE_M) | alloc_shared); buf->elem[0].e.sw_resp = cpu_to_le16(counter_id); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "counter resource could not be freed\n"); - kfree(buf); return status; } @@ -4540,6 +4470,39 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, .offs = {__VA_ARGS__}, \ } +/** + * ice_share_res - set a resource as shared or dedicated + * @hw: hw struct of original owner of resource + * @type: resource type + * @shared: is the resource being set to shared + * @res_id: resource id (descriptor) + */ +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) +{ + DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + u16 buf_len = __struct_size(buf); + int status; + + buf->num_elems = cpu_to_le16(1); + if (shared) + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) & + ~ICE_AQC_RES_TYPE_FLAG_SHARED); + + buf->elem[0].e.sw_resp = cpu_to_le16(res_id); + status = ice_aq_alloc_free_res(hw, buf, buf_len, + ice_aqc_opc_share_res); + if (status) + ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n", + type, res_id, shared ? "SHARED" : "DEDICATED"); + + return status; +} + /* This is mapping table entry that maps every word within a given protocol * structure to the real byte offset as per the specification of that * protocol header. @@ -4613,13 +4576,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match - * @tun_type: type of recipe tunnel + * @rinfo: information regarding the rule e.g. priority and action info * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, - enum ice_sw_tunnel_type tun_type) + const struct ice_adv_rule_info *rinfo) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4680,9 +4643,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /* If for "i"th recipe the found was never set to false * then it means we found our match - * Also tun type of recipe needs to be checked + * Also tun type and *_pass_l2 of recipe needs to be + * checked */ - if (found && recp[i].tun_type == tun_type) + if (found && recp[i].tun_type == rinfo->tun_type && + recp[i].need_pass_l2 == rinfo->need_pass_l2 && + recp[i].allow_pass_l2 == rinfo->allow_pass_l2) return i; /* Return the recipe ID */ } } @@ -4952,6 +4918,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, unsigned long *profiles) { DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_content *content; struct ice_aqc_recipe_data_elem *tmp; struct ice_aqc_recipe_data_elem *buf; struct ice_recp_grp_entry *entry; @@ -5012,6 +4979,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + /* Clear the result index of the located recipe, as this will be * updated, if needed, later in the recipe creation process. */ @@ -5022,26 +4991,24 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, /* if the recipe is a non-root recipe RID should be programmed * as 0 for the rules to be applied correctly. */ - buf[recps].content.rid = 0; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + content->rid = 0; + memset(&content->lkup_indx, 0, + sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask * to be 0 */ for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = 0x80; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = 0x80; + content->mask[i] = 0; } for (i = 0; i < entry->r_group.n_val_pairs; i++) { - buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; - buf[recps].content.mask[i + 1] = - cpu_to_le16(entry->fv_mask[i]); + content->lkup_indx[i + 1] = entry->fv_idx[i]; + content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]); } if (rm->n_grp_count > 1) { @@ -5055,7 +5022,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, } entry->chain_idx = chain_idx; - buf[recps].content.result_indx = + content->result_indx = ICE_AQ_RECIPE_RESULT_EN | ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & ICE_AQ_RECIPE_RESULT_DATA_M); @@ -5069,7 +5036,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, ICE_MAX_NUM_RECIPES); set_bit(buf[recps].recipe_indx, (unsigned long *)buf[recps].recipe_bitmap); - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; + + if (rm->need_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + + if (rm->allow_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; recps++; } @@ -5107,9 +5080,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + buf[recps].recipe_indx = (u8)rid; - buf[recps].content.rid = (u8)rid; - buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + content->rid = (u8)rid; + content->rid |= ICE_AQ_RECIPE_ID_IS_ROOT; /* the new entry created should also be part of rg_list to * make sure we have complete recipe */ @@ -5121,16 +5096,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, goto err_unroll; } last_chain_entry->rid = rid; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + memset(&content->lkup_indx, 0, sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = - ICE_AQ_RECIPE_LKUP_IGNORE; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; + content->mask[i] = 0; } i = 1; @@ -5142,8 +5114,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; list_for_each_entry(entry, &rm->rg_list, l_entry) { last_chain_entry->fv_idx[i] = entry->chain_idx; - buf[recps].content.lkup_indx[i] = entry->chain_idx; - buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + content->lkup_indx[i] = entry->chain_idx; + content->mask[i++] = cpu_to_le16(0xFFFF); set_bit(entry->rid, rm->r_bitmap); } list_add(&last_chain_entry->l_entry, &rm->rg_list); @@ -5155,7 +5127,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, status = -EINVAL; goto err_unroll; } - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; recps++; rm->root_rid = (u8)rid; @@ -5220,6 +5192,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; recp->n_grp_count = rm->n_grp_count; recp->tun_type = rm->tun_type; + recp->need_pass_l2 = rm->need_pass_l2; + recp->allow_pass_l2 = rm->allow_pass_l2; recp->recp_created = true; } rm->root_buf = buf; @@ -5388,6 +5362,9 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* set the recipe priority if specified */ rm->priority = (u8)rinfo->priority; + rm->need_pass_l2 = rinfo->need_pass_l2; + rm->allow_pass_l2 = rinfo->allow_pass_l2; + /* Find offsets from the field vector. Pick the first one for all the * recipes. */ @@ -5403,7 +5380,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); + *rid = ice_find_recp(hw, lkup_exts, rinfo); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; @@ -5839,7 +5816,9 @@ static bool ice_rules_equal(const struct ice_adv_rule_info *first, return first->sw_act.flag == second->sw_act.flag && first->tun_type == second->tun_type && first->vlan_type == second->vlan_type && - first->src_vsi == second->src_vsi; + first->src_vsi == second->src_vsi && + first->need_pass_l2 == second->need_pass_l2 && + first->allow_pass_l2 == second->allow_pass_l2; } /** @@ -5994,14 +5973,21 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID21] |= cpu_to_be16(ICE_PKT_TUNNEL_MASK); } +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= + cpu_to_be16(ICE_PKT_FROM_NETWORK); +} + void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= cpu_to_be16(ICE_PKT_VLAN_MASK); } @@ -6078,7 +6064,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || - rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) { + rinfo->sw_act.fltr_act == ICE_DROP_PACKET || + rinfo->sw_act.fltr_act == ICE_NOP)) { status = -EIO; goto free_pkt_profile; } @@ -6089,7 +6076,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, goto free_pkt_profile; } - if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_NOP) rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); @@ -6159,6 +6147,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | ICE_SINGLE_ACT_VALID_BIT; break; + case ICE_NOP: + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); + act &= ~ICE_SINGLE_ACT_VALID_BIT; + break; default: status = -EIO; goto err_ice_add_adv_rule; @@ -6439,7 +6432,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); + rid = ice_find_recp(hw, &lkup_exts, rinfo); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6533,59 +6526,6 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, } /** - * ice_rem_adv_rule_for_vsi - removes existing advanced switch rules for a - * given VSI handle - * @hw: pointer to the hardware structure - * @vsi_handle: VSI handle for which we are supposed to remove all the rules. - * - * This function is used to remove all the rules for a given VSI and as soon - * as removing a rule fails, it will return immediately with the error code, - * else it will return success. - */ -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle) -{ - struct ice_adv_fltr_mgmt_list_entry *list_itr, *tmp_entry; - struct ice_vsi_list_map_info *map_info; - struct ice_adv_rule_info rinfo; - struct list_head *list_head; - struct ice_switch_info *sw; - int status; - u8 rid; - - sw = hw->switch_info; - for (rid = 0; rid < ICE_MAX_NUM_RECIPES; rid++) { - if (!sw->recp_list[rid].recp_created) - continue; - if (!sw->recp_list[rid].adv_rule) - continue; - - list_head = &sw->recp_list[rid].filt_rules; - list_for_each_entry_safe(list_itr, tmp_entry, list_head, - list_entry) { - rinfo = list_itr->rule_info; - - if (rinfo.sw_act.fltr_act == ICE_FWD_TO_VSI_LIST) { - map_info = list_itr->vsi_list_info; - if (!map_info) - continue; - - if (!test_bit(vsi_handle, map_info->vsi_map)) - continue; - } else if (rinfo.sw_act.vsi_handle != vsi_handle) { - continue; - } - - rinfo.sw_act.vsi_handle = vsi_handle; - status = ice_rem_adv_rule(hw, list_itr->lkups, - list_itr->lkups_cnt, &rinfo); - if (status) - return status; - } - } - return 0; -} - -/** * ice_replay_vsi_adv_rule - Replay advanced rule for requested VSI * @hw: pointer to the hardware structure * @vsi_handle: driver VSI handle diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index c84b56fe84a5..db7e501b7e0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -22,6 +22,16 @@ #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) +#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) +#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) +#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) +#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) + +#define DUMMY_ETH_HDR_LEN 16 + /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { u16 vsi_num; @@ -191,6 +201,8 @@ struct ice_adv_rule_info { u16 vlan_type; u16 fltr_rule_id; u32 priority; + u16 need_pass_l2:1; + u16 allow_pass_l2:1; u16 src_vsi; struct ice_sw_act_ctrl sw_act; struct ice_adv_rule_flags_info flags_info; @@ -254,6 +266,9 @@ struct ice_sw_recipe { */ u8 priority; + u8 need_pass_l2:1; + u8 allow_pass_l2:1; + struct list_head rg_list; /* AQ buffer associated with this recipe */ @@ -340,9 +355,11 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id); /* Switch/bridge related commands */ void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup); +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup); int @@ -354,7 +371,6 @@ int ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); int ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); int ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle); bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle); int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); @@ -379,7 +395,6 @@ int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry); @@ -389,6 +404,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); +void ice_fill_eth_hdr(u8 *eth_hdr); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, @@ -397,4 +413,21 @@ int ice_update_recipe_lkup_idx(struct ice_hw *hw, struct ice_update_recipe_lkup_idx_params *params); void ice_change_proto_id_to_dvm(void); +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); +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid); +int ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd); +int ice_aq_add_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 num_recipes, struct ice_sq_cd *cd); +int +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); +int +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); + #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 4a34ef5f58d3..dd03cb69ad26 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -7,6 +7,8 @@ #include "ice_lib.h" #include "ice_protocol_type.h" +#define ICE_TC_METADATA_LKUP_IDX 0 + /** * ice_tc_count_lkups - determine lookup count for switch filter * @flags: TC-flower flags @@ -19,7 +21,13 @@ static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, struct ice_tc_flower_fltr *fltr) { - int lkups_cnt = 0; + int lkups_cnt = 1; /* 0th lookup is metadata */ + + /* Always add metadata as the 0th lookup. Included elements: + * - Direction flag (always present) + * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) + * - Tunnel flag (present if tunnel) + */ if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -54,10 +62,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) lkups_cnt++; - /* is VLAN TPID specified */ - if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID) - lkups_cnt++; - /* is CVLAN specified? */ if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) lkups_cnt++; @@ -84,10 +88,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) lkups_cnt++; - /* matching for tunneled packets in metadata */ - if (fltr->tunnel_type != TNL_LAST) - lkups_cnt++; - return lkups_cnt; } @@ -176,10 +176,9 @@ static u16 ice_check_supported_vlan_tpid(u16 vlan_tpid) static int ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, - struct ice_adv_lkup_elem *list) + struct ice_adv_lkup_elem *list, int i) { struct ice_tc_flower_lyr_2_4_hdrs *hdr = &fltr->outer_headers; - int i = 0; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) { u32 tenant_id; @@ -329,8 +328,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, } /* always fill matching on tunneled packets in metadata */ - ice_rule_add_tunnel_metadata(&list[i]); - i++; + ice_rule_add_tunnel_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); return i; } @@ -358,13 +356,16 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; bool inner = false; u16 vlan_tpid = 0; - int i = 0; + int i = 1; /* 0th lookup is metadata */ rule_info->vlan_type = vlan_tpid; + /* Always add direction metadata */ + ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { - i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list); + i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); headers = &tc_fltr->inner_headers; inner = true; @@ -431,8 +432,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, rule_info->vlan_type = ice_check_supported_vlan_tpid(vlan_tpid); - ice_rule_add_vlan_metadata(&list[i]); - i++; + ice_rule_add_vlan_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); } if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) { @@ -630,32 +630,83 @@ bool ice_is_tunnel_supported(struct net_device *dev) return ice_tc_tun_get_type(dev) != TNL_LAST; } -static int -ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr, - struct flow_action_entry *act) +static bool ice_tc_is_dev_uplink(struct net_device *dev) +{ + return netif_is_ice(dev) || ice_is_tunnel_supported(dev); +} + +static int ice_tc_setup_redirect_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct net_device *target_dev) { struct ice_repr *repr; + fltr->action.fltr_act = ICE_FWD_TO_VSI; + + if (ice_is_port_repr_netdev(filter_dev) && + ice_is_port_repr_netdev(target_dev)) { + repr = ice_netdev_to_repr(target_dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_is_port_repr_netdev(filter_dev) && + ice_tc_is_dev_uplink(target_dev)) { + repr = ice_netdev_to_repr(filter_dev); + + fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_tc_is_dev_uplink(filter_dev) && + ice_is_port_repr_netdev(target_dev)) { + repr = ice_netdev_to_repr(target_dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int +ice_tc_setup_drop_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr) +{ + fltr->action.fltr_act = ICE_DROP_PACKET; + + if (ice_is_port_repr_netdev(filter_dev)) { + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else if (ice_tc_is_dev_uplink(filter_dev)) { + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int ice_eswitch_tc_parse_action(struct net_device *filter_dev, + struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + int err; + switch (act->id) { case FLOW_ACTION_DROP: - fltr->action.fltr_act = ICE_DROP_PACKET; + err = ice_tc_setup_drop_action(filter_dev, fltr); + if (err) + return err; + break; case FLOW_ACTION_REDIRECT: - fltr->action.fltr_act = ICE_FWD_TO_VSI; - - if (ice_is_port_repr_netdev(act->dev)) { - repr = ice_netdev_to_repr(act->dev); - - fltr->dest_vsi = repr->src_vsi; - fltr->direction = ICE_ESWITCH_FLTR_INGRESS; - } else if (netif_is_ice(act->dev) || - ice_is_tunnel_supported(act->dev)) { - fltr->direction = ICE_ESWITCH_FLTR_EGRESS; - } else { - NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode"); - return -EINVAL; - } + err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev); + if (err) + return err; break; @@ -696,10 +747,6 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) goto exit; } - /* egress traffic is always redirect to uplink */ - if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) - fltr->dest_vsi = vsi->back->switchdev.uplink_vsi; - rule_info.sw_act.fltr_act = fltr->action.fltr_act; if (fltr->action.fltr_act != ICE_DROP_PACKET) rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx; @@ -713,13 +760,21 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_info.flags_info.act_valid = true; if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { + /* Uplink to VF */ rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; - } else { + } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS && + fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) { + /* VF to Uplink */ rule_info.sw_act.flag |= ICE_FLTR_TX; rule_info.sw_act.src = vsi->idx; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + } else { + /* VF to VF */ + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } /* specify the cookie as filter_rule_id */ @@ -1343,24 +1398,24 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, dissector = rule->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PPPOE) | - BIT(FLOW_DISSECTOR_KEY_L2TPV3))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PPPOE) | + BIT_ULL(FLOW_DISSECTOR_KEY_L2TPV3))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); return -EOPNOTSUPP; } @@ -1382,10 +1437,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, */ headers = &fltr->inner_headers; } else if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { @@ -1745,16 +1800,17 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, /** * ice_parse_tc_flower_actions - Parse the actions for a TC filter + * @filter_dev: Pointer to device on which filter is being added * @vsi: Pointer to VSI * @cls_flower: Pointer to TC flower offload structure * @fltr: Pointer to TC flower filter structure * * Parse the actions for a TC filter */ -static int -ice_parse_tc_flower_actions(struct ice_vsi *vsi, - struct flow_cls_offload *cls_flower, - struct ice_tc_flower_fltr *fltr) +static int ice_parse_tc_flower_actions(struct net_device *filter_dev, + struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) { struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); struct flow_action *flow_action = &rule->action; @@ -1769,7 +1825,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi, flow_action_for_each(i, act, flow_action) { if (ice_is_eswitch_mode_switchdev(vsi->back)) - err = ice_eswitch_tc_parse_action(fltr, act); + err = ice_eswitch_tc_parse_action(filter_dev, fltr, act); else err = ice_tc_parse_action(vsi, fltr, act); if (err) @@ -1856,7 +1912,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, if (err < 0) goto err; - err = ice_parse_tc_flower_actions(vsi, f, fltr); + err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr); if (err < 0) goto err; diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index ae98d5a8ff60..b2f5c9fe0149 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -21,6 +21,7 @@ #define _ICE_TRACE_H_ #include <linux/tracepoint.h> +#include "ice_eswitch_br.h" /* ice_trace() macro enables shared code to refer to trace points * like: @@ -240,6 +241,95 @@ DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_req); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_done); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_complete); +DECLARE_EVENT_CLASS(ice_esw_br_fdb_template, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry(__array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(int, flags)), + TP_fast_assign(strscpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->data.addr, ETH_ALEN); + __entry->vid = fdb->data.vid; + __entry->flags = fdb->flags;), + TP_printk("net_device=%s addr=%pM vid=%u flags=%x", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_create, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_find_and_delete, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DECLARE_EVENT_CLASS(ice_esw_br_vlan_template, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry(__field(u16, vid) + __field(u16, flags)), + TP_fast_assign(__entry->vid = vlan->vid; + __entry->flags = vlan->flags;), + TP_printk("vid=%u flags=%x", + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_create, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_cleanup, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +#define ICE_ESW_BR_PORT_NAME_L 16 + +DECLARE_EVENT_CLASS(ice_esw_br_port_template, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port), + TP_STRUCT__entry(__field(u16, vport_num) + __array(char, port_type, ICE_ESW_BR_PORT_NAME_L)), + TP_fast_assign(__entry->vport_num = port->vsi_idx; + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + strscpy(__entry->port_type, + "Uplink", + ICE_ESW_BR_PORT_NAME_L); + else + strscpy(__entry->port_type, + "VF Representor", + ICE_ESW_BR_PORT_NAME_L);), + TP_printk("vport_num=%u port type=%s", + __entry->vport_num, + __entry->port_type) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_link, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_unlink, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + /* End tracepoints */ #endif /* _ICE_TRACE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 52d0a126eb61..9e97ea863068 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2306,9 +2306,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) return; - if (!tx_ring->ptp_tx) - return; - /* Tx timestamps cannot be sampled when doing TSO */ if (first->tx_flags & ICE_TX_FLAGS_TSO) return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 166413fc33f4..daf7b9dbb143 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -380,7 +380,6 @@ struct ice_tx_ring { #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ - u8 ptp_tx; } ____cacheline_internodealigned_in_smp; static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index c8322fb6f2b3..7e06373e14d9 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -450,7 +450,7 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[first_idx]; if (xdp_res & ICE_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_res & ICE_XDP_TX) { if (static_branch_unlikely(&ice_xdp_locking_key)) diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a09556e57803..a18ca0ff879f 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ +/* Copyright (c) 2018-2023, Intel Corporation. */ #ifndef _ICE_TYPE_H_ #define _ICE_TYPE_H_ @@ -129,6 +129,7 @@ enum ice_set_fc_aq_failures { enum ice_mac_type { ICE_MAC_UNKNOWN = 0, ICE_MAC_E810, + ICE_MAC_E830, ICE_MAC_GENERIC, }; @@ -277,6 +278,8 @@ struct ice_hw_common_caps { u8 dcb; u8 ieee_1588; u8 rdma; + u8 roce_lag; + u8 sriov_lag; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; @@ -820,6 +823,13 @@ struct ice_mbx_data { u16 async_watermark_val; }; +/* PHY model */ +enum ice_phy_model { + ICE_PHY_UNSUP = -1, + ICE_PHY_E810 = 1, + ICE_PHY_E822, +}; + /* Port hardware description */ struct ice_hw { u8 __iomem *hw_addr; @@ -841,6 +851,7 @@ struct ice_hw { u8 revision_id; u8 pf_id; /* device profile info */ + enum ice_phy_model phy_model; u16 max_burst_size; /* driver sets this value */ @@ -899,17 +910,20 @@ struct ice_hw { /* INTRL granularity in 1 us */ u8 intrl_gran; -#define ICE_PHY_PER_NAC 1 -#define ICE_MAX_QUAD 2 -#define ICE_NUM_QUAD_TYPE 2 -#define ICE_PORTS_PER_QUAD 4 -#define ICE_PHY_0_LAST_QUAD 1 -#define ICE_PORTS_PER_PHY 8 -#define ICE_NUM_EXTERNAL_PORTS ICE_PORTS_PER_PHY +#define ICE_PHY_PER_NAC_E822 1 +#define ICE_MAX_QUAD 2 +#define ICE_QUADS_PER_PHY_E822 2 +#define ICE_PORTS_PER_PHY_E822 8 +#define ICE_PORTS_PER_QUAD 4 +#define ICE_PORTS_PER_PHY_E810 4 +#define ICE_NUM_EXTERNAL_PORTS (ICE_MAX_QUAD * ICE_PORTS_PER_QUAD) /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; + u32 pkg_seg_id; + u32 pkg_sign_type; u32 active_track_id; + u8 pkg_has_signing_seg:1; u8 active_pkg_name[ICE_PKG_NAME_SIZE]; u8 active_pkg_in_nvm; @@ -963,6 +977,7 @@ struct ice_hw { DECLARE_BITMAP(hw_ptype, ICE_FLOW_PTYPE_MAX); u8 dvm_ena; u16 io_expander_handle; + u8 cgu_part_number; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ @@ -1033,14 +1048,15 @@ enum ice_sw_fwd_act_type { ICE_FWD_TO_Q, ICE_FWD_TO_QGRP, ICE_DROP_PACKET, + ICE_NOP, ICE_INVAL_ACT }; struct ice_aq_get_set_rss_lut_params { - u16 vsi_handle; /* software VSI handle */ - u16 lut_size; /* size of the LUT buffer */ - u8 lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ u8 *lut; /* input RSS LUT for set and output RSS LUT for get */ + enum ice_lut_size lut_size; /* size of the LUT buffer */ + enum ice_lut_type lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ + u16 vsi_handle; /* software VSI handle */ u8 global_lut_id; /* only valid when lut_type is global */ }; @@ -1142,9 +1158,6 @@ struct ice_aq_get_set_rss_lut_params { #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) - /* AQ API version for LLDP_FILTER_CONTROL */ #define ICE_FW_API_LLDP_FLTR_MAJ 1 #define ICE_FW_API_LLDP_FLTR_MIN 7 diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index ea3310be8354..b7ae09952156 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -56,6 +56,8 @@ static void ice_release_vf(struct kref *ref) { struct ice_vf *vf = container_of(ref, struct ice_vf, refcnt); + pci_dev_put(vf->vfdev); + vf->vf_ops->free(vf); } @@ -304,6 +306,237 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) } /** + * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN + * @vf: VF to add MAC filters for + * @vsi: Pointer to VSI + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds either a VLAN 0 or port VLAN based filter after reset. + */ +static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct device *dev = ice_pf_to_dev(vf->pf); + int err; + + if (ice_vf_is_port_vlan_ena(vf)) { + err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); + if (err) { + dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", + vf->vf_id, err); + return err; + } + + err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); + } else { + err = ice_vsi_add_vlan_zero(vsi); + } + + if (err) { + dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", + ice_vf_is_port_vlan_ena(vf) ? + ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); + return err; + } + + err = vlan_ops->ena_rx_filtering(vsi); + if (err) + dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", + vf->vf_id, vsi->idx, err); + + return 0; +} + +/** + * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration + * @vf: VF to re-apply the configuration for + * + * Called after a VF VSI has been re-added/rebuild during reset. The PF driver + * needs to re-apply the host configured Tx rate limiting configuration. + */ +static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + int err; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (vf->min_tx_rate) { + err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", + vf->min_tx_rate, vf->vf_id, err); + return err; + } + } + + if (vf->max_tx_rate) { + err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", + vf->max_tx_rate, vf->vf_id, err); + return err; + } + } + + return 0; +} + +/** + * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value + * @vf: VF to configure trust setting for + */ +static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) +{ + assign_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps, vf->trusted); +} + +/** + * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA + * @vf: VF to add MAC filters for + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. + */ +static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + u8 broadcast[ETH_ALEN]; + int status; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (ice_is_eswitch_mode_switchdev(vf->pf)) + return 0; + + eth_broadcast_addr(broadcast); + status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", + vf->vf_id, status); + return status; + } + + vf->num_mac++; + + if (is_valid_ether_addr(vf->hw_lan_addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, + ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", + &vf->hw_lan_addr[0], vf->vf_id, + status); + return status; + } + vf->num_mac++; + + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); + } + + return 0; +} + +/** + * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config + * @vsi: Pointer to VSI + * + * This function moves VSI into corresponding scheduler aggregator node + * based on cached value of "aggregator node info" per VSI + */ +static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + int status; + + if (!vsi->agg_node) + return; + + dev = ice_pf_to_dev(pf); + if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { + dev_dbg(dev, + "agg_id %u already has reached max_num_vsis %u\n", + vsi->agg_node->agg_id, vsi->agg_node->num_vsis); + return; + } + + status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, + vsi->idx, vsi->tc_cfg.ena_tc); + if (status) + dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", + vsi->idx, vsi->agg_node->agg_id); + else + vsi->agg_node->num_vsis++; +} + +/** + * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset + * @vf: VF to rebuild host configuration on + */ +static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vf_set_host_trust_cfg(vf); + + if (ice_vf_rebuild_host_mac_cfg(vf)) + dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", + vf->vf_id); + + if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) + dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", + vf->vf_id); + + if (ice_vf_rebuild_host_tx_rate_cfg(vf)) + dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", + vf->vf_id); + + if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) + dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", + vf->vf_id); + + /* rebuild aggregator node config for main VF VSI */ + ice_vf_rebuild_aggregator_node_cfg(vsi); +} + +/** + * ice_set_vf_state_qs_dis - Set VF queues state to disabled + * @vf: pointer to the VF structure + */ +static void ice_set_vf_state_qs_dis(struct ice_vf *vf) +{ + /* Clear Rx/Tx enabled queues flag */ + bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); + bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); +} + +/** + * ice_vf_set_initialized - VF is ready for VIRTCHNL communication + * @vf: VF to set in initialized state + * + * After this function the VF will be ready to receive/handle the + * VIRTCHNL_OP_GET_VF_RESOURCES message + */ +static void ice_vf_set_initialized(struct ice_vf *vf) +{ + ice_set_vf_state_qs_dis(vf); + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); +} + +/** * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild * @vf: the VF being reset * @@ -596,12 +829,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf) int ice_reset_vf(struct ice_vf *vf, u32 flags) { struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; struct device *dev; int err = 0; bool rsd; dev = ice_pf_to_dev(pf); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -612,6 +849,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (flags & ICE_VF_RESET_LOCK) mutex_lock(&vf->cfg_lock); else @@ -704,19 +952,12 @@ out_unlock: if (flags & ICE_VF_RESET_LOCK) mutex_unlock(&vf->cfg_lock); - return err; -} + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); -/** - * ice_set_vf_state_qs_dis - Set VF queues state to disabled - * @vf: pointer to the VF structure - */ -static void ice_set_vf_state_qs_dis(struct ice_vf *vf) -{ - /* Clear Rx/Tx enabled queues flag */ - bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); - bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); - clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); + return err; } /** @@ -960,211 +1201,6 @@ bool ice_is_vf_link_up(struct ice_vf *vf) } /** - * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value - * @vf: VF to configure trust setting for - */ -static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) -{ - if (vf->trusted) - set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); - else - clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); -} - -/** - * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA - * @vf: VF to add MAC filters for - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. - */ -static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - u8 broadcast[ETH_ALEN]; - int status; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (ice_is_eswitch_mode_switchdev(vf->pf)) - return 0; - - eth_broadcast_addr(broadcast); - status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", - vf->vf_id, status); - return status; - } - - vf->num_mac++; - - if (is_valid_ether_addr(vf->hw_lan_addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", - &vf->hw_lan_addr[0], vf->vf_id, - status); - return status; - } - vf->num_mac++; - - ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); - } - - return 0; -} - -/** - * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN - * @vf: VF to add MAC filters for - * @vsi: Pointer to VSI - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds either a VLAN 0 or port VLAN based filter after reset. - */ -static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) -{ - struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); - struct device *dev = ice_pf_to_dev(vf->pf); - int err; - - if (ice_vf_is_port_vlan_ena(vf)) { - err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); - if (err) { - dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", - vf->vf_id, err); - return err; - } - - err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); - } else { - err = ice_vsi_add_vlan_zero(vsi); - } - - if (err) { - dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", - ice_vf_is_port_vlan_ena(vf) ? - ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); - return err; - } - - err = vlan_ops->ena_rx_filtering(vsi); - if (err) - dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", - vf->vf_id, vsi->idx, err); - - return 0; -} - -/** - * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration - * @vf: VF to re-apply the configuration for - * - * Called after a VF VSI has been re-added/rebuild during reset. The PF driver - * needs to re-apply the host configured Tx rate limiting configuration. - */ -static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - int err; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (vf->min_tx_rate) { - err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", - vf->min_tx_rate, vf->vf_id, err); - return err; - } - } - - if (vf->max_tx_rate) { - err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", - vf->max_tx_rate, vf->vf_id, err); - return err; - } - } - - return 0; -} - -/** - * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config - * @vsi: Pointer to VSI - * - * This function moves VSI into corresponding scheduler aggregator node - * based on cached value of "aggregator node info" per VSI - */ -static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int status; - - if (!vsi->agg_node) - return; - - dev = ice_pf_to_dev(pf); - if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { - dev_dbg(dev, - "agg_id %u already has reached max_num_vsis %u\n", - vsi->agg_node->agg_id, vsi->agg_node->num_vsis); - return; - } - - status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, - vsi->idx, vsi->tc_cfg.ena_tc); - if (status) - dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", - vsi->idx, vsi->agg_node->agg_id); - else - vsi->agg_node->num_vsis++; -} - -/** - * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset - * @vf: VF to rebuild host configuration on - */ -void ice_vf_rebuild_host_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (WARN_ON(!vsi)) - return; - - ice_vf_set_host_trust_cfg(vf); - - if (ice_vf_rebuild_host_mac_cfg(vf)) - dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", - vf->vf_id); - - if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) - dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", - vf->vf_id); - - if (ice_vf_rebuild_host_tx_rate_cfg(vf)) - dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", - vf->vf_id); - - if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) - dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", - vf->vf_id); - - /* rebuild aggregator node config for main VF VSI */ - ice_vf_rebuild_aggregator_node_cfg(vsi); -} - -/** * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access * @vf: VF that control VSI is being invalidated on */ @@ -1293,23 +1329,6 @@ void ice_vf_vsi_release(struct ice_vf *vf) } /** - * ice_vf_set_initialized - VF is ready for VIRTCHNL communication - * @vf: VF to set in initialized state - * - * After this function the VF will be ready to receive/handle the - * VIRTCHNL_OP_GET_VF_RESOURCES message - */ -void ice_vf_set_initialized(struct ice_vf *vf) -{ - ice_set_vf_state_qs_dis(vf); - clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_DIS, vf->vf_states); - set_bit(ICE_VF_STATE_INIT, vf->vf_states); - memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); -} - -/** * ice_get_vf_ctrl_vsi - Get first VF control VSI pointer * @pf: the PF private structure * @vsi: pointer to the VSI diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 48fea6fa0362..93c774f2f437 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -72,7 +72,7 @@ struct ice_vfs { struct mutex table_lock; /* Lock for protecting the hash table */ u16 num_supported; /* max supported VFs on this PF */ u16 num_qps_per; /* number of queue pairs per VF */ - u16 num_msix_per; /* number of MSI-X vectors per VF */ + u16 num_msix_per; /* default MSI-X vectors per VF */ unsigned long last_printed_mdd_jiffies; /* MDD message rate limit */ }; @@ -82,7 +82,7 @@ struct ice_vf { struct rcu_head rcu; struct kref refcnt; struct ice_pf *pf; - + struct pci_dev *vfdev; /* Used during virtchnl message handling and NDO ops against the VF * that will trigger a VFR */ @@ -123,6 +123,9 @@ struct ice_vf { u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; u16 num_vf_qs; /* num of queue configured per VF */ + u8 vlan_strip_ena; /* Outer and Inner VLAN strip enable */ +#define ICE_INNER_VLAN_STRIP_ENA BIT(0) +#define ICE_OUTER_VLAN_STRIP_ENA BIT(1) struct ice_mdd_vf_events mdd_rx_events; struct ice_mdd_vf_events mdd_tx_events; DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); @@ -133,6 +136,8 @@ struct ice_vf { /* devlink port data */ struct devlink_port devlink_port; + + u16 num_msix; /* num of MSI-X configured on this VF */ }; /* Flags for controlling behavior of ice_reset_vf */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 6f3293b793b5..0c7e77c0a09f 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -32,13 +32,11 @@ int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable); bool ice_is_vf_trusted(struct ice_vf *vf); bool ice_vf_has_no_qs_ena(struct ice_vf *vf); bool ice_is_vf_link_up(struct ice_vf *vf); -void ice_vf_rebuild_host_cfg(struct ice_vf *vf); void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf); void ice_vf_ctrl_vsi_release(struct ice_vf *vf); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi); void ice_vf_invalidate_vsi(struct ice_vf *vf); void ice_vf_vsi_release(struct ice_vf *vf); -void ice_vf_set_initialized(struct ice_vf *vf); #endif /* _ICE_VF_LIB_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index b1ffb81893d4..80dc4bcdd3a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -21,6 +21,105 @@ noop_vlan(struct ice_vsi __always_unused *vsi) return 0; } +static void ice_port_vlan_on(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + vlan_ops->add_vlan = noop_vlan_arg; + vlan_ops->del_vlan = noop_vlan_arg; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + } + + /* all Rx traffic should be in the domain of the assigned port VLAN, + * so prevent disabling Rx VLAN filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; + + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; +} + +static void ice_port_vlan_off(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + } else { + vlan_ops->del_vlan = ice_vsi_del_vlan; + } + + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; +} + +/** + * ice_vf_vsi_enable_port_vlan - Set VSI VLAN ops to support port VLAN + * @vsi: VF's VSI being configured + * + * The function won't create port VLAN, it only allows to create port VLAN + * using VLAN ops on the VF VSI. + */ +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_on(vsi); +} + +/** + * ice_vf_vsi_disable_port_vlan - Clear VSI support for creating port VLAN + * @vsi: VF's VSI being configured + * + * The function should be called after removing port VLAN on VSI + * (using VLAN ops) + */ +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_off(vsi); +} + /** * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI * @vsi: VF's VSI being configured @@ -39,91 +138,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) if (WARN_ON(!vf)) return; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; + if (ice_vf_is_port_vlan_ena(vf)) + ice_port_vlan_on(vsi); + else + ice_port_vlan_off(vsi); - /* outer VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - vlan_ops->add_vlan = noop_vlan_arg; - vlan_ops->del_vlan = noop_vlan_arg; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } else { - vlan_ops = &vsi->inner_vlan_ops; + vlan_ops = ice_is_dvm_ena(&pf->hw) ? + &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; - /* inner VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h index 875a4e615f39..df8aa09df3e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -13,7 +13,11 @@ void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi); #ifdef CONFIG_PCI_IOV void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi); +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi); +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi); #else static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) { } #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index dcf628b1fccd..1c7b4ded948b 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -428,7 +428,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - len = sizeof(struct virtchnl_vf_resource); + len = virtchnl_struct_size(vfres, vsi_res, 0); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { @@ -486,6 +486,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_CRC; + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; @@ -498,9 +501,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; - vfres->max_vectors = vf->pf->vfs.num_msix_per; + vfres->max_vectors = vf->num_msix; vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; - vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; @@ -962,7 +965,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + if (vrl->lut_entries != ICE_LUT_VSI_SIZE) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -978,7 +981,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE)) + if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret, @@ -1520,7 +1523,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) u16 num_q_vectors_mapped, vsi_id, vector_id; struct virtchnl_irq_map_info *irqmap_info; struct virtchnl_vector_map *map; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int i; @@ -1532,7 +1534,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) * there is actually at least a single VF queue vector mapped */ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - pf->vfs.num_msix_per < num_q_vectors_mapped || + vf->num_msix < num_q_vectors_mapped || !num_q_vectors_mapped) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -1554,7 +1556,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) /* vector_id is always 0-based for each VF, and can never be * larger than or equal to the max allowed interrupts per VF */ - if (!(vector_id < pf->vfs.num_msix_per) || + if (!(vector_id < vf->num_msix) || !ice_vc_isvalid_vsi_id(vf, vsi_id) || (!vector_id && (map->rxq_map || map->txq_map))) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1600,9 +1602,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; int i = -1, q_idx; + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) goto error_param; @@ -1621,6 +1638,15 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } for (i = 0; i < qci->num_queue_pairs; i++) { + if (!qci->qpair[i].rxq.crc_disable) + continue; + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_CRC) || + vf->vlan_strip_ena) + 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 || @@ -1666,6 +1692,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; + if (qpi->rxq.crc_disable) + vsi->rx_rings[q_idx]->flags |= + ICE_RX_FLAGS_CRC_STRIP_DIS; + else + vsi->rx_rings[q_idx]->flags &= + ~ICE_RX_FLAGS_CRC_STRIP_DIS; + if (qpi->rxq.databuffer_size != 0 && (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || qpi->rxq.databuffer_size < 1024)) @@ -1710,6 +1743,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_SUCCESS, NULL, 0); @@ -1724,6 +1762,13 @@ error_param: vf->vf_id, i); } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + + ice_lag_move_new_vf_nodes(vf); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); @@ -2409,6 +2454,21 @@ static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) } /** + * ice_vsi_is_rxq_crc_strip_dis - check if Rx queue CRC strip is disabled or not + * @vsi: pointer to the VF VSI info + */ +static bool ice_vsi_is_rxq_crc_strip_dis(struct ice_vsi *vsi) +{ + unsigned int i; + + ice_for_each_alloc_rxq(vsi, i) + if (vsi->rx_rings[i]->flags & ICE_RX_FLAGS_CRC_STRIP_DIS) + return true; + + return false; +} + +/** * ice_vc_ena_vlan_stripping * @vf: pointer to the VF info * @@ -2437,6 +2497,8 @@ static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) if (vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; + else + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, @@ -2472,6 +2534,8 @@ static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) if (vsi->inner_vlan_ops.dis_stripping(vsi)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; + else + vf->vlan_strip_ena &= ~ICE_INNER_VLAN_STRIP_ENA; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, @@ -2615,12 +2679,14 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - /* Read flexiflag registers to determine whether the - * corresponding RXDID is configured and supported or not. - * Since Legacy 16byte descriptor format is not supported, - * start from Legacy 32byte descriptor. + /* RXDIDs supported by DDP package can be read from the register + * to get the supported RXDID bitmap. But the legacy 32byte RXDID + * is not listed in DDP package, add it in the bitmap manually. + * Legacy 16byte descriptor is not supported. */ - for (i = ICE_RXDID_LEGACY_1; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + rxdid->supported_rxdids |= BIT(ICE_RXDID_LEGACY_1); + + for (i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) @@ -2647,6 +2713,8 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) { struct ice_vsi *vsi = ice_get_vf_vsi(vf); + vf->vlan_strip_ena = 0; + if (!vsi) return -EINVAL; @@ -2656,10 +2724,16 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) if (ice_vf_is_port_vlan_ena(vf) && !ice_is_dvm_ena(&vsi->back->hw)) return 0; - if (ice_vf_vlan_offload_ena(vf->driver_caps)) - return vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q); - else - return vsi->inner_vlan_ops.dis_stripping(vsi); + if (ice_vf_vlan_offload_ena(vf->driver_caps)) { + int err; + + err = vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q); + if (!err) + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; + return err; + } + + return vsi->inner_vlan_ops.dis_stripping(vsi); } static u16 ice_vc_get_max_vlan_fltrs(struct ice_vf *vf) @@ -3433,6 +3507,11 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ice_vsi_is_rxq_crc_strip_dis(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto out; + } + ethertype_setting = strip_msg->outer_ethertype_setting; if (ethertype_setting) { if (ice_vc_ena_vlan_offload(vsi, @@ -3453,6 +3532,8 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) * enabled, is extracted in L2TAG1. */ ice_vsi_update_l2tsel(vsi, l2tsel); + + vf->vlan_strip_ena |= ICE_OUTER_VLAN_STRIP_ENA; } } @@ -3464,6 +3545,9 @@ static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ethertype_setting) + vf->vlan_strip_ena |= ICE_INNER_VLAN_STRIP_ENA; + out: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); @@ -3525,6 +3609,8 @@ static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) * in L2TAG1. */ ice_vsi_update_l2tsel(vsi, l2tsel); + + vf->vlan_strip_ena &= ~ICE_OUTER_VLAN_STRIP_ENA; } } @@ -3534,6 +3620,9 @@ static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) goto out; } + if (ethertype_setting) + vf->vlan_strip_ena &= ~ICE_INNER_VLAN_STRIP_ENA; + out: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index daa6a1e894cf..24b23b7ef04a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2021, Intel Corporation. */ +/* Copyright (C) 2021-2023, Intel Corporation. */ #include "ice.h" #include "ice_base.h" @@ -1422,8 +1422,8 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, */ static void ice_vf_fdir_dump_info(struct ice_vf *vf) { + u32 fd_size, fd_cnt, fd_size_g, fd_cnt_g, fd_size_b, fd_cnt_b; struct ice_vsi *vf_vsi; - u32 fd_size, fd_cnt; struct device *dev; struct ice_pf *pf; struct ice_hw *hw; @@ -1442,12 +1442,25 @@ static void ice_vf_fdir_dump_info(struct ice_vf *vf) fd_size = rd32(hw, VSIQF_FD_SIZE(vsi_num)); fd_cnt = rd32(hw, VSIQF_FD_CNT(vsi_num)); - dev_dbg(dev, "VF %d: space allocated: guar:0x%x, be:0x%x, space consumed: guar:0x%x, be:0x%x\n", - vf->vf_id, - (fd_size & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, - (fd_size & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S, - (fd_cnt & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, - (fd_cnt & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S); + switch (hw->mac_type) { + case ICE_MAC_E830: + fd_size_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_size); + fd_size_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_size); + fd_cnt_g = FIELD_GET(E830_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt); + fd_cnt_b = FIELD_GET(E830_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt); + break; + case ICE_MAC_E810: + default: + fd_size_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_size); + fd_size_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_size); + fd_cnt_g = FIELD_GET(E800_VSIQF_FD_CNT_FD_GCNT_M, fd_cnt); + fd_cnt_b = FIELD_GET(E800_VSIQF_FD_CNT_FD_BCNT_M, fd_cnt); + } + + dev_dbg(dev, "VF %d: Size in the FD table: guaranteed:0x%x, best effort:0x%x\n", + vf->vf_id, fd_size_g, fd_size_b); + dev_dbg(dev, "VF %d: Filter counter in the FD table: guaranteed:0x%x, best effort:0x%x\n", + vf->vf_id, fd_cnt_g, fd_cnt_b); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 5b4a0abb4607..76266e709a39 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -202,6 +202,24 @@ int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) return ice_vsi_manage_vlan_insertion(vsi); } +static void +ice_save_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + vlan->sw_flags2 = info->sw_flags2; + vlan->inner_vlan_flags = info->inner_vlan_flags; + vlan->outer_vlan_flags = info->outer_vlan_flags; +} + +static void +ice_restore_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + info->sw_flags2 = vlan->sw_flags2; + info->inner_vlan_flags = vlan->inner_vlan_flags; + info->outer_vlan_flags = vlan->outer_vlan_flags; +} + /** * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN * @vsi: the VSI to update @@ -218,6 +236,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; info = &ctxt->info; info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | @@ -259,6 +278,33 @@ int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); } +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; + struct ice_vsi_ctx *ctxt; + int ret; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_inner_vlan = 0; + ctxt->info = vsi->info; + info = &ctxt->info; + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) + dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return ret; +} + /** * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on @@ -647,6 +693,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; @@ -689,9 +736,6 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) * used if DVM is supported. Also, this function should never be called directly * as it should be part of ice_vsi_vlan_ops if it's needed. * - * This function does not support clearing the port VLAN as there is currently - * no use case for this. - * * Use the ice_vlan structure passed in to set this VSI in a port VLAN. */ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) @@ -705,3 +749,37 @@ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); } + +/** + * ice_vsi_clear_outer_port_vlan - clear outer port vlan + * @vsi: VSI to configure + * + * The function is restoring previously set vlan config (saved in + * vsi->vlan_info). Setting happens in port vlan configuration. + */ +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_outer_vlan = 0; + ctxt->info = vsi->info; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h index f459909490ec..f0d84d11bd5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -7,6 +7,12 @@ #include <linux/types.h> #include "ice_vlan.h" +struct ice_vsi_vlan_info { + u8 sw_flags2; + u8 inner_vlan_flags; + u8 outer_vlan_flags; +}; + struct ice_vsi; int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); @@ -17,6 +23,7 @@ int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi); int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi); int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi); int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi); int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); @@ -28,5 +35,6 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi); int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi); int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi); #endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h index 5b47568f6256..b2d2330dedcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -21,6 +21,7 @@ struct ice_vsi_vlan_ops { int (*ena_tx_filtering)(struct ice_vsi *vsi); int (*dis_tx_filtering)(struct ice_vsi *vsi); int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*clear_port_vlan)(struct ice_vsi *vsi); }; void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a7fe2b4ce655..99954508184f 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -217,21 +217,16 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) */ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { - struct ice_aqc_add_tx_qgrp *qg_buf; + DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + u16 size = __struct_size(qg_buf); struct ice_q_vector *q_vector; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - u16 size; int err; if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) return -EINVAL; - size = struct_size(qg_buf, txqs, 1); - qg_buf = kzalloc(size, GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - qg_buf->num_txqs = 1; tx_ring = vsi->tx_rings[q_idx]; @@ -240,7 +235,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) err = ice_vsi_cfg_txq(vsi, tx_ring, qg_buf); if (err) - goto free_buf; + return err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; @@ -249,29 +244,28 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) qg_buf->num_txqs = 1; err = ice_vsi_cfg_txq(vsi, xdp_ring, qg_buf); if (err) - goto free_buf; + return err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_rxq(rx_ring); if (err) - goto free_buf; + return err; ice_qvec_cfg_msix(vsi, q_vector); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); if (err) - goto free_buf; + return err; clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); -free_buf: - kfree(qg_buf); - return err; + + return 0; } /** @@ -546,19 +540,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) } /** - * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring - * @rx_ring: Rx ring - */ -static void ice_bump_ntc(struct ice_rx_ring *rx_ring) -{ - int ntc = rx_ring->next_to_clean + 1; - - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(ICE_RX_DESC(rx_ring, ntc)); -} - -/** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring * @xdp: Pointer to XDP buffer @@ -572,8 +553,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, @@ -589,6 +576,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + +out: xsk_buff_free(xdp); return skb; } @@ -597,7 +607,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring */ -static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -619,7 +629,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) } if (!completed_frames) - return; + return 0; if (likely(!xdp_ring->xdp_tx_active)) { xsk_frames = completed_frames; @@ -649,6 +659,8 @@ skip: xdp_ring->next_to_clean -= cnt; if (xsk_frames) xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + + return completed_frames; } /** @@ -666,37 +678,72 @@ skip: static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { + struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; u32 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; - dma_addr_t dma; - - if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) { - ice_clean_xdp_irq_zc(xdp_ring); - if (!ICE_DESC_UNUSED(xdp_ring)) { - xdp_ring->ring_stats->tx_stats.tx_busy++; - return ICE_XDP_CONSUMED; - } + struct xdp_buff *head; + u32 nr_frags = 0; + u32 free_space; + u32 frag = 0; + + free_space = ICE_DESC_UNUSED(xdp_ring); + if (free_space < ICE_RING_QUARTER(xdp_ring)) + free_space += ice_clean_xdp_irq_zc(xdp_ring); + + if (unlikely(!free_space)) + goto busy; + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + if (free_space < nr_frags + 1) + goto busy; } - dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); - - tx_buf = &xdp_ring->tx_buf[ntu]; - tx_buf->xdp = xdp; - tx_buf->type = ICE_TX_BUF_XSK_TX; tx_desc = ICE_TX_DESC(xdp_ring, ntu); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, - 0, size, 0); - xdp_ring->xdp_tx_active++; + tx_buf = &xdp_ring->tx_buf[ntu]; + head = xdp; + + for (;;) { + dma_addr_t dma; + + dma = xsk_buff_xdp_get_dma(xdp); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + + tx_buf->xdp = xdp; + tx_buf->type = ICE_TX_BUF_XSK_TX; + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); + /* account for each xdp_buff from xsk_buff_pool */ + xdp_ring->xdp_tx_active++; + + if (++ntu == xdp_ring->count) + ntu = 0; + + if (frag == nr_frags) + break; + + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_buf = &xdp_ring->tx_buf[ntu]; + + xdp = xsk_buff_get_frag(head); + size = skb_frag_size(&sinfo->frags[frag]); + frag++; + } - if (++ntu == xdp_ring->count) - ntu = 0; xdp_ring->next_to_use = ntu; + /* update last descriptor from a frame with EOP */ + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S); return ICE_XDP_TX; + +busy: + xdp_ring->ring_stats->tx_stats.tx_busy++; + + return ICE_XDP_CONSUMED; } /** @@ -752,6 +799,34 @@ out_failure: return result; } +static int +ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!size) + return 0; + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -762,9 +837,14 @@ out_failure: int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; + u32 ntc = rx_ring->next_to_clean; + u32 ntu = rx_ring->next_to_use; + struct xdp_buff *first = NULL; struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; + u32 cnt = rx_ring->count; bool failure = false; int entries_to_alloc; @@ -774,6 +854,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) xdp_prog = READ_ONCE(rx_ring->xdp_prog); xdp_ring = rx_ring->xdp_ring; + if (ntc != rx_ring->first_desc) + first = *ice_xdp_buf(rx_ring, rx_ring->first_desc); + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -783,7 +866,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) u16 vlan_tag = 0; u16 rx_ptype; - rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = ICE_RX_DESC(rx_ring, ntc); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -795,51 +878,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use)) + if (unlikely(ntc == ntu)) break; - xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); + xdp = *ice_xdp_buf(rx_ring, ntc); size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; - if (!size) { - xdp->data = NULL; - xdp->data_end = NULL; - xdp->data_hard_start = NULL; - xdp->data_meta = NULL; - goto construct_skb; - } xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); + if (!first) { + first = xdp; + xdp_buff_clear_frags_flag(first); + } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + break; + } + + if (++ntc == cnt) + ntc = 0; + + if (ice_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { failure = true; + first = NULL; + rx_ring->first_desc = ntc; break; } else if (xdp_res == ICE_XDP_CONSUMED) { - xsk_buff_free(xdp); + xsk_buff_free(first); } else if (xdp_res == ICE_XDP_PASS) { goto construct_skb; } - total_rx_bytes += size; + total_rx_bytes += xdp_get_buff_len(first); total_rx_packets++; - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, xdp); + skb = ice_construct_skb_zc(rx_ring, first); if (!skb) { rx_ring->ring_stats->rx_stats.alloc_buf_failed++; break; } - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; if (eth_skb_pad(skb)) { skb = NULL; @@ -858,18 +951,22 @@ construct_skb: ice_receive_skb(rx_ring, skb, vlan_tag); } - entries_to_alloc = ICE_DESC_UNUSED(rx_ring); + rx_ring->next_to_clean = ntc; + entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { - if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) { + /* ntu could have changed when allocating entries above, so + * use rx_ring value instead of stack based one + */ + if (failure || ntc == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); + xsk_clear_rx_need_wakeup(xsk_pool); return (int)total_rx_packets; } @@ -894,7 +991,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc), 0, desc->len, 0); *total_bytes += desc->len; @@ -921,7 +1018,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]), 0, descs[i].len, 0); *total_bytes += descs[i].len; |